Mr. Sibo Prasad Patro received his MCA in 2012 from Sambalpur University, Odisha and his M.Tech (Computer Science and Engineering) in 2014 from BPUT, Raurkela, Odisha. He is currently pursuing his Ph.D in Computer Science and Engineering at GIET University, Gunupur, Odisha under the supervision of Dr. NeelamadhabPadhy and Dr. Rahul Deo Sah. He has published several SCI and Scopus indexing journals. He has also published few conference papers. He has more than 17 years of teaching experience. His research interest includes data mining, machine learning, deep learning, IoT and their application to engineering. Currently he is working as Assistant Professor in the department of Computer Science and Engineering, GIET University, Gunupur. He has received a best paper presentation award in ICCSEA-2020 an International Conference organized by GIET University, Gunupur.
IoT-Based Tomato Leaf Disease Prediction Using Deep Learning Techniques Ayushman Panigrahy, Sumatra Kumar Panda, Sibo Prasad Patro 2025 International Conference on Next Generation of Green Information and Emerging Technologies Giet 2025, 2025 Precision agriculture could be greatly enhanced by the combination of deep learning and the Internet of Things (IoT), specifically targeting leaf disease diagnosis. These advanced technologies offering a great promise for advancing precision agriculture, particularly in disease forecasting. Plant diseases impact the safety and availability of plants for human and animal use. They also pose a hazard to food safety, which lowers crop production and quality and decreases food availability and access. Innovative disease detection techniques are required in order to lower plant losses brought on by disease. Conventional agricultural disease detection techniques frequently depend on human inspection and professional intervention, which can be labor-intensive, time-taking and prone to mistakes. With the advent of smart farming, disease prediction can be automated and provides a preventive strategy to crop health management. This study aims to develop a DL-based model for early identification of diseases in tomato leaves. Through an IoT architecture system farmers obtain instant disease predictions which help minimize agricultural losses. Initially, through the help of a Raspberry Pi camera, the leaf images are collected, and they are transmitted to Raspberry Pi for processing and analyzing using DL models, specifically MobileNet-V2, Resnet50, VGG16, MobileNet-V2, EfficientNet-B0 and custom builded CNN for tomato leave disease detection. The proposed integrated IoT-based system and DL significantly improves the accuracy of disease prediction of a tomato plant. The batch normalization, Adam optimizer and L2 used for regularization, using such technique, the model produced 98.35% of accuracy for tomato leaf disease detection. The model proved great accuracy in identifying a range of plant diseases, allowing for early intervention and lowering the need for chemical pesticides.
Prediction and Monitoring of Human Being Mental Health Using Machine Learning Classifiers Rasmita Gantayet, Sibo Prsad Patro, Neelamadhab Padhy 2025 International Conference on Emerging Trends in Networks and Computer Communications Etncc 2025 Proceedings, 2025 Nowadays, Mental health disorder is a very common and growing concern worldwide, affecting millions of people as well as the environment. Inaccurate diagnoses are a major cause of traditional method failure. Early prediction systems provide for prompt action, which may lessen long-term impacts. By collecting the data from wearable sensors, selfreported questionnaires, and electronic health records, machine learning offers techniques for forecasting mental health outcomes. Using clinical, behavioral, and demographic data, this project will create and evaluate a machine learning (ML) model to predict anxiety, stress, and depression. The model was evaluated using AdaBoost, Logistic regression, decision trees, random forests, and an additional tree classifier. In order to enhance accuracy, we tested stacking and boosting techniques using Python's scikit-learn grid Cross-validation and search techniques for hyperparameter optimization. The model accuracy is calculated using AUC-ROC, F1-score, recall, accuracy, and precision. Stacking coupled on base learners' strengths for improved performance, while focusing on challenging cases to improve accuracy.
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 Accurate software size and estimation are pivotal for preparing budgets, bidding on projects, and establishing key performance indicators (KPIs) during the early stages of software development, ultimately influencing project success. According to the Project Management Institute (PMI), managing the triple constraints of scope, cost, and time is crucial for software projects. Historically, vendors and companies have relied on various estimation methods, including sharing past estimates with a central server for model training and evaluation. However, these estimates often remain confidential on local servers. Objective: To overcome this challenge, we propose implementing a federated learning framework to harness artificial intelligence (AI) while ensuring the privacy of vendors' historical estimates. This framework allows sensitive data to remain on local servers without being transferred to a central server. Additionally, we utilize machine learning techniques to predict software costs accurately. Material/Methods: In this innovative framework, machine learning models are trained and evaluated on local servers, which share encrypted weights, biases, and accuracy scores with a central server. The iterative process continues until the model achieves the necessary accuracy. To predict costs, inputs such as computer language, methodology, domain, duration, delivery rate, size, and cost per hour are provided to the central server. The central server then predicts the costs based on these inputs, leveraging the aggregated weights and biases received from the local servers. This process employs a federated averaging algorithm for model aggregation, where the global model is updated by averaging the updates from local models.
A Deep Learning Approach for Enhancing Cardiovascular Disease Prediction Using ECG Data Aparna Baboo, Sibo Prasad Patro, Sachikanta Dash 2nd International Conference on Signal Processing Communication Power and Embedded Systems Scopes 2024, 2024 Cardiovascular diseases (CVD) are a leading cause of death due to blocked arteries that impact blood circulation. Early medical detection can identify CVD, but predicting future risks remains a challenge. In this research we have used three model ResNet101, VGG16, InceptionV3 for CVD prediction using ECG image data. The model finds prediction from three deep learning algorithm and we compare their predictions and find the ResNet101 model with best performance. ECG arrhythmia dataset, downloaded from Kaggle repository, contains classified image data divided into training (80%) and testing (20%) sets. The model captures patterns in these images to detect CVD. ResNet101, the best model obtained 99.94% accuracy, 99.94% Fl score, 99.94%, precision, 99.94% recall. outperforming individual models and traditional methods. This study highlights the efficiency of deep learning in medical applications, providing a reliable and rapid tool for CVD prediction. Future research will focus on improving accuracy with additional deep learning techniques.
IoT based Smart Parking System: A Proposed Algorithm and Model Sibo Prasad Patro, Padmaja Patel, Murali Krishna Senapaty, Neelamadhab Padhy, Rahul Deo Sah 2020 International Conference on Computer Science Engineering and Applications Iccsea 2020, 2020
IoT-Based Tomato Leaf Disease Prediction Using Deep Learning Techniques SK Panda, SP Patro 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
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
Evaluating Regression Models for Student Grade Prediction with a Focus on Interpretability and Accuracy M Tompala, N Padhy, R Panigrahi, SP Patro International Conference on Intelligent Computing and Communication, 296-305 , 2025 2025
A Deep Learning Approach for Enhancing Cardiovascular Disease Prediction Using ECG Data A Baboo, SP Patro, S Dash 2024 2nd International Conference on Signal Processing, Communication, Power … , 2025 2025 Citations: 11
Cardiac Thermodynamic Optimization Through Personalized Activity Recommendations V Sivani, SP Patro, P Potluri International Conference on Machine Learning, IoT and Big Data, 332-341 , 2025 2025
Revolutionizing Agricultural Health: Deep Learning for Crop Disease Diagnosis PR Parida, SP Patro, N Padhy 2024 Third International Conference on Trends in Electrical, Electronics … , 2025 2025
Enhancing Mental Disorder Prediction Using Machine Learning and Boosting Algorithms R Gantayet, SP Patro, N Padhy Doctoral Symposium on Computational Intelligence, 105-114 , 2025 2025
Deepfake Image Detection Using Hybrid Deep Learning Techniques SP Barik, SP Patro, N Padhy Doctoral Symposium on Computational Intelligence, 115-123 , 2025 2025
Analysis of Cardiovascular Disease Prediction Using Various Machine Learning and Deep Learning Algorithms SP Patro, N Padhy Intelligent Technologies: Concepts, Applications, and Future Directions … , 2024 2024
Integration of IoT and Machine Learning for Real-Time Monitoring and Control of Heart Disease Patients N Padhy, R Panigrahi, SP Patro, VK Swain, KK Sahu Proceedings 105 (1), 32 , 2024 2024 Citations: 2
A secure IoT-cloud based remote health monitoring for heart disease prediction using machine learning and deep learning techniques SP Patro, N Padhy Engineering Proceedings 56 (1), 241 , 2023 2023 Citations: 10
A secure remote health monitoring for heart disease prediction using machine learning and deep learning techniques in explainable artificial intelligence framework SP Patro, N Padhy Engineering Proceedings 58 (1), 78 , 2023 2023 Citations: 16
A Secure Remote Health Monitoring for Heart Disease Prediction using machine learning and deep learning techniques in XAI framework SP PATRO, N Padhy Chem. Proc 56 , 2023 2023
Comparative Analysis Using Data Mining Techniques to Predict the Air Quality and Their Impact on Environment RD Sah, N Padhy, N Salimath, SP Patro, SJ Abbas, RR Dutta Proceedings of Fourth International Conference on Computer and Communication … , 2023 2023
Anticipation of Heart Disease Using Improved Optimization Techniques S Prasad, N Padhy¹, RD Sah Computing, Communication and Learning: First International Conference … , 2023 2023
Classification model for heart disease prediction using correlation and feature selection techniques SP Patro, N Padhy, RD Sah 2022 OITS International Conference on Information Technology (OCIT), 29-34 , 2022 2022 Citations: 2
Anticipation of heart disease using improved optimization techniques SP Patro, N Padhy, RD Sah International Conference on Computing, Communication and Learning, 91-102 , 2022 2022 Citations: 2
A Road Map for Classification of Heart Disease Using Machine Learning Classifier SP Patro, N Padhy, RD Sah Next Generation of Internet of Things: Proceedings of ICNGIoT 2022, 687-702 , 2022 2022 Citations: 2
Heart Rate Monitoring Using IoT and AI for Aged Person: A Survey SP Patro, N Padhy, RD Sah The Role of IoT and Blockchain, 39-59 , 2022 2022 Citations: 1
MOST CITED SCHOLAR PUBLICATIONS
Heart disease prediction by using novel optimization algorithm: A supervised learning prospective SP Patro, GS Nayak, N Padhy Informatics in Medicine Unlocked 26, 100696 , 2021 2021.0 Citations: 138
Ambient assisted living predictive model for cardiovascular disease prediction using supervised learning SP Patro, N Padhy, D Chiranjevi Evolutionary intelligence 14 (2), 941-969 , 2021 2021.0 Citations: 76
Security issues over E-commerce and their solutions SP Patro, N Padhy, R Panigrahi Int. J. of Advanced Research in Computer and Communication Engineering 5 (12) , 2016 2016.0 Citations: 27
IoT based smart parking system: a proposed algorithm and model SP Patro, P Patel, MK Senapaty, N Padhy, RD Sah 2020 International Conference on Computer Science, Engineering and … , 2020 2020.0 Citations: 23
A secure remote health monitoring for heart disease prediction using machine learning and deep learning techniques in explainable artificial intelligence framework SP Patro, N Padhy Engineering Proceedings 58 (1), 78 , 2023 2023.0 Citations: 16
An improved ensemble learning approach for the prediction of cardiovascular disease using majority voting prediction SP Patro, N Padhy, RD Sah International Journal of Modelling, Identification and Control 41 (1-2), 68-86 , 2022 2022.0 Citations: 12
A Deep Learning Approach for Enhancing Cardiovascular Disease Prediction Using ECG Data A Baboo, SP Patro, S Dash 2024 2nd International Conference on Signal Processing, Communication, Power … , 2025 2025.0 Citations: 11
A secure IoT-cloud based remote health monitoring for heart disease prediction using machine learning and deep learning techniques SP Patro, N Padhy Engineering Proceedings 56 (1), 241 , 2023 2023.0 Citations: 10
An ensemble approach for prediction of cardiovascular disease using meta classifier boosting algorithms SP Patro, N Padhy, RD Sah International Journal of Data Warehousing and Mining (IJDWM) 18 (1), 1-29 , 2022 2022.0 Citations: 9
An rhmiot framework for cardiovascular disease prediction and severity level using machine learning and deep learning algorithms SP Patro, N Padhy International Journal of Ambient Computing and Intelligence (IJACI) 13 (1), 1-37 , 2022 2022.0 Citations: 5
Diabetics Patients Analysis Using Deep Learning and Gradient Boosted Trees RD Sah, SP Patro, N Padhy, N Salimath 2021 8th International Conference on Computing for Sustainable Global … , 2021 2021.0 Citations: 5
Heart disease prediction by using novel optimization algorithm: A supervised learning prospective. Informatics in Medicine Unlocked, 26, 100696 SP Patro, GS Nayak, N Padhy Elsevier , 2021 2021.0 Citations: 5
Ambient assisted living predictive model for cardiovascular disease prediction using supervised learning. Evol. Intell. 14, 1–29 (2021) SP Patro, N Padhy, D Chiranjevi Citations: 5
A Cyclic Scheduling for Load Balancing on Linux in Multi-core Architecture N Padhy, A Panda, SP Patro Smart Intelligent Computing and Applications: Proceedings of the Third … , 2019 2019.0 Citations: 3
Integration of IoT and Machine Learning for Real-Time Monitoring and Control of Heart Disease Patients N Padhy, R Panigrahi, SP Patro, VK Swain, KK Sahu Proceedings 105 (1), 32 , 2024 2024.0 Citations: 2
Classification model for heart disease prediction using correlation and feature selection techniques SP Patro, N Padhy, RD Sah 2022 OITS International Conference on Information Technology (OCIT), 29-34 , 2022 2022.0 Citations: 2
Anticipation of heart disease using improved optimization techniques SP Patro, N Padhy, RD Sah International Conference on Computing, Communication and Learning, 91-102 , 2022 2022.0 Citations: 2
A Road Map for Classification of Heart Disease Using Machine Learning Classifier SP Patro, N Padhy, RD Sah Next Generation of Internet of Things: Proceedings of ICNGIoT 2022, 687-702 , 2022 2022.0 Citations: 2
Analysis of Information Security through Crypto - Stenography with Reference to E - Cipher Methods SP Patro International Journal of Advanced Research in Computer and Communication … , 2017 2017.0 Citations: 2
Heart Rate Monitoring Using IoT and AI for Aged Person: A Survey SP Patro, N Padhy, RD Sah The Role of IoT and Blockchain, 39-59 , 2022 2022.0 Citations: 1
