Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/293513
Title: Multiagent system for cooperative decision making in academic environment
Researcher: Modgil, Puneet
Guide(s): Devi, M. Syamala
Keywords: Artificial Intelligence
Decision Making
Fuzzy Logic
Multiagent
Ontology
University: Panjab University
Completed Date: 2019
Abstract: Multiagent System for Cooperative Decision Making in Academic Environment (MASCDAE) is a collection of four subsystems where each subsystem contains one or more agents that coordinate with each other to facilitate cooperative decision making in Academic Environment. The four subsystems of newlineMASCDAE are Admission Scrutiny subsystem, Meeting Scheduling subsystem, Meeting Facilitation subsystem, and Research Asset Management subsystem. newlineIn the Admission Scrutiny subsystem, the main knowledge-intensive tasks of admissions are scrutinising admission forms filled by admission seekers. Scrutiny is performed by capturing the knowledge from the web and relevant sources and scrutinising the information. This work is assigned to three agents, namely Form agent, Record agent and Scrutiny agent. newlineMeeting Scheduling subsystem involves finding a suitable slot for an academic meeting. Coordinator schedules meeting considering the preferences of participants along with their significance. Meeting newlineScheduling subsystem aids coordinator in solving this problem by proposing a meeting schedule which takes into consideration both, i.e. significance and preferences of various participants. This subsystem newlineuses fuzzy logic inferencing embedded in Fuzzy Inference agent to achieve the objective. newlineMeeting Facilitation subsystem involves aiding facilitator/coordinator in processing opinions and views of various participants in the meeting. This subsystem attempts to find the polarities of opinions on newlinevarious agenda points by participants. In order to achieve this objective, this subsystem uses the classification model implemented using machine learning algorithm of logistic regression. This model is newlinetrained with sixteen lakh labelled tuples. newlineAll the subsystems are tested separately first and then after integrating all of them into a single system on the web platform. Results were found as desired.
Pagination: ix, 165p.
URI: http://hdl.handle.net/10603/293513
Appears in Departments:Department of Computer Science and Application

Files in This Item:
File Description SizeFormat 
01_title_page.pdfAttached File34.8 kBAdobe PDFView/Open
02_certificate.pdf58.28 kBAdobe PDFView/Open
03_acknowledgement .pdf48.46 kBAdobe PDFView/Open
04_abstract.pdf159.58 kBAdobe PDFView/Open
05_list of figures.pdf68.01 kBAdobe PDFView/Open
06_list of tables.pdf67.79 kBAdobe PDFView/Open
07_abbreviations.pdf51.91 kBAdobe PDFView/Open
08_contents.pdf58.2 kBAdobe PDFView/Open
09_chapter1.pdf110.67 kBAdobe PDFView/Open
10_chapter2.pdf147.79 kBAdobe PDFView/Open
11_chapter3.pdf479.41 kBAdobe PDFView/Open
12_chapter4.pdf324.56 kBAdobe PDFView/Open
13_chapter5.pdf1.91 MBAdobe PDFView/Open
14_chapter6.pdf724.68 kBAdobe PDFView/Open
15_chapter7.pdf631.46 kBAdobe PDFView/Open
16_chapter8.pdf101.88 kBAdobe PDFView/Open
17_annexures.pdf338.76 kBAdobe PDFView/Open
19_bibliography.pdf97.59 kBAdobe PDFView/Open
21_student_approval_form.pdf165.64 kBAdobe PDFView/Open
80_recommendation.pdf101.88 kBAdobe PDFView/Open
Show full item record


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: