Kaustubh Rajendra Kulkarni
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
Kaustubh Rajendra Kulkarni has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Pradnya Patil
Department of Computer Engineering, K J Somaiya Institute of Technology, Mumbai, India
2 shared publications - Priyanka Sharma
Computer Science and Engineering, Swami Keshvanand Institute of Technology, Management and Gramothan, Jaipur, Rajasthan, India
2 shared publications - Ahmad Reza Naghsh-Nilchi
Department of Artificial Intelligence, Faculty of Computer Engineering, University of Isfahan, Isfahan, Iran
1 shared publication - Cagri Ozcinar
MSK.AI, London, U.K.
1 shared publication - Egils Avots
CV Lab, University of Tartu, Tartu, Estonia
1 shared publication Golamreza Anbarjafari
CV Lab, University of Tartu, Estonia
1 shared publication
Latest Publications
- Open Access
- 15 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Social Media Analytics for Monsoon Trends in India: A Multi- Platform NLP Approach
- 15 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessSocial Media Analytics for Monsoon Trends in India: A Multi- Platform NLP Approach
- Open Access
- 15 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Transfer Learning for Agricultural Disease Recognition: Performance Evaluation of Modern CNN Architectures
Agricultural productivity faces significant challenges from plant diseases, particularly in resource-constrained environments where traditional diagnostic methods are inadequate. This study evaluates the effectiveness of modern convolutional neural network (CNN) architectures for automated plant disease identification through transfer learning methodologies. We systematically compare five distinct approaches: a custom-designed CNN alongside four pre-trained models (EfficientNetB0, ResNet101, InceptionV3, and MobileNetV2) using a comprehensive dataset of over 130,000 plant images. Interestingly, EfficientNetB0 achieves superior performance with 97.10% validation accuracy, while our custom CNN architecture attains competitive results at 95.76% accuracy. The findings indicate that transfer learning approaches significantly enhance model performance while reducing computational requirements, making them particularly suitable for deployment in agricultural settings with limited technological infrastructure. This research contributes to the growing body of knowledge on AI-driven agricultural solutions and provides practical insights for implementing scalable disease detection systems.
- 15 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessTransfer Learning for Agricultural Disease Recognition: Performance Evaluation of Modern CNN Architectures
Agricultural productivity faces significant challenges from plant diseases, particularly in resource-constrained environments where traditional diagnostic methods are inadequate. This study evaluates the effectiveness of modern convolutional neural network (CNN) architectures for automated plant disease identification through transfer learning methodologies. We systematically compare five distinct approaches: a custom-designed CNN alongside four pre-trained models (EfficientNetB0, ResNet101, InceptionV3, and MobileNetV2) using a comprehensive dataset of over 130,000 plant images. Interestingly, EfficientNetB0 achieves superior performance with 97.10% validation accuracy, while our custom CNN architecture attains competitive results at 95.76% accuracy. The findings indicate that transfer learning approaches significantly enhance model performance while reducing computational requirements, making them particularly suitable for deployment in agricultural settings with limited technological infrastructure. This research contributes to the growing body of knowledge on AI-driven agricultural solutions and provides practical insights for implementing scalable disease detection systems.
- 28 May 2024
- Published by IGI Global Scientific Publishing
- p. 56-74
Algorithmic Issues, Challenges, and Theoretical Concerns of ChatGPT
Large language model (LLM) ChatGPT has made tremendous progress in natural language processing (NLP), especially in human-quality text production, multilingual translation, and content creation. However, because of its extensive use, algorithmic issues, challenges, and theoretical queries come up. Fairness, bias, explainability, generalization, originality, inventiveness, and safety are the main topics of this study's examination of ChatGPT's intricate theoretical and algorithmic components. It looks into the possibility of explainability, transferability, generalization, bias in the data, and the model's capacity to provide original and imaginative content. It also covers possible issues including harmful use, disseminating incorrect information, and offensive or misleading content. These limitations can be addressed so that ChatGPT can be improved to provide LLMs that are more dependable, accountable, and long-lasting while posing no needless risks.
- 28 May 2024
- Published by IGI Global Scientific Publishing
- p. 56-74
Algorithmic Issues, Challenges, and Theoretical Concerns of ChatGPT
Large language model (LLM) ChatGPT has made tremendous progress in natural language processing (NLP), especially in human-quality text production, multilingual translation, and content creation. However, because of its extensive use, algorithmic issues, challenges, and theoretical queries come up. Fairness, bias, explainability, generalization, originality, inventiveness, and safety are the main topics of this study's examination of ChatGPT's intricate theoretical and algorithmic components. It looks into the possibility of explainability, transferability, generalization, bias in the data, and the model's capacity to provide original and imaginative content. It also covers possible issues including harmful use, disseminating incorrect information, and offensive or misleading content. These limitations can be addressed so that ChatGPT can be improved to provide LLMs that are more dependable, accountable, and long-lasting while posing no needless risks.
- Open Access
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 621-628
Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification
Facial dynamics can be considered as unique signatures for discrimination between people. These have started to become important topic since many devices have the possibility of unlocking using face recognition or verification. In this work, we evaluate the efficacy of the transition frames of video in emotion as compared to the peak emotion frames for identification. For experiments with transition frames we extract features from each frame of the video from a fine-tuned VGG-Face Convolutional Neural Network (CNN) and geometric features from facial landmark points. To model the temporal context of the transition frames we train a Long-Short Term Memory (LSTM) on the geometric and the CNN features. Furthermore, we employ two fusion strategies: first, an early fusion, in which the geometric and the CNN features are stacked and fed to the LSTM. Second, a late fusion, in which the prediction of the LSTMs, trained independently on the two features, are stacked and used with a Support Vector Machine (SVM). Experimental results show that the late fusion strategy gives the best results and the transition frames give better identification results as compared to the peak emotion frames.
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 621-628
Open AccessChanges in Facial Expression as Biometric: A Database and Benchmarks of Identification
Facial dynamics can be considered as unique signatures for discrimination between people. These have started to become important topic since many devices have the possibility of unlocking using face recognition or verification. In this work, we evaluate the efficacy of the transition frames of video in emotion as compared to the peak emotion frames for identification. For experiments with transition frames we extract features from each frame of the video from a fine-tuned VGG-Face Convolutional Neural Network (CNN) and geometric features from facial landmark points. To model the temporal context of the transition frames we train a Long-Short Term Memory (LSTM) on the geometric and the CNN features. Furthermore, we employ two fusion strategies: first, an early fusion, in which the geometric and the CNN features are stacked and fed to the LSTM. Second, a late fusion, in which the prediction of the LSTMs, trained independently on the two features, are stacked and used with a Support Vector Machine (SVM). Experimental results show that the late fusion strategy gives the best results and the transition frames give better identification results as compared to the peak emotion frames.