Publications - AmritaCREATE

In a farming community, different types of commodities may need to be transported to different destinations, like the market, storage unit or a processing unit, during the harvest season. To organize efficient transportation in such a setting, the problem is formulated as a Vehicle Routing Problem with Pickups and Deliveries, by considering a virtual field and a virtual destination for delivery of each commodity. To solve this particular problem instance, four common metaheuristics - iterative hill-climbing, guided local search, tabu search, and simulated annealing - were tried and their performances based on total tour lengths for different run times were compared. Basic implementations of these metaheuristics were done using Google OR tools. Guided local search was found to produce good solutions quicker than others. In the long run, tabu search was able to find a slightly better solution. Simulated annealing was prone to get trapped in a local optimum for hours.

Addressing socio‐economic factors in ecological restoration projects is critical for the effectiveness of restoration practices and scaling of restoration efforts. To achieve sustainability of restoration projects, the drivers of hOLabs of Digital India,uman activity leading to the degradation need to be addressed. An under researched concept in ecological restoration is the impact of behavior change of stakeholders and communities involved, despite the strong link prior research has shown to exist between environmental quality and human behavior. This article explores the importance of addressing the behavioral change of stakeholders engaged in restoration to achieve sustainability of efforts; it investigates how behavior change models are linked and represented in global environmental governance documents, and it discusses how behavioral intervention and policy instruments could be included in ecological restoration projects. For future work, the article proposes the integration of behavior change interventions in the design of restoration projects and policies.

In many rural Indian schools, English is a second language for teachers and students. Intelligent tutoring systems have good potential because they enable students to learn at their own pace, in an exploratory manner. This paper describes a 3-year longitudinal study of 2123 Indian students who used the intelligent tutoring system, AmritaITS. The aim of the study was to use the students’ interaction logs with AmritaITS to: (1) predict student performance, in English and Mathematics subjects, via summative and formative assessments, (2) predict students who may be at risk of failing the final examination and (3) screen students who may have reading difficulties. The prediction models for summative assessments were significantly improved by formative assessments scores, along with AmritaITS logs. The receiver operating characteristic (ROC) curve showed that students at risk of failing a class could be identified early, with high sensitivity and specificity. The models also provide recommendations for the amount of time required for students to use the system, and reach the appropriate grade level. Finally, the models demonstrated promise in identifying students who might be at risk of suffering from reading difficulties.

This paper describes an after-school education program in rural India. The program maintains 53 education centers in remote villages in 21 states of India. For the allocation of resources, we first describe the results of an multi-attribute utility assessment, where 130 teachers, coordinators, and people associated with the program specified their opinion on factors that are most important on running a successful after-school education center. We then formulate the problem of optimal resource allocating as a generalized assignment problem. To solve this problem, three different metaheuristics are compared: iterated hill climbing, tabu search, and simulated annealing. It is found that tabu search is giving the best performance.

This paper describes an after-school education program in rural India. The program maintains 53 education centers in remote villages in 21 states of India. This paper discusses the technology to monitor and coordinate these centers that are distributed over a wide area. It also describes the education technology that is used in the after-school education centers.

Online Labs (OLabs) is a major Digital India initiative with over 135 online experiments mapped to high school curriculum. For each experiment, OLabs provides background on the theory, animations, simulations, videos, viva voce questions, and links to additional resources. OLabs has been translated to multiple Indian languages. As part of scaling OLabs to the nation, over 16,000 teachers in all Indian states have been trained across India. The current manuscript presents a survey of 112 teachers who attended OLabs workshops and uses OLabs in the classroom. The study's purpose is to understand the effective implementation of teacher training, to understand how OLabs is used in school laboratory experiments, and to understand how OLabs can supplement or replace real laboratories. A majority of teachers agree that repetition of OLabs experiments helps improve understanding of the concepts. There exists a strong correlation between the teachers' perception of the quality of videos and animations and the teachers' attitude on the usefulness of virtual laboratory software. Whether or not teachers feel that virtual laboratory software is useful to students is strongly associated with whether or not teachers feel that software is sufficiently fast and responsive. With regard to the workshops, teachers place high emphasis on the importance of establishing a clear agenda during the workshops. Finally, almost all teachers agree that OLabs can be an effective supplement to real laboratories.

Despite the high prevalence of reading disabilities among Indian children, many school teachers are not adept at identifying and assessing these difficulties. Screening tools for reading disabilities are available in English but are unavailable in many Indian languages. Reading disabilities manifest differently depending on the characteristics of the language being studied. This paper compares reading difficulties that arise when studying English and Malayalam. In a previous study, we designed a bilingual screening test in English and Malayalam and tested it with 135 school children in Kerala. In the current study, the screening test was modified in light of the findings from our previous study. We administered our updated bilingual screening test to 25 second grade children, ages 7–8, who were studying at two other schools in Kerala. Student errors were classified into multiple categories. Similarities and differences between errors in English and Malayalam were identified, and the errors that were specific to Malayalam were analyzed in further detail.

Understanding the quantity and quality of solar energy that can be harnessed at a site is essential for estimating and optimizing the cost of energy production for most developing and developed nations. This article details the design of an efficient, low-cost system to measure solar irradiance using dual-axis tracking, irradiation sensors, and an algorithm to track the solar position. The sensed data is acquired using a data acquisition system and provides a user-friendly remote access using a collaborative platform to monitor and control real-time data with options to change parameters and graphically display the data and live streaming. Evaluating a potential site for solar energy installation could be studied without acquiring expensive equipment. Positive results from the study conducted to capture the perceived usefulness, overall adaptability and ease in understanding of underlying scientific concepts and their retention for novice users indicate the effectiveness of the system developed.

This exploratory study examined the potential for adapting Online Labs (OLabs), an innovative educational initiative of Digital India, for use in secondary schools in Côte d’Ivoire, West Africa. OLabs provides exposure to and participation in scientific experiments for students attending low-resource schools and cannot provide expensive laboratory equipments. Following a site visit in India, we examined Côte d’Ivoire curriculum documents and interviewed a variety of Ivorian stakeholders including school principals, science teachers, and students to evaluate needs and identify which experiments might be best suited for the Côte d’Ivoire context. Thirty experiments across the three scientific disciplines were identified as appropriate, and of these, 12 were translated from English to French, the official language of instruction in Côte d’Ivoire. These 12 experiments were published online and tested in Côte d’Ivoire by Ivorian teachers in terms of connectivity, user registration, accessibility to the translated experiments, and clarity of the content of translated experiments. The translated experiments were tested by teachers (n = 5) from Côte d’Ivoire. 80% of participants in this test rated the connectivity platform as good and indicated that the translated experiments were easily accessible. However, their deployment, monitoring, and empirical evaluation will necessarily need to be accompanied by public authorities and organizations of goodwill.

In this paper, a tribal village in India was examined, where a community farming model for cultivation of lemon-grass is being proposed. To ensure effective implementation of the program, two mathematical problems were identified, for facility location and vehicle routing. Solutions to the problems were found, using a geographic information system; the results obtained were compared with a common routing heuristic and a convenient location for the facility. Findings include savings of about 14 percent in the transportation costs.

In many Indian schools, a high student-teacher ratio makes it an uphill struggle for teachers to assess the knowledge of individual students and deficiencies in the students' understanding. Teachers should have a clear picture on what concepts each student has mastered, and which concepts the teacher needs to review in greater detail. This paper investigates the students' concept knowledge, based on the interaction of the students with an intelligent tutoring system. The Feature-Aware Student knowledge Tracing (FAST) algorithm was used, since the algorithm facilitates the separation of lesson-specific skills from concept knowledge. Data from 2400 first-grade students from 28 schools were used for the analysis. Findings include a moderate fit model and an easy interpretation of the model parameters.

Age is less important than proximity to death as a predictor of costs. However, the pattern of social and nursing care costs is different from that for acute medical care. In planning services it is important to take into account the relatively larger impact of aging on social and nursing care than on acute care.

SwastyaSIM is a simulation-based, multilingual, interactive learning environment designed to supplement the training of community health workers. It includes medical training and diagnostic tests relevant to common village ailments that are designed to be sensitive to socio-cultural perspectives. This platform supports training, reporting and assessing health workers. Findings from a pilot study with health workers are discussed.

Purpose: The purpose of this paper is to illustrate an Inclusive Digital Literacy Framework for vulnerable populations in rural areas under the Digital India program. Key challenges include addressing multiple literacies such as health literacy, financial literacy and eSafety for low-literate learners in low-resource settings with low internet bandwidth, lack of ICT facilities and intermittent electricity. Design/methodology/approach: This research implemented an educational model based on the proposed framework to train over 1,000 indigenous people using an integrated curriculum for digital literacies at remote settlements. The model uses mobile technology adapted for remote areas, context enabled curriculum, along with flexible learning schedules. Findings: The education model exemplifies a viable strategy to overcome persistent challenges by taking tablet-based digital literacies directly to communities. It engages different actors such as existing civil societies, schools and government organizations to provide digital literacy and awareness thereby improving both digital and life skills. It demonstrates the potential value of a comprehensive Digital Literacy framework as a powerful lever for Digital Inclusion. Practical Implications: Policy makers can use this transformational model to extend the reach and effectiveness of Digital Inclusion through the last mile enhancing existing training and service centers that offer the traditional model of Digital Literacy Education. Originality/value: This innovative mobile learning model based on the proposed Digital Framework for Inclusion instilled motivation, interest and confidence while providing effective digital training and conducting exams directly in the tribal settlements for low-literate learners in remote settings. Through incorporating multiple literacies, this model serves to empower learners, enhance potential, improve well-being and reduce the risk of exploitation. © 2018, Emerald Publishing Limited.

Purpose of Review: This article discusses the advances, methods, challenges, and future directions of data-driven methods in advancing precision oncology for biomedical research, drug discovery, clinical research, and practice. Recent Findings: Precision oncology provides individually tailored cancer treatment by considering an individual’s genetic makeup, clinical, environmental, social, and lifestyle information. Challenges include voluminous, heterogeneous, and disparate data generated by different technologies with multiple modalities such as Omics, electronic health records, clinical registries and repositories, medical imaging, demographics, wearables, and sensors. Statistical and machine learning methods have been continuously adapting to the ever-increasing size and complexity of data. Precision Oncology supportive analytics have improved turnaround time in biomarker discovery and time-to-application of new and repurposed drugs. Precision oncology additionally seeks to identify target patient populations based on genomic alterations that are sensitive or resistant to conventional or experimental treatments. Predictive models have been developed for cancer progression and survivorship, drug sensitivity and resistance, and identification of the most suitable combination treatments for individual patient scenarios. In the future, clinical decision support systems need to be revamped to better incorporate knowledge from precision oncology, thus enabling clinical practitioners to provide precision cancer care. Summary: Open Omics datasets, machine learning algorithms, and predictive models have enabled the advancement of precision oncology. Clinical decision support systems with integrated electronic health record and Omics data are needed to provide data-driven recommendations to assist clinicians in disease prevention, early identification, and individualized treatment. Additionally, as cancer is a constantly evolving disorder, clinical decision systems will need to be continually updated based on more recent knowledge and datasets.

Educational schemes for marginalized communities such as SC/ST were introduced by the Government of India with the aim of providing equal opportunity for scheduled tribe and scheduled caste to empower them with free educational facilities. For such programs to be effective, SC/ST members need to be aware of them and need to have a positive attitude towards them. However, due to the practice of untouchability and the remoteness of their dwellings, SCs and STs have suffered isolation from mainstream population for several centuries. As a consequence, they continue to suffer from a high degree of educational exclusion. Upliftment of SCs and STs, both economically and socially, will be only possible through inclusive education efforts. This study focus on the role ofawareness on educational schemes in attaining primary and secondary education among SC/ST communities in two rural villages in Coimbatore. The major findings of the study reveals that most of marginalized communities continue to remain unaware of the educational schemes and are unable to utilize all the provisions of the schemes. © 2018 Academic Press.

A standardized dyslexia screening test can help in identifying the vast number of undiagnosed dyslexics in Indian schools; needless to say, such a test should produce consistent and reproducible results. This study investigated reliability and consistency among raters of a Malayalam-English dyslexia screening in India. Paper-based tests were administered to groups of students, and four raters evaluated the answer sheets of 208 second-grade students (ages 6-7). Inter-rater agreement, intraclass agreement, and internal consistency were calculated. Our findings include good agreement among raters' appraisals for most error types and tasks. Internal consistency for a few tasks was low, possibly because these tasks evaluated more than one skill. A few error types need to be redefined and a few tasks need to be more skill-specific to enable unambiguous and fruitful interpretation by different raters in the future.

Medical tests such as urinalysis, and other colori-metric assays require the measurement of changes in color. For such applications, this paper presents an innovative, low-cost color sensor, based on reflective color sensing. The proffered system is constituted of a light-intensity sensor and an RGB (red, green, blue) LED, placed on strategic geometries. Various regression models for calibration of the color sensor were investigated. Using cross validation with a training set of 160 colors, a cubic-spline regression model was selected. The accuracy and robustness of the novel sensor are also discussed.

Rural India lacks easy access to health practitioners and medical centers, depending instead on community health workers. In these areas, common ailments that are easy to manage with medicines, often lead to medical escalations and even fatalities due to lack of awareness and delayed diagnosis. The introduction of wearable health devices has made it easier to monitor health conditions and to connect doctors and patients in urban areas. However, existing initiatives have not succeeded in providing adequate health monitoring to rural and low-literate patients, as current methods are expensive, require consistent connectivity and expect literate users. Our design considerations address these concerns by providing low-cost medical devices connected to a low-cost health platform, along with personalized guidance based on patient physiological parameters in local languages, and alerts to medical practitioners in case of emergencies. This patient-centric integrated healthcare system is designed to manage the overall health of villagers with real-time health monitoring of patients, to offer guidance on preventive care, and to increase health awareness and self-monitoring at an affordable price. This personalized health monitoring system addresses the health-related needs in remote and rural areas by (1) empowering health workers in monitoring of basic health conditions for rural patients in order to prevent escalations, (2) personalized feedback regarding nutrition, exercise, diet, preventive Ayurveda care and yoga postures based on vital parameters and (3) reporting of patient data to the patient's health center with emergency alerts to doctor and patient. The system supports community health workers in the diagnostic procedure, management, and reporting of rural patients, and functions well even with only intermittent access to Internet.

There is an explosive growth in e-Learning platforms, jointly developed by multiple institutions, which provide for virtual learning content. However, many are inadequate to support the complex requirements for collaborative development of distributed learning such as accommodation of wide-ranging technologies, servers, and remote equipment controlled by diverse software. Our solution is a multi-tier architecture that supports collaborative development, publishing in various online and print formats, security, audit, and access controls. Our design considerations include a highly scalable platform, use of open technologies, templates that provide pedagogical structure, multilingual functionality, and shared virtual availability of lab equipment from multiple geographic locations, along with secure access to remote equipment.

We consider the problem of routing multiple teams of health workers during a vaccination campaign. We formulate the routing problem as a bi-objective team orienteering problem with additional constraints. The two objectives are to minimize the total time and to maximize vaccination coverage. The set of Pareto-optimal solutions is computed by an epsilon-constraint method. Small instances of the problem can be solved exactly by branch-and-cut, and larger instances by heuristic methods. As an example for the model, we consider optimal tour planning for the Measles and Rubella Campaign in Kochi, South India.

The Cognitive Theory of Multimedia Learning (CTML) offers insights on creating, organizing and presenting multimedia content in a way that can enhance the effectiveness of learners. While several studies have been conducted to verify these principles, not many have been done using content presented on low cost tablets. In this paper, we present our experimental study on the retention and understanding by children when learning content a) adheres to CTML and b) offered on low cost tablets. In our study we used Online Labs theory and videos and incorporated CTML principles into it. According to CTML principle it will maximize learning without causing cognitive overload. The study sample was 58 students from an English medium secondary education school from south India. The experiment involves a control and experiment group where the control group is tested on content which does not adhere to CTML and the experimental group is tested on content designed based on CTML. A pre-test is conducted to assess the level of pre-knowledge in the subject and a post-test is conducted to assess the retention and understanding by students. This suggests that tablet content incorporated with CTML principle can lead to a deeper understanding of the subject.

Combining nuchal translucency (NT) and serum biochemistry during first-trimester screening is accepted as a good model for aneuploidy screening, offering over 92% detection rate. Frontomaxillary facial angle (FMF) measurement has been shown to further improve the screening for trisomy 21. Existing methods that measure NT and FMF, are either manual or semi-automated and may be subject to measurement errors by sonographers. This paper presents an automated and computerized algorithm for the measurement of both NT and FMF. Only fetal images in the neutral position are considered in the study. The FMF angle is calculated by segmenting out the region of interest, line fitting at the frontal bone and upper part of the palate and calculating the angle between the lines. NT measurement is done by automating the calculation of the maximum width of the fluid-filled space under the skin at the back of fetus's

We consider the problem of optimal planning of tours, during an extensive vaccination campaign. Our primary goal was to vaccinate as many children as possible, while investing as little resources as possible. The trade-off between the number of dispensed vaccinations and the magnitude of invested resources in the vaccination campaign is formulated as a bi-objective optimization problem. We discuss how the Pareto front, for this problem, can be deduced using genetic algorithms. We verified the viability of our approach in the planning of the Measles and Rubella (MR) Campaign in tribal areas of Kerala, a state in southern India.

Online Labs or OLabs refers to a virtual learning system for the conduct/management of practicals in a laboratory. OLabs can be configured to handle practical experiments from various subjects like Physics, Chemistry, Biology Mathematics and English, etc. Besides the theory on which it is based, each experiment may involve one or more procedure, simulator, animation, videos, viva voce questions, and links to other relevant resources. A teacher training workshop was conducted using OLabs, where teachers were instructed on the planning and setup of Lab experiments for secondary (9th & 10th grade) and senior secondary (11th & 12th grade) classes. The aim of this study was to comprehend the effectiveness of deployment of the OLabs tool for teacher training. Likert-analysis of the ensuing workshop-survey revealed that a majority of teachers were in favor of, and even repeat the OLabs experiments. Majority of the respondents were convinced that OLabs systems offer an improved understanding of theoretical concepts. Albeit they may not entirely replace the real physical labs, OLabs can provide numerous opportunities for enhanced learning of basic concepts.

A problem that is prevalent among many of the tribal communities in Kerala is the addiction to alcohol, tobacco and drugs. Keeping youngsters from becoming addicted is a major part of the battle and is easier than trying to de-addict them later. We discuss an integrated program that trained 1000 indigenous, primarily adolescents and young adults, in digital literacy and health awareness using tablet technology in their native language. The tablet modules were designed for lowliterate learners. Technology enhanced health literacy, substance abuse and mental health modules were designed for youth and adolescents. A survey was administered to 98 students in four villages belonging to the Irula and Muthuvan communities to understand the prevalence of substance abuse and awareness about ill effects of the substance abuse after the training. Index Terms—substance abuse, health awareness, digital literacy, tablet learning, tribal communities.

Dyslexia is a complex learning disorder that impairs the acquisition of reading and writing skills. The manifestation of dyslexia in an individual depends not only upon individual cognitive differences, but also on the language used. We are engaged in a long-term study on the early assessment and remediation of dyslexia in children in Kerala State, South India, where Malayalam is spoken at home and English and Malayalam are taught in school. We have designed bilingual MalayalamEnglish dyslexia screening tests and have administered them in schools in Kerala. This paper reports on a study where our screening test was administered to 39 second-grade students in three Government schools, and spelling errors in dictation and text-copying tasks were classified as phonological and orthographic errors. Despite the transparent orthography of Malayalam, poor readers made more spelling errors in Malayalam than English, possibly due to the large number of intricate letters and letter combinations in the Malayalam alphabet. We therefore suggest that a dyslexic child be drilled in the use of a few frequently occurring letters, especially in the initial stages of learning to read Malayalam.

Online Labs (OLabs) is an innovative learning tool focused on virtual laboratory experiments for secondary school education. The purpose of this present study is to examine student perceptions regarding learning when using simple lowcost activities (Activity Based Learning (ABL)) that teach the same concepts as the corresponding science OLabs experiment. Our sample consisted of 131 students (male=66, female=65) studying in the 8th grade. All students had the same level of exposure to science courses at the school. A five-point Likert scale questionnaire was administered to understand students' interest, ease of use and attitude towards OLabs-based ABL. The investigation revealed that a sizable majority of the students, were excited about using OLabs based ABL methodology, in their current curriculum as well as in the future. The gender based analysis showed that female candidates were more interested in using ABL methodology. Our findings contribute to the design of a new pedagogy model for incorporating low-cost science activities with virtual labs to reach students in schools that do not have access to science labs.

Intelligent tutoring systems (ITS) supplement traditional learning by providing personalized instruction. Predicting student performance in formative and summative assessments can help educators and parents determine suitable learning interventions. In this article, interaction log data from three south Indian schools using Amrita Learning ITS were gathered and analyzed. We investigated the extent to which information from the system improves the prediction of students' performance on both formative and summative assessments. Results indicated that prediction improves significantly for both formative and summative assessments when compared to models that only use pretest information.

The Indian state of Kerala has a high literacy rate and human development index compared to other states in India. But this has not extended to the tribal population of the state. Female tribal populations are particularly disadvantaged for a variety of reasons including vulnerability to exploitation and abuse. This study investigates factors contributing to the high dropout rate and evaluates the success of a computer literacy intervention with tribal girls who had previously dropped out of the education system. A sample of 31 students in two centers was administered a survey to identify why the girls had dropped out of the school system. The analysis showed three clusters of learners. The students received computer literacy training after which they took an externally certified examination in basic Digital Literacy and computer concepts. Policy recommendations to decrease the dropout rate, ensure safety, and encourage further education for tribal girls are presented.

Dyslexia is a learning disability that affects accurate and fluent word reading and spelling. Despite its prevalence, many primary school teachers and educators in India are unaware of dyslexia. Consequently, many students struggle through school without appropriate support. To facilitate identification of dyslexic students, we designed a screening test and administered it to 135 primary school children studying in Government and private schools in Haripad, a small town in Kerala State, India. The tasks included letter recognition, word recognition, recognition of rhyming words, spelling tests, and handwriting tasks in English and Malayalam (the local language), and assessed phonological awareness, visual processing, rapid naming, and motor skills. The students' answers were analyzed, mistakes were categorized, and possible causes for the mistakes were examined.

In remote rural areas, the availability of trained and qualified teachers is poor. Rural teaching is teachercentric instead of student-centric. A systematic monitoring system to ensure that teachers practice the methods they learn at pre- or in-service trainings is not yet in place. Plagued by such deficiencies, present day rural education in India lacks quality, and children read, write, and compute several levels below grade level. Our intervention comes from the premise that reform approach in rural education should be at the grassroots level, involving comprehensive change in teaching and learning attitudes, teaching methodology and subject matter expertise. Amrita Rural India Tablet Education Teacher Training Program is a technology-enabled training program for teachers that train them to be change-agents and influence both children and communities to bring about sustainable change in attitudes as well as education and learning outcomes. AmritaRITE utilizes cutting edge mobile learning technology in both teaching and monitoring, to improve quality and accountability, even in low-electricity and intermittent-connectivity areas. The comprehensive program trains teachers in tablet-supported teaching methodologies, multi-age classrooms, classroom management styles suited to specific environment, addressing different learning modalities, developing student critical thinking, identifying learning disabilities and overcoming social barriers such as educating girls and low literacy communities.

Reduction of teacher and student absenteeism, together with consistent teacher support and training, are critical factors in improving the quality of education in rural India. As part of an ongoing project involving schools and educational centers in rural areas spread across 21 Indian states, this study investigated how implementation of two simple, accessible technologies could not only reduce absenteeism but also increase teachers' effectiveness and improve student performance. In addition to students and teachers, key stakeholders included educational coordinators who provided support and monitoring regarding use of WhatsApp and two additional apps designed specifically to support simple educational improvements. In our study we coded and analyzed nine months of messages (nþinspace}=þinspace}8968), both photographs and texts, posted by 26 participants. The number of text messages related to attendance was strongly positively correlated with frequency of interactions between coordinators and teachers. Our approach resulted in increased teacher and student attendance, as well as improvements in lessons and other planned educational activities. This model functions well in rural settings where there is poor internet connectivity and lack of supporting infrastructure. Remote schools can easily adopt this tablet-based model to reduce teacher absenteeism, improve teaching techniques, improve educational resources, and increase student performance.

Cybersecurity is increasingly becoming relevant in India. In recent years, the Indian government has been in-centivizing cashless transactions and few villages have been completely digitized. A major concerns of digitization is the rising cyber crimes such as malware infections, cyberbullying and other online financial frauds. Nearly 70% of India lives in villages. Channelising the young minds in villages towards informed use of technology and information security awareness can greatly benefit the cyber safety of the country. In this paper, we describe a game-based training model for imparting cybersecurity education and awareness for village students in India. We conducted pilot workshops in two different villages in Andhra Pradesh, a southern state in India. We blended constructivist pedagogy along with game based learning and collaboration. The training involved theory classes along with practical and game

India has made good progress in many of the Millennium Development Goals but a dismal number of children in remote and rural India continue to drop out of school or perform poorly in reading, arithmetic and sciences. Our model for Inclusive Education, called Amrita Rural India Tablet enhanced Education (AmritaRITE, 2016) is inspired and guided by the principle of providing both ‘Education for a Living’ and ‘Education for Life’ skills. AmritaRITE integrates traditional school educational goals with awareness regarding moral, scientific, technological, ecological, and social issues. The curriculum includes such topics as health and nutrition, moral values, technology skills, gender equality, child labor and trafficking awareness as well as respect for each other and for Mother Nature to ensure the holistic growth of the child. To achieve these goals, our program utilizes sophisticated multilingual mobile learning aids that are adapted for rural areas to work with low-bandwidth Internet. The methodology evolved through our experiences working in 41 remote villages in 21 diverse states of India over a period of two years; thus, the AmritaRITE program was designed for adaptability to individual community circumstances. School systems and NGOs can incorporate key elements of AmritaRITE’s holistic curriculum, models for community involvement, teacher training and e-learning technology to achieve quality and inclusive education in both village and urban environments.

Medical Virtual Patient Simulator (MedSIM) is a cutting-edge E-learning innovation for medical and other health professionals. It consists of a framework that supports various patient cases, tailored by interdisciplinary medical teams. Each virtual patient case follows the critical path to be followed for a specific patient in a hospital. MedSIM takes the student on a journey that enables the student to interview, examine, conduct physical, systematic and ultimately reach a diagnosis based on the path that is chosen.

Annex 3. Attendance of the Workshop (Speakers and Observers) Participants and Speakers Allende, Jorge (Chile) Arber, Werner (Switzerland) Archer, Margaret (UK) Arancibia, Luis (Colombia) Bhavani, Rao R.(India) Basu, Kaushik (USA) Blamont, Jacques (France) Coppens, Yves (France) Hillis, Daniel W.(USA) Holman, John (UK) Hugonnier, Bernard (France) Koizumi, Hideaki (Japan) Lee, Yee Cheong (Malaysia) Léna, Marguerite (France) Léna, Pierre (France) Lu, Mai (China) Palmeyro, Enrique (Argentina) Pasquinelli, Elena (France) Prema, Nedungadi (Amrita University, India) Ramanathan, Veerhabhadran (USA) Ross, Courtney (USA) Sachs, Jeffrey (USA) Samroo, Manzoor (Pakistan) Sánchez-Sorondo, Marcelo (Vatican) Sánchez Terán, Gonzalo (Spain) Singer, Wolf (PAS, Germany) Strauss, Sydney (Israel) Suñol, Ignacio (Colombia) Tobechi, Anyadike … Von Braun, Joachim

Lately, modern applications like information retrieval, semantic scene classification, music categorization and functional genomics classification highly require multi label classification. A rule mining algorithm apriori is widely used for rule generation. But Apriori is used many times on categorical data, it is seldom used for numerical data. This leads to an idea that with proper data pre-processing, a lot of intangible rules can be derived from such numerical datasets. Since the algorithm will check each and every datasets, we used a simple k-means clustering approach for dividing the processing space of Apriori and thus rules are generated for each cluster. The accuracy of the algorithm is calculated using hamming loss and is presented in the paper. This hybrid algorithm directly aims to find out hidden patterns in huge numerical datasets and make reliable label prediction easier.

Learning to read correctly is a key requirement of language learning. In rural India, due to lack of teachers and technology, tablets offer a creative and motivating learning environment. Tablet technology has the advantage of mobility, allowing users to learn at their own pace and convenience. However, the non-availability of electricity and Internet can be unique challenges. At Amrita CREATE, language-learning solutions have been developed for students to learn and read on the tablets. It uses advanced speech recognition technique to provide feedback and intervention. Proposed system is unique in its ability to evaluate words and phrases and corrects the learner as they articulate the sentence. This system works without Internet and on the lower processing power of android tablets. Silence detection and multiple-synchronized recognition have been introduced in this paper which greatly enhance the ability to provide feedback to the user in real-time. The combination of the two helps in achieving successful recognition of longer and continuous sentence.

Predicting Student Performance is the process that predicts the successful completion of a task by a student. Such systems may be modeled using a three-mode tensor where the three entities are user, skill, and task. Recommendation systems have been implemented using Dimensionality reduction techniques like Higher Order Singular Value Decomposition (HOSVD) combined with Kernel smoothing techniques to bring out good results. Higher Order Orthogonal Iteration (HOOI) algorithms have also been used in recommendation systems to bring out the relationship between the three entities, but the prediction results would be largely affected by the sparseness in the tensor model. In this paper, we propose a generic enhancement to HOOI algorithm by combining it with Kernel smoothing techniques. We perform an experimental comparison of the three techniques using an ITS dataset and show that our proposed method improves the prediction for larger datasets.

Matrix factorization is the most popular approach to solving prediction problems. However, in the recent years multiple relationships amongst the entities have been exploited in order to improvise the state-of-the-art systems leading to a multi relational matrix factorization (MRMF) model. MRMF deals with factorization of multiple relationships existing between the main entities of the target relation and their metadata. A further improvement to MRMF is the Weighted Multi Relational Matrix Factorization (WMRMF) which treats the main relation for the prediction with more importance than the other relations. In this paper, we propose to enhance the prediction accuracy of the existing models by personalizing it based on student knowledge and task difficulty. We enhance the WMRMF model by incorporating the student and task bias for prediction in multi-relational models. Empirically we have shown using over five hundred thousand records from Knowledge Discovery dataset provided by Data Mining and Knowledge Discovery competition that the proposed approach attains a much higher accuracy and lower error(Root Mean Square Error and Mean Absolute Error) compared to the existing models.

Optical character recognition (OCR) transforms printed text to editable format and digital writing on smart devices. Learning to write programs has made learners trace an alphabet to learn the flow of writing and OCR by itself is less effective as it ignores the directional flow of writing and only focuses on the final image. Our research designed a unique android-based multilingual game-like writing app that enhances the writing experience. A key focus of the research was to compare and identify character recognition algorithms that are effective on low-cost android tablets with limited processing capabilities. We integrate a quadrant-based direction checking system with artificial neural networks and compare it to the existing systems. Our solution has the dual advantage of evaluating the writing direction and significantly increasing the accuracy compared to the existing systems. This program is used as the literacy tool in many villages in rural India.

Medical Virtual Patient Simulator (MedVPS) is a cutting-edge eLearning innovation for medical and other health professionals. It consists of a framework that supports various patient cases, tailored by interdisciplinary medical teams. Each virtual patient case follows the critical path to be followed for a specific patient in a hospital. MedVPS takes the student on a journey that enables the student to interview, examine, conduct physical, systematic and ultimately reach a diagnosis based on the path that is chosen. After the interactions, the student must decide whether each response is normal or abnormal and use the virtual findings to identify multiple probable diagnoses or reexamine the virtual patient with the goal to narrow down to the correct disease and then provide treatment. We present the architecture and functionality of the MedVPS platform and include a pilot study with medical students. © Springer International Publishing Switzerland 2016.

ICT-enabled virtual and remote labs have become a platform augmenting user engagement in blended education scenarios enhancing University education in rural India. A novel trend is the use of remote laboratories as learning and teaching tools in classrooms and elsewhere. This paper reports case studies based on our deployment of 20 web-based virtual labs with more than 170+ online experiments in Biotechnology and Biomedical engineering discipline with content for undergraduate and postgraduate education.

The problem of high dimensionality in multi-label domain is an emerging research area to explore. A strategy is proposed to combine both multiple regression and hybrid k-Nearest Neighbor algorithm in an efficient way for high-dimensional multi-label classification. The hybrid kNN performs the dimensionality reduction in the feature space of multi-labeled data in order to reduce the search space as well as the feature space for kNN, and multiple regression is used to extract label-dependent information from the label space. Our multi-label classifier incorporates label dependency in the label space and feature similarity in the reduced feature space for prediction. It has various applications in different domains such as in information retrieval, query categorization, medical diagnosis, and marketing.

The problem of high dimensionality in multi-label domain is an emerging research area to explore. A strategy is proposed to combine both multiple regression and hybrid k-Nearest Neighbor algorithm in an efficient way for high-dimensional multi-label classification. The hybrid kNN performs the dimensionality reduction in the feature space of multi-labeled data in order to reduce the search space as well as the feature space for kNN, and multiple regression is used to extract label-dependent information from the label space. Our multi-label classifier incorporates label dependency in the label space and feature similarity in the reduced feature space for prediction. It has various applications in different domains such as in information retrieval, query categorization, medical diagnosis, and marketing.

Matrix factorization is the most popular approach to solving prediction problems. However, in the recent years multiple relationships amongst the entities have been exploited in order to improvise the state-of-the-art systems leading to a multi relational matrix factorization (MRMF) model. MRMF deals with factorization of multiple relationships existing between the main entities of the target relation and their metadata. A further improvement to MRMF is the Weighted Multi Relational Matrix Factorization (WMRMF) which treats the main relation for the prediction with more importance than the other relations. In this paper, we propose to enhance the prediction accuracy of the existing models by personalizing it based on student knowledge and task difficulty. We enhance the WMRMF model by incorporating the student and task bias for prediction in multi-relational models. Empirically we have shown using over five hundred thousand records from Knowledge Discovery dataset provided by Data Mining and Knowledge Discovery competition that the proposed approach attains a much higher accuracy and lower error(Root Mean Square Error and Mean Absolute Error) compared to the existing models.

The problem of high dimensionality in multi-label domain is an emerging research area to explore. A strategy is proposed to combine both multiple regression and hybrid k-Nearest Neighbor algorithm in an efficient way for high-dimensional multi-label classification. The hybrid kNN performs the dimensionality reduction in the feature space of multi-labeled data in order to reduce the search space as well as the feature space for kNN, and multiple regression is used to extract label-dependent information from the label space. Our multi-label classifier incorporates label dependency in the label space and feature similarity in the reduced feature space for prediction. It has various applications in different domains such as in information retrieval, query categorization, medical diagnosis, and marketing.

Personalization and adaptation are at the core of Intelligent Tutoring Systems. The Bayesian Knowledge Tracing (BKT) Student Model is a time-tested method that maintains information about students' knowledge levels for the different skills in the topic domain. In our previous work, we had proposed the Personalized, Clustered, Bayesian Knowledge Tracing (PC-BKT) model that individualizes the learning of skills for each student and additionally improves the prediction for the cold start problem. A clustering of both students and skills based on a student and skill capability matrix was used to learn the prior skills to deal with the cold start problem, which is the prediction for either new skills or new students. Both the BKT and the PC-BKT models assume that a skill once learnt is never forgotten. But forgetting is pervasive. If a previously learnt skill is not used for a while, there is a higher chance of forgetting it. One of the factors that influence the forgetting is the time duration before the current attempt at using a skill and the previous attempt. We incorporate forgetting as a time decay function in the BKT and PC-BKT models and show significant increase in the accuracy of the student prediction.

An Intelligent Tutoring System (ITS) supplements traditional learning methods and is used for personalized learning purposes that range from exploring simple examples to understanding intricate problems. The Bayesian Knowledge Tracing (BKT) model is an established method for student modeling. A recent enhancement to the BKT model is the BKT-PPS (Prior Per Student) which introduces a prior learnt for each student. Although this method demonstrates improved prediction results compared to the others, there are several aspects that limit its usefulness; (a) for a student, the prior learning is common for all skills, however in reality, it varies for each skill (b) Different students have varying learning capabilities; therefore these students cannot be considered as a homogenous group. In this paper, we aim to improve the prediction of student performance using an enhanced BKT model called the PC-BKT (Personalized & Clustered) with individual priors for each student and skill, and dynamic clustering of students based on changing learning ability. We evaluate the predictions in terms of future performance within ASSISTments intelligent tutoring dataset using over 240,000 log data and show that our models increase the accuracy of student prediction in both the general and the cold start problem.

Our paper proposes a new pedagogical approach for learning chemistry practical experiments based on three modes of inquiry-based learning namely; structured, guided and open. Online Labs (OLabs) is a web-based learning environment for science practical experiments that include simulations, animations, tutorials and assessments. Inquiry-based learning is a pedagogy that supports student-centered learning and encourages them to think scientifically. It develops evidence based reasoning and creative problem solving skills that result in knowledge creation and higher recall. We discuss the methodology and tools that OLabs provides to enable educators to design three types of inquiry-based learning for Chemistry experiments. The integration of inquiry-based learning into OLabs is aligned with the Indian Central Board of Secondary Education (CBSE) goal of nurturing higher order inquiry skills for student centered and active learning. Inquiry-based OLabs pedagogy also empowers the teachers to provide differentiated instruction to the students while enhancing student interest and motivation.

In this paper we describe the architecture of an e-learning environment that blends concept maps with Online Labs (OLabs) to enhance student performance in biology. In the Indian context, a secondary school student’s conceptual understanding of hard topics in biology is at risk because of a lack of qualified teachers and necessary equipments in labs to conduct experiments. Concept map provides a visual framework which allows students to get an overview of a concept, its various sub concepts and their relationships and linkages. OLabs with its animations, videos and simulations is an interactive, immersive approach for practicing science experiments. The blended e-learning environment was tested by systematically developing a concept map for the concept “Photosynthesis” and by successfully integrating it into the OLabs environment. Our blended approach to concept understanding has interesting implications for the teacher who is engaged in training programs.

Computer science (CS) and its enabling technologies are at the heart of this information age, yet its adoption as a core subject by senior secondary students in Indian schools is low and has not reached critical mass. Though there have been efforts to create core curriculum standards for subjects like Physics, Chemistry, Biology, and Math, CS seems to have been kept outside the purview of such efforts leading to its marginalization. As a first step, using the Darmstadt model from the ITiCSE working group that provides a systematic categorization approach to CS education in schools, we coded and analyzed the CS situation for the Indian schools. Next, we focused on the motivation category of the Darmstadt model and investigated behavioral intentions of secondary school students and teachers from 332 schools in India. Considering the CS subject as an educational innovation, using Rogers’ Theory of Diffusion of Innovations, we propose a pedagogical framework for innovation attributes that can significantly predict-adoption of the CS subject among potential-adopter students and teachers. Data was analyzed to answer research questions about student and teacher intentions, influence of gender, school management, and school location in adopting CS. Interestingly, girls, urban students, teachers, and private schools were seen favoring the adoption of CS. An important issue that needed to be addressed, however, was the interchangeable use of terms like CS, Informatics, ICT, and digital literacy. Through our article, we offer a promising picture of the educational policy directives and the academic environment in India that is rapidly growing and embracing CS as a core subject of study in schools. We also analyze the factors that influence the adoption of CS by school students and teachers and conclude that there is a very positive response for CS among educators and students in India.

This paper examines the dynamics of access and exclusion in children’s Internet use, in both private and public school spaces and interrogates the role of socioeconomic and demographic predictors as well as the schooling system in shaping Internet habits. More specifically, it explores the nature of Internet use by primary school children, mainly for education and information and attempts to understand the differences across and within two types of schools- a rural public school and an elite private school. Through in-depth interviews, this research investigates the level of computer and Internet literacy among the primary school children in the age group of 8-10 years and reports the differences observed among the various social dimensions. It attempts to stress the significance and need in today’s context to provide the opportunities for physical and material access so that disadvantaged children are not excluded from the digital opportunities. © Media Watch.

The Shodhganga@ INFLIBNET Centre provides a platform for research students to deposit their Ph. D. theses and make it available to the entire scholarly community in open access. Shodhganga Mirror Site

Personalization and adaptation are at the core of Intelligent Tutoring Systems. The Bayesian Knowledge Tracing (BKT) Student Model is a time-tested method that maintains information about students' knowledge levels for the different skills in the topic domain. In our previous work, we had proposed the Personalized, Clustered, Bayesian Knowledge Tracing (PC-BKT) model that individualizes the learning of skills for each student and additionally improves the prediction for the cold start problem. A clustering of both students and skills based on a student and skill capability matrix was used to learn the prior skills to deal with the cold start problem, which is the prediction for either new skills or new students. Both the BKT and the PC-BKT models assume that a skill once learnt is never forgotten. But forgetting is pervasive. If a previously learnt skill is not used for a while, there is a higher chance of forgetting it. One of the factors that influence the forgetting is the time duration before the current attempt at using a skill and the previous attempt. We incorporate forgetting as a time decay function in the BKT and PC-BKT models and show significant increase in the accuracy of the student prediction.

An Intelligent Tutoring System (ITS) supplements traditional learning methods and is used for personalized learning purposes that range from exploring simple examples to understanding intricate problems. The Bayesian Knowledge Tracing (BKT) model is an established method for student modeling. A recent enhancement to the BKT model is the BKT-PPS (Prior Per Student) which introduces a prior learnt for each student. Although this method demonstrates improved prediction results compared to the others, there are several aspects that limit its usefulness; (a) for a student, the prior learning is common for all skills, however in reality, it varies for each skill (b) Different students have varying learning capabilities; therefore these students cannot be considered as a homogenous group. In this paper, we aim to improve the prediction of student performance using an enhanced BKT model called the PC-BKT (Personalized & Clustered) with individual priors for each student and skill, and dynamic clustering of students based on changing learning ability. We evaluate the predictions in terms of future performance within ASSISTments intelligent tutoring dataset using over 240,000 log data and show that our models increase the accuracy of student prediction in both the general and the cold start problem.

Experimental learning combined with theoretical learning enhances the conceptual understanding of a subject. Therefore, the Online Labs (OLabs) that hosts science experiments was developed. OLabs uses interactive simulations with theory, procedure, animations, videos, assessments and reference material. Our study blended OLabs with concept maps to examine if it enhances students' learning in Biology. Concept mapping is a framework that provides a deeper knowledge of a subject by understanding the relationships among concepts. The study was quasi-experimental; pre-test, post-test and a satisfaction survey was used as measurement instruments. The study sample was 54 students from a school in Haripad, Kerala, India. The students were randomly grouped into a control and an experimental group. The experimental group that used concept maps as a learning aid scored slightly higher, suggesting blending concept maps can lead to a deeper understanding of the subject. Gender difference did not significantly affect the scores.

The field of data mining is concerned with finding interesting patterns from an unstructured data. A simple, popular as well as an efficient clustering technique for data analysis is k-means. But classical k-means algorithm can only be applied to numerical data where k is a user given value. But the data generated from a wide variety of domains are of mixed form and it is effortful to trust on a user given value for k. So our objective is to effectively use an association rule mining algorithm which can automatically compute the number of clusters and a pairwise distance measure for calculating the distance in mixed data. We have done experimentations with real mixed data taken from the UCI repository.

Many students struggle with reading when whole group instruction forms the core of the reading program. This is especially true when teaching second language students. The proposed intervention methodology combines multiple proven methods to improve reading skills in students. The study focused on using differentiated instruction and multiple assessments such as Informal Reading Inventory (IRI), Qualitative Spelling Inventory (QSI), Running Records, Dynamic Indicators of Basic Early Literacy Skills (DIBELS), High-frequency words and phonological awareness. After the usage of the said tools, students learnt to follow a firm reading routine, respect classroom procedures, work in teams and solve problems independently. This five-month study examined the benefits of the differentiated instruction with thirty six 5th grade students, who were the second language English learners in a school in the state of Karnataka, India. The key findings from this study indicated that differentiating instruction and using small group instruction assisted and improved students' reading and writing proficiency. With our proposed method, 94% of the students improved their reading comprehension by a minimum of three grade levels. An unexpected benefit was a positive change in attitude and behavior of the students along with increased confidence.

Self Organizing Maps perform clustering of data based on unsupervised learning. It is of concern that initialization of the weight vector contributes significantly to the performance of SOM and since real world datasets being high-dimensional, the complexity of SOM tend to increase tremendously leading to increased time consumption as well. Our work focuses on the analysis of different weight initialization strategies and various dimensionality reduction measures with the intent to make SOM flexible for handling high-dimensional datasets. We use two methods of comparison, one on projected space and another before projection. The datasets used are real world datasets taken from UCI repository.

India's medical education domain is one of the largest in the world. Medical Simulation aims to provide a medically accurate simulation that benefits the medical students to learn and understand any medical cases. Medical Simulations facilitates students with interactive learning and real-time feedback which does not risk the patient's life. Simulations can be performed any number of time until they have build their knowledge base and confidence in the given medical case. We propose a medically realistic cataract surgery simulation developed with a game engine. The users will be able to interact and use the on screen elements using hand gestures. A Motion recognition device captures every hand movement of the users and the simulation responds accordingly to provide feedback in real-time. Every movement is accurately tracked in the simulation and has a significant outcome on the subject based on the type of simulation. The simulated medical procedures for cataract surgery include using Surgical Tools, Surgical Procedures, Artificial Lens Implantation etc. Medical Simulation is being designed to provide an easy to use learning environment to replicate the clinical scenarios and allow features such as interactively practicing and providing feedbacks for medical skills development.

The reliability of automated essay scoring (AES) has been the subject of debate among educators. Most systems treat essays as a bag of words and evaluate them based on LSA, LDA or other means. Many also incorporate syntactic information about essays such as the number of spelling mistakes, number of words and so on. Towards this goal, a challenging problem is to correctly understand the semantics of the essay to be evaluated so as to differentiate the intended meaning of terms used in the context of a sentence. We incorporate an unsupervised word sense disambiguation (WSD) algorithm which measures similarity between sentences as a preprocessing step to our existing AES system. We evaluate the enhanced AES model with the Kaggle AES dataset of 1400 pre-scored text answers that were manually scored by two human raters. Based on kappa scores, while both models had weighted kappa scores comparable to the human raters, the model with the WSD outperformed the model without the WSD.

Feature selection algorithms look to effectively and efficiently find an optimal subset of relevant features in the data. As the number of features and the data size increases, new methods of reducing the complexity while maintaining the goodness of the features selected are needed. We review popular feature selection algorithms such as the probabilistic search algorithm based Las Vegas Filter (LVF) and the complete search based Automatic Branch and Bound (ABB) that use the consistency measure. The hybrid Quick Branch and Bound (QBB) algorithm first runs LVF to find a smaller subset of valid features and then performs ABB with the reduced feature set. QBB is reasonably fast, robust and handles features which are interdependent, but does not work well with large data. In this paper, we propose an enhanced QBB algorithm called QBB Iterative (QBB-I).QBB-I partitions the dataset into two, and performs QBB on the first partition to find a possible feature subset. This feature subset is tested with the second partition using the consistency measure, and the inconsistent rows, if any, are added to the first partition and the process is repeated until we find the optimal feature set. Our tests with ASSISTments intelligent tutoring dataset using over 150,000 log data and other standard datasets show that QBB-I is significantly more efficient than QBB while selecting the same subset of features. © Springer International Publishing Switzerland 2014.

Virtual Labs (VLAB) is a multi-institutional Open Educational Resources (OER) initiative, exclusively focused on lab experiments for engineering education. This project envisages building a large OER repository, containing over 1650 virtual experiments mapped to the engineering curriculum. The introduction of VLAB is a paradigm shift in an educational system that is slow to change. Treating VLAB OER as an educational technology innovation, its adoption by potential-adopter engineering students (N=131) is modeled based on Roger's theory of perceived attributes. Regression and factor analysis were used to analyze the data. Results indicate that the attributes of Compatibility, Ease of Use, Relative Advantage, and Trialability significantly influence potential-adopter students' intention to adopt an innovation like VLAB. The study also observed that using OER (such as VLAB) on desktops and low-cost tablets had similar effects in student performance to using physical labs. This has interesting implications for education policy-makers who are looking to reduce the digital divide.

Luz gave the Treasurer’s report. She noted that the Society’s finances have significantly improved over the last couple of years. She noted that the starting cash on hand as of January 1, 2012 was $474,401.96. As of June 30, 2011 we had $157,970.68 in total income and $76,980.36 in total disbursements and thus our current cash on hand is $555,392.28. Roger Millsap gave the Editorial Council report. A total of 159 new manuscripts were submitted to Psychometrika so far in the 2012–2013. This figure compares to 144 during the 2010–2011 and 151 for 2010–2011. Our ARCS submission rate was down this year, with only 40 manuscripts this year compared to 50 last year. Considering the entire decision pool to date for 2012–2013 (both new and revised), decisions were made on 253 manuscripts. Of the 253 manuscripts, 23% were accepted, 14% were conditionally accepted, 28% were given a revise and

Abstracting is permitted with credit to the source. Libraries are permitted to photocopy beyond the limit of U.S. copyright law for private use of patrons those articles in this volume that carry a code at the bottom of the first page, provided the per-copy fee indicated in the code is paid through Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA 01923. For reprint or republication permission, email to IEEE Copyrights Manager at pubs-permissions@ieee.org(link sends e-mail)

Online Labs are revolutionizing education by offering access to content anytime and from any place. The OLabs project has had a deep impact on learning capabilities of students by providing an integrated environment that includes videos, animations, simulations and textual content. It has also helped to substitute teachers wherever there have been gaps. OLabs offers an excellent platform for the improvement of Science, Technology, Engineering and Maths (STEM) education which has been the focus of several countries in recent times. The current content in OLabs is 2 dimensional. 2D content comes with its own limitations of low accuracy and low realism and hence moving to browser based 3D representations is important to offer an enriching experience to the learner. WebGL offers the powerful capability of rendering 2D as well as 3D content in any browser without the need to install additional applications or components. With the advent of WebGL, writing 3D applications have become simpler since most details are abstracted from the programmer. New features are added almost every week in WebGL by the community making it rich and powerful. In this paper we present our work on implementing, in 3D, a convex lens experiment in OLabs Physics using WebGL and dynamic cube mapping. We propose to extend this work to more experiments in Physics and Chemistry, demonstrate it to students and measure their learning.

The high computational complexity of text classification is a significant problem with the growing surge in text data. An effective but computationally expensive classification is the k-nearest-neighbor (kNN) algorithm. Principal Component Analysis (PCA) has commonly been used as a preprocessing phase to reduce the dimensionality followed by kNN. However, though the dimensionality is reduced, the algorithm requires all the vectors in the projected space to perform the kNN. We propose a new hybrid algorithm that uses PCA & kNN but performs kNN with a small set of neighbors instead of the complete data vectors in the projected space, thus reducing the computational complexity. An added advantage in our method is that we are able to get effective classification using a relatively smaller number of principal components. New text for classification is projected into the lower dimensional space and kNN is performed only with the neighbors in each axis based on the principal that vectors that are closer in the original space are closer in the projected space and also along the projected components. Our findings with the standard benchmark dataset Reuters show that the proposed model significantly outperforms kNN and the standard PCA-kNN hybrid algorithms while maintaining similar classification accuracy. Cite this R

Multi-label classification is an emerging research area in which an object may belong to more than one class simultaneously. Existing methods either consider feature similarity or label similarity for label set prediction. We propose a strategy to combine both k-Nearest Neighbor (kNN) algorithm and multiple regression in an efficient way for multi-label classification. kNN works well in feature space and multiple regression works well for preserving label dependent information with generated models for labels. Our classifier incorporates feature similarity in the feature space and label dependency in the label space for prediction. It has a wide range of applications in various domains such as in information retrieval, query categorization, medical diagnosis and marketing.

Information Retrieval (IR) systems such as search engines retrieve a large set of documents, images and videos in response to a user query. Computational methods such as Automatic Text Summarization (ATS) reduce this information load enabling users to find information quickly without reading the original text. The challenges to ATS include both the time complexity and the accuracy of summarization. Our proposed Information Retrieval system consists of three different phases: Retrieval phase, Clustering phase and Summarization phase. In the Clustering phase, we extend the Potential-based Hierarchical Agglomerative (PHA) clustering method to a hybrid PHA-ClusteringGain-K-Means clustering approach. Our studies using the DUC 2002 dataset show an increase in both the efficiency and accuracy of clusters when compared to both the conventional Hierarchical Agglomerative Clustering (HAC) algorithm and PHA.

An Intelligent Tutoring System (ITS) supplements traditional learning methods and is used for personalized learning purposes that range from exploring simple examples to understanding intricate problems. The Bayesian Knowledge Tracing (BKT) model is an established method for student modeling. A recent enhancement to the BKT model is the BKT-PPS (Prior Per Student) which introduces a prior learnt for each student. Although this method demonstrates improved prediction results compared to the others, there are several aspects that limit its usefulness; (a) for a student, the prior learning is common for all skills, however in reality, it varies for each skill (b) Different students have varying learning capabilities; therefore these students cannot be considered as a homogenous group. In this paper, we aim to improve the prediction of student performance using an enhanced BKT model called the PC-BKT (Personalized & Clustered) with individual priors for each student and skill, and dynamic clustering of students based on changing learning ability. We evaluate the predictions in terms of future performance within ASSISTments intelligent tutoring dataset using over 240,000 log data and show that our models increase the accuracy of student prediction in both the general and the cold start problem.

Sentiment analysis is a valuable knowledge resource to understand collective sentiments from the Web and helps make better informed decisions. Sentiments may be positive, negative or objective and the method of assigning sentiment weights to terms and sentences are important factors in determining the accuracy of the sentiment classification. We use standard methods such as Natural Language Processing, Support Vector Machines and SentiWordNet lexical resource. Our work aims at improving the sentiment classification by modifying the sentiment values returned by SentiWordNet for intensifiers based on the context to the semantic of the words related to the intensifier. We also reassign some of the objective words to either positive or negative sentiment. We test our sentiment classification method with product reviews of digital cameras gathered from Amazon and ebay and shows that our method improves the prediction accuracy.

In this paper we describe the architecture of an e-learning environment that blends concept maps with Online Labs (OLabs) to enhance student performance in biology. In the Indian context, a secondary school student’s conceptual understanding of hard topics in biology is at risk because of a lack of qualified teachers and necessary equipments in labs to conduct experiments. Concept map provides a visual framework which allows students to get an overview of a concept, its various sub concepts and their relationships and linkages. OLabs with its animations, videos and simulations is an interactive, immersive approach for practicing science experiments. The blended e-learning environment was tested by systematically developing a concept map for the concept “Photosynthesis” and by successfully integrating it into the OLabs environment. Our blended approach to concept understanding has interesting implications for the teacher who is engaged in training programs.

In our research we have designed pedagogy for Low Cost Tablets (LCT) to enhance early grade reading in multi-grade classrooms in rural areas of India. The use of LCT helps meet the challenge of education in areas where there is a lack of qualified tutors and shortage of computing resources. The program has been implemented with (N=38) students in tribal areas of Kerala. Reading was the most common problem with the primary children, while mathematics and reading comprehension was a major challenge for children who were in middle school. Our pilot study students were able to learn faster on their own without requiring formal training due to the ease of use and the touch based interface of LCT, and they liked the idea of repeating lessons as many times as they wished. Teachers were trained in the use of LCT for assessment and early intervention and effective ways to bring up the reading skills of the students. Our findings confirm that LCT is powerful motivator in education and has a huge potential to address the issue of school dropouts. Our proposed pedagogy for LCT and findings will be of interest to educational policy makers who are looking at LCT options such as Aakash tablets to improve literacy levels among early grade learners.

A large number of ethical hacking competitions are organized worldwide as Capture The Flag (CTF) events. But there does not exist a framework to evaluate and rank CTFs that will guide participants as to which CTF's to participate. In a CTF event, the participants are required to either solve a set of challenges to gain points or they are required to defend their system by eliminating the vulnerabilities while attacking other's system vulnerabilities. We are proposing a framework that would evaluate and rank CTFs according to factors like similarity of the tasks to the common critical vulnerabilities, solvability of tasks, periodicity, training given prior to CTF, geographical reach, problem solving skills etc. In the next step these factors are systematically assigned weights using Analytic Hierarchy Process. As part of frame work creation and validation, ten CTFs have been analysed. Our analysis indicates that: All CTFs fall in to one of the three categories (jeopardy, attack-defence and mixed); CTFs often adopt popular software vulnerabilities and threats as tasks to be solved; Only few CTFs give formal training prior to the event; Complexity of the tasks to be solved varies from CTF to CTF. Five CTFs were ranked using the newly developed framework.

The world of today is not looking for innovations that are mere incremental but those that are disruptive. Aakash, the Low Cost Tablet (LCT) initiative by Indian govt. was launched in 2011 amidst dominance by the likes of Apple, Amazon, and Samsung etc. Single most objective of this initiative was affordable ICT learning tool for the 220+ million students. LCT like Aakash can be seen as a disruptive innovation from the as they are simple to use, cheap, low performing, targeted at low portion of mainstream market and focused on social sectors like education, health to increase access and equity. Within Rogers theory of Diffusion of Innovation, we propose a framework for innovation attributes that can significantly predict student and teacher behavior intentions and motivations towards LCT for use in classrooms. Authors investigate the innovation attributes for adoption of LCT in a social group comprising of (N=121) potential-adopter students and teachers from India. The results revealed that motivations for adopting LCT are strongly associated with innovation attributes like relative advantage, compatibility, ease of use, peer influence, perceived enjoyment and perceived usefulness. Overall, both teachers and students expressed positive attitude towards using LCT as it enhanced their digital literacy skills. Bigger question is to identify what kind of new teacher training program, models and approaches and learning environment are required for successful adoption of educational innovation like LCT. Findings contribute to the design of new pedagogical models that maximizes learning potential of LCTs for K12 education.

The reliability of automated essay scoring (AES) has been the subject of debate among educators. Most systems treat essays as a bag of words and evaluate them based on LSA, LDA or other means. Many also incorporate syntactic information about essays such as the number of spelling mistakes, number of words and so on. Towards this goal, a challenging problem is to correctly understand the semantics of the essay to be evaluated so as to differentiate the intended meaning of terms used in the context of a sentence. We incorporate an unsupervised word sense disambiguation (WSD) algorithm which measures similarity between sentences as a preprocessing step to our existing AES system. We evaluate the enhanced AES model with the Kaggle AES dataset of 1400 pre-scored text answers that were manually scored by two human raters. Based on kappa scores, while both models had weighted kappa scores comparable to the human raters, the model with the WSD outperformed the model without the WSD.

Within the context of Roger’s Diffusion of Innovation theory we propose a pedagogical framework for attributes that can significantly affect student adoption of collaborative learning environment like multi-user, multi-touch tabletop. We investigated the learning outcomes of secondary school students in India collaboratively using OLabs on a tabletop (EG1 = 30) vs. individually using at desktops (EG2 = 92). We analyzed the nature of communication, touch and non-touch gesture actions, position around the tabletop, focus group interviews, and pre and post test scores. Using Bass model the study also accounts for the inter influence of related group of potential adopter teachers who are likely to exert positive influence on students. The results revealed that learning outcomes on tabletop are strongly associated with innovation attributes like Relative Advantage, Compatibility, Ease of Use, Perceived Enjoyment, Perceived usefulness and Teachers support. Overall students expressed much more positive attitude to adopt tabletop technology for learning vs. desktop. We find that the mean group performance gain is significant with collaboration using tabletop and significantly greater than the group using desktops. We also find that the group interactions with the tabletop area significant factor that contributes to the group's average performance gain. However, the total time spent in while using the tabletop is surprisingly not a significant factor in the performance gain. Our findings contribute to the design of new pedagogical models for science learning that maximizes the collaborative learning potential of tabletops.

 

Keywords: Laboratory, Diffusion, Innovation, Simulation, Collaboration, tabletop, experiments

Experimental learning plays paramount role in Physics education. Experimental physics requires phenomenological investigations in several cases and this includes understanding visible and invisible heuristic procedures to discern underlying concepts. This study investigates the invisible yet evident occurrences of physical phenomena that are difficult to grasp from a learner's perspective. In this work the contribution of compounded effects of using computational techniques, multimedia enhanced simulations and interactive animations to draw the learner's attention to those physically undiscernable aspects of physics experiments is presented. The study has investigated three physics experiments by engineering students (N= 42) and the methodology focused on differentiating the learning outcomes between classroom teaching, laboratory experimentation and virtual laboratories. The students were divided into two batches. Visual and conceptual understanding was quantified by assessments that included their visual and conceptual understanding. Our study not only revealed severe limitations in learning invisible phenomena based on traditional classroom methods but also empirically validated the positive impact on learning outcomes when the classroom method is combined with Virtual Labs approach.

While there is large body of work examining efficacy of Virtual Labs in engineering education, studies to date have lacked modeling Blended Labs (BL) – mix of Virtual Labs (VL) and Physical Labs (PL) for science experimentation at the university engineering level. Using Rogers theory of perceived attributes, this paper provides a research framework that identifies the attributes for BL adoption in a social group comprising of (N=246) potential adopter undergraduate engineering students. Using Bass model the study also accounts for the interinfluence of related group of potential adopter faculties who are likely to exert positive influence on students. The results revealed that acceptance of BL as an innovation and its learning outcomes are strongly associated with innovation attributes like Relative Advantage, Compatibility, Ease of Use, Department and Faculty support. Learning outcomes are very positive under BL when compared to PL, though within BL, ordering of PL and VL was not significant. For certain innovation attributes gender differences were significant. Overall students expressed much more positive attitude to adopt BL model for learning than using only PL.

Keywords: Virtual Labs, Blended Learning, Innovation Diffusion, Experiments, Engineering, interinfluence

In large classrooms with limited teacher time, there is a need for automatic evaluation of text answers and real-time personalized feedback during the learning process. In this paper, we discuss Amrita Test Evaluation & Scoring Tool (A-TEST), a text evaluation and scoring tool that learns from course materials and from human-rater scored text answers and also directly from teacher input. We use latent semantic analysis (LSA) to identify the key concepts. While most AES systems use LSA to compare students’ responses with a set of ideal essays, this ignores learning the common misconceptions that students may have about a topic. A-TEST also uses LSA to learn misconceptions from the lowest scoring essays using this as a factor for scoring. ‘A-TEST’ was evaluated using two datasets of 1400 and 1800 pre-scored text answers that were manually scored by two teachers. The scoring accuracy and kappa scores between the derived ‘A-TEST’ model and the human raters were comparable to those between the human raters.

Keywords: Feature extraction, Essay scoring, text analysis, text mining, Latent Semantic Analysis (LSA), SVD, Natural Language Process- NLP, AES

t

India's educational challenge includes a large school going population, shortage of science teachers and lack of science labs in many schools. To counter this challenge, the Online Labs (OLabs) pedagogy is designed as a complete learning environment with tutorials, theory, procedure, animations, videos and simulations while the assessment includes conceptual, experimental, procedural and reporting skills.

We discuss two separate empirical studies using OLabs to study the performance gains, student attitudes and preferences while using physical labs, desktops and tablets. The first study was at a school that compared students who learnt individually with OLabs on desktops, to students who learnt with the traditional teacher led physical labs. The second study was at a science camp and compared OLabs on desktops to OLabs that were context adapted for android tablets. There were significant differences between the physical labs and the self study mode using OLabs on desktops, but no significant differences between OLabs on desktops compared to OLabs on tablets.

 

Keywords—Olabs; traditional labs; animation; simulation; online labs; virtual labs; elearning; cognitive learning; conceptual skills; experimental skills; procedural skills; reporting skills; assessment

Virtual labs for science experiments are a multimedia technology innovation. A possible growth pattern of the perceived critical mass for virtual labs adoption is modeled using (N=240) potential-adopter teachers based on Roger’s theory of diffusion and of perceived attributes. Results indicate that perceived critical mass influences behavior intention to adopt a technology innovation like Virtual Labs and is affected by innovation characteristics like relative advantage, ease of use and compatibility. The work presented here models the potential-adopter teacher’s perceptions and identifies the relative importance of specific factors that influence critical mass attainment for an innovation such as Virtual Labs.

 

Keywords - virtual labs; innovation diffusion; critical mass; simulation; lab experiments

Biotechnology is becoming more popular and well identified as a mainline industry. Students have shown greater interest in learning the techniques. As a discipline, biotechnology has led to new advancements in many areas. Criminal investigation has changed dramatically thanks to DNA fingerprinting. Significant advances in forensic medicine, anthropology and wildlife management have been noticed in the last few years. Biotechnology has brought out hundreds of medical diagnostic tests that keep the blood safe from infectious diseases such as HIV and also aid detection of other conditions early enough to be successfully treated. Medical kits for diabetes, blood cholesterol and home pregnancy tests are also biotechnology diagnostic products. Industrial biotech applications have led to cleaner processes that produce less waste and use less energy and water in such industrial sectors as chemicals, pulp and paper, textiles, food, energy, and metals and minerals. Laundry detergents produced in many countries contain biotechnology-based enzymes making them nature friendly and safer. Agricultural biotechnology benefits farmers, consumers and the environment by increasing yields and farm income, decreasing pesticide applications and improving soil and water quality, and providing healthful foods for consumers. Biotechnology has created more than 200 new therapies and vaccines, including products to treat cancer, diabetes, HIV/AIDS and autoimmune disorders.

A new modelling approach for diffusion of personalized learning as an educational process innovation in social group comprising adopter-teachers is proposed. An empirical analysis regarding the perception of 261 adopter-teachers from 18 schools in India about a particular personalized learning framework has been made. Based on this analysis, teacher training (TT) has been identified as one of the dominant factor which can significantly influence decision by teachers to adopt the educational innovation. Different situations corresponding to fixed and time dependent dynamic carrying capacity of potential adopter-teachers at any time have been developed. New generalized models capturing the growth dynamics of the innovation diffusion process in conjunction with the evolutionary carrying capacity of potential adopters are investigated. The coupled dynamics allows forecasting the likelihood of success or failure of new educational innovation in a given context. Different scenarios for TT are considered based on constant growth rate model; proportional growth rate model; stratified growth rate model. The proposed modelling framework would be of great interest to education policy makers as it has the potential to predict the likelihood of success or failure of new educational innovation.

 

Keywords - Teacher training ; Personalized learning; Carrying capacity ; Innovation diffusion; Dynamic model; Educational innovation

Most personalized learning systems are designed for either personal computers (e-learning) or mobile devices (m-learning). Our research has resulted in a cloud-based adaptive learning system that incorporates mobile devices into a classroom setting. This system is fully integrated into the formative assessment process and, most importantly, coexists with the present e-learning environment. Unlike many mobile learning systems, this system provides teachers with real-time feedback about individual and group learners. Its scalable and extendable architectural framework includes the server-side pedagogical recommendation of content adaptation based on the users’ knowledge-levels and preferences. Content is also automatically adapted to the end device that is being used. This context-aware delivery allows users to switch between e-learning and m-learning, and between devices, without any loss in personalized content. Our work builds on a web-based Adaptive Learning and Assessment System (ALAS) that is built on the Knowledge Space Theory model. At present, this system is used at school computer labs and our goal was to widen this user-base by enhancing this system to support personalized learning on mobile devices. This study describes our process of developing this technology, and contains an empirical analysis of students’ performance, perceptions, and achievements when using ALAS on both personal computers and mobile devices.

 

Keywords - Adaptive assessment ; Mobile learning ; Personalized learning ; Adaptive learning ; Mobile device ; Mobility ; Intelligent tutoring ; m-Learning; e-Learning

The crucial role of hands-on science experiments in the school science curriculum is universally accepted. However, a formal assessment of practical skills is lacking, with most schools employing traditional theory-based or multiplechoice questions (MCQs) to evaluate students. In this paper, the authors present a framework for learning-enabled assessment of practical skills, which gives due consideration to both the structure of the practical assignments and the feedback that promotes learning. This approach opens up many new possibilities that require constructivist learning and higher-order thinking skills. Judgment of skills based on performance reports may decrease students’ confidence, whereas scaffolds used during the assessment process can improve students’ proficiency. The design of various online scaffolds—used during assessment that help students focus and redirect their efforts to the appropriate task needed for mastery of a skill—are discussed here. Early studies have shown that students prefer these types of assessment to more traditional ones, where intervention includes appropriate hands-on simulation or interactive animation or a given concept.

India has embarked on a National Mission project to build over 150 Virtual Labs (VL) targeting over 1450 experiments mapped to the under graduate and postgraduate curriculum. Due to the lack of user centric tools and mechanisms for VL authors, it became crucial to architect a Virtual Labs Collaborative and Accessibility Platform (VLCAP) for use by the large scientific community building multi-disciplinary VL.With multi-tier, scalable architecture at its core, the technology platform allows VL builders to focus on particular logic of their experiments. The axiomatic design of the user interfaces built into the various modules including VL workbench, collaborative content management, repositories and so on assists in functional use of the elements while reducing the overall development time of VL by individual users. Integration of common tasks in user management, such as single sign-on, role based access control etc. enhances flexibility without compromising on security.

For enhanced education at the level of University courses such as those in biology or biotechnology, one of the key elements is the need of time and expertise to allow the student to familiarize laboratory techniques in par with regular theory. The Sakshat Amrita virtual biotechnology lab project focusing on virtualizing wet-lab techniques and integrating the learning experience has added a new dimension to the regular teaching courses at the University. Establishing virtual labs requires both domain knowledge and virtualizing skills via programming, animation and device-based feedback. Challenges in the biotechnology sector in setting up a laboratory that integrates both the feel and phenomenon includes the medley of multiple techniques. This paper reports one such cost-effective process used in virtualizing a real biotechnology lab at the University-level. The major challenge in setting up an effective knowledge dissemination for laboratory courses was not only the scientific approach of biotechnology, but included the virtualization aspects such as usage/design scalability, deliverability efficiency, network connectivity issues, security and speed of adaptability to incorporate and update changes into existing experiments. This paper also discusses an issue-specific case-study of a functional virtual lab in biotechnology and its many issues and challenges. © 2010 IEEE.

This paper presents Amrita Learning, a web-based, multimedia-enabled, Adaptive Assessment and Learning System for schools. Computer-based adaptive assessments aim to use an optimal and individualized assessment path to determine the knowledge level of students. The new goal for adaptive assessment is based on educational outcomes, which describe what learners must be able to do as a result of items studied. Assessment based on outcomes creates the initial roadmap for the educational model, ensuring that students are not learning items that are already mastered. Learners and instructors can accurately determine their areas of strengths and weaknesses, and use this to determine future instruction. This paper explains the underlying principles used in the initial adaptive assessment followed by evaluation that is closely interwoven with learning. An expert module continuously adjusts the content and method of presentation based on the sequence of learner's recent responses and prior knowledge. The system maintains and updates both the individual learner profile and group profiles. Amrita Learning, targeted to school students, is built upon the principles of spiral learning with mixed presentation from multiple skill areas, thus providing continuous reinforcement in all skill-areas. The proposed competency model has been pilot tested in both city and rural area schools. In the majority of cases where students used it consistently, there were quantifiable improvements in learning levels and performance in schools. Summaries of the results and recommendations are included in this paper.

This paper presents the extensions of Amrita Learning, a web-based, multimedia-enabled, Adaptive Assessment and Learning System for schools to facilitate Continuous and Comprehensive Evaluation (CCE). Continuous Evaluation refers to the formative assessment from the beginning of instruction and periodically during instruction and is closely interwoven with learning. Amrita Learning's CCE extension supports adaptive assessments directly mapped to CBSE curriculum, monitors proper implementation of CCE and automates, enforces, and gathers usage and performance statistics. Being an adaptive system, it already supports self-paced learning, constructivist, mixed presentation, mastery, and spiral learning. The proposed competency model has been developed and is being pilot tested at schools in India. Initial results of the study are discussed in this paper.

We present the adaptive simulations of Amrita Learning, a web-based, interactive eLearning program that aims to create a realistic mathematics and science laboratory environment for school students to study equipments, perform simulation experiments interactively, measure or analyze results, and understand their application, It teaches abstract concepts, such as flow of electrons and magnetic fields, using highly sophisticated and interactive simulations. The adaptive simulations follow the time tested principles of Amrita Learning, a previously discussed adaptive learning system, including adaptive sequencing, presentation and feedback. This novel system enables students to work at their own pace with learning level, content and presentation individualized based on a dynamically updated student profile. While individualized simulations, animations, tutorials, and assessments enrich learning experience, simultaneous access to the content by thousands of students makes the return on investment very high. Student feedback and assessments are used to compare the adaptive simulations and animations with the traditional laboratory. Results show that while the majority of the students preferred the ease of use, adaptive feedback and additional learning options of the adaptive simulations, they missed the group discussions and extra attention from the teacher at the traditional lab.

For enhanced education at the level of University courses such as those in biology or biotechnology, one of the key elements is the need of time and expertise to allow the student to familiarize laboratory techniques in par with regular theory. The Sakshat Amrita virtual biotechnology lab project focusing on virtualizing wet-lab techniques and integrating the learning experience has added a new dimension to the regular teaching courses at the University. Establishing virtual labs requires both domain knowledge and virtualizing skills via programming, animation and device-based feedback. Challenges in the biotechnology sector in setting up a laboratory that integrates both the feel and phenomenon includes the medley of multiple techniques. This paper reports one such cost-effective process used in virtualizing a real biotechnology lab at the University-level. The major challenge in setting up an effective knowledge dissemination for laboratory courses was not only the scientific approach of biotechnology, but included the virtualization aspects such as usage/design scalability, deliverability efficiency, network connectivity issues, security and speed of adaptability to incorporate and update changes into existing experiments. This paper also discusses an issue-specific case-study of a functional virtual lab in biotechnology and its many issues and challenges.