Qualification: 
Ph.D, M.Tech, B-Tech
nm_dhanya@cb.amrita.edu

Dr. Dhanya N. M. currently serves as Assistant Professor at Department of Computer Science, School of Engineering, Coimbatore. Her research includes energy efficiency in smartphones using cloud technology. She is also interested in android application development for various applications like IoT.

Education

  • 2017 : PhD in Information and Communication Engineering
    Anna University
    Chennai, India.
  • 2006-2008 : M.E. in Computer Science and Engineering
    Sri Krishna College of Engineering and Technology
    Combatore, Tamilnadu India
  • 2000-2004 : BTech in Computer Science and Engineering
    College of Engineering
    Kidangoor, Kerala, India

Experience

Year Affiliation
July 2014 - Present Assistant Professor, Department of Computer Science and Engineering at Amrita Vishwa Vidyapeetham, Coimbatore
January 2008 to July 2014 Assistant Professor, Department of Computer Science and Engineering at Sri Krishna College of Engineering & Technology, Coimbatore

Teaching

  • Data Science 
  • Machine Learning and Deep Learning 
  • Compiler Design 
  • Android Application Development 
  • Formal Languages and Automata Theory 

Invited Talks

  • Delivered a technical talk on “Web Services and Mobile Cloud Computing” at Karpagam University, Coimbatore. 
  • Delivered a technical talk on “Mobile Cloud Offloading” at Info Institute of Technology, Coimbatore. 
  • Delivered a Session in AICTE sponsored 2 Week  FDP on Deep Learning and Computational Intelligence for Bio-Informatics, at Sri Krishna College of Engineering, Coimbatore 
  • Delivered a Session in ATAL FDP on Data Science at Erode Senguthar Engineering College. 
  • Delivered a Session in  AICTE Training and Learning (ATAL) Academy  Sponsored One Week Online Faculty Development Programme (FDP) on “Intelligent Computing in Data Science”, at Sri Krishna College of Engineering, Coimbatore 
  •  Delivered a Session in  AICTE sponsored STTP on  Deep Learning based analysis of Images and Video Analytics at Kalaignar Karunanidhi Institute of Technology, Coimbatore- 641402  

Publications

Publication Type: Conference Paper

Year of Publication Title

2021

Dhanya N. M., “An Empirical Evaluation of Bitcoin Price Prediction Using Time Series Analysis and Roll Over”, in Inventive Communication and Computational Technologies, Singapore, 2021.[Abstract]


Bitcoin has attracted considerable attention in today’s world because of the combination of encryption technology along with the monetary units. For traders, Bitcoin leads to a promising investment because of its highly fluctuating price. Block chain technology assists in the transactions of documentation. The characteristics of the bitcoin which is derived from the blockchain technology has led to diverse interests in the field of economics. The bitcoin data is selected from 2013 to 2018, over a period of 5 years for this analysis. Here a new roll over technology is applied where new data is obtained over time which will close out the old information during machine training. This mechanism will help in incorporating new information in the short-term learning. The results show that the rollover mechanism improves the time series prediction accuracy.

More »»

2020

S. Lakshminarayanan, Dr. (Col.) Kumar P. N., and Dhanya N. M., “Implementation of Blockchain-Based Blood Donation Framework”, in IFIP Advances in Information and Communication Technology, 2020, vol. 578, pp. 276–290.[Abstract]


Existing blood management systems in India function as Information Management systems that lack dynamic updates of blood usage and detailed blood trail information, starting from donation to consumption. There exists no communication platform for surplus blood in one region to be requested from another region where blood is scarce, leading to wastage of blood. Lack of transparency and proper blood quality checks have led to several cases of blood infected with diseases such as HIV being used for transfusion. This paper aims at mitigating these issues using a blockchain-based blood management system. The issue of tracking the blood trail is modelled as a supply-chain management issue. The proposed system, implemented in the Hyperledger Fabric framework, brings more transparency to the blood donation process by tracking the blood trail and also helps to curb unwarranted wastage of blood by providing a unified platform for the exchange of blood and its derivatives between blood banks. For ease of use, a web application is also built for accessing the system.

More »»

2020

N. B. Raut and Dhanya N. M., “A Green Dynamic Internet of Things (IoT)-Battery Powered Things Aspect-Survey”, in Soft Computing: Theories and Applications, Singapore, 2020.[Abstract]


The basic utility of IoT is to convert every physical object into the source of information. Devices linked to the Internet have a tremendous growth for a couple of years; therefore, innovative areas of applications related to IoT have opened, and this moves toward new challenges as green IoT paradigm. Managing the energy by the demanding connected devices in the IoT system and viewing the consumption of energy is a big challenge. The green IoT opens two broader areas. The first one focuses on the designing of energy-efficient devices, communication protocols, and networking architecture for interconnecting the physical objects; the second area speaks about cutting carbon emission, pollution, and enhance energy efficiency. This paper presents the profound view of potential technologies of energy-efficient IoT systems, toxic pollution, and management of E-waste, specifically in battery-powered devices. We investigated the literature and presented the various application of green IoT and barriers in Greener IoT implementation.

More »»

2017

C. R. Athira and Dhanya N. M., “Three dimensional geo-tweet visualization system for spatio-temporal events”, in Proceedings of the 2017 2nd IEEE International Conference on Electrical, Computer and Communication Technologies, ICECCT 2017, 2017.[Abstract]


Geo-tweet visualization help users know the events that is happening over the space and time from the tweets or wikipedia while they click on the specified location for a 3D based tag visualization. Normal events are detected by system which happens anywhere or anytime using machine learning algorithm and special events are also extracted by comparing current situation to normal regularities. Generally, people look for location along with its route and information about surrounding tourist locations for which system provides spatial context of location which is being harvested from freely available source like wikipedia, Twitter, tumblr etc... Initially, Geo-referenced information are gathered which are closed to specified points and then gathered data is filtered based on frequency of words from data harvested, which is then visualized as a tag cloud in android mobile. Visualization details could be adjusted interactively based on interest of the client by changing radius of specified region. Visualization of tag cloud is then summarized to aid user to gain an overview of current situation that is happening over the time.

More »»

2017

Dhanya N. M. and Athira, C. K., “Three dimensional tagcloud visualization for intelligent tourism”, in 2017 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017, 2017.[Abstract]


Metadata creation along with growth of social bookmarking emerged an approach named tagging. Often people look for location along with its route and detailed information about its surrounding. Mobile users may opt for current event that is taking place in the current location along with historical background of their surroundings and events that happen over time. They are provided with information on spatial context of location which harvests context information from freely available source and tag cloud visualization is created for this data. Firstly, Geo-referenced data which is close to selected point is gathered. Then gathered information is filtered based on the frequency of words from harvested data. Filtered data is then visualized as tag cloud in android mobile. Based on client's interest, visualization detail can interactively be adjusted by changing radius of selected region. Summary of tag cloud is visualized to help user gain overview of current situation. © 2017 IEEE.

More »»

2016

Dhanya N. M., Dr. Senthil Kumar T., Sujithra, C., Prasanth, S., and Shruthi, U. K., “Pedagogue: A Model for Improving Core Competency Level in Placement Interviews Through Interactive Android Application”, in Proceedings of the International Conference on Soft Computing Systems, 2016.[Abstract]


This paper discusses about developing a mobile application running on the cloud server. The Cloud acclaims a new era of computing, where application services are provided through the Internet. Though mobile systems are resource-constrained devices with limited computation power, memory, storage, and energy, the use of cloud computing enhances the capability of mobile systems by offering virtually unlimited dynamic resources for computation and storage. The challenge faced here is that traditional smartphones do not support cloud, these applications require specialized mobile cloud application model. The core innovativeness of the application lies in its delivery structure as an interactive android application centered on emerging technologies like mobile cloud computing–that improves the core competencies of the students by taking up online tests posted by the faculty in the campus. The performance of this application has been presented using scalability, accessibility, portability, security, data consistency, user session migration, and redirection delay

More »»

2015

Dhanya N. M. and Kousalya, G., “Adaptive and Secure Application Partitioning for Offloading in Mobile Cloud Computing”, in Security in Computing and Communications, Cham, 2015.[Abstract]


Smart phones are capable of providing smart services to the users very similar to laptops and desktop computers. Despite of all these capabilities battery life and computational capabilities are still lacking. By combining mobiles with cloud will reduce all these disadvantages because cloud is having infinite resources for processing. But in cloud security is a major concern. Since mobile devices contain private data a secure offloading of application is necessary. In this paper we are proposing a secure partitioning of application so that the most sensitive or vulnerable part of the application can be kept in the mobile and rest of the application can be offloaded to the cloud.

More »»

Publication Type: Book Chapter

Year of Publication Title

2018

Dhanya N. M., Govardhanan, K., Balarksihnan, P., and Raj, P., “Fuzzy-logic-based decision engine for offloading iot application using fog computing”, in Handbook of Research on Cloud and Fog Computing Infrastructures for Data Science, 2018, pp. 175-194.[Abstract]


Mobile is getting increasingly popular and almost all applications are shifting into smartphones. Even though lots of advantages are there for smartphones, they are constrained by limitations in battery charge and the processing capacity. For running resource-intensive IoT applications like processing sensor data and dealing with big data coming from the IoT application, the capacity of existing smartphones is not enough, as the battery will be drained quickly, and it will be slow. Offloading is one of the major techniques through which mobile and cloud can be connected together and has emerged to reduce the complexity and increase the computation power of mobiles. Other than depending on the distant cloud for offloading, the extended version of cloud called fog computing can be utilized. Through offloading, the computationally intensive tasks can be shifted to the edge fog devices, and the results can be collected back at the mobile side reducing the burden. This chapter has developed mobile cloud offloading architecture for decision making using fuzzy logic where a decision is made as to whether we can shift the application to cloud or not depending on the current parameters of both cloud and the mobile side. Cloud computing introduces a number of variables depending on which offloading decision must be taken. In this chapter, the authors propose a fuzzy-logic-based algorithm which takes into consideration all the parameters at the mobile and cloud that will affect the offloading decision.

More »»

Publication Type: Journal Article

Year of Publication Title

2018

Dhanya N. M., “Anti-Theft Vehicle Tracking System Using GPS and Location Prediction”, International Journal on Advanced Science, Engineering and Information Technology, vol. 8, no. 6, pp. 2584–2589, 2018.[Abstract]


Currently the number of private vehicles is increasing day by day and hence the importance of tracking and theft prevention. Recently the vehicle tracking systems are getting wide popularity and can be used in tracking in case of stolen vehicles. Real-time applications like Vehicle Tracking System is developed using Arduino board with a microcontroller. We have developed a vehicle tracking system with a Smartphone which is less expensive and reliable when compared to the existing system as there is no need for extra hardware. The objective is to develop an application for tracking vehicles, which will help the cab owners to track their car all the time and to predict the location of the vehicle in the case of a failing GPS (Global Positioning System). Time series prediction algorithm is used to predict the location of the vehicle if GPS is in off mode. The vehicle tracking system installed will update the GPS coordinates of the vehicle continued to the cloud, and this data can be used for predicting the location of the vehicle in case of emergency. This system can also be used to generate the bills after finishing the freight in the form of an SMS based on the distance traveled, which can be calculated from the latitude and longitude data. The GPS data can be mapped to the Google maps to track the location in real time. Compared with the existing system, this system is having the advantage of location prediction from the historic location data, and the cost is reduced by almost half.

More »»

2018

V. S. and Dhanya N. M., “Performance analysis of various regression algorithms for time series temperature prediction”, Journal of Advanced Research in Dynamical and Control Systems, vol. 10, no. 03-Special Issue, pp. 996–1000, 2018.[Abstract]


In this fast developing world weather forecasts based on temperature, humidity and precipitation are of greater importance to agriculture. For example, farmers rely on temperature forecasts to decide day-to-day activities. Computer based Prediction techniques can be employed to predict the future temperature based on the existing data so that the farmers can plan their activities ahead which ultimately results in improved production yield. For a successful forecasting, Selection of right prediction algorithm is of paramount importance, so that the results will be highly accurate with less forecast error. Hence the aim of this paper is to focus on comparing various Machine learning and deep learning regression algorithms applied on temperature data, and thereby evaluating which regression algorithms are best in minimizing the overall prediction error. After the successful prediction of data, human effort is required to interpret the modeled data and to make it understandable to the end user.

More »»

2018

Dhanya N. M. and Harish, U. C., “Sentiment analysis of twitter data on demonetization using machine learning techniques”, Lecture Notes in Computational Vision and Biomechanics, vol. 28, pp. 227-237, 2018.[Abstract]


Social media like twitter and Facebook is seen as a space where public opinions are formed in today’s world. The data from these tweets and posts can provide valuable insights for policy makers and other agencies to propose and implement policies better. An attempt is made in this paper to understand the public opinion on the recently implemented demonetization policy in India. A sentiment analysis is carried out on twitter data set using machine learning approaches. Twitter data from November 9th to December 3rd is considered for analysis. The data set is pre-processed for cleaning the data and making it possible for analysis. A final set of 5000 tweets are analysed using machine learning techniques like SVM, Naïve Bayes classifier and Decision tree and the results are compared. © 2018, Springer International Publishing AG.

More »»

2017

Dhanya N. M., Kousalya, G., and Balakrishnan P., “Dynamic mobile cloud offloading prediction based on statistical regression”, Journal of Intelligent and Fuzzy Systems, vol. 32, pp. 3081-3089, 2017.[Abstract]


Due to the advancement of mobile technology, a large number of computationally intensive applications are created for smart phones. But the limitations of battery and processing power of smart phones are making it inferior to laptops and desktop computers. Mobile Cloud Offloading (MCO) allows the smart phones to offload computationally intensive tasks to the cloud, making it more effective in terms of energy, speed or both. Increased networking capacity due to the availability of high speed Wi-Fi and cellular connections like 3G/4G makes offloading more efficient. Even then, the choice of offloading is not always advisable, because of the highly dynamic context information of mobile devices and clouds. In this paper, we propose a dynamic decision making system, which will decide whether to offload or do the tasks locally, depending on the current context information and the optimization choice of the user. Metrics are developed for time, energy and combination of time and energy to assess the proposed system. A test bed is implemented and the results are showing improvements from the currently existing methods. © 2017-IOS Press and the authors. All rights reserved.

More »»

2016

Dhanya N. M. and Kousalya, Gb, “Context aware offloading decision and partitioning in mobile cloud computing”, Asian Journal of Information Technology, vol. 15, pp. 2177-2185, 2016.[Abstract]


The development of cloud and mobile technology leads to Mobile Cloud Computing (MCC). MCC has become a major service structure now a days. The limitations in the battery power of mobile can be overcome with the help of cloud technology which is having infinite amount of resources. Offloading is a method for improving the capabilities of resource limited smartphones by augmenting with cloud resources. The mobile applications can be partitioned into two in such a way that heavier parts are executed at the cloud and the rest is executed in the mobile itself. This study designs a system for offloading and partitioning architecture which will take into consideration of all the contextual information related to a mobile. The decision of offloading and partitioning is taken considering the current connectivity, memory status, battery charge, etc. The evaluation results reveal that this algorithm gives performance improvement, less overhead to the mobile side and the prediction accuracy of context aware decision engine. A light weight partition algorithm is used for splitting the application. The results shows significant improvement in time and energy consumed. © Medwell Journals, 2016.

More »»

2015

Dhanya N. M. and Kousalya, Gb, “The effect of cloudlets in offloading application to cloud from mobile devices for energy efficiency”, International Journal of Applied Engineering Research, vol. 10, pp. 10041-10054, 2015.[Abstract]


Mobile is a device which is increasing in popularity day by day with powerful cameras and other facilities. We can utilize the power of mobiles in lot of applications. But battery capacity is a scarce resource in mobiles till now. So utilizing the high resolution cameras and using minimum battery power applications are advisable for mobile devices. Similarly we are considering two more application one a chess game and another is a sorting applications with different constraints. In this paper we propose a three tier architecture. Instead of depending on the distant cloud resources alone we are utilizing the nearby resource called cloudlet which can be accessed through wifi connectivity which is available everywhere nowadays. The cloudlet is a powerful resource which is in close proximity and by using this, the overall performance such as response time, efficiency can be increased. This paper analyses the effect of cloudlet in each application. © Research India Publications.

More »»
  • Scopus: Author ID: 56595089600
  • ORCID