Jyotshna Dongardive
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jyotshna Dongardive has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Siby Abraham
Department of Maths & Stats, G. N. Khalsa College University of Mumbai India
3 shared publications - Pinky Panda
University of Mumbai
2 shared publications - Vishal Shaha
University of Mumbai
2 shared publications - Ankit Agarwal1 shared publication
Annie Rajan
DCT’s Dhempe College of Arts and Science
1 shared publication- Bikram Ghosh
Guru Nanak Khalsa College
1 shared publication
Latest Publications
- 2 August 2026
- Published by Springer Nature
- p. 157-169
MetaNodeNet: A Hybrid Knowledge Graph Embedding Model for Predicting Gene-Disease Associations in Multifactorial Disorders
- 2 August 2026
- Published by Springer Nature
- p. 157-169
MetaNodeNet: A Hybrid Knowledge Graph Embedding Model for Predicting Gene-Disease Associations in Multifactorial Disorders
- 2 August 2026
- Published by Springer Nature
- p. 57-71
A Multimodal Framework for Peak Player Performance
- Open Access
- 30 October 2025
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 18 (38) , 3124-3135
Leveraging Artificial Intelligence in Learning Management Systems: A Systematic Review of Applications and Impacts in Higher Education
Objectives: This review examines global research published between 2020 - 2024 on integrating artificial intelligence (AI) into Learning Management Systems (LMS) in higher education. It identifies dominant platforms and applications, evaluates methodological practices, and highlights unresolved challenges. Methods: Following the PRISMA guidelines, 44 peer-reviewed articles were retrieved from Scopus, Web of Science, and IEEE Xplore. Each study was coded according to platform, AI application, dataset, algorithm, feature selection, interpretability approach, and outcomes. Bibliometric mapping was performed using VOSviewer. Findings: Research activity increased sharply during the pandemic (2020-2022) and stabilised after 2023. Most contributions came from Saudi Arabia, India, and China, while Africa and Latin America were rarely represented. Moodle accounted for about one-quarter of the reviewed studies. Predictive analytics was the most frequent application, with models such as kNN, Random Forest (RF), and PCA showing strong performance. However, few studies employed explainable AI (XAI) methods such as SHAP and LIME appeared in less than 5% of studies and dataset dependence, particularly on OULAD, limited cross-institutional replication. Novelty: Unlike earlier descriptive reviews, this study provides the first cross-platform quantitative synthesis of AI-enabled LMS research. It benchmarks predictive accuracy across algorithms, identifies methodological bottlenecks, and highlights neglected areas, including dataset diversity, XAI, inclusivity, and pedagogical validation. Keywords: Artificial Intelligence, Learning Management Systems, Higher Education, Predictive Analytics, Explainable AI
- 30 October 2025
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 18 (38) , 3124-3135
Open AccessLeveraging Artificial Intelligence in Learning Management Systems: A Systematic Review of Applications and Impacts in Higher Education
Objectives: This review examines global research published between 2020 - 2024 on integrating artificial intelligence (AI) into Learning Management Systems (LMS) in higher education. It identifies dominant platforms and applications, evaluates methodological practices, and highlights unresolved challenges. Methods: Following the PRISMA guidelines, 44 peer-reviewed articles were retrieved from Scopus, Web of Science, and IEEE Xplore. Each study was coded according to platform, AI application, dataset, algorithm, feature selection, interpretability approach, and outcomes. Bibliometric mapping was performed using VOSviewer. Findings: Research activity increased sharply during the pandemic (2020-2022) and stabilised after 2023. Most contributions came from Saudi Arabia, India, and China, while Africa and Latin America were rarely represented. Moodle accounted for about one-quarter of the reviewed studies. Predictive analytics was the most frequent application, with models such as kNN, Random Forest (RF), and PCA showing strong performance. However, few studies employed explainable AI (XAI) methods such as SHAP and LIME appeared in less than 5% of studies and dataset dependence, particularly on OULAD, limited cross-institutional replication. Novelty: Unlike earlier descriptive reviews, this study provides the first cross-platform quantitative synthesis of AI-enabled LMS research. It benchmarks predictive accuracy across algorithms, identifies methodological bottlenecks, and highlights neglected areas, including dataset diversity, XAI, inclusivity, and pedagogical validation. Keywords: Artificial Intelligence, Learning Management Systems, Higher Education, Predictive Analytics, Explainable AI
- 1 October 2025
- Published by Springer Nature
- p. 271-285
Cricket Betting Through Machine Learning: Enhancing Decision-Making
- 1 October 2025
- Published by Springer Nature
- p. 271-285
Cricket Betting Through Machine Learning: Enhancing Decision-Making
- 30 July 2025
- Published by Springer Nature
- p. 353-364
Multiple Regression to Calculate Indian Premier League Player Auction Price Using Player Performance Attributes
- 30 July 2025
- Published by Springer Nature
- p. 353-364
Multiple Regression to Calculate Indian Premier League Player Auction Price Using Player Performance Attributes
- 4 May 2025
- Published by Springer Nature
- p. 277-288
Sign Language Interpreter Using Machine Learning Model for Mobile Devices
- 4 May 2025
- Published by Springer Nature
- p. 277-288
Sign Language Interpreter Using Machine Learning Model for Mobile Devices
- Open Access
- 29 April 2025
- Published by Perception Publishing in The Voice of Creative Research
- Vol. 7 (2) , 323-335
Music Creation Using a Hybrid Model of LLM And LSTM
Over the years music generation using artificial intelligence and deep learning have undergone lots of progress. There are platforms such as Magneta, MuseNet, Deep Back which incorporates deep learning and LSTM models in their architecture. Along with that platform such as music, riffusion, MIDI which incorporates LLM based learning methods. These models are useful, but there are very few researches which incorporate LLM and LSTM architecture for music generation and improve their individual limitations and combine their strengths. Hence, this will be the major highlight of the research. The LLM based models offer sequential structural richness and LSTM ensures temporal consistency. The approach will involve encoding MIDI sequences into English text format, allowing the LLM to process musical structures with natural language processing techniques. The output is then refined using an LSTM-based decoder to enhance the coherence of note transitions and rhythmic consistency. The hybrid model approaches to discover the potential of combining sequence modelling for improved AI driven music composition, which can make an interesting blend between creativity and machines.
- 29 April 2025
- Published by Perception Publishing in The Voice of Creative Research
- Vol. 7 (2) , 323-335
Open AccessMusic Creation Using a Hybrid Model of LLM And LSTM
Over the years music generation using artificial intelligence and deep learning have undergone lots of progress. There are platforms such as Magneta, MuseNet, Deep Back which incorporates deep learning and LSTM models in their architecture. Along with that platform such as music, riffusion, MIDI which incorporates LLM based learning methods. These models are useful, but there are very few researches which incorporate LLM and LSTM architecture for music generation and improve their individual limitations and combine their strengths. Hence, this will be the major highlight of the research. The LLM based models offer sequential structural richness and LSTM ensures temporal consistency. The approach will involve encoding MIDI sequences into English text format, allowing the LLM to process musical structures with natural language processing techniques. The output is then refined using an LSTM-based decoder to enhance the coherence of note transitions and rhythmic consistency. The hybrid model approaches to discover the potential of combining sequence modelling for improved AI driven music composition, which can make an interesting blend between creativity and machines.
- Open Access
Reaching Optimized Parameter Set, Protein Secondary Structure Prediction Using Neural Network
We propose an optimized parameter set for protein secondary structure prediction using three layer feed forward back propagation neural network. The methodology uses four parameters viz. encoding scheme, window size, number of neurons in the hidden layer and type of learning algorithm. The input layer of the network consists of neurons changing from 3 to 19, corresponding to different window sizes. The hidden layer chooses a natural number from 1 to 20 as the number of neurons. The output layer consists of three neurons, each corresponding to known secondary structural classes viz. alpha helix, beta strands and coils respectively. It also uses eight different learning algorithms and nine encoding schemes. Exhaustive experiments were performed using non-homologues dataset. The experimental results were compared using performance measures like Q3, sensitivity, specificity, Mathew correlation coefficient and accuracy. The paper also discusses the process of obtaining a stabilized cluster of 2530 records from a collection of 11340 records. The graphs of these stabilized clusters of records with respect to accuracy are concave, convergence is monotonic increasing and rate of convergence is uniform. The paper gives BLOSUM62 as the encoding scheme, 19 as the window size, 19 as the number of neurons in the hidden layer and One- Step Secant as the learning algorithm with the highest accuracy of 78%. These parameter values are proposed as the optimized parameter set for the three layer feed forward back propagation neural network for the protein secondary structure predictionv
Open AccessReaching Optimized Parameter Set, Protein Secondary Structure Prediction Using Neural Network
We propose an optimized parameter set for protein secondary structure prediction using three layer feed forward back propagation neural network. The methodology uses four parameters viz. encoding scheme, window size, number of neurons in the hidden layer and type of learning algorithm. The input layer of the network consists of neurons changing from 3 to 19, corresponding to different window sizes. The hidden layer chooses a natural number from 1 to 20 as the number of neurons. The output layer consists of three neurons, each corresponding to known secondary structural classes viz. alpha helix, beta strands and coils respectively. It also uses eight different learning algorithms and nine encoding schemes. Exhaustive experiments were performed using non-homologues dataset. The experimental results were compared using performance measures like Q3, sensitivity, specificity, Mathew correlation coefficient and accuracy. The paper also discusses the process of obtaining a stabilized cluster of 2530 records from a collection of 11340 records. The graphs of these stabilized clusters of records with respect to accuracy are concave, convergence is monotonic increasing and rate of convergence is uniform. The paper gives BLOSUM62 as the encoding scheme, 19 as the window size, 19 as the number of neurons in the hidden layer and One- Step Secant as the learning algorithm with the highest accuracy of 78%. These parameter values are proposed as the optimized parameter set for the three layer feed forward back propagation neural network for the protein secondary structure predictionv
- 12 January 2016
- Published by Springer Nature in Neural Computing and Applications
- Vol. 28 (8) , 1947-1974
Reaching optimized parameter set: protein secondary structure prediction using neural network
- 12 January 2016
- Published by Springer Nature in Neural Computing and Applications
- Vol. 28 (8) , 1947-1974
Reaching optimized parameter set: protein secondary structure prediction using neural network
- 10 December 2015
- Published by Springer Nature
- p. 163-171
Protein Sequence Classification Based on N-Gram and K-Nearest Neighbor Algorithm
- 10 December 2015
- Published by Springer Nature
- p. 163-171
Protein Sequence Classification Based on N-Gram and K-Nearest Neighbor Algorithm