images
  ISSN 2583-2913
Latest Updates
  • Articles are invited for the first issue of Indian Journal of Science and Research.
  • Join Indian Journal of Science and Research as reviewer, editorial board member.
  • Congratulations!!! To all the members for Joining editorial board of Indian Journal of Science and Research.
Why Publish With Us
Fast reviewing process: Adopting the fast reviewing process we communicate with authors at all stages till publication. Proactive teams of reviewers from National and International front help us to complete the process within the time.
IJSR dose not impose any publication fee or processing charges.
Article In Press
Title: INVESTIGATING HOW CHATGPT CAN IMPROVE LEARNING OUTCOMES FOR IT STUDENTS, COMPARING TRADITIONAL STUDY METHODS WITH AI-ASSISTED LEARNING TOOLS
Author: April Thet Su and Hlaing Htake Khaung Tin*
Keyword: ChatGPT, IT students, Traditional study methods, AI-assisted, Learning Tools
Page No: 01-09
DOI: https://doi.org/10.5281/zenodo.17165029
Abstract: Abstract: This research examines the potential of ChatGPT as an AI-facilitated learning instrument for the purpose of improving learning outcomes among IT students and comparing it with conventional s tudy techniques. As artificial intelligence becomes more a part of learning, there is need to address how such resources can be used to enhance and facilitate the learning of students. We apply mixed methods using quantitative academic performance measures and qualitative student surveys measures to assess the impact of ChatGPT on key factors of learning including understanding, retention, and engagement. The findings show that the students utilizing ChatGPT possess much greater mastery of sophisticated IT concepts as well as increased levels of motivation compared to students who utilize traditional study methods. The present study achieves the pedagogically transformative potential of AI-based learning technologies in higher education. The research provides pedagogical implications for the way the AI should best be incorporated into the curriculum towards achieving the development of a more effective and interactive learning environment for IT students. Keywords: ChatGPT, IT students, Traditional study methods, AI-assisted, Learning Tools Download PDF


Title: A COMPARATIVE STUDY OF AI MODELS FOR SAW WELD QUALITY ASSESSMENT WITH AN IOT-BASED HYBRID MONITORING SYSTEM
Author: Mirza Farhatulla Baig* and Prof. Dharmendra Dubey
Keyword: Submerged Arc Welding, Statistical Modelling, Convolutional Neural Networks, Hybrid AI System, IoT Sensors
Page No: 10-19
DOI: https://doi.org/10.5281/zenodo.17181767
Abstract: In this paper we provide a direct comparison of weld quality assessment methods using statistical (engineering) modeling and deep learning. Deep learning was demonstrated using Convolutional Neural Ne tworks (CNNs) for Submerged Arc Welding (SAW) welding, using statistical modeling with additional engineered features pertaining to precision, counts of defects, area ratio, and the interpretation and modelling with fairly consistent performance classification metrics from weighing each feature as it related to weld quality. While CNNs had a visual experience of more complex defects, approached automated feature extraction, and object detection with fairly good results, the difficult pathway for us was to generalize; in essence construct a model that was fairly good but continued to generalize with all the historical datasets available. The hybrid AI model represented a statistical model with an automated CNN model; and offered a more accurate, robust, and flexible model fit as it could account for some of the dynamic nature of an industrial context. The use of IoT based sensing helped facilitate being dynamic regarding assessment and predictive maintenance. Collectively our hybrid presents a foundation for smart, autonomous systems for weld inspection acknowledging Industry 4.0 standards.Download PDF