Computer Science and Engineering

<p>Shiv Nadar University is a comprehensive, multidisciplinary, research-focused, and student-centric University offering a full range of academic programs at the undergraduate, postgraduate and doctoral level. With state-of-the-art infrastructure, the University comprises of academic wings, sophisticated labs, international standard sports facilities, amphitheaters, auditorium, conference rooms and smart classrooms. The University&rsquo;s goal is to become internationally recognized for the quality of its research and creative endeavors and their applicability to improving quality of life, generating new insights and expanding the boundaries of human knowledge creativity. Committed to excellence in teaching, research and service, the University aims to serve the higher education needs of India and the world beyond.</p>

Shiv Nadar University

A novel algorithm is introduced to track multiple circular objects present in a video using Helmholtz perception principle. First, segmentation of circular objects in the video frame is performed using the perception principle and then same perception principle is applied to track the circular objects. For each circular object present in video, we have taken an assessment of the meaningfulness of the shift of its center of gravity and meaningfulness of the deviation of the direction of movement of the object due to inter-frame displacement. We have shown that a logical threshold in the meaningfulness value tracks circular objects in a video effectively and efficiently. © 2009 IEEE.

(SoE) School of Engineering

World University root node

Proceedings of the 7th International Conference on Advances in Pattern Recognition, ICAPR 2009

Tracking multiple circular objects in video using helmholtz principle

We propose algorithms to extract groups of meaningful image level lines using Helmholtz perception principle. In this paper, the meaningfulness refers to the segmentation of circular and rectangular shapes in an image. We propose an objective assessment of meaningfulness of an image level line when the level line takes the shape of circle or rectangular segment. We have shown that a logical threshold in the meaningfulness value segments images from a variety of applications. © 2008 IEEE.

Proceedings - 6th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2008

Segmentation of circular and rectangular shapes in an image using helmholtz principle

The problem of sorting has been studied extensively and many algorithms have been suggested in the literature for the problem. Literature on parallel sorting is abundant. Many of the algorithms proposed, though being theoretically important, may not perform satisfactorily in practice owing to large constants in their time bounds. The algorithms presented in this paper have the potential of being practical. We suggest some novel sorting mechanisms specific to the Cell Broadband engine. We try to utilize the specifics of its architecture in order to get the optimum performance. As part of our comparative analysis we juxtapose these algorithms with similar ones implemented on Itanium 2 processor as well as the Pentium 4 processor. © 2008 IEEE.

Proceedings - IEEE Symposium on Computers and Communications

Efficient sorting algorithms for the cell broadband engine

The simplicity and proliferation of World Wide Web (WWW) has taken the availability of information to an unprecedented level. Moreover, this entire available information is in unstructured textual format that results search process inefficient. Simultaneously, development of web technology led to the new concept of semantic web [1], which is an extension of current web and seeks to make information understandable by machines. This creation of semantic web content involves semantic annotation of the web pages, extraction of essential data from the annotated web page and finally generation of semantic web page through processes that require high degree of engineering skill. We have developed integrated tool that helps in creation of semantic web page based on ontology [4] from HTML web page, thus enabling computers and people to work in cooperation in a better way. Semantic web page will help to process user's query in meaningful way. Copyright © 2007 IICAI.

Proceedings of the 3rd Indian International Conference on Artificial Intelligence, IICAI 2007

Automatic conversion of HTML pages to semantic web pages

A Question Answering (QA) system aims to return exact answers to natural language questions. While today information retrieval techniques are quite successful at locating within large collections of documents those that are relevant to a user's query, QA techniques that extract the exact answer from these retrieved documents still do not obtain very good accuracies. We approached the TREC 2007 Question Answering task as a semantics based question to answer matching problem. Given a question we aimed to extract the relevant semantic entities in it so that we can pin-point the answer. In this paper we show that our technique obtains reasonable accuracy compared to other systems.

NIST Special Publication

IITD-IBMIRL system for question answering using pattern matching, semantic type and semantic category recognition

Contact center agents typically respond to email queries from customers by selecting predefined answer templates that relate to the questions present in the customer query. In this paper we present a technique to automatically select the answer templates corresponding to a customer query email. Given a set of query-response email pairs we find the associations between the actual questions and answers within them and use this information to map future questions to their answer templates. We evaluate the system on a small subset of the publicly available Pine-Info discussion list email archive and also on actual contact center data comprising customer queries, agent responses and templates.

IJCAI International Joint Conference on Artificial Intelligence

Automatically selecting answer templates to respond to customer emails

Automatic filtering of information has become increasingly important in recent years due to large availability of electronic information. We present an approach for optimization of Information Retrieval System (IRS) by genetic algorithm and fuzzy sets in an adaptive filtering process. From the observed user preferences regarding documents in the sets retrieved, the system learns from the user's information needs. An interest profile is created that represents the needs as learned from the observed preferences in the user's area of interest. The proposed system will act as an offline information-filtering agent. The documents have been already downloaded from the Internet using google. The system generates a recommendation based on adaptive filtering using a set of keywords extracted from all documents evaluated by user. The process starts with the initial set of documents retrieved as the answer to user's initial query in the area of interest. The preferences given by the user are learned through explicit feedback on retrieved documents. The agent filters and ranks the retrieved information according to user's preferences using Genetic Algorithm (GA) and Fuzzy Set Theory. The system has been implemented using Java on Windows 98. © 2006 Taylor & Francis Group, LLC.

IETE Journal of Research

Information filtering using fuzzy-genetic algorithm approach

The world of text is increasing considerably. Hence, a successful summarization technology has a key role to play in the future of computing. This paper presents an efficient method of intelligently generating summaries, which uses operations derived from an analysis of human written abstracts. The algorithm uses both statistical and semantic based heuristics to produce cohesive extracts. In the proposed system, an efficient method for evaluating lexical chains as an intermediate step has been used. We have also introduced a method for finding text cohesion and implemented the same in the summarizer. The proposed summarizer also edits long extracted sentences, using reduction to remove non essential phrases. The system has been implemented using JAVA standard Development kit. Copyright © IICAI 2005.

Proceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005

Automatic text summarization

A hybrid information extraction (IE) framework based on geographical term detection approach has been developed to extract geographical information from an unrestricted Hindi text The relationship between geographical entities extracted with the adjacent text is shown graphically so that information about these entities can be related. The system, a combination of statistically and linguistically motivated techniques, identifies single geographical names and multiple geographical names as well. The method is applied on Hindi language text, but the approach can be adapted for other languages also. The paper presents some experiments illustrating the accuracy of the method. The system being developed is in a prototype stage and will be extended to include relation mark-up as well. © 2005 IEEE.

Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05

Hybrid framework for information extraction for geographical terms in hindi language texts

The advent of e-commerce has brought about a radical change in the process of auctions. This has given bidders flexibility to try and get best possible deals by participating in multiple auctions. This has also provided sellers with the opportunity of unlawfully bidding (skill bidding) in their auctions with the sole purpose of increasing their payoffs. This paper looks at the concept of shill bidding and also introduces another concept (mole bidding) through which seller can increase their payoffs. The proposed solution is based on software agents. This paper shows a high level decision making framework for sellers using mole agent (automated alias for a mole bidder) to bid across various overlapping English auctions with varying start and end times. © 2005 IEEE.

Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet