Jinsi Jose
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jinsi Jose has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Angelo Baby
Christ University, Bangalore, Rajagiri College of Social Sciences
2 shared publications - Akshay Raj
Smater Codes
1 shared publication - Amrutha Kallingal
Department of Computer Science, CHRIST University, Bangalore 560029, India
1 shared publication - C. Smera
CHRIST (Deemed to be University)
1 shared publication - Deepa V. Jose
Christ University
1 shared publication - Deepa V. Jose
Christ University
1 shared publication
Latest Publications
- Open Access
- 11 November 2025
- Published by Brazilian Journals in Veredas do Direito
- Vol. 22 (4) , e223612
REDUNDANCY REDUCTION AND SENTENCE PRIORITISATION OF THE STUDENT LECTURE NOTES USING SOFT COSINE IMPLEMENTED MMR ALGORITHM
In the realm of education, the efficacy of lecture notes in aiding student learning is pivotal. This study explores the integration of the Soft cosine measure (SCM) with the Maximal marginal relevance (MMR) algorithm to reduce redundancy and prioritize essential sentences in student lecture notes. Traditional cosine similarity often overlooks the semantic similarity between terms with different surface forms, leading to suboptimal redundancy reduction. The Soft Cosine Measure addresses this by accounting for word similarity based on semantic relationships, improving sentence relevance and uniqueness assessment. In our approach, SCM is employed within the MMR framework to iteratively select sentences that maximize relevance to the main lecture content while minimizing redundancy with previously selected sentences. This hybrid method ensures that the final summary encompasses a broader range of key concepts and topics discussed during lectures, providing a more comprehensive and coherent overview. Experimental evaluations on a dataset of lecture notes demonstrate that the SCM-implemented MMR algorithm significantly outperforms traditional summarization techniques in both reducing redundancy and maintaining the informativeness of summaries. The Soft Cosine Implemented MMR Algorithm (SCIMMR) gives the ROUGE values between 0.821 to 0.901. This novel approach offers a robust solution for the automatic summarization of lecture notes, aiding students in efficiently reviewing and studying educational materials.
- 11 November 2025
- Published by Brazilian Journals in Veredas do Direito
- Vol. 22 (4) , e223612
Open AccessREDUNDANCY REDUCTION AND SENTENCE PRIORITISATION OF THE STUDENT LECTURE NOTES USING SOFT COSINE IMPLEMENTED MMR ALGORITHM
In the realm of education, the efficacy of lecture notes in aiding student learning is pivotal. This study explores the integration of the Soft cosine measure (SCM) with the Maximal marginal relevance (MMR) algorithm to reduce redundancy and prioritize essential sentences in student lecture notes. Traditional cosine similarity often overlooks the semantic similarity between terms with different surface forms, leading to suboptimal redundancy reduction. The Soft Cosine Measure addresses this by accounting for word similarity based on semantic relationships, improving sentence relevance and uniqueness assessment. In our approach, SCM is employed within the MMR framework to iteratively select sentences that maximize relevance to the main lecture content while minimizing redundancy with previously selected sentences. This hybrid method ensures that the final summary encompasses a broader range of key concepts and topics discussed during lectures, providing a more comprehensive and coherent overview. Experimental evaluations on a dataset of lecture notes demonstrate that the SCM-implemented MMR algorithm significantly outperforms traditional summarization techniques in both reducing redundancy and maintaining the informativeness of summaries. The Soft Cosine Implemented MMR Algorithm (SCIMMR) gives the ROUGE values between 0.821 to 0.901. This novel approach offers a robust solution for the automatic summarization of lecture notes, aiding students in efficiently reviewing and studying educational materials.
- 1 August 2023
- Published by Springer Nature
- p. 81-89
Machine Learning Algorithms for Prediction of Mobile Phone Prices
- 1 August 2023
- Published by Springer Nature
- p. 81-89
Machine Learning Algorithms for Prediction of Mobile Phone Prices
- 17 February 2023
- Published by Springer Nature
- p. 611-627
Psychosomatic Study of Criminal Inclinations with Profanity on Social Media: Twitter
- 17 February 2023
- Published by Springer Nature
- p. 611-627
Psychosomatic Study of Criminal Inclinations with Profanity on Social Media: Twitter
- Open Access
- 1 February 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (1) , 1134-1141
Deep learning algorithms for intrusion detection systems in internet of things using CIC-IDS 2017 dataset
Due to technological advancements in recent years, the availability and usage of smart electronic gadgets have drastically increased. Adoption of these smart devices for a variety of applications in our day-to-day life has become a new normal. As these devices collect and store data, which is of prime importance, securing is a mandatory requirement by being vigilant against intruders. Many traditional techniques are prevailing for the same, but they may not be a good solution for the devices with resource constraints. The impact of artificial intelligence is not negligible in this concern. This study is an attempt to understand and analyze the performance of deep learning algorithms in intrusion detection. A comparative analysis of the performance of deep neural network, convolutional neural network, and long short-term memory using the CIC-IDS 2017 dataset.
- 1 February 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (1) , 1134-1141
Open AccessDeep learning algorithms for intrusion detection systems in internet of things using CIC-IDS 2017 dataset
Due to technological advancements in recent years, the availability and usage of smart electronic gadgets have drastically increased. Adoption of these smart devices for a variety of applications in our day-to-day life has become a new normal. As these devices collect and store data, which is of prime importance, securing is a mandatory requirement by being vigilant against intruders. Many traditional techniques are prevailing for the same, but they may not be a good solution for the devices with resource constraints. The impact of artificial intelligence is not negligible in this concern. This study is an attempt to understand and analyze the performance of deep learning algorithms in intrusion detection. A comparative analysis of the performance of deep neural network, convolutional neural network, and long short-term memory using the CIC-IDS 2017 dataset.
- 6 December 2021
- Published by Springer Nature
- p. 727-741
On Combinatorial Handoff Strategies for Spectrum Mobility in Ad Hoc Networks: A Comparative Review
- 6 December 2021
- Published by Springer Nature
- p. 727-741
On Combinatorial Handoff Strategies for Spectrum Mobility in Ad Hoc Networks: A Comparative Review
- Open Access
- 1 April 2017
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 10 (13) , 1-5
Performance Analysis of Gamification Over the Traditional Classroom in Education
Gamification is widely used in various areas such as education, business and health. The main objective or focus of this paper is to presents Gamification as the better way to teach students over the traditional classrooms. To achieve this goal we have created a history based game, targeting undergraduate students who learn this content as part of their syllabus. At each level the details of student's performance are stored and analyzed. On the other hand, give the same contents to the students through the traditional classrooms. To evaluate the performance we conducted a pre and posttest. The result showed 75% increment in student's performance.
- 1 April 2017
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 10 (13) , 1-5
Open AccessPerformance Analysis of Gamification Over the Traditional Classroom in Education
Gamification is widely used in various areas such as education, business and health. The main objective or focus of this paper is to presents Gamification as the better way to teach students over the traditional classrooms. To achieve this goal we have created a history based game, targeting undergraduate students who learn this content as part of their syllabus. At each level the details of student's performance are stored and analyzed. On the other hand, give the same contents to the students through the traditional classrooms. To evaluate the performance we conducted a pre and posttest. The result showed 75% increment in student's performance.