Dr. Johnson Kolluri
Assistant Professor
Computer Science & Artficial Intelligence
NIT-Mizoram
15
DAA
Computer Vision, Deep Learning
Assistant Professor
Computer Science & Artficial Intelligence
NIT-Mizoram
15
DAA
Computer Vision, Deep Learning
(Ph.D) in CSE
M.Tech in CSE
B.Tech in CSE
Ph.D
PG
UG
Ranganayaki, V.S., Kolluri, J., Siripuri, K. et al. Energy-Efficient Data Gathering in Wireless Sensor Networks Using Hybrid Oppositional Fruitfly and Bacterial Foraging Optimization. Int J Netw Distrib Comput (2026). https://doi.org/10.1007/s44227-026-00109-z.
Juyal, P.K., Kolluri, J. & Siripuri, K. Federated generative adversarial network with hybrid transformer-GRU and explainable AI for financial fraud detection. Sci Rep (2026). https://doi.org/10.1038/s41598-026-61476-9
G. Devibai, C. Veena, K. V. Kumar, J. Kolluri, S. K. Medishetti and R. Vempati, "Zebra Optimization Algorithm-based Task Scheduling for Efficient Cloud-Fog Environments," 2026 International Conference on Computer Networks and Inventive Communication Technologies (ICCNCT), Erode, India, 2026, pp. 250-258, doi: 10.1109/ICCNCT68477.2026.11590035.
S. Marathe, C. Veena, J. Kolluri, V. S. Kiran, S. K. Medishetti and R. Vempati, "An Intelligent DDPG Framework for Cost-Efficient Task Scheduling in Multi-Cloud Environment," 2026 7th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), Tirunelveli, India, 2026, pp. 969-977, doi: 10.1109/ICICV68925.2026.11554699.
J. Dasari, B. Dhanunjaya, K. V. Kumar, J. Kolluri, R. Vempati and S. K. Medishetti, "QANA: Intelligent Metaheuristic Task Scheduling for ML Workloads in Cloud Environment," 2026 8th International Conference on Inventive Material Science and Applications (ICIMA), Namakkal, India, 2026, pp. 1646-1654, doi: 10.1109/ICIMA68728.2026.11564268.
C. Veena, S. K. Medishetti, J. Kolluri, A. Vanaja, R. Vempati and V. S. Kiran, "GAO: Intelligent Framework for Energy, Cost, and Temperature Optimization in Multi-Cloud Systems," 2026 8th International Conference on Inventive Material Science and Applications (ICIMA), Namakkal, India, 2026, pp. 43-50, doi: 10.1109/ICIMA68728.2026.11564845.
C. Manjunath, K. Manchikanti, J. Kolluri, R. Vempati, C. Veena and S. K. Medishetti, "Meta FOA: Classifying and Scheduling of IoT Tasks in Cloud Computing Environment," 2026 6th International Conference on Expert Clouds and Applications (ICOECA), Bengaluru, India, 2026, pp. 846-854, doi: 10.1109/ICOECA68095.2026.11485107.
12. G. Sujatha, K. Manchikanti, J. Kolluri, R. Vempati, R. S. Velamakanni and S. Kumar Medishetti, "XDL-IRTS: an Intelligent and Resilient Task Scheduling in Large-Scale Cloud Environments," 2026 8th International Conference on Intelligent Sustainable Systems (ICISS), Tirunelveli, India, 2026, pp. 1-9, doi: 10.1109/ICISS67859.2026.11454061.
G. Sreenivasan, P. Prathima, J. Kolluri, K. Ashok, R. Vempati and S. K. Medishetti, "Fuzzy-DRL: Cost and Energy Efficient Task Scheduling in Cloud-Fog Computing Environment," 2026 8th International Conference on Intelligent Sustainable Systems (ICISS), Tirunelveli, India, 2026, pp. 650-657, doi: 10.1109/ICISS67859.2026.11453829.
R. Vempati and J. Kolluri, "Transformer-Based Intrusion Detection and Protection Systems: An Innovative Method for Reducing Cyberattacks," 2025 2nd International Conference on Intelligent Systems for Cybersecurity (ISCS), Gurugram, India, 2025, pp. 1-5, doi: 10.1109/ISCS69371.2025.11386393.
V. G. S, P. Prasant, R. Madamala and J. Kolluri, "Optimi1zing Soil Moisture Prediction and Crop Yield Enhancement for Medicinal Plants Using Convolutional Neural Networks in Precision Agriculture," 2025 International Conference on Computing, Intelligence, and Application (CIACON), Durgapur, India, 2025, pp. 1-6, doi: 10.1109/CIACON65473.2025.11189722.
S. L. Lakshmi, V. R. Kanth and J. Kolluri, "Enhancing Text Classification with an Attention-Integrated CNN-SVM Hybrid Model," 2025 International Conference on Computing, Intelligence, and Application (CIACON), Durgapur, India, 2025, pp. 1-6, doi: 10.1109/CIACON65473.2025.11189691.
G. Sreenivasan, P. Prathima, J. Kolluri, K. Ashok, R. Vempati and S. K. Medishetti, "Fuzzy-DRL: Cost and Energy Efficient Task Scheduling in Cloud-Fog Computing Environment," 2026 8th International Conference on Intelligent Sustainable Systems (ICISS), Tirunelveli, India, 2026, pp. 650-657, doi: 10.1109/ICISS67859.2026.11453829.
G. Sujatha, K. Manchikanti, J. Kolluri, R. Vempati, R. S. Velamakanni and S. Kumar Medishetti, "XDL-IRTS: an Intelligent and Resilient Task Scheduling in Large-Scale Cloud Environments," 2026 8th International Conference on Intelligent Sustainable Systems (ICISS), Tirunelveli, India, 2026, pp. 1-9, doi: 10.1109/ICISS67859.2026.11454061.
Kolluri, J., Dash, S.K., Das, R. et al. Surveillance video–based pedestrian detection for smart transportation using machine learning techniques. Discov Appl Sci 8, 398 (2026). https://doi.org/10.1007/s42452-026-08466-8
Johnson Kolluri, Dr.Shaik Razia, Soumya Ranjan Nayak “Text Classification using Machine Learning and Deep Learning Models” published at International Conference on Artificial Intelligence in Manufacturing & Renewable Energy(ICAIMRE-2019),25&26th Oct-2019.
Johnson Kolluri and Ranjita Das “Ship Detection from Satellite Images with an Advanced deep learning model (single Shot Detector (SSD))” International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA 2022) June18-19,2022, conference proceedings by Springer Smart Innovation, Systems and Technologies(SIST).
Johnson Kolluri, vinay kumar kotte,M.S.B Phridviraj and Dr.Shaik Razia ”Reducing Overfitting Problem in Machine Learning Using Novel L1/4 Regularization Method” published at Fourth International Conference on Trends in Electronics and Informatics (ICOEI-2020), DVD Part Number: CFP20J32-DVD; ISBN: 978-1-7281-5517-3, June-2020.
Johnson Kolluri, Ranjita Das "An efficient Synergic Model with Contrast Limited Adaptive Histogram Equalization model for Object Classification in Ship Detection," 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), 2022, pp. 1-7, doi: 10.1109/MysuruCon55714.2022.9972532.
Ganesh, V., Johnson Kolluri, J., Maada, A.R., Ali, M.H., Thota, R., Nyalakonda, S. (2022). Real-Time Video Processing for Ship Detection Using Transfer Learning. In: Chen, J.IZ., Tavares, J.M.R.S., Shi, F. (eds) Third International Conference on Image Processing and Capsule Networks. ICIPCN 2022. Lecture Notes in Networks and Systems, vol 514. Springer, Cham. https://doi.org/10.1007/978-3-031-12413-6_54.
Johnson Kolluri, V Ganesh and vinay kumar kotte, “Diabetics Prediction using Logistic Regression and Feature Normalization” published at Fourth International Conference on Innovative Communication and smart Electrical systems (ICSES-2021), Organised by:St.Joseph’s Institute of Technology,Chennai,India; ISBN: 978-1-6654-3520-8, 24th &25th September,2021.
Johnson Kolluri, V. ChandraShekar Rao, Gouthami velakanti, Siripuri Kiran, sumukham Sravanthi , S.Venkatramulu “Text Classification Using Deep Neural Networks” published at 5th International Conference On Intelligent Computing and Communication (ICICC-2021), paper ID-108 held at Dayananda Sagar University, Bengaluru ,India, November-2021
Johnson Kolluri, K.Vinay Kumar, C.Srinivas, Siripuri Kiran, Swapna Saturi, Ravula Rajesh “COVID-19 Detection from X-rays using Deep Learning Model” published at 5th International Conference On Intelligent Computing and Communication (ICICC-2021), paper ID-108 held at Dayananda Sagar University, Bengaluru ,India, November-2021.
Johnson kolluri, N Anusha, Dr. C.V GuruRao “Refinement Trust Model Creation For Service Oriented Architecture Using Interface Theory” Published at International Journal of Computer Science Information and Engineering, Technologies, Issue-3-Vol-3-series-1, ISSN:2277-4408,01-september-2013.
Johnson Kolluri, Rajitha Jampala,” Observing the Protection of Confidential Location System for WSNs” published at International Journal Computer Technology and Applications , vol 3(5), ISSN:2229-6093,1807-1812,sep-oct 2012.
Johnson Kolluri, Sumera Mohammadi, Dr.C.V.Gururao” The Future of Wireless -IEEE STANDARD 802.16 for Global Broadband Wireless Access ” published at International Journal of Research Computational Technology, vol.2 Issue.3, ISSN:0975-5665, June-2012.
Johnson Kolluri, Dr.Shaik Rajia, Dr.Niranjan Polala “A Comparative Study of Deep Learning Models used for Object identification” published at Compliance Engineering Journal(UGC-Care Journal) Vol-10/Issue-09, ISSN 0898-3577, 2019.
Johnson Kolluri, Ch Anila, S.P Anand Raj “Secure Data Transfer In CLOUD By Using Aes” published at International journal of Engineering and Science Research Vol-3/Issue-10/4864-4871, ISSN 2277-2685, October-2013.
Johnson kolluri, N Anusha, Dr. C.V GuruRao “Refinement Trust Model Creation For Service Oriented Architecture Using Interface Theory” Published at International Journal of Computer Science Information and Engineering, Technologies, Issue-3-Vol-3-series-1, ISSN:2277-4408,01-september-2013.
Kolluri, J., & Das, R. (2025). Multimodal image analysis based pedestrian detection using optimization with classification by hybrid machine learning model. International Journal of Image, Graphics and Signal Processing, 17(1), 31–44. https://doi.org/10.5815/ijigsp.2025.01.03
Johnson Kolluri, Sandeep Kumar Dash and Ranjita Das “Plant Disease Identification Based on Multimodal Learning” International Journal of Intelligent Systems and Applications in Engineering(2024). ISSN:2147-6799, Volume 12, No 15S (2024).
Johnson Kolluri, Ranjita Das “An Evaluation of Deep Learning- Based Object Identification” IJRITCC(2022). https://doi.org/10.17762/ijritcc.v10i1s.5795, ISSN: 2321-8169 Volume: 10 Issue: 1, 9 November 2022.
Johnson Kolluri, Sandeep Kumar Dash, Ranjita Das “MM_Fast_RCNN_ResNet: Construction of Multomodel Faster RCNN Inception and ResNet V2 for Pedestrian Tracking and Detection” is accepted in the International Journal of Maritime Engineering (ISSN/E-ISSN : 1479-8751/1740- 0716).
Johnson Kolluri, Ranjita Das “Intelligent Multimodal Pedestrian Detection using Hybrid Metaheuristic Optimization with Deep Learning Model” Image and Vision Computing(2023). https://doi.org/10.1016/j.imavis.2023.104628, March-2023.
Johnson Kolluri, D. Suresh Babu, B. Raju, S. Swapna, D. Ramesh & Rajitha Bonagiri “Dengue symptoms classification analysis with improved conditional probability decision analysis” Appl Nanosci (2022). https://doi.org/10.1007/s13204-022-02387-9, 11 February 2022.
Title: Solar Park Monitoring and Fault Detection System Using IoT and Machine Learning Description: The Solar Park Monitoring and Fault Detection System using IoT and Machine Learning is an innovative solution designed to enhance the efficiency, reliability, and maintenance of large-scale solar power installations. This system integrates Internet of Things (IoT) technology with advanced Machine Learning (ML) algorithms to provide real-time data monitoring, predictive analytics, and automated fault detection. Key Feat
The proposed invention is a smart, non-invasive skin patch designed for continuous, real-time health monitoring. It tracks multiple vital biomarkers such as glucose, heart rate, hydration, and stress levels, providing personalized insights through AI-driven analysis. This innovation enables proactive healthcare management, offering timely predictions and alerts to users and healthcare providers. 1. Sensor Monitoring: The patch contains multiple biosensors that measure vital signs and health biomarkers
The invention presents a real-time emotion detection system that integrates ensemble natural language processing and machine learning techniques. The system includes an input processing module, an ensemble NLP module with transformer-based models and sentiment analysis algorithms, a feature aggregation unit, a machine learning classifier module, and an output/feedback module. By combining multiple NLP models and classifiers, the system improves accuracy, scalability, and adaptability in dynamic communication environments. It
A BCI headset that captures brain signals using EEG sensors and uses deep learning to detect user intent. It predicts actions and executes commands in a digital environment with reduced latency (100–150 ms), enabling faster and intuitive interaction
An advanced AI framework that combines Graph Neural Networks (GNN) and Transformer models to analyze multimodal data, including bioacoustic signals and environmental inputs, for early disaster prediction and adaptive response.
A multimodal AI-based system using Faster R-CNN with Inception and ResNet architectures to detect and track pedestrians from RGB and infrared data, ensuring high accuracy and reliable performance in real-time environments
A wearable device with biosensors that monitors physiological parameters and uses AI to analyze health data, predict risks, and provide personalized health insights for preventive care.
A smart bottle equipped with sensors to monitor liquid intake and medication usage, providing context-aware reminders and automated pill access to improve hydration and medication adherence, especially for elderly users.
This invention proposes a self-calibrating multimodal sensor fusion system that combines data from multiple sensors using uncertainty-aware deep neural networks to improve pedestrian detection accuracy. It employs Bayesian fusion, confidence estimation, automatic sensor calibration, and edge optimization to provide reliable, real-time pedestrian detection for autonomous vehicles, ADAS, and intelligent transportation systems.
This invention presents a real-time pedestrian detection system that integrates RGB, depth, and infrared sensors with adaptive multimodal data fusion to accurately detect and localize pedestrians. It incorporates confidence estimation, explainable AI, and lightweight inference to deliver reliable, transparent, and computationally efficient pedestrian detection for autonomous vehicles, ADAS, and intelligent transportation systems.
This invention introduces a hybrid hyperspectral–multimodal AI framework for early diagnosis of mint plant diseases by integrating hyperspectral imaging and environmental sensing. It uses adaptive data fusion and temporal intelligence to detect disease at an early stage, correlate environmental stress factors, and support accurate, proactive, and sustainable precision agriculture.
This invention introduces a causal reasoning-driven multimodal system for automated image captioning that combines visual and language features to generate accurate, context-aware captions. It integrates explainable AI and causal inference to improve transparency, interpretability, and semantic understanding for intelligent vision applications.
This invention presents a semantic causality and knowledge fusion system for explainable vision-language image captioning. It combines visual features, semantic knowledge, and causal reasoning to generate accurate, context-aware image captions with transparent explanations, improving interpretability and reliability in AI-powered vision applications.
This invention presents a hybrid multimodal emotion analysis system that combines facial micro-expressions, physiological signals, and deep learning-based fusion for accurate emotion recognition. It enables reliable and real-time emotion analysis for applications in healthcare, human-computer interaction, driver monitoring, and intelligent surveillance.
This invention presents a transformer-driven multimodal emotion recognition system that integrates facial micro-expressions and physiological responses for accurate emotion classification. It leverages transformer-based fusion to provide robust, real-time emotion recognition for healthcare, human-computer interaction, security, and intelligent monitoring applications.
This invention presents a context-guided multimodal emotion understanding system that integrates facial expressions, micro-expressions, physiological signals, and contextual information for accurate emotion recognition. It employs adaptive multimodal fusion and deep learning to enable reliable, real-time emotion analysis for healthcare, human-computer interaction, and intelligent monitoring applications.
This invention presents a multimodal object detection system with contextual interpretation that combines visual analysis, object detection, and semantic understanding to accurately identify and interpret objects. It integrates multimodal data fusion and contextual reasoning to enhance object recognition for intelligent surveillance, autonomous systems, and smart vision applications.
This invention presents an AI-powered biomedical research assistance system that supports biomedical research through intelligent knowledge retrieval, automated prompt generation, and contextual analysis. It optimizes research workflows, improves the quality of AI-assisted outputs, and enhances efficiency in biomedical research and scientific decision-making.
This invention presents an explainable Vision Transformer-based system for uncertainty-aware disaster forecasting and resilient decision support. It combines geospatial data analysis, uncertainty estimation, and explainable AI to deliver accurate disaster predictions and support timely, risk-informed emergency response and disaster management.
This invention presents an AI-enabled healthcare prediction system that integrates Federated Learning and Explainable Clinical BERT to securely analyze electronic health records. It enables accurate disease prediction, interpretable clinical decision support, and privacy-preserving collaboration across healthcare institutions, improving patient outcomes and treatment planning.
This invention presents a graph-based cross-attention emotion recognition system that integrates facial micro-expressions and speech prosody for accurate emotion classification. It combines graph neural networks and cross-attention mechanisms to enable robust, interpretable, and real-time emotion recognition for healthcare, human-computer interaction, and intelligent systems.
This invention presents an edge-intelligent multimodal vision system for real-time medicine tablet recognition with context-aware natural language audio assistance. It combines computer vision, deep learning, and natural language processing to accurately identify medicines and provide personalized voice guidance, enabling safe, privacy-preserving, and accessible medication support for healthcare applications.
This invention presents a deep learning-based system for automated stroke lesion localization and segmentation from medical images. It accurately identifies and classifies stroke lesions, provides lesion quantification, and supports clinical decision-making, enabling faster and more reliable diagnosis for improved patient care.
This invention presents a pedestrian detection and adaptive traffic signal management system that integrates camera, infrared, and LiDAR sensors with AI-based multimodal fusion. It enables accurate pedestrian detection, adaptive traffic signal control, and real-time traffic management, improving pedestrian safety and smart transportation efficiency.
This invention presents an explainable AI-based decision support system for automated dermatological disease diagnosis. It combines deep learning, medical image analysis, and explainable AI to accurately detect skin diseases while providing transparent, reliable predictions that support clinical decision-making and improve diagnostic confidence.
