Teaching: Rajendra Akerkar

Research

Research Expertise: Knowledge Based Systems, Natural Language Interface, Nature-Inspired Computing, Case Based Reasoning, Knowledge Representation & Reasoning, Semantic Web, ICT based Semantic Interoperability and Usability, Machine Learning, Mathematical Modeling, Data and Web Mining.
Application Areas Include: Knowledge Management, Medical and Health Care, Sustainable tourism, Information Security, Web Intelligence, etc.

Research & Development projects

Major R&D Projects Done: 7 International and 6 National.


Major Funding Agencies:

TWAS,
UNESCO,
Industrial (Multinational) Funding,
Department of Science & Tech., Government of India,
NBHM, Department of Atomic Energy, Government of India.

Current Projects (on-going/ recently Completed):

Project Title: ICT based Semantic Interoperability

Coordinator: Rajendra Akerkar

Type & Funding: Research Project (2009 - )

To develop and evaluate new methods for development and evolution of the Semantic Web methodologies and tools for sustainable tourism. We will investigate Knowledge technologies that can be used to improve the accuracy of searches and obtain a superior matching between customer expectations and tourism products. Also we will examine how to accomplish semantic interoperability between web sources and services.

Project Title: Knowledge Discovery to explore correlations between Mind Conditions and Physical Elements of Human beings.
Coordinators: Rajendra Akerkar & Manish Joshi

Type & Funding: Research Project (2007 - )

Man is not simply a machine,as Descartes suggested more than 300 years ago. It seems we have come full circle in our beliefs about the mind - body relationship. Body and mind clearly interact and in complex ways that we do not yet fully understand. This project aims at establishing correlation between patient symptoms and probable disturbances in patient’s mind using models of knowledge discovery in databases.

Project Title: Adaptive HTML Analysis to Automatically Wrapper Generation.

Coordinators: Rajendra Akerkar, David Camacho and María Dolores Rodríguez-Moreno

Type & Funding: Research Project /Submitted

In this project, we propose an approach, based on Artificial Intelligence techniques, to extract information from HTML pages and to add automatically semantic tags to them (extracted from a given ontology). Our project will use both, an adaptive interaction with the user, and several machine learning algorithms to adapt the wrapper generation process to the necessities of the users. The integration of both, Information Extraction and Software Agents technologies, to automatically generate adaptive wrappers could be an important issue in the evolution of new algorithms (and their related applications). These algorithms could be able to aid manage the current complexity of the Web (designed for humans not for software programs), and to alleviate the problem of extract (and manage) semantic data from the current Web systems. To study how these techniques can be adapted to the current Semantic Web-based technologies.

Project Title: Instructional Designs for Distance Education: Neural Net Enabled Distance Learning Model.

Project Coordinators: Prof. Rajendra Akerkar and Dr. A. Bagal (USA)

Type & Funding: Industrial (2007 - )

The unique “one-to-one” nature of distance learning offers a unique opportunity to tailor the instructional process for the benefit of the student as well as the organization. Neural Net Technology offers an “add-on” possibility for the computer/teacher to learn about the student, and adjust the course content as well as the pace to best suit the student. This will result in educating the student rather than issuing a pass/fail grade based on a process designed to fit all. Knowledge represented in the human brain as the strength of a very large number of interconnections between a very large number of nodes called neurons. Based on actual experience, the human brain adjusts the interconnection strength to adapt to new environments. In case of distance learning, this would entail the administrative software program adjusting the course content, through an on-going comparison of the student’s performance against a set of established “thresholds”.

Project Title: Machine Learning for Data Mining in Medicine.

Coordinators: Rajendra Akerkar

Type & Funding: Industrial Project (2003 - 2007)

The central idea of this research work was: Can useful and new knowledge be discovered from large collection of medical data by means of Data Mining, in particular by the method of machine learning from examples with artificial neural nets and case based reasoning? In this research phase, we have tested machine learning approaches used in mining of medical data, distinguishing between symbolic and sub-symbolic data mining methods and applications of these methods in medicine have been considered.

Project Title: Intelligent Natural Language Interface.

Coordinators: Rajendra Akerkar and Manish Joshi

Type: Research Project (Partially Completed in July 2007)

Natural Language Interface helps user to interact with computer in non-formal manner by answering various questions posed by user. Key-word matching based paradigm generate answers, however these answers often affected by problems caused by some language Dependant phenomena like semantic symmetry and ambiguous modification. Current methods described in literature tackles these problems using in depth parsing whereas we have formulated rules to tackle linguistic phenomena using shallow parsing. We have developed an Intelligent Natural Language Interface (ENLIGHT) comprising of newly formulated shallow parsing based algorithms in conjunction with some AI techniques to train the system. We have then tested results obtained from the ENLIGHT system. As compare to other systems which requires in depth parsing for extracting correct answer ENLIGHT system is more effective and efficient. Results are compared using different metrics like precision, mean reciprocal rank, response time and ENLIGHT system show better performance.

Our algorithms will be implemented for search engine technology in the next phase.

Project Title: A Knowledge Representation and Reasoning System

Coordinators: Rajendra Akerkar, D. Rajesh Duthie

Type: Research Project (Completed in December 2005)

The general task of work in knowledge representation and reasoning (KRR) is, trivially, the representation of knowledge. The kind of knowledge for which the representation task has been undertaken is secondary to the description of the overall task as an exercise in knowledge representation. Thus, the task of representing and using mathematical, commonsense, visual language based, and logic knowledge is "lumped" together under the KRR. We would like to argue that, in the task of natural language processing and understanding, language syntax, semantics, and pragmatics imposes constraints on any computational formalism. In this project, we present KRR system for the representation of knowledge associated with natural language dialog. We say that this may done with minimal loss of inferential power and will result in and enriched representation language capable of supporting complex natural language description, some discourse phenomena, standard first-order inference, inheritance and terminological sub-assumptions. The aim of the new logic and its implementation in a KRR system are as follows: A study of some characteristics of natural language that a KRR system should support, a KRR system to present a formalization of a propositional semantic network based knowledge representation and reasoning system that addressed our goals for NLP, a KRR system in which mapping from natural language sentences into logical form sentences be as direct as possible. The work also include other related aspects of the above mentioned problems.

Project Title: A Computational Model for Knowledge Intensive Learning

Coordinators: Rajendra Akerkar, Rajeshree Belekar

Type: Research Project (Completed in December 2007)

The framework represents a perspective on knowledge, reasoning and learning that aims at satisfying   three   fundamental   system   requirements. All   requirements   are   based   on   the assumption that competent and robust systems need a thorough, relatively deep knowledge model as a fundament for understanding, i.e. as a background pool of knowledge from which plausible   explanations   are   generated   to   support   reasoning   steps   and learning   decisions concerning the more shallow, associational knowledge in past cases and heuristic rules. The system developed under this project works for majority type of adult diabetic patients.

Previous major projects in mathematics

1. Project Title: Computational Combinatorial Structures on Hilbert Scheme.
    Funding agency: NBHM, Dept. of Atomic Energy, Government of India. (1997-99)
2. Project Title: Symbolic/Numeric Algebraic Constraints Solving (SNACS).
    Partial Support: Third World Academy of Sciences, Italy. (1999-2000)
4. Project Title: Computer Algebra Applications in Industry
    Funding Agency: Dept. of Science & Technology, Government of India. (1997-98)

Recent doctoral supervision

North Maharashtra University, Jalgaon, and Shivaji University, Kolhapur , India.

Manish R. Joshi: Natural Language Interface.

           (Ph.D. in Computer Science, North Maharashtra University, Jalgaon, India (2007))

Natural Language Interface helps user to interact with computer in non-formal manner by answering various questions posed by user. Key-word matching based paradigm generate answers, however these answers often affected by problems caused by some language dependant phenomena like semantic symmetry and ambiguous modification. Current methods described in literature tackles these problems using in depth parsing whereas we have formulated rules to tackle linguistic phenomena using shallow parsing. We have developed an Intelligent Natural Language Interface (ENLIGHT) comprising of newly formulated shallow parsing based algorithms in conjunction with some AI techniques to train the system. We have tested results obtained from the ENLIGHT system. As compare to other systems, which requires in depth parsing for extracting correct answer, ENLIGHT system is more effective and efficient. Results are compared using different metrics like precision, mean reciprocal rank, response time and ENLIGHT system show better performance.

D. Rajesh Duthie: Knowledge Representation and Reasoning System.

        (Ph.D. in Computer Science, Shivaji University, Kolhapur, India (2009))

The general task of work in knowledge representation and reasoning (KRR) is, trivially, the representation of knowledge. In this work, we have presented a KRR formalism for the representation of knowledge associated with natural language dialog. The aim was to develop the new logic and its implementation in a KRR system.

Rajeshree Belekar: Knowledge Intensive Learning.

        (PhD in Computer Science, Shivaji University, Kolhapur, India (2009))

The work introduces a dietary planner system which combines case based reasoning and rule based reasoning approaches to solve a problem.

Recent Masters project supervision

Ara Shamirzaian: Automation of Software Configuration Management, 2005.

There has been considerable progress concerning support for software configuration management (CM) in environments and tools. This project's intent is to highlight the user concepts provided by existing CM systems. These are shown as a spectrum. In the spectrum, concepts are seen as extensions to, or generalizations of, other concepts. There is difficulty associated with extracting concepts from CM systems since there is no commonality in terminology concerning CM functionality throughout the software engineering community and many CM systems implement variations on concepts. As a result, each concept presented is described as it exists in one particular CM system. A part of highlighting the concepts involves discussing the scope of issues important to users of CM systems. No single CM system provides all the functionality required by the different kinds of users of CM systems. Rather, each CM system addresses some part of the spectrum of concepts. To complete the report, the CM capabilities of the systems used as examples are briefly described.

Armine Ghazaryan: Web Driven Graphical Voice Xml Toolkit Quickspider, 2005.

Nowadays VoiceXML scenarios are common not only for companies and organizations but also for ordinary people, who want to create their own scenarios. The thing is that although this scenarios might be seem very easy, in reality creation process is not an easy task and moreover it is time consuming. Many users are not aware of syntax, principles, and restrictions of VoiceXML.
The project is aimed to develop a user-friendly web based module for creating, editing, and saving VoiceXML scenarios without knowledge of VoiceXML. The idea was to ease VoiceXML scenario creation. QuickSpider is a graphical web-based tool for building VoiceXML scripts that can be used in voice over IP environments such as Voice Mail Systems or Interactive Voice Response systems.
This is Client-Server application that is designed and implemented separately. The project provides server side design, and implementation details, namely, how to convert user made Graphical Model into VoiceXML file. Special developed protocol makes the process of that conversion efficient and effective.

Hovhannes Muradyan : Web Driven Graphical Voice XML Toolkit Quickspider, 2005.

To withstand the severe competition in the world market, nowadays IT companies try to be as much flexibly as possible. One way to reach the desired flexibility is to detach business logic from the system itself, namely, instead of omnipresent hard code, use flexible text-based scenarios, very much like Voice XML scenarios, which might be later on changed by any non-professional user of the system in favor of their needs.
The main idea of the Web-based Graphical Tool called QuickSpider is to simplify the Voice XML script building process. Voice XML is a XML based markup language for describing the interaction/dialog scenarios between the users and the system. During that interaction the system plays the voice menu to the user asking to make a selection by pressing some button on the phone. The outcome of that interaction is communicating some information to the user, transferring the call to a new destination, playing the stored voice message and the like. In legacy systems these interaction scenarios were mainly hard-coded in the software; however the new generation of Voice XML based systems is much flexible and allows the user to customize that interaction dialog without rebuilding the software (just replacing the existing Voice XML script with the desired one). Nevertheless, even though the Voice XML approach is very flexible and time saving compared to that of its predecessors, the Voice XML language is not so user friendly to be used by regular users without special knowledge and training.

Karen Aghajanyan: Online Business Directory Web Application, 2005.

The companies use internet as powerful tool of information delivery to potential client. Now it is not enough just to have a website in the internet, because lot of customers search for products and services through the search engines and information incubators. The goal of this project is to create, database with multi-language support, which will store information and profiles of the various business companies and users who will browse the information, as well as appropriate software which will provide the information and allows entering, modifying and deleting it.

Lusine Avanesyan : Customer Relationship Management for Business Support Center, 2006.

The customization of open source products becomes one of the most applicable and useful techniques in software development. Open source software is "free software" available for viewing, altering according to the requirements and re-distributing. Customer Relationship Management (CRM) is software for growing businesses to help centralize and effectively manage contacts; business processes, communications and all customer related information in a single application.
CRM for BSC is customized software for Business Support Center (BSC) - a well-known consulting company in Armenia. The customization is done on Centraview's open source CRM available at http://www.centraview.com. Centraview's CRM has high level architecture of software design patterns and the abstraction through business/data layers and presentation layer. Built on the Enterprise Java (J2EE) platform and optimized for Windows environment, CRM for BSC leverages open source technologies such as Apache Tomcat, JBoss and MySQL. The whole system works on Struts which is a server-side Java framework. Struts combines two of the most popular server-side Java technologies - JSPs and Servlets into a server-side implementation of the Model View Controller (MVC) design pattern. The Model part of MVC is done using Enterprise Java Beans (EJB). Struts it used mainly for creating Web applications that easily separate the presentation layer and allow it to be abstracted from the transaction/data layers.
CRM for BSC includes integrated and powerful contact management, scheduling of business activities such as trainings, consulting and development programs with their own stages, as well as document management, customer service, human resource management and reports. The Centraview's product contains several modules which would never be used by BSC that is why they were totally removed and new ones were written: from Cenraview's 210 database tables only 20 are customized and 35 tables are added for BSC specific functionality; from more than 1600 java files of Centraview only 200 are customized, many are removed and another 300 are just newly created. So the whole architecture and style of software is kept as it was, some important part is customized and lots of new functionality is added.

185 students have successfully completed Masters’ Projects and 62 students have done Diploma Projects (software development) in the area of Computer Applications/ Information Systems under my supervision in India and Armenia.