Baisakhi Chakraborty

Knowledge Management with Case-Based Reasoning applied on Fire Emergency Handling

Case-Based Reasoning is a Knowledge Management mechanism that allows knowledge acquisition through learning and experience undergone in the process of problem solving applying similarity-based reasoning. Problem representation is by means of metadata representation of certain knowledge items stored in a repository termed Case-Base. This paper discusses on a Fire Emergency Handling System where fire cases have ontological representation implemented in Object-oriented Java platform that assists fire fighters or administrators to take a decision on the resources required to handle or control fire.

Case Based Reasoning methodology for diagnosis of Swine Flu

Case Based Reasoning (CBR) has become a successful methodology for problem solving, reasoning and learning. It is applied for diagnosis and decision support in the medical field in several areas. This is because CBR methodology is analogous to the process of human reasoning and natural problem solving. In this paper, a CBR aided Swine Flu Diagnostic Assistant (SFDA) prototype has been developed that assists diagnosis of Swine Flu.

A Personnel Centric Knowledge Management System

A Knowledge Management System (KMS) is designed to serve as an effective tool for the proper extraction, utilization and dissemination of knowledge. Traditional KMS models incur cost overhead on the extraction of tacit knowledge and conversion to explicit knowledge. The proposed model in this paper takes the concept of mining the tacit knowledge and using it in the KMS instead of following conventional KMS norms. Through interactions and socialization of the personnel participating in the system, the tacit knowledge is extracted, converted to explicit knowledge and preserved in the Knowledge Management System through proper maintenance of knowledge repository. Our model is based on the technology that encourages active participation and sharing of tacit knowledge through interactions of individuals in the knowledge environment. The model builds a database of queries based on user feedback and the database is enhanced and maintained through creation of tags that makes the KMS dynamic and easily maintainable.

Automated Knowledge Provider System with Natural Language Query Processing

ABSTRACT Knowledge management system (KMS) is an effective tool for knowledge extraction, utilization, and dissemination. When a client or user sends query to the KMS, it is expected to provide response to the query. This paper proposes an automated knowledge provider system (AKPS) that accepts a natural language request of a user in a query–response model where natural language query will be automatically converted to the conceptual form of database. This model is a grammatical rule-based automated model that can extract knowledge from knowledge database resident within the AKPS independently without any manual intervention. The model maps the natural language query into the physical data model, and sends response to the user from a well-organized and well-defined database.

Application of CBR on viral fever detection system(VFDS)

In this paper an approach for developing knowledge-based viral fever detection system based on the methodology of case-based reasoning (CBR) is described. CBR is an approach for solving problems based on solutions of similar past case. Cases are stored in a database of cases called a case base (CB). To solve an actual problem a notation of similarities between problems is used to retrieve similar cases from the case base. The solutions of these similar cases are then used as starting points for solving the actual problem. This paper discusses on a viral fever detection system (VFDS) which helps the hospital or medical centre to detect the type of disease the patient is suffering from after being affected by some particular viral fever with its respective symptoms.

Application of Case-based reasoning for ship turning emergency to prevent collision

Ships and naval vessels are significant expensive properties of the nation. They transport expensive goods and often contribute to countrys security. They may face many critical emergency cases in sea that lead to accidents, collision, ship overturn leading to a destructive effect on life, property and environment. One of the major reasons for ship accidents is due to human error. To reduce accidents and ship collisions during ocean navigation, application of automated navigational aids in terms of intelligent decision taking facilities are on the rise. Case-based reasoning (CBR) is a problem solving technique that solves present problem taking reference from variety of similar problem situations. It can render decision-making easier by retrieving past solutions from situations that are similar to the one at hand and make necessary adjustments in order to adapt them. In this paper, a Case-based reasoning system for handling ship turning problem has been proposed. The systems accuracy depends on the efficient retrieval of possible solutions, and the proposed algorithm improves the effectiveness of solving the similarity to a new case at the other hand.

Knowledge-Based System Architecture on CBR for Detection of Cholera Disease

Case-based reasoning (CBR) is an appropriate methodology that applies logical reasoning using similarity measure to relate a current problem case with past similar cases. It has been applied successfully in medical diagnosis and has been experimented in different domains of application in diagnosis and detection. In this paper, we have proposed knowledge-based decision support system which uses the concept of CBR to detect cholera disease. CBR is problem solving method which is derived from artificial intelligence and is based on some base cases which can be revised in order to determine homogeneous cases for new problem. Experimental results show that the proposed model Cholera Easy Detection System (CEDS) assists the doctors to make a consistent decision. Through this work, we are intending to provide facility to the medical research scholars as well as medical unit in order to help them identify cholera when the patient is infected with correspondence symptoms of that disease. Moreover, the CEDS also assists in minimizing errors of deviation that have been found to be noticeable cause of medical errors.

A combination of CBR and bottom up approach for fever detection

In this paper, an application of knowledge-based fever detection based on the combination of methodology of case-based reasoning (CBR) and bottom up approach has been proposed. CBR is an approach for solving problems based on solutions of similar past case. Cases are stored in a database of cases called a case base (CB). To solve an actual problem a notation of similarities between problems is used to retrieve similar cases from the case base. The solutions of these similar cases are then used as starting points for solving the actual problem. Bottom up approach is needed when there are multiple solutions and among these, only one solution needs to be identified. This paper discusses on a fever detection system which helps the hospitals to detect the type of fever the patient is suffering from using symptoms of patients.

A knowledge worker centric KMS for smart E-services

KMS is an effective tool for utilization of knowledge through generation and expansion of Data Base (DB). Tacit knowledge of personnel is mined through a system of active interaction and participation of the personnel interacting in the knowledge environment of the organization. The proposed KMS is used as a smart help desk to provide Responses to client queries. The initial DB is dynamically expanded through generation of tags from client queries.

KMS with hierarchical administrative architecture: A knowledge administrator perspective

A Knowledge Management System (KMS) refers to a system for managing knowledge in organizations, supporting creation, capture, storage and dissemination of information. KMS is viewed as an essential tool to extract tacit knowledge from data, convert it to explicit knowledge and preserve the same for future utilization. The system involves creation of a knowledge repository using the extracted knowledge and disseminating it in the form of query response systems. In this work, we have proposed the architecture for an administrator-centric KMS which revolves around the concept of Knowledge Administrator (KA) with a Knowledge Worker (KW) standard. KA is responsible for maintenance as well as security and efficiency of the framework which are essential for a reliable KMS. In this system, the Knowledge Worker (KW) structure is hierarchical which provides scope for building a knowledge repository which is often encountered to be critical in some of its applications. The Knowledge Base (KB) is built on tag extraction based on inverted indexing. The system was a learning automation which used the available client feedback in response to the query answered from the knowledge base. The knowledge repository interacted with data using a framework created based on inverted indexing. A salient feature of the architecture is the notion of Probabilistic Optimum Performance (POP) factor used for rating KWs. The rating which is determined by past performance and client feedback acts as a driving force for a more comprehensive KB as its interaction with its environment increases.