Qualification: 
M.E
p_siniraj@cb.amrita.edu

Sini Raj P. currently serves as Assistant Professor at Department of Computer Science and Engineering, School of Engineering, Coimbatore Campus. Her areas of research include Data Mining and Data Structures.

Publications

Publication Type: Conference Paper

Year of Publication Publication Type Title

2018

Conference Paper

M. Velamuri, Narayanan, A., and Sini Raj P., “A Profound Inquiry of Diversified Application and Trends in Big Data Analytics”, in Ubiquitous Communications and Network Computing, Cham, 2018, vol. 218, pp. 104-115.[Abstract]


Big Data plays a major role in every field in recent days. Analyzing, storing and visualizing the varied and complex data collected are important tasks for which Big Data tools are used. Big Data handles data in a more efficient manner. So, Big Data is preferably used in enterprises, organizations, companies, business etc. Henceforth, there are various fields such as healthcare/medical, business, sports, education, stock market, web and entertainment etc., which use big data tools. The motive of this paper is to give an insight into different types of analytics that are used in various fields and also to give a detailed study of various organizations and the extent they use the analytics in their respective fields.

More »»

2017

Conference Paper

Sini Raj P. and Sathyan, S., “A Deeper Insight on Developments and Real-Time Applications of Smart Dust Particle Sensor Technology”, in International Conference On Computational Vision and Bio Inspired Computing(ICCVBIC 2017) , 2017.

2017

Conference Paper

Sini Raj P., M, S., and Gowtham, R., “A Comprehensive Study on the Usefulness of Multi-objectives in Recommender Systems”, in International Conference On Computational Vision and Bio Inspired Computing(ICCVBIC 2017) , 2017.

2017

Conference Paper

G. Ramesh, Mathi, S., Sini Raj P., Krishnamoorthy, V., and Gowtham, R., “An Automated Vision-based Method to Detect Elephants for Mitigation of Human-elephant Conflicts”, in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017.[Abstract]


Human-elephant conflict is a frontline conservation issue in the world. The loss and fragmentation of elephant's habitat owing to the increased human encroachment leads to a notable conservation issue. It raises the need for a non-invasive and efficient solution for the mitigation of human-elephant conflicts. Consequently, deploying a vision based surveillance method in the real time environment can prove to be significantly useful to provide the warnings well in advance thereby reducing the human elephant conflict. In this paper, a method for the identification of elephant as an object using image processing is proposed. The method dynamically learns from the trained images with different backgrounds, lighting conditions. Further, it classifies the input image based on the features of color and texture. The outcomes demonstrate that the proposed method effectively deals with the detection of elephants in near and far distances, cluttered and occluded environment

More »»

Publication Type: Journal Article

Year of Publication Publication Type Title

2017

Journal Article

Sini Raj P. and Dayanand, V., “A Detailed Study of Search Engine Optimization and an Analysis of SEO Using Standard Ranking and Maximum Margin Ranking Algorithms”, Journal of Adv Research in Dynamical & Control Systems, 2017.

2017

Journal Article

Sini Raj P., R. Raj, A., and Haresh, V., “Comparitive Study of Emotion Detection Using Multevel HMM and Convolution Neural Networks from Real Time Videos”, International Journal of Pure and Applied Mathematics, vol. 114, pp. 71-81, 2017.

2017

Journal Article

Sini Raj P. and Dayanand, V., “A Monitoring Framework for Indian Public Bus Transportation Using Machine Learning Techniques”, International Journal of Pure and Applied Mathematics, vol. 114, pp. 59-69, 2017.

2017

Journal Article

S. B. Lakshmi, Sini Raj P., and R. Vikram, R., “Sentiment Analysis using Deep Learning Technique CNN with KMeans”, International Journal of Pure and Applied Mathematics, vol. 114, pp. 47-57, 2017.[Abstract]


Sentiment analysis has already started playing a vital role in most of social media. Whether it is social networking sites or video or audio based systems, people are interested in knowing the sentiments which will help them to identify whether the word is positive, negative or neutral. Sentiment analysis in turn helps to detect the emotions. In the proposed work sentiment analysis is used to find the review for a particular movie by using a novel combination of deep learning technique CNN and unsupervised learning method K means upon movie reviews, which gives a better estimation of the sentiments than the existing methods which are currently available. This minimal improvement in the accuracy is expected to get improved when applied to a larger corpus of big data where it will show its significance.

More »»

2017

Journal Article

Sini Raj P. and Divya, M., “Comparative Study of Machine Learning Algorithms Over Big Data Sets”, Journal of Advanced Research in Dynamical and Control Systems, vol. 9, pp. 72-79, 2017.[Abstract]


As time moves, the approaches and the algorithms in the emerging field of machine learning also changes. It’s always important to consider and get familiarized with the recent algorithms developed in this field and also to know where exactly these algorithms may be applied in a real time scenario. This paper focuses on three things namely what machine learning is and its impact on the field of big data, what are the major machine learning algorithms used in big data scenario and which of the machine learning algorithms will provide best accuracy with lesser error rate when applied over real time big datasets?.The major objective of this paper is to help the researchers understand and be updated about the recent advancements in the rapid growing area of Machine learning and Big data.

More »»

2017

Journal Article

B. Sri Datta, Ganapathy, R., Sini Raj P., Dr. Shriram K Vasudevan, and SN, A., “An Inventive and Innovative Alternate for Legacy Chain Pulling System through Internet of Things”, Indonesian Journal of Electrical Engineering and Computer Science, vol. 6, no. 3, p. pp. 688 ~ 694, 2017.[Abstract]


Indian Railways made a move in replacing the chain pulling system with the new mobile based communication system where the loco pilot’s mobile phone number shall be shared with all the passengers through a message. Despite the efforts taken to remove the chains from the train, there is a great probability of misuse through the mobile phone number provided. We aim to build a more efficient and secure solution based on the Internet of Things, which is a buzz word in the market. Our proposed system provides an alarm fixed at specific locations in the compartments of a train. In case of emergency, the passenger has to press the alarms’ button, which captures the scene using a built-in digital camera. The system also alarms the Loco-Pilot, Travelling Ticket Examiner, as well as the compartment so as to provide immediate possible help through the fellow co-passengers. The pilot slows down the train to an optimum speed whilst the travelling ticket examiner checks and confirms the pilot whether he has to stop the train. The entire system can be controlled through an authenticated mobile application provided to the ticket examiner. The pictures captured by the camera and other crucial details are uploaded to a cloud-based real-time database. Thus, saving time and taxpayers’ money as well as helping the railways to perform analytics and come up with feasible solutions to the problems of the passengers. The system has the potential to deal with the most prevailing cargo theft like that of coal, by alerting the staff without having to stop the train, making the convicts’ escapes impossible. This also definitely avoids the improper pulling of chains and thereby not causing any hassle to the passengers as well as diminishes the economic loss to the government by reducing the time delay.

More »»

2015

Journal Article

Sini Raj P., Y Sasira, R., Revathi, L., and Rubaasri, S., “Internet of Things: A Vision Through Data Mining, Cloud Computing and Semantic Technologies”, International Journal of Applied Engineering Research , vol. 10, pp. 29051-29060, 2015.

2015

Journal Article

C. Suresh, B. Yedugiri, K., Sini Raj P., and Sreedhar, S., “Inspecting the proficiency of novel algorithms on sparse data domains for efficient recommendation-a glance”, Research Journal of Applied Sciences, Engineering and Technology, vol. 10, pp. 812-815, 2015.[Abstract]


Recommender systems have played a major role in almost all the domains today where human interaction happens with system. Depending on the user's choice, a recommender system presents some promising suggestions by observing all the activities of the user on the web and thus, helps to find out similar users and interested products. All the ratings provided by the user is stored in a rating matrix. Sometimes it so happens that the users may view the item, but not always rate it; which makes the dataset sparse. Performing operations on such sparse datasets by recommender engines may not give precise suggestions to the user. This study aims to make such sparse datasets denser by applying the two novel methods, FST and UTAOS; and thereby implementing any of the collaborative filtering techniques upon it to showcase the efficiency in recommendation. Results reveal that FST outperforms the UTAOS approach in terms of sparse datasets which paves the way for an efficient recommendation. © Maxwell Scientific Organization, 2015.

More »»

2014

Journal Article

B. Shriladha, Magudeswaran, S., Sini Raj P., and Subathra P., “Library Book Recommendation System using CF-Apriori Algorithm”, International Journal of Applied Engineering Research, vol. 9, pp. 8089-8096, 2014.[Abstract]


There is eventually a transition from traditional libraries to digital libraries; there can also be a transition from digital library to recommended digital library. This paper proposes a better way to facilitate user search process and recommend books based on past library usage and similar users interest. We create the library recommendation system using Apriori algorithm and Collaborative Filtering (CF). Apriori algorithm produces the association rules which can be applied for large database. Collaborative filtering Algorithm is used to recommend the books of similar user profiles. For a recommendation system, data collection, processing data in addition with user data is required, where user ratings plays a crucial role. Automatizing the support count estimation in Apriori algorithm can be done to improve the efficiency of the system as a future work.

More »»

2014

Journal Article

K. B. Yedugiri, Chandni, S., Sini Raj P., and Souparnika, S., “Recommender systems - A deeper insight”, International Journal of Applied Engineering Research, vol. 9, pp. 28521-28531, 2014.[Abstract]


Recommender systems have become very popular in day to day life. Various e-commerce websites, social network sites and web search use vast usage of recommender engines and various algorithms to find out the user profiles of customers, thereby use those profiles to find similar users. With the advancement of World Wide Web, there arose a constant need to connect people from different parts of the world in various ways possible. It called for efforts to provide techniques that can bring forth common interests among users. Recommender system is such a system wherein information is gathered based on the preferences of the users and item data sets. These sources of information provide output, which can help users to predict and recommend it to other users. The implementation of RS has increased in the internet, which explained its use in diverse areas like recommending movies, applications, gadgets, songs, websites, research and discussion forums etc. where user can give ratings to an item of his choice; thus creating a rating matrix. © Research India Publications.

More »»

Faculty Research Interest: