Experienced Associate Professor with a demonstrated history of working in the Technical education industry. Skilled in Research, E-Learning, Lecturing, Teaching, and Higher Education. Strong education professional with a Doctor of Philosophy ( focused on Natural Language Processing from Manipal University Jaipur. Working as Associate Professor at the School of Information Technology, Manipal University Jaipur, India.
EDUCATION
Awarded PhD in 2018 Specialization in Natural Language Processing
RESEARCH INTERESTS
Natural Language Processing, Digital Image Processing, Computer vision, AI and soft computing
74
Scopus Publications
622
Scholar Citations
15
Scholar h-index
17
Scholar i10-index
Scopus Publications
Transformer augmented hybrid deep learning for explainable multi class pest classification Vivek Kumar Verma, Ashish Kumar, Varda Pareek, Yogesh Kumar Scientific Reports, 2026 Agricultural pests continue to impose serious threats to global food security by causing major yield losses across diverse cropping systems, making early and accurate identification vital for effective pest management. With the growing integration of digital technologies in modern agriculture, deep-learning-based pest recognition has become a promising approach to surpass the limitations of manual scouting and conventional monitoring practices. This work presents a comprehensive experimental evaluation of multiple deep-learning architectures for multi-class pest classification via image-level classification covering 19 pest species. The study investigates classical CNNs (MobileNetV2, VGG16), compound-scaled models (EfficientNetB0/B3, EfficientNetV2-B0), residual architectures (ResNet50), automated NAS models (Xception, NASNetLarge), and novel hybrid CNN-Transformer designs including Hybrid InceptionResNetV2, Hybrid ResNet50 + CBAM, Hybrid EffNet-Transformer, and Hybrid EfficientNetV2-S + Transformer. To enhance foreground isolation and reduce background complexity in field images, segmentation-driven preprocessing is employed using GrabCut, Watershed, SLIC, and Felzenszwalb, generating structure-refined image representations for downstream classification. Results show that attention-augmented hybrid models consistently outperform standalone CNNs, with the Hybrid EfficientNetV2-S + Transformer achieving the highest performance with 0.8800 validation accuracy, 0.849 macro-F1, and 0.4560 validation loss. These findings highlight the effectiveness of combining convolutional feature hierarchies with global self-attention for reliable multi-species pest classification and offer meaningful guidance for developing intelligent precision agriculture systems.
Comprehensive analysis of gender recognition performance using MobileNet and vision transformer with Grad-CAM and LIME Bhavna Saini, Vivek Kumar Verma, Ch. Karthikeya Varma, D. Sinega Discover Artificial Intelligence, 2026 Gender recognition is a significant subfield in artificial intelligence and can be used in many applications, for example: security systems, suggestions, and biometric identification. This work evaluates the performance of MobileNet and ViT architectures for gender classification using real world and synthetic datasets. From the experimental results, we find that the overall performance of MobileNet is outstanding in real-life applications with the highest accuracy, recall, and F1 score due to feature extraction with its lightweight architecture. On the other hand, ViT is powerful, but it needs a lot of training data to fine-tune its performance. Various Explainable AI (XAI) techniques, including Grad CAM and LIME, were utilized to improve model interpretability by shedding light on the rationale behind the decision-making process and highlighting the most salient features that contribute to the classification process. These results indicate that MobileNet is suitable for real-time applications, while ViT shows potential for optimization through fine tuning and additional data. Future studies should also investigate hybrid models, strategies for mitigating bias, and improved explainability for fairness and reliability in gender classification systems.
Super-resolution generative network for enhanced Parkinson’s disease diagnosis using brain magnetic resonance imaging Bali Devi, Sumit Srivastava, Vivek Kumar Verma Engineering Research Express, 2026 One hallmark of PD is the degeneration of dopamine-producing neurons in substantia nigra of the brain, and resulting in motor impairments, such as tremor or rigidity. It has been difficult to make an early and accurate diagnosis because of overlapping symptoms with other neurological diseases and limitations in conventional diagnostic tools. In order to tackle the challenges in PD, we propose a new hybrid architecture of SRGAN and SCO. Unlike previous approach for Alzheimer’s our method enhances low-resolution MRI and PET images presenting higher diagnostic potential. The approach could be carried out in clinics with limited screening capability. Super-Resolution GAN (SRGAN) An SRGAN was constructed which used a customised variation of DeepResNet (i.e. ResNet-150 with skip connections), the Generative Adversarial Network (GAN) and the Gaussian filter to enhance the quality of the MRI and PET images. Various operations were performed on the input images as pre-processing, such as, contrast stretching, noise filtering, gamma correction and pixel-normalization to clear input for the model. Our SRGAN model was better performing than the existing CNN models like DenseNet, AlexNet, VGG19 and ResNet with an accuracy of 96.5%, F1 score of 94.5% and balanced accuracy (BAAC) of 93.5%. Moreover, the skip connection optimization (SCO) of the SRGAN improved over various optimization methods such as GA, ACO, GWO, SGD, ADAM and AdaMax. The results demonstrate that the proposed model outperforms existing methods for the prediction of Parkinson’s disease.
Talk to Me, Like Me: Modular Personalization of Emotional AI via Behavioral Metadata, Fine-Tuning, RAG, Prompts, and Agentic Reasoning Rishik Gupta, Om Dabral, Prakhar Shukla, Vivek Kumar Verma, Hardik Sharma, Sanyam Kathed, Hith Rahil Nidhan, Bagesh Kumar Cogmaec 2025 Proceedings of the 1st International Workshop on Cognition Oriented Multimodal Affective and Empathetic Computing Co Located with mm 2025, 2025 We present a framework for emotionally personalized conversational agents that interpret linguistic content and behavioral cues—tone, latency, and non-verbal signals—in speech. From unscripted interviews with 40 participants, we annotate utterances for six universal emotions (joy, sadness, fear, anger, surprise, disgust) and enrich them with metadata (e.g., hesitation, laughter, response latency). We test four strategies: LoRA fine-tuning of LLaMA-3 8B, Retrieval-Augmented Generation (RAG) with emotion-aware retrieval, prompt-based emotion conditioning, and agentic reasoning, each in metadata-enriched and text-only modes. Metadata boosts Pearson correlation by 5–12% and cuts MSE by up to 30%. LoRA with metadata achieves the highest alignment (r = 0.868, MSE= 0.0073), while prompt engineering offers an efficient trade-off (r= 0.765,MSE= 0.015). RAG and agentic reasoning improve long-dialogue coherence. We compare computational cost, environmental impact, and interpretability, showing how modular personalization enables empathetic AI without retraining large models.
Adaptive security reinforcement learning for enhanced cryptographic vehicle-to-vehicle communication security Ankit Mundra, Pankaj Vyas, Vivek Kumar Verma Journal of Discrete Mathematical Sciences and Cryptography, 2025 Secure and reliable Vehicle-to-Vehicle (V2V) communications are critical in the age of connected vehicles and intelligent transport systems. This paper introduces a new technique, Adaptive Security Reinforcement Learning (ASRL), which aims at adjusting and learning cryptographic techniques according to effective on-the-fly information about vehicles. Marine security settings can be automatically adjusted via ASRL by using reinforcement learning to optimize set security settings, such as Elapsed Time, Speed, RPM, Acceleration, Engine Load, Fuel Level and Temperature, given changing conditions. The purpose of this adaptive approach is to keep safety and efficiency in balance, so that the overall security of vehicular communication can be improved without reducing operational performance. The solution involves multivariate polynomial lattices (MPL) for strong cryptographic underpinnings, quantum resilient cryptography for secure models against yet-to-become quantum-based threats, and discretized mathematical implies for optimized algorithms. The system also uses state-of-the art techniques to withstand algebraic and combinatorial attacks, including the use of designs and Boolean functions. The paper presents the conceptual framework of ASRL, by defining state space, action space and reward function in the idealized scenario and describing learning algorithm in detail, together with simulations to illustrate its effectiveness. Through this holistic treatment, we provide a working solution to evolving security threats in V2V communications, and hence we enable safer and more resilient vehicular networks.
Decentralized and Lightweight Transformer-Based Framework for Cybersecurity in Vehicular Networks Department of Information Technology, Manipal University Jaipur, Jaipur, Rajasthan, 302022, India, Ankit Mundra, Pankaj Vyas, Department of Information Technology, Manipal University Jaipur, Jaipur, Rajasthan, 302022, India, Vivek Kumar Verma, Department of Information Technology, Manipal University Jaipur, Jaipur, Rajasthan, 302022, India Engineered Science, 2025 The seamless incorporation of communication and computer control systems in today's vehicles has increased the capability but created serious security risks. In this work, we propose a decentralized and lightweight transformer-based intrusion detection system (IDS) for automotive cybersecurity to address the above issues in a scalable and flexible fashion. By utilizing the car hacking dataset (CHD), the proposed approach not only introduces advanced feature engineering by considering temporal features like time differences and message frequency, as well as payload entropy, to efficiently represent vehicular communication patterns, but also considers structural information within the vehicular network. Uses a transformer model for sequence-to-sequence (Seq2Seq) for processing controller area network (CAN) bus data; thus, sophisticated anomalies such as denial of service (DoS), fuzzy, and spoofing attacks can be accurately detected. These attention mechanisms and positional encoding in the model improve the capability of learning the sequence dependencies and context interdependence in vehicular data. Evaluation results showed that the framework has a high precision (96.7%), recall (95.3%) and attack detection rate (ADR, 97.5%), and low false alarm rate (FAR, 3.4%), with a real-time detection capability at average time to detect (ATD) of 22 milliseconds. These results confirm that the IDS is a trusted, effective, and cost-effective technique to protect modern vehicular networks from new cyber threats. The framework is planned to be taken forward so that additional vehicular protocols and deployment can be valid for the real world.
Adaptive Reinforcement Learning Strategies for Enhanced Precision Agriculture: Challenges and Future Directions Nandini Babbar, Ashish Kumar, Vivek Kumar Verma Reinforcement Learning Foundations and Applications, 2025 Precision Agriculture (PA) has emerged as a transformative approach to farming, aimed at optimizing field-level management regarding crop farming. Adaptive Reinforcement Learning (RL) offers significant potential to enhance the decisionmaking process in PA by enabling dynamic, data-driven strategies that respond to the complexities of agricultural environments. This chapter presents a comprehensive study of Reinforcement Learning (RL) applications within the domain of precision agriculture. Agriculture, as a sector, is undergoing a rapid transformation, driven by the integration of advanced technologies aiming to increase efficiency, sustainability, and crop yield. This chapter explores the integration of RL in PA, focusing on the methodologies, applications, challenges, and prospects for future development. Through detailed analysis, we present a roadmap for harnessing RL to achieve sustainable, efficient, and productive agricultural practices.
Multi Class Skin Disease Classification Using T5 and BERT Based NLP Models Vivek Kumar Verma, Shubhi Kulshrestha, Bhavna Saini 2025 International Conference on Computing Technologies Icoct 2025, 2025 Effective and automated diagnostic methods are required due to the rising incidence of dermatological illnesses, especially in clinical settings with limited resources. Despite the wealth of clinical narratives and medical records, text-based categorisation of dermatological disorders is still understudied. Traditional image-based techniques for skin disease classification have received a lot of attention. The present work provides a multi-class skin disease classification framework using advanced NLP models (T5 and BERT). The proposed working method for solving class imbalance problem, semantic diversity problem and having a complex medical language, works with text-level entries of dermatological diseases and assigns them to given classes. In the proposed work, we utilized a large clinical notes dataset that had been annotated by domain-experts across 13 different classes of skin diseases. Tokenization, stop word removal, and domain-specific embedding generation were among the initial pre- processing stages of our method that receive unique attention within the context of dermatological vocabulary. Then we adapted pretrained transformers—namely T5 and BERT—for the procedure of multiclass text classification. We used common metrics like accuracy, F1-score, precision, and recall to measure the performance of the implemented models. These results were compared to the results from both conventional machine learning algorithms and state-of-the-art transformer architectures. As per comparative analysis, our method obtained considerably higher classification accuracy which highlights the power of transformer-based architectures in modelling complex medical textual data. Our work contributes to the rapidly evolving field of AI-augmented dermatological diagnosis through a scalable text-centric classification approach. Such an approach also has the potential to complement existing image-based diagnostic tools and thereby improve overall clinical decision-making abilities. For future work, we want to investigate multimodal learning methods to combine text data with visual data and improve diagnostic accuracy while expanding practical clinical uses.
Preface Smart Innovation Systems and Technologies, 2025
Machine Learning Techniques for Prediction of Diabetes Tarun Jain, Payal Garg, Jalak Yogesh Patel, Div Chaudhary, Horesh Kumar, Vivek K. Verma, Rishi Gupta Healthcare Solutions Using Machine Learning and Informatics, 2022
Machine Learning Techniques for Prediction of Mental Health Tarun Jain, Ashish Jain, Priyank Singh Hada, Horesh Kumar, Vivek K Verma, Aayush Patni Proceedings of the 3rd International Conference on Inventive Research in Computing Applications Icirca 2021, 2021
Audio to Sign Language Translator Web Application Anju Yadav, Rahul Saxena, Bhavna Saini, Vivek K Verma, Vibhav Srivastava 2021 International Conference on Computational Performance Evaluation Compe 2021, 2021
A review on controlling of julia and mandelbrot sets International Journal of Advanced Science and Technology, 2019
Hybrid approach for optimized resource allocation load balancing in cloud infrastructure International Journal of Advanced Science and Technology, 2019
Paradigms of image compression and encryption: A review Pratistha Mathur, Anju Yadav, Viveak Kumar Verma, Renuka Purohit 2019 2nd International Conference on Intelligent Communication and Computational Techniques ICCT 2019, 2019
Talk to Me, Like Me: Modular Personalization of Emotional AI via Behavioral Metadata, Fine-Tuning, RAG, Prompts, and Agentic Reasoning R Gupta, O Dabral, P Shukla, VK Verma, H Sharma, S Kathed, HR Nidhan, ... Proceedings of the 1st International Workshop on Cognition-oriented … , 2025 2025
Decentralized and Lightweight Transformer-Based Framework for Cybersecurity in Vehicular Networks A Mundra, P Vyas, VK Verma Engineered Science , 2025 2025 Citations: 7
Predicting Wheat Yield Using Sequential and Deep Convolutional Neural Networks N Babbar, A Kumar, VK Verma 2024 5th International Conference on Electronics and Sustainable … , 2024 2024 Citations: 1
Artificial Immune System Algorithms for Optimizing Nanoparticle Design in Targeted Drug Delivery A Kumar, V Verma Bio‐Inspired Optimization for Medical Data Mining, 169-183 , 2024 2024 Citations: 1
Exploring the Potential of Dingo Optimizer: A Promising New Metaheuristic Approach A Yadav, VK Verma Bio‐Inspired Optimization for Medical Data Mining, 141-153 , 2024 2024
Comprehensive Analysis of Mental Health Insights from Social Media: Taxonomies, Computational Methods, and Resources S Tuli, VK Verma, P Mathur 2024 15th International Conference on Computing Communication and Networking … , 2024 2024 Citations: 1
Prediction of Wheat Yield by Novel SDC-LSTM Framework N Babbar, A Kumar, VK Verma Brazilian Archives of Biology and Technology 67, e24230773 , 2024 2024 Citations: 2
Cognitive equilibrium and instability: Lyapunov stability analysis in mental health research VK Verma, B Saini, T Jain, P Dadheech Journal of Interdisciplinary Mathematics 27 (2), 273–283 , 2024 2024 Citations: 1
Enhancing Trust in AI-Generated Medical Narratives: A Transparent Approach for Simplifying Radiology Reports VK Verma, B Saini International Conference on Information and Communication Technology for … , 2023 2023 Citations: 4
Optimizing Medical Image Report Generation with Varied Attention Mechanisms PM Reddy, VK Verma, MVC Varma 2023 6th International Conference on Contemporary Computing and Informatics … , 2023 2023 Citations: 3
Quantum Digital Signatures (QDS): A novel approach to safeguarding electronic health records B Saini, VK Verma, PK Tiwari, MVC Varma Journal of Discrete Mathematical Sciences and Cryptography 26 (5), 1613–1622 , 2023 2023 Citations: 1
Forecasting Wheat Yield Using Long Short-Term Memory Considering Soil and Metrological Parameters N Babbar, A Kumar, VK Verma 2023 3rd International Conference on Intelligent Communication and … , 2023 2023 Citations: 2
Comparison of Artificial Decision Techniques for Detection of Sarcastic News Headlines T Jain, H Kumar, P Garg, A Pillai, A Sinha, VK Verma International Journal of Cyber Behavior, Psychology and Learning (IJCBPL) 13 … , 2023 2023 Citations: 1
Sentiment Analysis on COVID-19 Vaccine Tweets using Machine Learning and Deep Learning Algorithms T Jain, VK Verma, AK Sharma, B Saini, N Purohit, H Mahdin, M Ahmad, ... International Journal of Advanced Computer Science and Applications 14 (5) , 2023 2023 Citations: 17
Machine Learning Techniques for Prediction of Diabetes T Jain, P Garg, JY Patel, D Chaudhary, H Kumar, VK Verma, R Gupta Healthcare Solutions Using Machine Learning and Informatics, 205-235 , 2022 2022
Device to Device Communication in 5G Network using Device-Centric Resource Allocation Algorithm C Goswami, A Das, KI Ogaili, VK Verma, V Singh, DK Sharma 2022 4th International Conference on Inventive Research in Computing … , 2022 2022 Citations: 37
SMS spam classification using machine learning techniques T Jain, P Garg, N Chalil, A Sinha, VK Verma, R Gupta 2022 12th international conference on cloud computing, data science … , 2022 2022 Citations: 37
Prediction of Personality Trait using Machine Learning on Online Texts RK Cherukuru, A Kumar, S Srivastava, VK Verma 2022 International Conference for Advancement in Technology (ICONAT), 1-8 , 2022 2022 Citations: 7
An Empirical Analysis of Heart Disease Prediction Using Data Mining Techniques A Kumar, SS Sanjith, R Cherukuru, VK Verma, T Jain, A Yadav Data Engineering for Smart Systems: Proceedings of SSIC 2021, 377-389 , 2022 2022 Citations: 3
A Metaheuristic Optimization Approach-Based Anomaly Detection With Lasso Regularization VK Verma, P Garg, PK Tiwari, TK Jain International Journal of Software Innovation (IJSI) 10 (1), 1-11 , 2022 2022
MOST CITED SCHOLAR PUBLICATIONS
Machine Learning Techniques for Prediction of Mental Health T Jain, A Jain, PS Hada, H Kumar, VK Verma, A Patni 2021 Third International Conference on Inventive Research in Computing … , 2021 2021 Citations: 92
Evaluation of machine learning algorithms for the detection of fake bank currency A Yadav, T Jain, VK Verma, V Pal 2021 11th International Conference on Cloud Computing, Data Science … , 2021 2021 Citations: 45
Device to Device Communication in 5G Network using Device-Centric Resource Allocation Algorithm C Goswami, A Das, KI Ogaili, VK Verma, V Singh, DK Sharma 2022 4th International Conference on Inventive Research in Computing … , 2022 2022 Citations: 37
SMS spam classification using machine learning techniques T Jain, P Garg, N Chalil, A Sinha, VK Verma, R Gupta 2022 12th international conference on cloud computing, data science … , 2022 2022 Citations: 37
Smart systems and IoT: Innovations in computing AK Somani, RS Shekhawat, A Mundra, S Srivastava, VK Verma Springer Singapore , 2020 2020 Citations: 28
A comprehensive review on automation of Indian sign language VK Verma, S Srivastava, N Kumar 2015 international conference on advances in computer engineering and … , 2015 2015 Citations: 28
Local invariant feature-based gender recognition from facial images VK Verma, S Srivastava, T Jain, A Jain Soft Computing for Problem Solving: SocProS 2017, Volume 2, 869-878 , 2019 2019 Citations: 26
A study on sentiment analysis of mental illness using machine learning techniques PK Tiwari, M Sharma, P Garg, T Jain, VK Verma, A Hussain IOP Conference Series: Materials Science and Engineering 1099 (1), 012043 , 2021 2021 Citations: 24
Fragmentation of handwritten touching characters in Devanagari script S Kapoor, V Verma International Journal of Information Technology, Modeling and Computing … , 2014 2014 Citations: 22
Dissecting word embeddings and language models in natural language processing VK Verma, M Pandey, T Jain, PK Tiwari Journal of Discrete Mathematical Sciences and Cryptography 24 (5), 1509-1515 , 2021 2021 Citations: 21
Audio to Sign Language Translator Web Application A Yadav, R Saxena, B Saini, VK Verma, V Srivastava 2021 International Conference on Computational Performance Evaluation (ComPE … , 2021 2021 Citations: 19
City crime mapping using machine learning techniques N Yadav, A Kumar, R Bhatnagar, VK Verma The International Conference on Advanced Machine Learning Technologies and … , 2020 2020 Citations: 19
A joint medical image compression and encryption using AMBTC and hybrid chaotic system A Yadav, B Saini, VK Verma, V Pal Journal of Discrete Mathematical Sciences and Cryptography 24 (8), 2233-2244 , 2021 2021 Citations: 18
Sentiment Analysis on COVID-19 Vaccine Tweets using Machine Learning and Deep Learning Algorithms T Jain, VK Verma, AK Sharma, B Saini, N Purohit, H Mahdin, M Ahmad, ... International Journal of Advanced Computer Science and Applications 14 (5) , 2023 2023 Citations: 17
Removal of obstacles in Devanagari script for efficient optical character recognition VK Verma, PK Tiwari 2015 International Conference on Computational Intelligence and … , 2015 2015 Citations: 16
Key Feature Extraction and Machine Learning-Based Automatic Text Summarization VK Verma, A Yadav, T Jain Emerging Technologies in Data Mining and Information Security: Proceedings … , 2019 2019 Citations: 15
Performance prediction for crop irrigation using different machine learning approaches T Jain, P Garg, PK Tiwari, VK Kuncham, M Sharma, VK Verma Examining the Impact of Deep Learning and IoT on Multi-Industry Applications … , 2021 2021 Citations: 12
Automated Detection and Classification of Breast Cancer Tumour Cells using Machine Learning and Deep Learning on Histopathological Images A Yadav, VK Verma, V Pal, V Jain, V Garg 2021 6th International Conference for Convergence in Technology (I2CT), 1-6 , 2021 2021 Citations: 8
Paradigms of image compression and encryption: A review P Mathur, A Yadav, VK Verma, R Purohit 2019 2nd International Conference on Intelligent Communication and … , 2019 2019 Citations: 8
Soft-Computing-Based Approaches for Plant Leaf Disease Detection: Machine-Learning-Based Study VK Verma, T Jain Applications of Image Processing and Soft Computing Systems in Agriculture … , 2019 2019 Citations: 8
