Pradeep Kumar Mahapatro

@adityatekkali.edu.in

Assistant Professor
Aditya Institute of Technology and Management

Pradeep Kumar Mahapatro


               Download Compact PDF  
https://researchid.co/pradeepmahapatro
Pradeep Kumar Mahapatro is an Assistant Professor in the Department of Artificial Intelligence & Machine Learning, Aditya Institute of Technology and Management, Tekkali, Srikakulam District, Andhra Pradesh, India. He completed his M.S., M.Phil., M. Tech., at Berhampur University, Berhampur. He has more than 15 years of teaching experience at Centurion University, Parlakhemundi, Odisha. Currently, he is pursing a Ph.D. in CSE at GIETU, Gunupur, Odisha. His research interests include machine learning and data analytics, operating system, software engineering, and database management system. He has published number of research papers in various reputable journals and has attended a number of international conferences at various levels.

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Agricultural and Biological Sciences, Engineering, Computer Engineering
20

Scopus Publications

31

Scholar Citations

3

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • Secure and Collaborative Crop Disease Prediction with Federated eep Learning: Safeguarding Data Sovereignty in Agriculture
    Sadananda Behera, Neelamadhab Padhy, Rasmita Panigrahi, Pradeep Kumar Mahapatro, Dasaradha Arangi
    Artificial Intelligence in Context of Digital Sovereignty Series Digital Sovereignty and Human Centric AI, 2026
    Sustainable agriculture is no longer a buzzword but is a necessity. Use of Artificial Intelligence (AI) is rapidly increasing and transforming agriculture, especially in areas like early crop disease detection and prediction. These technology-driven prediction and detections helps in prevention, early identification, and data-driven decision making, and help farmers boost yields, reduce losses, which are the key factors in achieving long-term agricultural sustainability. However, many of these traditional AI systems depend on centralized data collection, often requiring farmers and institutions to share sensitive, localized agrarian data. This raises critical concerns about digital data privacy, ownership, and sovereignty. In the context of agriculture, where data is mainly tied to local practices, regional biodiversity, and a mix of small and large farmers with different economic backgrounds, maintaining strict data confidentiality is essential. In this context, Federated Learning (FL) provides a promising solution. Instead of pooling data in a single location, FL allows AI models to be trained directly on local devices or servers, keeping the raw data with the farmers. Our approach uses the power of deep learning with the privacy-preserving nature of federated systems in a secure environment where IoT sensor data is used to train the model locally, and the model is suitable to be deployed in a resource-constrained environment to predict crop diseases. We use a subset of the PlantVillage dataset to compare the predictive performance of centralized Deep Learning (ResNet-50) with Federated Learning algorithms such as FedAvg, FedProx, and FedBN. Our findings reveal that, whereas centralized models obtain the maximum accuracy (98.7%), federated models, notably FedBN, provide a convincing trade-off with 97.1% accuracy and only 40 communication rounds, ensuring data privacy without significantly sacrificing performance. The statistical study shows no significant difference in prediction accuracy (p > 0.05) between centralized and federated models.
  • An IoT Based Intelligent and Real-Time Parking Management System
    Sibo Prasad Patro, Rasmita Gantayet, Pradeep Kumar Mahapatro, Dasaradha Arangi, Neelamadhab Padhy
    Lecture Notes in Networks and Systems, 2026
  • Does Sampling Improve the Precision-Recall Trade-off in Fraud Detection Systems? An Empirical Study Using Ensemble Machine Learning Models
    Chandra Sekhar Dash, Neelamadhab Padhy, Rasmita Panigrahi, Asish Kumar Patnaik, Pradeep Kumar Mahapatro, Dasaradha Arangi
    Esic 2026 Proceedings 6th International Conference on Emerging Systems and Intelligent Computing, 2026
    Background: Fraud detection is a key difficulty in financial and digital systems, due to the huge imbalance in nature. This study presented the machine learning models to early predict and improve the fraud detection so that the performance of fraud detection is improved. Objective: This study employed the three data sampling techniques to understand the behaviour and the transactional attributes, such as i) no sampling, (ii) Synthetic Minority Oversampling Technique (SMOTE), and (iii) SMOTETomek hybrid sampling. Apart from these, we also conducted the experimental work where the five machine learning models (AdaBoost, Gradient Boosting, RandomForest (weighted and balanced variants), EasyEnsemble, and ExtraTrees) were used to detect and identify the fraudulent behaviour in the transactional dataset. Result: From our experimental observation, we found AdaBoost performed well in comparison to the others, with the highest AUC-ROC of 0.8881 on the original dataset. The results reveal that balanced tree-based models demonstrated superior stability, especially under hybrid sampling, with ExtraTrees achieving perfect cross-validation consistency (CV_AUC =1.0). SMOTETomek provided cleaner class separation and improved reliability compared to SMOTE. Overall, the findings emphasize the need to combine ensemble learning with robust augmentation strategies to combat excessive class imbalance, providing an effective strategy for enhancing fraud detection systems in realworld applications.
  • Exploring Chili Plant Health: A Comprehensive Study Using IoT Sensors and Machine Learning Classifiers
    Kiran Kumar Sahu, Vishal Kumar Swain, Rasmita Panigrahi, Neelamadhab Padhy, Pradeep Kumar Mahapatro, Dasaradha Arangi
    Lecture Notes in Networks and Systems, 2026
  • Crop Yield Prediction using Federated Learning: A Privacy-Preserving Approach for Decentralized Agriculture Data
    Satyajit Pujapanda, Sriya Mishra, Debasish Mahapatra, Gyanendra Sahoo, Neelamadhab Padhy, Pradeep Kumar Mahapatro
    Esic 2026 Proceedings 6th International Conference on Emerging Systems and Intelligent Computing, 2026
    Food security and economic growth of the world depend on agriculture. It is also significant to anticipate rich crops well since this will bring good management and favourable allocation of resources. It is a prerequisite in all the classic practices of machine learning approaches that all data be gathered together in one place. The storage gives rise to problems such as a lack of privacy and sharing of huge data sets, especially in instances where data is harvested at varying locations. That is the issue that the present paper attempts to address with the help of Federated Learning (FL). This method gives farmers the ability to create a model of machine learning without the need to disclose their data. We developed and tested the project on real data in Python and TensorFlow. These findings indicated that FL could be used as an alternative to conventional methods, and it is best suited to agriculture.
  • Optimizing Crop Recommendation through Stacking and Feature Analysis of Ensemble Classifiers
    Pradeep Kumar Mahapatro, Rasmita Panigrahi, Neelamadhab Padhy
    Esic 2025 5th International Conference on Emerging Systems and Intelligent Computing Proceedings, 2025
    Farming is the source to increase agricultural productivity. Modern precision farming depends on a crop recommendation system which is used by some data-driven methods to predict a suitable crop based on the environmental conditions. To improve the accuracy of forecasting the model combines feature analysis with stacking ensemble approaches. This model also integrates with random forest (RF), gradient boosting, and XGboost. Selecting feature analysis techniques, the model assesses parameters like soil type, temperature, rainfall, and pH level. Based on soil and climate conditions the stacked model provides reliable suggestions to the farmer in making decisions for environmentally friendly farming. The main objective of this paper is to optimize the crop based on the stacking Regressor as well as the ensemble classifier. Nine machine learning classifiers are used to achieve it but among all RF classifiers outperform i.e. accuracy of 0.995455, precision of 0.995671, and recall of 0.995455. Apart from these we also used the filter-based selection (correlation) and wrapper-based selection (RFE) to provide top models for crop recommendation. The top 3 performers (Random Forest, Extra Trees, and XGBoost) are used to make an ensemble for optimizing the crop.
  • Performance Improvement of Machine Learning Algorithms Through Information-Theoretic Class Based Feature Multicorrelation Enabled Feature Selection for Cervical Cancer Prediction
    Kurman Sangeeta, Sumitra Kisan, Kalyana Kiran Kumar, Pradeep Kumar Mahapatro
    Communications in Computer and Information Science, 2025
  • Evaluating Machine Learning Algorithms for Environmental Impact Prediction
    Debasish Pradhan, Shibani Subhadarshini, Neelamadhab Padhy, Pradeep Kumar Mahapatro, Dasaradha Arangi
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
    The Environmental Impact Tracker (EIT) is an innovative application that is designed in such a way that it can monitor and visualize the data both for individuals and organizations. Its main objective is to guide the users about their day-to-day life activities by tracking the past habits that are creating an impact on the environment. The EIT is an efficient application that uses advanced machine learning algorithms such as SVMs, Random Forest Regression, and various classification techniques to analyze and interpret the data. It is found that data SVM performed well and got the accuracy 94.10 %. EIT helps the users proactively organize their behavior to minimize the negative impact on the environment. The EIT is a technological innovation that can be harnessed to promote sustainability and environmental impacts.
  • Cartpole Balancer Using Deep Q-Network
    Pradeep Kumar Mahapatro, Pasina Yaswanth, Challa Meghana, Tamada Rushanth, Peddinti Somesh
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
    In this paper, we purely focused on the algorithm called Deep Q-Network (DQN) to solve CartPole environment, a classic reinforcement learning task. The goal of the Cartpole task is to balance the pole on a moving cart by applying the sequences of left or right forces. In traditional approaches, such as Manual Rule-Based Controller, Random Agent Method and many are there which are struggling to deal with the complexity of this task. In contrast, DQN leverages deep learning to approximate the optimal action-value function, enabling the agent to learn a policy that maximizes cumulative reward through interactions with environment. This project implements DQN algorithm, training a deep neural network to predict Q-values for the different state-action pairs. Through iterative updates and experience replay, the agent learns to maintain the pole in an upright position for extended periods. The performance of the DQN agent is evaluated based on its ability to achieve and maintain balance, demonstrating the effectiveness of deep reinforcement learning in complex control tasks.
  • Improving Cross-Project Defect Prediction Through Feature Selection and Model Optimization
    Usha Kiran, Neelamadhab Padhy, Rasmita Panigrahi, Dasaradha Arangi, Pradeep Kumar Mahapatro
    2025 International Conference on Next Generation of Green Information and Emerging Technologies Giet 2025, 2025
    Bug- and defect-free software is a high priority in the field of software engineering. The main aim of this study is to predict defects in cross-projects. This study includes the analysis of various studies to give an all-around approach to studying defect prediction to enrich the software quality. Objective: This study's main focus is on defect prediction. To identify the possibility of defect-prone areas before the testing to improve the software quality. In this study, we have used SVM, CNN, XGBoost, RF, and MLP Models to train for defect prediction. Materials/Methods: The data have been collected from different software projects, and the latest techniques to detect defect prediction have been employed. We have taken into consideration Project A, Project B, and Cross Projects for this study. Several Machine learning and Deep learning algorithms, along with tools for statistical Analysis, have been used to design well-planned and structured models for defect prediction. Statistical Significance (Statistical Analysis): From the statistical analysis, we have observed that there is a high level of interdependency between defect prediction and software quality. The results of the data analysis and the validity of the models have been taken into consideration in this study. Conclusion: This study has shed light on the huge benefits of early defect prediction, which reduces the time and effort during the testing phase and helps in improving the software quality. This research is targeted to improve the quality of software by reducing defects, thereby improving its performance, reliability, and quality of the system. From the study, we have seen that there is a consistent improvement in F1-score and Accuracy due to feature selection.
  • Software cost estimation using AI and Federated Learning
    Tirupati Sahu, Neelamadhab Padhy, Rasmita Panigrahi, Pradeep Kumar Mahapatro, Dasaradha Arangi, Sibo Prasad Patro
    Proceedings 2025 IEEE 3rd International Symposium on Sustainable Energy Signal Processing and Cybersecurity Isssc 2025, 2025
  • Enhancing Classification Performance in Health Condition Prediction: A Comparative Study of Machine Learning Models with SMOTE and Sensitivity Trade-Off Analysis
    Rasmita Panigrahi, Neelamadhab Padhy, Asish Kumar Patnaik, Archana Patnaik, Dasaradha Arangi, Pradeep Kumar Mahapatro
    Ocit 2025 Proceedings 23rd Oits International Conference on Information Technology, 2025
  • Mathematical Framework for Sampling Technique Selection in Financial Fraud Detection: Experimental Validation of SMOTE and ADASYN
    Sangita Mishra, Neelamadhab Padhy, Rasmita Panigrahi, Dasaradha Arangi, Pradeep Kumar Mahapatro, Asish Kumar Patnaik
    Ocit 2025 Proceedings 23rd Oits International Conference on Information Technology, 2025
  • Enhanced Health Care System with Chatbot and Voicebot Using Deep Learning
    Pradeep Kumar Mahapatro, Karakavalasa Sreedhar, Savirigana Inusha, Konkena Niteeshkumar, Ankadala Mahesh Babu, Reshi Pulla
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
  • Language Prediction and Text Emotion Analysis by Utilizing Machine Learning Concepts and Algorithms
    Jyotiram Manik, Neelamadhab Padhy, Jogabrata Manik, Santosh Kumar Panda, Pradeep Kumar Mahapatro, Dasaradha Arangi
    Ocit 2025 Proceedings 23rd Oits International Conference on Information Technology, 2025
  • Anomaly Detection in High-Dimensional Data Streams Using Machine Learning and Deep Learning Classifiers
    Chiranjeevi Jami, Kumar Sekhar Yetcherla, Thamira Pooja, Gundabala Sandhya Rani, Balaga Siva Srinivas, Pradeep Kumar Mahapatro
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
  • Fuel Consumption Prediction Using Machine Learning: A Data-Driven Approach
    Biswajit Mahakhud, Pedina Sasi Kiran, Neelamadhab Padhy, Tapan Kumar Behera, Tirupatisahu, Pradeep Kumar Mahapatro, Dasaradha Arangi
    2025 International Conference on Next Generation of Green Information and Emerging Technologies Giet 2025, 2025
  • Reviewing the Landscape: Component-Based Software Engineering Practices and Challenges
    Pradeep Kumar Mahapatro, Neelamadhab Padhy
    Esic 2024 4th International Conference on Emerging Systems and Intelligent Computing Proceedings, 2024
  • Comparative Analysis of Optimization Techniques and Hybrid Classification Models for Enhanced Soil Fertility Prediction
    Pradeep Kumar Mahapatro, Rasmita Panigrahi, Neelamadhab Padhy Gandhi
    2nd International Conference on Signal Processing Communication Power and Embedded Systems Scopes 2024, 2024
  • Integrated Internet of Things and Artificial Intelligence System for Real-Time Multi-Nutrient Water Quality Analysis in Agriculture †
    Pradeep Kumar Mahapatro, Rasmita Panigrahi, Neelamadhab Padhy
    Engineering Proceedings, 2024

RECENT SCHOLAR PUBLICATIONS

  • An In-Depth Comparative Analysis of Machine Learning Models for Soil Fertility Prediction
    H Behera, B Nayak, R Kumar Gouda, N Padhy, R Panigrahi, ...
    Engineering Proceedings 124 (1), 116 , 2026
    2026
  • Secure and Collaborative Crop Disease Prediction with Federated Deep Learning: Safeguarding Data Sovereignty in Agriculture
    DA Sadananda Behera, Neelamadhab Padhy, Rasmita Panigrahi, Pradeep Kumar ...
    Artificial Intelligence in Context of Digital Sovereignty 1, 20 , 2026
    2026
  • Comparative Evaluation of Machine Learning Classifiers for Breast Cancer Diagnosis: A Comprehensive Statistical Analysis
    SS Das, A Mahaprasad, N Padhy, S Misra, R Panigrahi, PK Mahapatro, ...
    Engineering Proceedings 124 (1), 35 , 2026
    2026
    Citations: 1
  • Comparative Evaluation of Machine Learning Classifiers for Breast Cancer Diagnosis: A Comprehensive Statistical Analysis
    DA Sambit Subhankar Das, Atal Mahaprasad, Neelamadhab Padhy,Srikant Misra ...
    MDPI , 2026
    2026
  • Crop Yield Prediction Using Federated Learning: A Privacy-Preserving Approach for Decentralized Agriculture Data
    S Pujapanda, S Mishra, D Mahapatra, G Sahoo, N Padhy, PK Mahapatro
    2026 International Conference on Emerging Systems and Intelligent Computing … , 2026
    2026
  • Does Sampling Improve the Precision-Recall Trade-off in Fraud Detection Systems? An Empirical Study Using Ensemble Machine Learning Models
    CS Dash, N Padhy, R Panigrahi, AK Patnaik, PK Mahapatro, D Arangi
    2026 International Conference on Emerging Systems and Intelligent Computing … , 2026
    2026
  • Artificial Intelligence(EditionFirst)
    MCSK Mr.Dasaradha Arangi, Dr. M. V. B. Chandrasekhar, Dr.B.Kiran Kumar, Mr.K ...
    2026
  • Language Prediction and Text Emotion Analysis by Utilizing Machine Learning Concepts and Algorithms
    J Manik, N Padhy, J Manik, SK Panda, PK Mahapatro, D Arangi
    2025 OITS International Conference on Information Technology (OCIT), 240-245 , 2025
    2025
  • Enhancing Classification Performance in Health Condition Prediction: A Comparative Study of Machine Learning Models with SMOTE and Sensitivity Trade-Off Analysis
    R Panigrahi, N Padhy, AK Patnaik, A Patnaik, D Arangi, PK Mahapatro
    2025 OITS International Conference on Information Technology (OCIT), 209-214 , 2025
    2025
  • Mathematical Framework for Sampling Technique Selection in Financial Fraud Detection: Experimental Validation of SMOTE and ADASYN
    S Mishra, N Padhy, R Panigrahi, D Arangi, PK Mahapatro, AK Patnaik
    2025 OITS International Conference on Information Technology (OCIT), 1-6 , 2025
    2025
  • VLSI-Based Abnormal Heartbeat Detection via Knowledge-Infused Dynamic Spiking Graph Neural Network Optimized with Wader Hunt Algorithm
    MPKM Dr. Aditya Mandloi, Mr. Kush Soni, Dr. Vinita Tomar , Smt. Gosavi ...
    2025
  • Enhancing Agricultural Productivity with Machine Learning-Based Soil Fertility Prediction
    H Behera, B Nayak, RK Gouda, N Padhy, PK Mahapatro
    MDPI , 2025
    2025
  • Improving Cross-Project Defect Prediction Through Feature Selection and Model Optimization
    U Kiran, N Padhy, R Panigrahi, D Arangi, PK Mahapatro
    2025 International Conference on Next Generation of Green Information and … , 2025
    2025
  • Fuel Consumption Prediction Using Machine Learning: A Data-Driven Approach
    B Mahakhud, PS Kiran, N Padhy, TK Behera, Tirupatisahu, PK Mahapatro
    2025 International Conference on Next Generation of Green Information and … , 2025
    2025
  • Software cost estimation using AI and Federated Learning
    T Sahu, N Padhy, R Panigrahi, PK Mahapatro, D Arangi, SP Patro
    2025 IEEE 3rd International Symposium on Sustainable Energy, Signal … , 2025
    2025
  • 5G and Beyond Communication
    MPKM Dr. Shambhu Sharan Srivastava, Dr. S.V.Ramanan, Mr. Balaram Das, Mr. D ...
    2025
  • An IoT Based Intelligent and Real-Time Parking Management System
    SP Patro, R Gantayet, PK Mahapatro, D Arangi, N Padhy
    International Conference on Intelligent Computing and Communication, 199-206 , 2025
    2025
  • Enhanced health care system with chatbot and voicebot using deep learning
    PK Mahapatro, K Sreedhar, S Inusha, K Niteeshkumar, AM Babu, R Pulla
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-5 , 2025
    2025
    Citations: 1
  • Cartpole Balancer Using Deep Q-Network
    PK Mahapatro, P Yaswanth, C Meghana, T Rushanth, P Somesh
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-5 , 2025
    2025
    Citations: 1
  • Anomaly Detection in High-Dimensional Data Streams Using Machine Learning and Deep Learning Classifiers
    C Jami, KS Yetcherla, T Pooja, GS Rani, BS Srinivas, PK Mahapatro
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-5 , 2025
    2025

MOST CITED SCHOLAR PUBLICATIONS

  • Integrated Internet of Things and artificial intelligence system for real-time multi-nutrient water quality analysis in agriculture
    PK Mahapatro, R Panigrahi, N Padhy
    Engineering Proceedings 82 (1), 72 , 2024
    2024
    Citations: 12
  • Reviewing the Landscape: Component-Based Software Engineering Practices and Challenges
    PK Mahapatro, N Padhy
    2024 International Conference on Emerging Systems and Intelligent Computing … , 2024
    2024
    Citations: 7
  • EFFECT OF VOLUME FRACTION ALONG WITH CONCENTRATION PARAMETER IN THE DUSTY INCOMPRESSIBLE FLUID
    PKMDKD B. K. Rath
    Advances and Applications in Fluid Mechanics 20 (1), 117-125 , 2017
    2017
    Citations: 3
  • Exploring Chili Plant Health: A Comprehensive Study Using IoT Sensors and Machine Learning Classifiers
    KK Sahu, VK Swain, R Panigrahi, N Padhy, PK Mahapatro, D Arangi
    Doctoral Symposium on Computational Intelligence, 539-549 , 2025
    2025
    Citations: 2
  • Integrated IoT and AI Systems for Real-Time Multi-Nutrient Water Quality Analysis in Agriculture
    PK Mohapatra, R Panigrahi, N Padhai
    Eng. Proc , 2024
    2024
    Citations: 2
  • Comparative Evaluation of Machine Learning Classifiers for Breast Cancer Diagnosis: A Comprehensive Statistical Analysis
    SS Das, A Mahaprasad, N Padhy, S Misra, R Panigrahi, PK Mahapatro, ...
    Engineering Proceedings 124 (1), 35 , 2026
    2026
    Citations: 1
  • Enhanced health care system with chatbot and voicebot using deep learning
    PK Mahapatro, K Sreedhar, S Inusha, K Niteeshkumar, AM Babu, R Pulla
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-5 , 2025
    2025
    Citations: 1
  • Cartpole Balancer Using Deep Q-Network
    PK Mahapatro, P Yaswanth, C Meghana, T Rushanth, P Somesh
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-5 , 2025
    2025
    Citations: 1
  • Optimizing Crop Recommendation through Stacking and Feature Analysis of Ensemble Classifiers
    PK Mahapatro, R Panigrahi, N Padhy
    2025 International Conference on Emerging Systems and Intelligent Computing … , 2025
    2025
    Citations: 1
  • Performance Improvement of Machine Learning Algorithms Through Information-Theoretic Class Based Feature Multicorrelation Enabled Feature Selection for Cervical Cancer Prediction
    K Sangeeta, S Kisan, KK Kumar, PK Mahapatro
    International Conference on Computing, Communication and Learning, 165-180 , 2024
    2024
    Citations: 1
  • An In-Depth Comparative Analysis of Machine Learning Models for Soil Fertility Prediction
    H Behera, B Nayak, R Kumar Gouda, N Padhy, R Panigrahi, ...
    Engineering Proceedings 124 (1), 116 , 2026
    2026
  • Secure and Collaborative Crop Disease Prediction with Federated Deep Learning: Safeguarding Data Sovereignty in Agriculture
    DA Sadananda Behera, Neelamadhab Padhy, Rasmita Panigrahi, Pradeep Kumar ...
    Artificial Intelligence in Context of Digital Sovereignty 1, 20 , 2026
    2026
  • Comparative Evaluation of Machine Learning Classifiers for Breast Cancer Diagnosis: A Comprehensive Statistical Analysis
    DA Sambit Subhankar Das, Atal Mahaprasad, Neelamadhab Padhy,Srikant Misra ...
    MDPI , 2026
    2026
  • Crop Yield Prediction Using Federated Learning: A Privacy-Preserving Approach for Decentralized Agriculture Data
    S Pujapanda, S Mishra, D Mahapatra, G Sahoo, N Padhy, PK Mahapatro
    2026 International Conference on Emerging Systems and Intelligent Computing … , 2026
    2026
  • Does Sampling Improve the Precision-Recall Trade-off in Fraud Detection Systems? An Empirical Study Using Ensemble Machine Learning Models
    CS Dash, N Padhy, R Panigrahi, AK Patnaik, PK Mahapatro, D Arangi
    2026 International Conference on Emerging Systems and Intelligent Computing … , 2026
    2026
  • Artificial Intelligence(EditionFirst)
    MCSK Mr.Dasaradha Arangi, Dr. M. V. B. Chandrasekhar, Dr.B.Kiran Kumar, Mr.K ...
    2026
  • Language Prediction and Text Emotion Analysis by Utilizing Machine Learning Concepts and Algorithms
    J Manik, N Padhy, J Manik, SK Panda, PK Mahapatro, D Arangi
    2025 OITS International Conference on Information Technology (OCIT), 240-245 , 2025
    2025
  • Enhancing Classification Performance in Health Condition Prediction: A Comparative Study of Machine Learning Models with SMOTE and Sensitivity Trade-Off Analysis
    R Panigrahi, N Padhy, AK Patnaik, A Patnaik, D Arangi, PK Mahapatro
    2025 OITS International Conference on Information Technology (OCIT), 209-214 , 2025
    2025
  • Mathematical Framework for Sampling Technique Selection in Financial Fraud Detection: Experimental Validation of SMOTE and ADASYN
    S Mishra, N Padhy, R Panigrahi, D Arangi, PK Mahapatro, AK Patnaik
    2025 OITS International Conference on Information Technology (OCIT), 1-6 , 2025
    2025
  • VLSI-Based Abnormal Heartbeat Detection via Knowledge-Infused Dynamic Spiking Graph Neural Network Optimized with Wader Hunt Algorithm
    MPKM Dr. Aditya Mandloi, Mr. Kush Soni, Dr. Vinita Tomar , Smt. Gosavi ...
    2025