Mayuri A. Mehta
Mayuri A. Mehta has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Ketan Kotecha
Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University), Pune, India
6 shared publications Devesh C. Jinwala
Department of Computer Engineering, S. V. National Institute of Technology, Surat, India
4 shared publications- Mitali Desai
Sarvajanik University
3 shared publications - Nakul R. Dave
Vishwakarma Government Engineering College
3 shared publications - Andreas Holzinger
Human-Centered AI Lab, Institute of Forest Engineering, Department of Ecosystem Management, Climate and Biodiversity, University of Natural Resources and Life Sciences (BOKU), Vienna, Austria
2 shared publications - Dheeraj Kumar Singh
Parul University
2 shared publications
Latest Publications
- Open Access
- 18 May 2026
- Published by Elsevier in SSRN Electronic Journal
Technology Acceptance Level (TAL): A Human-Centered Metric for Evaluating Trustworthy Artificial Intelligence in Agriculture
Artificial intelligence (AI) systems are increasingly proposed for agricultural decision support, precision farming and precision livestock farming (PLF), yet large-scale and durable adoption by practitioners remains the exception rather than the rule. Established maturity scales such as the Technology Readiness Level (TRL) capture the engineering progression of a technology from basic principles to operational deployment, but they are agnostic to whether end users actually rely on the resulting system in their daily work. This paper introduces the Technology Acceptance Level (TAL) as a complementary, human-centered metric for evaluating the usability, trustworthiness and operational uptake of AI in agriculture. TAL is defined as a nine-level ordinal scale, anchored in the Technology Acceptance Model and the European Union ethics guidelines for Trustworthy AI, that captures the trajectory from initial exposure of a system to a practitioner up to its stable, autonomous integration into routine decision-making. Each level is operationalised by a small set of measurable criteria spanning perceived usefulness, perceived ease of use, transparency, reliability under changing conditions, and alignment with agricultural workflows. We provide a mathematically grounded aggregation rule based on a non-compensatory, minimum-of-dimensions principle that prevents a single weak dimension from being masked by strong scores elsewhere, and we derive a confidence interval for TAL estimates from practitioner survey data. The framework is illustrated through three representative use cases—variable-rate nitrogen management in arable cropping, vision-based fruit detection for selective harvesting, and computer-vision-based lameness detection in dairy cattle—demonstrating how the same AI artefact can occupy very different acceptance levels across deployment contexts. By explicitly addressing the human-in-the-loop, TAL provides a practical instrument to diagnose adoption barriers, prioritise iterative system improvement, and steer the transition from technically functional prototypes to practically accepted, trustworthy AI in the agri-food sector.
- 18 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTechnology Acceptance Level (TAL): A Human-Centered Metric for Evaluating Trustworthy Artificial Intelligence in Agriculture
Artificial intelligence (AI) systems are increasingly proposed for agricultural decision support, precision farming and precision livestock farming (PLF), yet large-scale and durable adoption by practitioners remains the exception rather than the rule. Established maturity scales such as the Technology Readiness Level (TRL) capture the engineering progression of a technology from basic principles to operational deployment, but they are agnostic to whether end users actually rely on the resulting system in their daily work. This paper introduces the Technology Acceptance Level (TAL) as a complementary, human-centered metric for evaluating the usability, trustworthiness and operational uptake of AI in agriculture. TAL is defined as a nine-level ordinal scale, anchored in the Technology Acceptance Model and the European Union ethics guidelines for Trustworthy AI, that captures the trajectory from initial exposure of a system to a practitioner up to its stable, autonomous integration into routine decision-making. Each level is operationalised by a small set of measurable criteria spanning perceived usefulness, perceived ease of use, transparency, reliability under changing conditions, and alignment with agricultural workflows. We provide a mathematically grounded aggregation rule based on a non-compensatory, minimum-of-dimensions principle that prevents a single weak dimension from being masked by strong scores elsewhere, and we derive a confidence interval for TAL estimates from practitioner survey data. The framework is illustrated through three representative use cases—variable-rate nitrogen management in arable cropping, vision-based fruit detection for selective harvesting, and computer-vision-based lameness detection in dairy cattle—demonstrating how the same AI artefact can occupy very different acceptance levels across deployment contexts. By explicitly addressing the human-in-the-loop, TAL provides a practical instrument to diagnose adoption barriers, prioritise iterative system improvement, and steer the transition from technically functional prototypes to practically accepted, trustworthy AI in the agri-food sector.
- Open Access
- 1 January 2025
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 28, 454-467
Transformer-powered precision: A DETR-based approach for robust detection in medical ultrasound with cholelithiasis as a case study
Background and objective: Transformers have demonstrated strong capabilities in capturing long-range dependencies in visual data, but their application to noisy, low-contrast medical imaging such as ultrasound remains limited. Cholelithiasis detection, often hindered by the inherent limitations of ultrasound imaging, requires more precise and robust computational approaches. This study introduces a detection architecture that integrates convolutional feature extraction with a customized Detection Transformer (DETR) to improve localization and detection in challenging ultrasound conditions. Methods: The proposed method combines convolutional inductive biases with transformer-based self-attention to capture both local and global spatial relationships. It was applied to the task of detecting gallstones and gallbladder regions in ultrasound images of cholelithiasis. The approach was benchmarked against state-of-the-art object detection models, including RT-DETR, YOLOv8, and YOLO-NAS. Radiologists validated the bounding boxes generated by the model to assess clinical reliability. Results: The custom DETR achieved confidence score up to 99 % in detecting gallstones and gallbladder regions, outperforming RT-DETR, YOLOv8, and YOLO-NAS. The method demonstrated mean average precision improvements of 13 % and 14 % compared to YOLOv8 and YOLO-NAS, respectively. Radiologist validation confirmed the clinical accuracy and robustness of the proposed detection framework. Conclusions: By effectively addressing the challenges of low-quality ultrasound imaging, the proposed DETR-based framework provides a reliable and generalizable approach for automated cholelithiasis detection. The findings highlight its potential for integration into real-world diagnostic workflows and its applicability to broader intelligent diagnostic systems at the intersection of computational science, medical informatics, and vision transformers.
- 1 January 2025
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 28, 454-467
Open AccessTransformer-powered precision: A DETR-based approach for robust detection in medical ultrasound with cholelithiasis as a case study
Background and objective: Transformers have demonstrated strong capabilities in capturing long-range dependencies in visual data, but their application to noisy, low-contrast medical imaging such as ultrasound remains limited. Cholelithiasis detection, often hindered by the inherent limitations of ultrasound imaging, requires more precise and robust computational approaches. This study introduces a detection architecture that integrates convolutional feature extraction with a customized Detection Transformer (DETR) to improve localization and detection in challenging ultrasound conditions. Methods: The proposed method combines convolutional inductive biases with transformer-based self-attention to capture both local and global spatial relationships. It was applied to the task of detecting gallstones and gallbladder regions in ultrasound images of cholelithiasis. The approach was benchmarked against state-of-the-art object detection models, including RT-DETR, YOLOv8, and YOLO-NAS. Radiologists validated the bounding boxes generated by the model to assess clinical reliability. Results: The custom DETR achieved confidence score up to 99 % in detecting gallstones and gallbladder regions, outperforming RT-DETR, YOLOv8, and YOLO-NAS. The method demonstrated mean average precision improvements of 13 % and 14 % compared to YOLOv8 and YOLO-NAS, respectively. Radiologist validation confirmed the clinical accuracy and robustness of the proposed detection framework. Conclusions: By effectively addressing the challenges of low-quality ultrasound imaging, the proposed DETR-based framework provides a reliable and generalizable approach for automated cholelithiasis detection. The findings highlight its potential for integration into real-world diagnostic workflows and its applicability to broader intelligent diagnostic systems at the intersection of computational science, medical informatics, and vision transformers.
- Open Access
- 19 December 2024
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 17 (1) , 1-21
Effective Stemmers Using Trie Data Structure for Enhanced Processing of Gujarati Text
- 19 December 2024
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 17 (1) , 1-21
Open AccessEffective Stemmers Using Trie Data Structure for Enhanced Processing of Gujarati Text
- 12 December 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (5) , 3265-3286
White blood cell segmentation using U-Net and its variants to improve leukemia diagnosis
- 12 December 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (5) , 3265-3286
White blood cell segmentation using U-Net and its variants to improve leukemia diagnosis
- 5 May 2024
- Published by Springer Nature
- p. 1-28
Digital Transformation of Public Services: Introduction, Current Trends and Future Directions
- 5 May 2024
- Published by Springer Nature
- p. 1-28
Digital Transformation of Public Services: Introduction, Current Trends and Future Directions
- Open Access
- 15 January 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 23 (1) , 1-51
A Systematic Review of Stemmers of Indian and Non-Indian Vernacular Languages
The stemming process is crucial and significant in the pre-processing step of natural language processing. The stemmer oversees the stemming process. It facilitates the extraction of morphological variants of a root or base word from the provided word. Over the period, several stemmers for various vernacular languages have been proposed. However, very few research studies have comprehensively investigated these available stemmers. This article makes multifold contributions. First, we discuss the various stemmers of 15 Indian and 17 non-Indian languages describing their key points, benefits, and drawbacks. All the Indian languages for which stemmers have been built are covered in this study. For the non-Indian languages, stemmers of commonly spoken languages have been covered. Second, we present a language-wise comparative analysis of stemmers based on our identified parameters. Third, we discuss the wordnets and dictionaries available for different languages. Fourth, we provide details of the datasets available for various languages. Fifth, we also provide challenges in existing stemmers and future directions for future researchers. The study presented in this article reveals that significant research has been carried out for the stemmers of influential languages such as English, Arabic, and Urdu. On the other hand, languages with d resources, such as Farsi, Polish, Odia, Amharic, and others, have received the least attention for research. Moreover, rigorous analysis reveals that most of the stemmers suffer from over-stemming errors. With a complete catalogue of available stemmers, this study aims at assisting the researchers and professionals working in the areas such as information retrieval, semantic annotation, word meaning disambiguation, and ontology learning.
- 15 January 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 23 (1) , 1-51
Open AccessA Systematic Review of Stemmers of Indian and Non-Indian Vernacular Languages
The stemming process is crucial and significant in the pre-processing step of natural language processing. The stemmer oversees the stemming process. It facilitates the extraction of morphological variants of a root or base word from the provided word. Over the period, several stemmers for various vernacular languages have been proposed. However, very few research studies have comprehensively investigated these available stemmers. This article makes multifold contributions. First, we discuss the various stemmers of 15 Indian and 17 non-Indian languages describing their key points, benefits, and drawbacks. All the Indian languages for which stemmers have been built are covered in this study. For the non-Indian languages, stemmers of commonly spoken languages have been covered. Second, we present a language-wise comparative analysis of stemmers based on our identified parameters. Third, we discuss the wordnets and dictionaries available for different languages. Fourth, we provide details of the datasets available for various languages. Fifth, we also provide challenges in existing stemmers and future directions for future researchers. The study presented in this article reveals that significant research has been carried out for the stemmers of influential languages such as English, Arabic, and Urdu. On the other hand, languages with d resources, such as Farsi, Polish, Odia, Amharic, and others, have received the least attention for research. Moreover, rigorous analysis reveals that most of the stemmers suffer from over-stemming errors. With a complete catalogue of available stemmers, this study aims at assisting the researchers and professionals working in the areas such as information retrieval, semantic annotation, word meaning disambiguation, and ontology learning.
- 7 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (18) , 54699-54727
Empirical evaluation of filter pruning methods for acceleration of convolutional neural network
- 7 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (18) , 54699-54727
Empirical evaluation of filter pruning methods for acceleration of convolutional neural network
- Open Access
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 140348-140381
Deep Learning-Based Dermatological Condition Detection: A Systematic Review With Recent Methods, Datasets, Challenges, and Future Directions
Dermatological conditions are a global health concern affecting all age groups. They encompass various skin issues such as rashes, moles, acne, blisters, hives, nodules, cysts, macules, and papules. Early diagnosis of dermatological conditions is crucial to prevent skin damage and chronic diseases. Recent advancements in artificial intelligence and medical image processing, particularly through deep learning, have significantly improved the precision and efficiency of dermatological disease detection by dermatologists. This paper thoroughly examines deep learning-based methods for detecting dermatological conditions from dermoscopic images. Specifically, it presents study of 22 methods that are used to detect dermatological conditions such as basal cell carcinoma, melanocytic nevus, seborrheic keratosis, psoriasis, benign keratosis, melanoma, acne, cold sore, warts, eczema, hives, shingles, scar, skin tag, inflammatory hyper pigment, cyst, dark circle, blackhead, burn and skin rash. It also covers clinical diagnostic methods for dermatological conditions, and the need for computer-aided diagnosis. In this paper, we have also proposed the categorization of deep learning-based dermatological condition detection methods. Moreover, the comprehensive summary of these methods is presented. In addition, this paper summarizes the majority of the datasets available for computer-aided detection of dermatological conditions. Furthermore, it presents enormous challenges and potential future research directions. This survey informs researchers about the latest advancements in deep learning-based detection methods for dermatological conditions and allows dermatologists to stay updated on technological breakthroughs in this area.
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 140348-140381
Open AccessDeep Learning-Based Dermatological Condition Detection: A Systematic Review With Recent Methods, Datasets, Challenges, and Future Directions
Dermatological conditions are a global health concern affecting all age groups. They encompass various skin issues such as rashes, moles, acne, blisters, hives, nodules, cysts, macules, and papules. Early diagnosis of dermatological conditions is crucial to prevent skin damage and chronic diseases. Recent advancements in artificial intelligence and medical image processing, particularly through deep learning, have significantly improved the precision and efficiency of dermatological disease detection by dermatologists. This paper thoroughly examines deep learning-based methods for detecting dermatological conditions from dermoscopic images. Specifically, it presents study of 22 methods that are used to detect dermatological conditions such as basal cell carcinoma, melanocytic nevus, seborrheic keratosis, psoriasis, benign keratosis, melanoma, acne, cold sore, warts, eczema, hives, shingles, scar, skin tag, inflammatory hyper pigment, cyst, dark circle, blackhead, burn and skin rash. It also covers clinical diagnostic methods for dermatological conditions, and the need for computer-aided diagnosis. In this paper, we have also proposed the categorization of deep learning-based dermatological condition detection methods. Moreover, the comprehensive summary of these methods is presented. In addition, this paper summarizes the majority of the datasets available for computer-aided detection of dermatological conditions. Furthermore, it presents enormous challenges and potential future research directions. This survey informs researchers about the latest advancements in deep learning-based detection methods for dermatological conditions and allows dermatologists to stay updated on technological breakthroughs in this area.
- 14 November 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (17) , 52275-52303
Analytics of deep model-based spatiotemporal and spatial feature learning methods for surgical action classification
- 14 November 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (17) , 52275-52303
Analytics of deep model-based spatiotemporal and spatial feature learning methods for surgical action classification
- 20 October 2022
- Published by Springer Nature
- p. 43-59
An Overview of Explainable AI Methods, Forms and Frameworks
- 20 October 2022
- Published by Springer Nature
- p. 43-59
An Overview of Explainable AI Methods, Forms and Frameworks