Qualification: 
Ph.D
Email: 
anbazhagan-m@cb.amrita.edu

Dr. M. Anbazhagan is an Assistant Professor in the Department of Computer Science and Engineering at Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore. He graduated with both his Under-Graduation and Post-Graduation in Computer Science and Engineering from Anna University. He received his Ph.D. from the National Institute of Technology, Tiruchirappalli. He is having 12+ years of experience as a computer engineering teacher gained from various institutes. His subjects of interest include data structures and algorithms, computer programming, mobile computing, information retrieval, database management systems and operating systems. 

Recommender Systems, Machine Learning, and Deep Learning are his current research areas of interest. He intends to leverage Recommender Systems by adopting more powerful deep neural networks and exploiting expressive information sources such as reviews, metadata etc. He is also interested in building Recommender Systems that make group recommendations and inter-domain Recommender Systems. In his 12+ years of experience, he has fruitfully guided 32 UG project and 5 PG project teams. He has also mentored two project teams that contested in AICTE’s Smart India Hackathon contest. In Jan 2012, he has been awarded as a national level winner by Wipro’s Mission10X for his best case study on “Incorporating Pedagogical Technique in Classroom Teaching”.

Publications

Publication Type: Journal Article

Year of Publication Title

2021

Dr. Anbazhagan M and Arock, M., “A class imbalance-aware review rating prediction using hybrid sampling and ensemble learning”, Multimedia Tools and Applications, vol. Vol. 80, 2021.[Abstract]


Imbalanced distribution of instances across the classes is a challenging issue when the underlying problem is of type classification. The reason is that classifiers will tend to favor the classes with a large number of instances i.e. instances of minority classes may be identified as instances of majority classes by the classifiers. In recent years, plenty of researches have been done to resolve the class imbalance issue in binary classification problems which resulted in many class imbalance learning techniques for binary classification problems. But, the class imbalance in multi-class classification problems did not draw much attention from the research community. Unlike binary class imbalance learning, multi-class imbalance learning techniques experience more than one majority class and more than one minority class. This paper tries to come up with a multi-class imbalanced learning technique that can overcome the effects of multi-class imbalance problem in review rating prediction tasks. The proposed model handles the multi-class imbalance issue by using the combination of hybrid sampling and ensemble learning techniques. Sampling techniques such as Random Under Sampling (RUS) and Synthetic Minority Over-sampling TEchnique(SMOTE) are jointly used in the proposed model to create balanced training sets for base learners. Also, the proposed model creates a powerful ensemble structure by amalgamating a manually created bagging ensemble and AdaBoost boosting ensembles. Experiments are done using the Amazon product dataset in order to investigate the performance of the proposed model. The experimental results show that the proposed Class Imbalance-Aware Review rating prediction(CIAR) model outperforms almost all the baseline models in-terms of G-mean, F-Score, and ROC_AUC_Score.

More »»

2020

Dr. Anbazhagan M and Arock, M., “Integrated topic modeling and sentiment analysis: a review rating prediction approach for recommender systems”, Turkish Journal of Electrical Engineering and Computer Sciences, vol. 28, pp. 107-123, 2020.[Abstract]


Recommender systems (RSs) are running behind E-commerce websites to recommend items that are likely to be bought by users. Most of the existing RSs are relying on mere star ratings while making recommendations. However, ratings alone cannot help RSs make accurate recommendations, as they cannot properly capture sentiments expressed towards various aspects of the items. The other rich and expressive source of information available that can help make accurate recommendations is user reviews. Because of their voluminous nature, reviews lead to the information overloading problem. Hence, drawing out the user opinion from reviews is a decisive job. Therefore, this paper aims to build a review rating prediction model that simultaneously captures the topics and sentiments present in the reviews which are then used as features for the rating prediction. A new sentiment-enriched and topic-modeling-based review rating prediction technique which can recognize modern review contents is proposed to facilitate this feature. Experimental results show that the proposed model best infers the rating from reviews by harnessing the vital information present in them.

More »»

2019

Dr. Anbazhagan M and Arock, M., “Review rating prediction using combined latent topics and associated sentiments: an empirical review”, Service Oriented Computing and Applications volume, 2019.[Abstract]


Understanding the tastes of each user and the characteristics of each product is necessary to predict how a user will respond to a new product. These latent user and product dimensions can be discovered with the help of user feedback. A numeric rating and its accompanying text review is the most widely available form of user feedback. A measure which encapsulates the contents of such reviews is often necessary as they have been found to significantly influence the shopping behavior of users. A fine-grained form of such measure that could act as a perfect feedback about the product is star rating. The review rating prediction tries to predict a rating corresponding to the given review. An approach that performs review rating prediction task by using the latent topics extracted from reviews and their associated sentiments is proposed in this paper. The proposed approach treats review rating prediction problem as a multi-class classification problem. An empirical review of topic modeling techniques such as (i) term frequency-inverse document frequency(TF-IDF), (ii) latent Dirichlet allocation(LDA), and (iii) nonnegative matrix factorization(NNMF) is performed in this work to investigate their efficiency. The proposed approach has a lot of advantages: Firstly, this approach accurately predicts product ratings by making use of the topics and their sentiments present in the reviews; this is useful in occasions where only reviews are available. Secondly, the discovered topics and their sentiments can be used to recognize informative reviews. Thirdly, it facilitates to justify the rating with review text. The experimental results show that the proposed model works well with latent topics and sentiments when the underlying model is trained using a deep learning technique.

More »»

2016

Dr. Anbazhagan M and Arock, M., “Collaborative Filtering Algorithms for Recommender Systems”, International Journal of Control Theory and Applications, vol. Vol. 9, No. 27 vol., pp. pp. 127-136, 2016.[Abstract]


Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you'll learn about some of Silicon Valley's best practices in innovation as it pertains to machine learning and AI. This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.

More »»

2012

Dr. Anbazhagan M, Anitha, M., and Mohamed, M. A. Maluk, “Sensor Grid Based Vision Status Monitoring in Eye Care System”, International Journal of Future Computer and Communication, vol. 1, 1 vol., 2012.[Abstract]


Wireless sensor networks play an important role in various applications including health care monitoring of patients. In health care monitoring various health conditions of patients are monitored by using bio medical sensor including the field of Ophthalmology for monitoring oculomotor behavior, cognitive visual function and vision deficiencies in diverse environments for various post surgical treatment. The Bio sensors deployed in this environment are resource constraint in nature with limited processing and communication power. The work have proposed Sensor Grid architecture called sensor grid based vision status monitoring in eye care system for monitoring the vision status of different groups of eye patients to provide a platform for ophthalmologists to share computational resources to facilitate quantifiable eye-movement analysis, diagnose and treat abnormalities or ocular disease in clinical situations to reduce the dormant propagation of eye diseases. The paper proposes a novel unique simulated model integrating ophthalmological sensors (bio sensors) with the grid to process and store the collected ophthalmology data to achieve better vision prediction rate in ophthalmological field with low latency, increased throughput and proper load balancing across the sensor grid.

More »»

2011

R. S. and Dr. Anbazhagan M, “An improved kangaroo transaction model using surrogate objects for distributed mobile system”, National Level Conference on Emerging Trends in Computing and Network Technologies, 2011.[Abstract]


The rapid growth in the use of wireless communication and mobile devices has created a potential for variety of mobile transaction support. The variety of mobile transaction models have already been developed for dealing with different challenging requirements in this environment. However, a transaction management in mobile computing environment faces several challenges such as scarce bandwidth, limited energy resources, asymmetry in wired and wireless connectivity, asymmetry in mobile and fixed hosts, and mobility of host and their limitations. Due to these constraints, data loss, frequent disconnection, unpredicted number of wireless and wired access and high transaction aborts have been occurred. In this paper we propose a new transaction scheme called Surrogate Object based mobile transaction model. The main focus is to support data caching at surrogate object for faster data access and database operations among mobile transactions at different mobile hosts in mobile environment. This is done by creating the surrogate object in the static network to act on behalf of each mobile device. One consequence of using the surrogate object model is that mobile devices would be transparent to the instability of wireless communication. The surrogate object can remain active, maintaining information regarding the current state and plays an active role on behalf of the device and reduces the network congestions, overcomes the asymmetry in wired and wireless access and achieve the low abort rate. The performance of the proposed model for mobile transaction is evaluated and compared in the absence of surrogate object. Results showed that a significant reduction in wireless access and abort probability can be obtained with the proposed model when measuring performance metrics.

More »»

Publication Type: Conference Paper

Year of Publication Title

2017

Dr. Anbazhagan M and Arock, M., “Credible user-review incorporated collaborative filtering for video recommendation system”, in 2017 International Conference on Intelligent Sustainable Systems (ICISS), Palladam, India, 2017.[Abstract]


A system that recommends an item to a user that he/she is likely to be interested in is said to be a recommender system. Collaborative Filtering(CF) is a technique used to implement recommender systems. CF uses numeric ratings given by users to find the nearest neighbors to the target user and generates recommendations. An upgraded collaborative filtering algorithm that uses credible user-reviews to generate accurate recommendations is proposed in this paper. While in the earlier CF approaches, mere numerical ratings are used for making recommendations, but overall ratings alone cannot properly reflect user's opinion about an item. Another deficiency associated with the existing rating based CF approaches is sparseness in rating database. Data sparsity problem can be got rid of, only if we have an alternate way of filling up the empty ratings. The proposed approach tries to do this by inferring numeric ratings from text reviews. Rating inference involves a sentiment analysis problem of finding the sentiment orientation and strength of opinion words expressed in user-reviews. Some existing recommender systems have already incorporated user-reviews for making better recommendations, but they did not take into account the credibility of those reviews. The proposed CF approach grades the credibility of user-reviews by considering the factors such as reputation of the reviewer and quality of the contents in review. Experimentation of the proposed framework is done and results are validated.

More »»

2016

Dr. Anbazhagan M and Arock, M., “Collaborative Filtering Algorithms for Recommender Systems - Conference”, in International Conference on Computing Communication and Information, 2016.[Abstract]


Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you'll learn about some of Silicon Valley's best practices in innovation as it pertains to machine learning and AI. This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.

More »»

2010

Dr. Anbazhagan M, “A Methodology of Grid Computing in Bio-Informatics Environments”, in National Level Conference on Innovation in Science, Engineering And Technology, 2010.

Seminars/Workshops/FDPs Attended/ Participated

  • Participated in a National level "One-week online Faculty Development Program on Python for Data Science" organized by MITS-Madanapalle from 24th to 28th June 2020.
  • Participated in a two-day International workshop on "Applications of Data Science" organized by SSN College of Engineering, Chennai from 29th to 30th June 2020.
  • Participated and successfully completed "Effective and Efficient Online Teaching in the Age of Corona,
  • A Hands On Workshop" organized by IIT-Bombay from 13th to 16th May 2020.
  • Participated in a "Five-day Faculty Development Program on Empowering Teachers in 21st Century Education" organized by NIT-Trichy under AICTE’s Margadharsan Scheme from 29th April to 3rd May 2019
  • Participated in a "Five-day Faculty Development Program on Salesforce Essentials for Business Specialists" organized by Salesforce and ICT Academy at Saranathan College of Engineering, Trichy from 23rd to 27th July 2018
  • Participated in a "Deep Dive Faculty Enablement Program on Foundation Program 5.0" organized by Infosys at Rajalakshmi Engineering College, Chennai on 23rd April to 27th April 2018
  • Completed a One-week Faculty Development Program on “Java Fundamentals and Programming”, organized by Oracle Academy in association with ICT Academy, at M.A.M. College of Engineering, from 9th Oct to 13th Oct 2017
  • Participated in “Salesforce Academic Directors Meet 2017”, organized by Saleforce in partnership with ICT Academy, on 21st of July 2017 at Fortune Pandiyan Hotel, Madurai.
  • Participated in “AWS EDUCATE DAY – 2017”, organized by Amazon Web Services in association with ICT Academy, at Hotel Radisson-Blu GRT, Chennai on 13th Jul 2017.
  • Completed a One-week ISTE Approved Short Term Training Program on “Robotics using Embedded C”, at Agnel Institute of Technology and Design, Mapusa, Goa, from 2nd to 6th Nov’15.
  • Completed a Training Program titled “Think Parallel: Training on Parallel Programming for Engineers and Scientists” at C-DAC, Knowledge Park, Bangalore, from 23rd to 27th Jun 2014.
  • Participated in a Two-day National Level Workshop on "Big-Data Analytics" at Anna University Regional Centre, Coimbatore from 18th to 19th Oct 2013.
  • Participated in a Two-week ISTE Workshop on "Database Management Systems", Organized by NIT-Trichy and Conducted by IIT-Bombay, from 21st to 31st May 2013.
  • Completed an AICTE Sponsored Short Term Course on “Advanced Computer Architecture” at IIT Madras from 17th to 21st Dec 2012.
  • Attended a Three-day “Train The Trainer Workshop on FP Training Tools and Methodologies”, organized by Infosys Campus Connect at Kamaraj College of Engineering and technology, Virudhunagar from 27th to 29th Sep 2012.
  • Successfully completed a Certification Training on “Mission10X Learning Approach”, organized by Wipro’s Mission10x at M.A.M College of Engineering, Trichy from 24th to 25th Jan 2012.
  • Participated in a Five-day Workshop on “Mission10X Learning Approach”, organized by Wipro’s Mission10X at M.A.M College of Engineering, Trichy from 13th to 17th Dec 2011.
  • Participated in an AICTE-MHRD Sponsored Short Term Training Programme on “Next Generation Data Management” at NIT - Karnataka, Surathkal, Karnataka, from 13th to 17th Jun 2011
    Attended a Three-day Workshop on “Cloud Computing” at IIT Madras, Chennai, from 18th to 20th Aug 2010.
  • Participated in a One-day Workshop on “Cloud Computing the Next Revolution of Information Technology” (Speaker: Prof. Rajkumar Buyya, Melbourne University) at M.A.M. College of Engineering, Trichy on 16th Dec 2009.
  • Participated in a Quality Improvement Program titled “Instructional Design and Delivery Methods”, conducted by NITTR, organized by M.A.M. College of Engineering, Trichy from 8th to 13th Dec 2008.

Reviewer

  • Electronic Commerce Research and Applications (Elsevier)
  • Super Computing (Springer)

Guest Lectures Delivered

  • Delivered a technical talk on “Research Issues in Recommender Systems” in a faculty development program on Recent Research Trends in Computing organized by Indra Ganesan College of Engineering, Trichy (June 2021).
  • Delivered two sessions on “Multicore and Multiprocessor Computers” and “Parallel Programming Paradigm” in a faculty development program on Multicore Architectures and Programming, sponsored by Anna University, held at Gnanamani College of Technology, Namakkal (July 2018).
  • Delivered two sessions on “Mobile Databases, Distributed Databases, and Parallel Databases” in a faculty development program on Advanced Databases, sponsored by Anna University, held at M.A.M. College of Engineering, Trichy (June 2013).
  • Conducted 20+ software trainings on “Microsoft Office Suit” for the employees of BHEL-Trichy between 2009 and 2013.
  • Conducted 5+ software trainings on “Microsoft Office Suit” for Tamil Nadu Women Police between 2009 and 2011.