Dr. Vidhya Balasubramanian joined Amrita in 2009; she comes to Amrita from the University of California Irvine, USA, where she received both her M. S. and Ph. D. (2008) in Computer Science. Her dissertation focused on Supporting Scalable Activity Modeling in Simulators. She has experience in large scale spatial temporal data management and customized multimedia information retrieval.

As a member of the Distributed Systems Middleware group in University of California, Irvine, USA, Dr. Vidhya worked on user-based multimedia content adaptation for distance learning. She has worked on building large simulation platforms for disaster response in the ITR-Rescue project, part of California Institute for Telecommunications and Information Technology (Calit2). She has worked on scalable multi-geography path planning algorithms in the context of designing integrated disaster response simulation test beds.

Her experience working on large systems has given her rich experience in large scale data management and scalable algorithms. She was the Principal Investigator of a DST funded project on Indoor GIS which is part of the Amrita Multidimensional Data Analytics Lab.

Dr. Balasubramanian joined Amrita because of her wish to be part of Ammas projects to serve society. She believes Amrita University has significantly improved the standards of education in India, and she wants to contribute to research and higher education as part of Amrita. Her current areas of interests are Spatial and temporal data management, Indoor Spatial Data Management, Scalable Data Architectures and Knowledge Representations for Information Retrieval. She is also interested in multimedia content adaptation and management, and geographical information systems.  She is currently advising PhD scholars in these areas.


Year Affiliation
July 2012 – Present Associate Professor, Dept of Computer Science and Engineering, Amrita School of Engineering, Ettimadai, Coimbatore
Feb 2009 - July 2012 Assistant Professor, Dept of Computer Science and Engineering, Amrita School of Engineering, Ettimadai, Coimbatore
Sep 2004 - 2008 Graduate Research Assistant, Rescue Project, University of California Irvine and Calit2
Sep 2001 – Sep 2004 Graduate Research Assistant, SUGA Project, University of California, Irvine





Publication Type: Journal Article
Year of Publication Publication Type Title
2016 Journal Article J. Muralikumar, Seelan, S. A., Vijayakumar, N., and Balasubramanian, V., “A statistical approach for modeling inter-document semantic relationships in digital libraries”, Journal of Intelligent Information Systems, pp. 1-22, 2016.[Abstract]

E-Learning repositories and digital libraries are fast becoming important sources for gathering information and learning material. Such systems must therefore provide services to support the learning needs of their users. When a retrieval system shows how its documents relate to each other semantically, a user gets the liberty to choose from different material, and direct his/her study in a focused manner. This calls for a model that identifies types of document relationships, that need to address different aspects of learning. This article defines three such types and a unique statistical model that can automatically identify them in technical/scientific documents. The model defines measures to quantify the degree of relatedness based on distinct statistical patterns exhibited by the common terms in a pair of documents. This approach does not strictly require a knowledge base or hypertext for identifying the characteristic relationship between two documents. Such a statistical model can be extended to build further relatedness types and can be used alongside various other techniques in digital library recommendation engines. Our experiments over a large number of technical documents show that our techniques effectively extract the different types of relationships between documents. More »»
2015 Journal Article V. Balasubramanian, Doraisamy, S. Gobu, and Kanakarajan, N. Kumar, “A Multimodal Approach for Extracting Content Descriptive Metadata from Lecture Videos”, Journal of Intelligent Information Systems, vol. 46, pp. 121–145, 2015.[Abstract]

The rapidly increasing availability of e-learning content and lecture videos over the internet, has brought forth an imperative need for developing effective content based retrieval systems. Comprehensive metadata extraction and support for topic-level search within videos are key factors in developing such systems. In this paper, we propose a multimodal metadata extraction system which extracts an optimal set of keyphrases and topic based segments that effectively summarize the content of a lecture video. The extraction process utilizes features from both audio transcripts and slide content in video streams. A hybrid approach combining a Naive Bayes classifier and a rule-based refiner is used for effective retrieval of the metadata in a lecture. The proposed content-descriptive metadata extraction technique has been evaluated using actual lecture videos from different sources, and our results show that our multimodal approach is effective in summarizing the lecture's content, potentially improving the user experience during retrieval and browsing.

More »»
2003 Journal Article V. Balasubramanian and Venkatasubramanian, N., “Server transcoding of multimedia information for cross disability access”, ACM MMCN, 2003.
Publication Type: Conference Paper
Year of Publication Publication Type Title
2015 Conference Paper V. Chandrasekaran, Narayan, K., Vasani, R. K., and Balasubramanian, V., “InPLaCE RFID: Indoor path loss translation for object localization in cluttered environments”, in 2015 IEEE 10th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2015, 2015.[Abstract]

<p>Radio Frequency Identification (RFID) is widely used in indoor positioning systems for object tracking and localization. However, there are several challenges that are yet to be addressed especially in 3-D space. When objects are cluttered densely, an arrangement synonymous to that of heaps of haphazardly arranged files in an office, locating and retrieving a file manually from the heap becomes a laborious task. In this paper, we address the challenge of localization and retrieval of objects in cluttered environments using passive RFID tags, by developing a novel indoor path loss translational model that considers the signal properties across the clutter. The proposed InPLaCE RFID system estimates the position of the object within a clutter by employing a robust translation model that accounts for the properties of the clutter and helps compensate for estimation errors over existing path loss models. Our experiments over different cluttered environments show that the proposed translational model improves the localization accuracy of objects over existing path loss models. © 2015 IEEE.</p>

More »»
2015 Conference Paper S. F. Xavier, Selvaraj, L. P., and Balasubramanian, V., “Enhancing statistical semantic networks with concept hierarchies”, in 2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015, 2015, pp. 1298-1307.[Abstract]

With the emergence of the semantic web, effective knowledge representation has gained importance. Statistically generated semantic networks are simple representations whose semantic power is yet to be completely explored. Though, these semantic networks are created with simple statistical measures without much overhead, they have the potential to express the semantic relationship between concepts. In this paper, we explore the capability of such networks and enhance them with concept hierarchies to serve as better knowledge representations. The concept hierarchies are built based on the level of importance of concepts. The level of importance/coverage of a concept within the given set of documents has to be taken into account to build an effective knowledge representation. In this paper, we provide a domain-independent, graph based approach for identifying the level of importance of each concept from the statistically generated semantic network which represents the entire document set. Insights about the depth of every concept is obtained by analysing the graph theoretical properties of the statistically generated semantic network. A generic concept hierarchy is created using a greedy strategy, and the original semantic network is reinforced with this concept hierarchy. Experiments over different data sets demonstrate that our approach works effectively in classifying concepts and generating taxonomies based on it, thereby effectively enhancing the semantic network. © 2015 IEEE.

More »»
2015 Conference Paper A. Sivaramakrishnan, Krishnamachari, M., and Balasubramanian, V., “Recommending Customizable Products: A Multiple Choice Knapsack Solution”, in Proceedings of the 5th International Conference on Web Intelligence, Mining and Semantics, New York, NY, USA, 2015.[Abstract]

Recommender systems have become very prominent over the past decade. Methods such as collaborative filtering and knowledge based recommender systems have been developed extensively for non-customizable products. However, as manufacturers today are moving towards customizable products to satisfy customers, the need of the hour is customizable product recommender systems. Such systems must be able to capture customer preferences and provide recommendations that are both diverse and novel. This paper proposes an approach to building a recommender system that can be adapted to customizable products such as desktop computers and home theater systems. The Customizable Product Recommendation problem is modeled as a special case of the Multiple Choice Knapsack Problem, and an algorithm is proposed to generate desirable product recommendations in real-time. The performance of the proposed system is then evaluated.

More »»
2014 Conference Paper A. H. and Balasubramanian, V., “A Model Independent and User-friendly Querying System for Indoor Spaces”, in Proceedings of the 20th International Conference on Management of Data, Mumbai, India, India, 2014.[Abstract]

Querying indoor information has become important with increasing demand for indoor pervasive applications in vogue. A number of applications have been developed like indoor navigation, localization etc., which work on the modeled indoor data. Different models like geometric, spatial and topological models exist for the indoor space. Existing query languages are model specific, and not user friendly. We propose a querying system which will work irrespective of the underlying model by hiding the complex details of the indoor model from the user. A querying framework is developed which abstracts out basic entities and primitive operators from multiple models. A text-based query language for the indoor space is built on this framework. A visual querying interface is developed which further simplifies the task of querying.

More »»
2010 Conference Paper V. Balasubramanian, Kalashnikov, D. V., Mehrotra, S., and Venkatasubramanian, N., “Efficient and Scalable Multi-geography Route Planning”, in Proceedings of the 13th International Conference on Extending Database Technology, New York, NY, USA, 2010.[Abstract]

This paper considers the problem of Multi-Geography Route Planning (MGRP) where the geographical information may be spread over multiple heterogeneous interconnected maps. We first design a flexible and scalable representation to model individual geographies and their interconnections. Given such a representation, we develop an algorithm that exploits precomputation and caching of geographical data for path planning. A utility-based approach is adopted to decide which paths to precompute and store. To validate the proposed approach we test the algorithm over the workload of a campus level evacuation simulation that plans evacuation routes over multiple geographies: indoor CAD maps, outdoor maps, pedestrian and transportation networks, etc. The empirical results indicate that the MGRP algorithm with the proposed utility based caching strategy significantly outperforms the state of the art solutions when applied to a large university campus data under varying conditions. More »»
2004 Conference Paper V. Balasubramanian and Venkatasubramanian, N., “GURU: A Multimedia Distance-learning Framework for Users with Disabilities”, in Proceedings of the 12th Annual ACM International Conference on Multimedia, New York, NY, USA, 2004.[Abstract]

GURU is a distance-learning environment that renders multimedia information to users with disabilities in an accessible manner. It is an implementation framework developed as part of an effort to provide accessible multimedia information to end users with perceptual (visual and auditory), cognitive or motor impairments. GURU is based on the MPEG-4 standard, and it modifies MP4 content and the presentation of the different objects in the scene dynamically based on users' visual, auditory and motor abilities. This paper briefly describes the implementation of the prototype framework and illustrates sample adaptations as implemented in this framework. More »»
Publication Type: Conference Proceedings
Year of Publication Publication Type Title
2014 Conference Proceedings H. Malla, Purushothaman, P., Rajan, S. V., and Balasubramanian, V., “Object level mapping of an indoor environment using RFID”, Ubiquitous Positioning Indoor Navigation and Location Based Service (UPINLBS), 2014. pp. 203-212, 2014.[Abstract]

Many of the indoor applications like navigation, indoor localization, object tracking require an indoor map. Indoor environments are dynamic in nature because of the objects present in it. To capture the essence of the indoor environment, it is essential to perform an object level mapping of an indoor space. This is because an object has the potential to alter the map of an indoor environment. Mapping a huge indoor environment could prove to be costly in terms of time with high infrastructure dependency. This compels us to find a simple solution in terms of cost, time and reliability to build an indoor map. The proposed solution should have minimal infrastructure dependence, so that it can be used in situations like disaster and rapid response scenarios, where the available infrastructure is minimal and time is of essence. We propose a Radio Frequency Identification(RFID) based approach which performs an object level mapping of the indoor environment using a portable RFID reader, RFID Ultra High Frequency(UHF) passive tags and inertial navigation sensors(INS). This approach identifies each object in the indoor environment using one or more passive tags. A novel algorithm has been developed which accurately maps the objects present in the indoor space. It is easily scalable to map huge indoor environments and can be applied without any intensive manual labor or expensive equipments. Our experiments show that this approach generates object level indoor maps with high accuracy.

More »»
2014 Conference Proceedings V. Balasubramanian, Krishnan, P., Krishnakumar, S., and Seshadri, R., “A Robust Environment adaptive Fingerprint Based Indoor Localization System”, In Proceedings of the 13th International Conference on Ad Hoc Networks and Wireless (ADHOC-NOW-2014), , vol. 8487. pp. 360 - 373, 2014.
2012 Conference Proceedings A. Balagopalan, Balasubramanian, L. L., Balasubramanian, V., Chandrasekharan, N., and Damodar, A., “Automatic keyphrase extraction and segmentation of video lectures”, Proceedings - 2012 IEEE International Conference on Technology Enhanced Education, ICTEE 2012. Kerala, pp. 1-10, 2012.[Abstract]

<p>Keyphrases are essential meta-data that summarize the contents of an instructional video. In this paper, we present a domain independent, statistical approach for automatic keyphrase extraction from audio transcripts of video lectures. We identify new features in audio transcripts, that capture key patterns characterizing keyphrases in lecture videos. A system for keyphrase extraction is designed that uses a supervised machine learning algorithm, based on a Naive-Bayes classifier to extract relevant keyphrases. Our extensive experimental studies show that our system extracts more relevant keywords than existing approaches. The paper also evaluates the performance of the proposed keyphrase extraction method for different categories of lectures. The extracted keyphrases are used further as features for automatic topic based segmentation of the video lectures. This process of automatic keyphrase extraction and segmentation results in a section-wise annotated video lecture which can be effectively viewed in a lecture browser. © 2012 IEEE.</p>

More »»
Publication Type: Book
Year of Publication Publication Type Title
2006 Book V. Balasubramanian, Massaguer, D., Mehrotra, S., and Venkatasubramanian, N., DrillSim: a simulation framework for emergency response drills. Springer, 2006.[Abstract]

Responding to natural or man-made disasters in a timely and effective manner can reduce deaths and injuries, contain or prevent secondary disasters, and reduce the resulting economic losses and social disruption. Appropriate IT solutions can improve this response. However, exhaustive and realistic validation of these IT solutions is difficult; proofs are not available, simulations lack realism, and drills are expensive and cannot be reproduced. This paper presents DrillSim: a simulation environment that plays out the activities of a crisis response (e.g., evacuation). It has capabilities to integrate real-life drills into a simulated response activity using an instrumented environment with sensing and communication capabilities. IT solutions can be plugged in the simulation system to study their effectiveness in disaster management and response. This way, by using a simulation coupled with an on-going drill, IT solutions can be tested in a less expensive but realistic scenario. More »»


  • UCI Living our Values, Student Honor Roll - Fall 2007


  • Association of Computing Machinery (ACM)
  • Institute of Electrical and Electronics Engineers (IEEE)
  • Computer Society of India (CSI)


Faculty Details


Faculty Email: