N. V. S. Pavan Kumar
Research Subjects
N. V. S. Pavan Kumar has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- B. H. Krishna Mohan
Department of CSE(AI-ML), RVR&JC College of Engineering, Guntur, India
2 shared publications - Kishore Kumar Kamarajugadda
Department of Electronics and Communication Engineering, Faculty of Science and Technology (IcfaiTech), ICFAI Foundation for Higher Education, Hyderabad, India
2 shared publications - Mallikarjuna Rao Gundavarapu
Computer Science and Engineering, Gokaraju Rangaraju Institute of Engineering and Technology, Bachupally, Hyderabad, Telangana, India
2 shared publications - Movva Pavani
Department of Electronics and Communication Engineering, Nalla Malla Reddy Engineering College, Hyderabad, India
2 shared publications - S. Bhargavi Latha
Department of CSE, GRIET, Hyderabad, Telangana, India
2 shared publications Anand Kumar Saraswathi Rathod
Department of CSE-(CyS,DS) and AI&DS, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, Hyderabad, India
1 shared publication
Latest Publications
- Open Access
- 3 October 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 685
Energy-efficient clustering and mobile sink routing in wireless sensor networks using quantum-inspired optimization and deep learning
- 3 October 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 685
Open AccessEnergy-efficient clustering and mobile sink routing in wireless sensor networks using quantum-inspired optimization and deep learning
- Open Access
- 2 August 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (4) , 25668-25676
Early Anomalus Action Detection in Surveillance Video Using MRCNN-LSTM Classification
Public space monitoring systems are critical for observing typical human behavior and detecting abnormal activities, especially in high-security environments. With the rise in public space thefts, there is a growing need for intelligent systems capable of detecting suspicious movements early enough to prevent criminal acts. Although Convolutional Neural Networks (CNNs) are widely used in image classification, they are inadequate to differentiate between abnormal and normal behavior and identify criminal activity in its early stage. To overcome these limitations, this study proposes a new hybrid model that combines Mask R-CNN (MRCNN) with Long Short-Term Memory (LSTM) networks for accurate object detection, tracking, and sequential behavior analysis. The main contribution of this study is a multistage anomaly detection pipeline that involves frame conversion, contrast enhancement, background removal, object tracking, and feature extraction. The MRCNN-LSTM framework can extract both spatial and temporal characteristics to allow precise early-stage anomaly detection. Thorough testing on three benchmarking datasets, UCF Crime, Snatch1.0, and CUHK, exhibited excellent performance, with a 93.6% accuracy for the UCF Crime dataset. Performance metrics such as observation ratio and time duration were used to assess the responsiveness and effectiveness of the system in real-time surveillance scenarios. This research advances the field of intelligent surveillance by enabling proactive threat mitigation through the early and precise detection of anomalous behavior.
- 2 August 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (4) , 25668-25676
Open AccessEarly Anomalus Action Detection in Surveillance Video Using MRCNN-LSTM Classification
Public space monitoring systems are critical for observing typical human behavior and detecting abnormal activities, especially in high-security environments. With the rise in public space thefts, there is a growing need for intelligent systems capable of detecting suspicious movements early enough to prevent criminal acts. Although Convolutional Neural Networks (CNNs) are widely used in image classification, they are inadequate to differentiate between abnormal and normal behavior and identify criminal activity in its early stage. To overcome these limitations, this study proposes a new hybrid model that combines Mask R-CNN (MRCNN) with Long Short-Term Memory (LSTM) networks for accurate object detection, tracking, and sequential behavior analysis. The main contribution of this study is a multistage anomaly detection pipeline that involves frame conversion, contrast enhancement, background removal, object tracking, and feature extraction. The MRCNN-LSTM framework can extract both spatial and temporal characteristics to allow precise early-stage anomaly detection. Thorough testing on three benchmarking datasets, UCF Crime, Snatch1.0, and CUHK, exhibited excellent performance, with a 93.6% accuracy for the UCF Crime dataset. Performance metrics such as observation ratio and time duration were used to assess the responsiveness and effectiveness of the system in real-time surveillance scenarios. This research advances the field of intelligent surveillance by enabling proactive threat mitigation through the early and precise detection of anomalous behavior.
- 1 January 2025
- Published by American Scientific Publishing Group (ASPG) LLC in Journal of Intelligent Systems and Internet of Things
- Vol. 17 (1) , 219-19-238
Explainable Artificial Intelligence Driven Intrusion Detection System for Enhancing Reliability and Interpretability in IoT Based Network Security Solutions
American scientific publishing group
- 1 January 2025
- Published by American Scientific Publishing Group (ASPG) LLC in Journal of Intelligent Systems and Internet of Things
- Vol. 17 (1) , 219-19-238
Explainable Artificial Intelligence Driven Intrusion Detection System for Enhancing Reliability and Interpretability in IoT Based Network Security Solutions
American scientific publishing group
- Open Access
- 7 October 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (10s) , 576-587
Nurturing Agribusiness: A Sustainable Farming System for Tomato Crop Management Leveraging Machine Learning
The agriculture industry is undergoing a transformative shift with the introduction of IoT technology, enabling global connectivity for farmers. This technology offers a plethora of advantages, ranging from precise seed selection based on soil analysis to efficient crop maintenance, water management, and enhanced marketing support for improved profitability. To further enhance tomato farming practices, we propose the implementation of a smart farmer marketing assistant that streamlines the process of segregating yield based on its growth stage, reducing labor and time requirements.Further, the frame work is capable of early-disease management system that can detect diseases like early blight,light blight, buck eye rot and anthranose and suggest remedy. By adopting this innovative approach, financial losses associated with traditional methods are minimized.The traditional practice of combining all categories of vegetables (ripened, unripened, and partially rotten) in a single container often results in reduced shelf life for the produce. In our framework, we employ color sorting to categorize the vegetables, ensuring proper packing into their respective bins. This valuable data is made accessible through a cloud environment, providing potential buyers with comprehensive information about the yield, its category, and pricing. This increased visibility empowers farmers to reach a global market and sell their produce at competitive prices. In this context, we present a case study focused on the tomato crop, where we have successfully developed a prototype utilizing ESP32, a color sensor, and Google Firebase. This comprehensive framework effectively harnesses the power of IoT, Machine Learning, and potential marketing strategies, transforming the way farmers manage their crops and connect with buyers on a global scale with highly accurate 87.9% experimental results.
- 7 October 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (10s) , 576-587
Open AccessNurturing Agribusiness: A Sustainable Farming System for Tomato Crop Management Leveraging Machine Learning
The agriculture industry is undergoing a transformative shift with the introduction of IoT technology, enabling global connectivity for farmers. This technology offers a plethora of advantages, ranging from precise seed selection based on soil analysis to efficient crop maintenance, water management, and enhanced marketing support for improved profitability. To further enhance tomato farming practices, we propose the implementation of a smart farmer marketing assistant that streamlines the process of segregating yield based on its growth stage, reducing labor and time requirements.Further, the frame work is capable of early-disease management system that can detect diseases like early blight,light blight, buck eye rot and anthranose and suggest remedy. By adopting this innovative approach, financial losses associated with traditional methods are minimized.The traditional practice of combining all categories of vegetables (ripened, unripened, and partially rotten) in a single container often results in reduced shelf life for the produce. In our framework, we employ color sorting to categorize the vegetables, ensuring proper packing into their respective bins. This valuable data is made accessible through a cloud environment, providing potential buyers with comprehensive information about the yield, its category, and pricing. This increased visibility empowers farmers to reach a global market and sell their produce at competitive prices. In this context, we present a case study focused on the tomato crop, where we have successfully developed a prototype utilizing ESP32, a color sensor, and Google Firebase. This comprehensive framework effectively harnesses the power of IoT, Machine Learning, and potential marketing strategies, transforming the way farmers manage their crops and connect with buyers on a global scale with highly accurate 87.9% experimental results.
- Open Access
- 4 April 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (3) , 273-282
Technology for Kisan Samanvayam: Nutrition Intelligibility of Groundnut Plant using IoT-ML Framework
Neolithic Demographic transition resulting the reduction of habitable land for cultivation. Hence the smart agriculture is the only way to cater higher food demand. The farming community of developing countries like India needs Kisan Samanvayam with futuristic technologies for financially viable cultivation. Technology place vital role in economically nourishment of soil fertility and crop management. In this regard we proposed IoT-ML framework for remotely assessing the soil nutrients (N, P,K), PH and early stage detection of crop deceases. Android APP which is a part and parcel of the frame work enable the farmer to have real time visual statistics of the soil nutrients, notifications and suggestions regarding to the crop management. JXCT Soil NPK sensors, PH sensors, Dual Core ESP32 Controllers, Firebase Cloud and Random Forest Decision Tree machine Learning Algorithm, Micromlgen serve this purpose. Unlike Solitary sensor for entire field, we have divided a hector into four subregions for effective monitoring local region needs. The presence of IoT with TinyML increased the robustness of the framework and results are encouraging with sandy loam soil.
- 4 April 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (3) , 273-282
Open AccessTechnology for Kisan Samanvayam: Nutrition Intelligibility of Groundnut Plant using IoT-ML Framework
Neolithic Demographic transition resulting the reduction of habitable land for cultivation. Hence the smart agriculture is the only way to cater higher food demand. The farming community of developing countries like India needs Kisan Samanvayam with futuristic technologies for financially viable cultivation. Technology place vital role in economically nourishment of soil fertility and crop management. In this regard we proposed IoT-ML framework for remotely assessing the soil nutrients (N, P,K), PH and early stage detection of crop deceases. Android APP which is a part and parcel of the frame work enable the farmer to have real time visual statistics of the soil nutrients, notifications and suggestions regarding to the crop management. JXCT Soil NPK sensors, PH sensors, Dual Core ESP32 Controllers, Firebase Cloud and Random Forest Decision Tree machine Learning Algorithm, Micromlgen serve this purpose. Unlike Solitary sensor for entire field, we have divided a hector into four subregions for effective monitoring local region needs. The presence of IoT with TinyML increased the robustness of the framework and results are encouraging with sandy loam soil.