Investigations on Welding Technology help ful for Society.
Applications Invited
Research On Variants to Control Viruses Helpfull For the Society in the World.
Applications Invited
16
Scopus Publications
Scopus Publications
An Explainable AI Approach to Alzheimer's Prediction using Ensemble Methods on Imbalanced Data Kande Archana, Mahesh Karre, K. Bharath Kumar, K. Balamurugan, Madhavi Karumudi, Bazani Shaik 2025 2nd Asia Pacific Conference on Innovation in Technology Apcit 2025, 2025 Alzheimer’s disease (AD) is a progressive neurodegenerative condition that necessitates early detection to enable effective interventions and slow its progression. This research presents an explainable machine learning approach using ensemble classifiers to predict Alzheimer’s risk based on demographic, clinical, cognitive, and lifestyle factors. Mutual Information (MI) was employed for feature selection, and models using Extra Trees, XGBoost, and AdaBoost classifiers were developed. The findings of this study reveal that ensemble methods, particularly XGBoost, significantly outperform individual models in predicting Alzheimer’s disease risk. The dataset, sourced from Kaggle, includes 2,149 patient records with 33 input features. After comprehensive preprocessing, which involved managing outliers, scaling, and oversampling for minority classes, the data was split into training and testing sets in an 80:20 ratio. Performance was evaluated using metrics such as accuracy, precision, recall, F1 score, and ROC-AUC. Among the models, XGBoost achieved the highest performance, with a test accuracy of 92.1%, a recall of 90.0%, and an ROC-AUC score of 96.7%, with AdaBoost and Extra Trees closely following. The confusion matrix indicates that XGBoost had the most true positives (271) and the fewest false negatives (30), highlighting its superior reliability in identifying positive AD cases. To enhance model transparency, SHAP (SHapley Additive Explanations) was used to analyze feature importance. SHAP summary and bar plots identified the top predictors. Overall, this study demonstrates the effectiveness of ensemble classifiers, especially XGBoost, in predicting Alzheimer’s and emphasizes the importance of Explainable AI for clinical trust. The use of SHAP improves interpretability, making the proposed system a practical and transparent tool for healthcare professionals aiming for early detection of Alzheimer’s risk.
An Explainable AI Approach to Heart Disease Prediction with Ensemble Methods on Imbalanced Data Mohd Arshad, V. R. Vimal, A. Hyils Sharon Magdalene, Machanuru Suresh Babu, Mohanraj S, Bazani Shaik 2025 3rd World Conference on Communication and Computing Wconf 2025, 2025 Cardiovascular diseases (CVDs) rank among the leading causes of death globally, accounting for over 17.9 million fatalities annually. Timely diagnosis and accurate prediction of heart conditions are crucial for reducing mortality rates and improving patient outcomes. This research presents an explainable artificial intelligence (XAI) framework that employs ensemble learning methods to predict heart disease from datasets with imbalanced classes. The study incorporates advanced preprocessing techniques, including outlier management, Box-Cox transformation, and SMOTE-based oversampling. Three ensemble classifiers—XGBoost, Extra Trees, and AdaBoost—were trained and fine-tuned using GridSearchCV. Evaluation metrics such as accuracy, precision, recall, F1-score, and AUC-ROC indicated that both XGBoost and Extra Trees achieved perfect scores (100%) across all measures, while AdaBoost showed a slightly lower test accuracy of 91.5% and an AUC of 0.98. Analysis of the confusion matrix revealed that XGBoost and Extra Trees had no misclassifications, demonstrating perfect sensitivity and specificity. Additionally, SHAP visualizations were used to interpret the model predictions, highlighting features like Chest Pain, Ca, and Thal as having the most significant impact on the results. Overall, the Extra Trees model was favored for its high accuracy and reduced computational demands, emphasizing the effectiveness of explainable ensemble approaches in enhancing early detection and building clinical confidence in AI-based heart disease prediction.
Reinforcement Learning for Dynamic Power Management in Embedded Systems Bhawani Sankar Panigrahi, Balachandra Pattanaik, Ojasvi Pattanaik, S. B G Tilak Babu, Pavithra G, Bazani Shaik 5th International Conference on Recent Trends in Computer Science and Technology Icrtcst 2024 Proceedings, 2024 Itaddresses the challenges that are associated with dynamic power management in embedded systems by utilizing techniques that are derived from the discipline of reinforcement learning (RL). Given the increasing complexity of embedded systems and the need for solutions that are efficient for energy consumption, RL is a potential technology that can dynamically optimize power utilization. This is particularly pertinent in light of the requirement for solutions that are efficient for energy consumption. The dynamic workload fluctuations that are inherent in embedded systems are taken into consideration in this research, which studies the integration of RL algorithms to control power levels in real time in an adaptive manner. This research also takes into account the variable workloads that are endemic to embedded systems. To evaluate the efficacy of RL-based dynamic power management strategies in comparison to traditional methods, with a specific emphasis on the potential for enhanced energy efficiency and system responsiveness, the goal of this is to evaluate the effectiveness of these strategies. The findings not only contribute to the improvement of understanding of the use of reinforcement learning in the setting of embedded systems, but they also provide insights into the utility of RL in meeting the evolving power management requirements in contemporary computing environments.
Deep Learning Techniques for Fault Detection in Industrial Machinery Bhawani Sankar Panigrahi, Thiyagarajan T, M. Tamilselvi, S. B G Tilak Babu, Pavithra G, Bazani Shaik 5th International Conference on Recent Trends in Computer Science and Technology Icrtcst 2024 Proceedings, 2024 The use of deep learning techniques for the purpose of improving fault detection in industrial machinery. It is of the utmost importance to have defect detection mechanisms that are both reliable and effective, since the complexity of industrial processes continues to increase. In this paper, the implementation of deep learning algorithms is investigated. These algorithms make use of neural networks to understand complex patterns and anomalies that are present in data coming from machinery. There are many different models that are being researched to see whether or not they are effective in detecting defects at early stages, limiting downtime, and eliminating costly interruptions. These models include convolutional neural networks (CNNs) and recurrent neural networks (RNNs). For the purpose of this , the performance of various methodologies is evaluated over a wide range of industrial situations, taking into consideration issues such as the variability of sensor data and noise. The findings demonstrate the promise of deep learning as a significant tool for enhancing defect detection skills, thereby paving the way for industrial equipment systems that are more reliable and resilient.
AI-Driven Drug Discovery: Computational Methods and Applications Gali Nageswara Rao, C. Gunasundari, S. B G Tilak Babu, Pavithra G, Vijay Kumar Dwivedi, Bazani Shaik 5th International Conference on Recent Trends in Computer Science and Technology Icrtcst 2024 Proceedings, 2024 Artificial intelligence (AI) and its revolutionary effects on the medication development process. The project explores the potential integration of artificial intelligence tools into the different phases of drug development using state-of-the-art computational methods. This project’s overarching goal is to assess how well target selection, lead compound optimization, and toxicity prediction are served by data analytics, predictive modelling, and machine learning algorithms. This research aims to analyze contemporary uses and breakthroughs in artificial intelligence (AI) to better understand how it improves drug discovery pipeline efficiency and accuracy. Beyond this, it delves into the challenges and opportunities of AI-driven drug discovery, with an emphasis on finding fresh approaches to old biomedical problems. The dynamic environment at the crossroads of AI and pharmaceutical sciences is better-understood thanks to this comprehensive analysis. It opens the door to more efficient drug development processes and the development of new therapeutic approaches.
Innovation Management Driven by AI: Approaches for Long-Term Competitive Advantage Y. P. Sai Lakshmi, Somasekhar Donthu, Y Manohar Reddy, Revathi V, Bazani Shaik, Rajeev Sobti Proceedings of International Conference on Communication Computer Sciences and Engineering Ic3se 2024, 2024 This paper explores the nuances of AI-driven business models, providing a comprehensive knowledge of their inception, evolution, and influence on conventional business approaches in a period where artificial intelligence (AI) is transforming business concepts. This scholarly inquiry aims to examine how artificial intelligence is changing business models, with a focus on the connection among advances in technology and business planning. The report highlights the major obstacles to AI adoption, including moral conundrums and technological difficulties, but it also reveals the enormous potential benefits of AI for corporate expansion and competitive benefits. The conclusion of the study emphasises the significance of ethical AI practices and suggests a balanced approach to AI integration, ongoing adaptation, and a collaboration between human perceptions and AI capacities. It encourages company executives to use AI as a catalyst for creative and sustainable corporate success, rather than just as a technical instrument. By offering a fundamental structure for next studies and real-world applications in AI-driven business innovation, this academic work makes a substantial contribution to the conversation around artificial intelligence in business.
AI-Driven Circuit Optimization for Energy-Efficient Electronics Design P. Horsley Solomon, Balachandra Pattanaik, Ojasvi Pattanaik, Pavithra G, D. Elamvazhudhi, Bazani Shaik 5th International Conference on Recent Trends in Computer Science and Technology Icrtcst 2024 Proceedings, 2024 The process of enhancing electronic circuits in order to improve energy efficiency is currently being made more efficient with the application of artificial intelligence (AI). In this day and age, where energy consumption is a big problem, the exploitation of techniques driven by artificial intelligence has shown to be an indispensable tool in the construction of electronic devices that reduce power consumption without sacrificing performance. This is achieved through the deployment of ways that are driven by artificial intelligence. Within the scope of this, the application of machine learning techniques is being researched for the purpose of analyzing and modifying circuit designs. There are several other variables that are taken into consideration, such as voltage, current, and the specifications of the components. The purpose of this research is to make a significant contribution to the development of electronic systems that are efficient in terms of energy consumption by utilizing circuit optimization that is driven by artificial intelligence capabilities. Because of this, the research will be able to satisfy the growing need for technology that is favourable to the environment. These discoveries not only offer valuable insights into the synergy that exists between artificial intelligence and the design of electronics, but they also pave the way for future improvements in technology that are aware of the amount of energy that is being consumed.
Deep Learning Techniques for Human Resource Management Optimization Pratyaksha Ranawat, Manish Kumar, A Karthik, Asha V, Amandeep Nagpal, Bazani Shaik Proceedings of International Conference on Communication Computer Sciences and Engineering Ic3se 2024, 2024 Because deep learning and machine learning (ML) techniques have the potential to totally change how firms manage their human capital, there has been a lot of interest in developing HRM procedures that use these techniques. Strong DSS (Decision Support System) technology must be incorporated into the HRM (Human Resource Management) profession in order to make judgements that are effective in today's competitive environment. This study focuses on the problem of prediction, decision making, prediction, and testing assistance in a HRM system. The paper discusses a creative decision support system for HR procedures. Machine learning and deep learning techniques have been offered as fundamental instruments for tracking various HR indicators in the systems developed and implemented analytical process. The description of the suggested methodology and a discussion of a outcomes from the experiments are included in the paper.
Deep Learning-Based Image Recognition for Electronic Components Identification Bhawani Sankar Panigrahi, Angelina Royappa, Dr Sandeep Monga, H. Geetha, Pavithra G, Bazani Shaik 5th International Conference on Recent Trends in Computer Science and Technology Icrtcst 2024 Proceedings, 2024 The use of deep learning techniques in the field of picture recognition for the purpose of identifying electronic components. Because of the growing complexity and variety of electronic devices, it is essential for manufacturing, maintenance, and quality control to be able to identify components in a way that is both efficient and accurate. This is accomplished through the utilization of deep learning algorithms, the utilization of convolutional neural networks (CNNs), and advanced image processing techniques in order to improve recognition skills. The suggested model displays higher accuracy in differentiating diverse electronic components, overcoming problems such as differences in size, orientation, and lighting conditions. Moreover, the model succeeds in overcoming these challenges effectively. Based on the findings, it appears that deep learning-based image recognition provides a strong solution for automating the identification process in electronic component analysis. This, in turn, contributes to better efficiency and reliability in the electronics industry. This research makes a contribution to the expanding field of computer vision and highlights the potential of deep learning in the advancement of electrical component identification systems.
