B.E. in Computer Science and Engineering, JNNCE, University Kuvempu Shimoga
M.Tech in Computer Science and Engineering, RVCE, Bangalore, VTU university.
Ph.D in Computer and Information Science , RVCE, Bangalore, VTU University.
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Science, Artificial Intelligence, Multidisciplinary, Computational Theory and Mathematics
52
Scopus Publications
25
Scholar Citations
3
Scholar h-index
1
Scholar i10-index
Scopus Publications
Brain Tumor Detection through Deep Learning-Based Medical Image Classification Vivek Kumar Gupta, Suresh Jain, Kailash Chandra Bandhu International Journal of Engineering Trends and Technology, 2026 Magnetic Resonance Imaging (MRI) classification of brain tumors has become a needed procedure in clinical diagnosis, where correct and timely diagnosis could be very useful in the planning of treatment and the outcome of the patient. Nevertheless, current methods of deep learning are largely limited to generalization because of single -dataset dependence, absence of attention, and interpretability. In response to these issues, this paper suggests a multi-faceted deep learning-based model of robust brain tumor classification with the use of heterogeneous MRI data. The main purpose of the study is to construct and test the effective classification model with multiple convolutional neural (CNN) architectures and attention-increased models. To guarantee the cross-dataset validation and strength, the study utilizes two publicly available datasets- the Figshare Brain Tumor Dataset and BraTS2020. All MRI images are subjected to a standardized preprocessing pipeline that includes resizing, normalization, and data augmentation. CNN-based VGG16, ResNet50, AlexNet, EfficientNetB0, and a newly designed lightweight LeNet with Squeeze-and-Excitation (SE) blocks are trained and optimized through transfer learning and tuned hyperparameters. Further, the experimental results will show that the suggested LeNet + SE model has the highest performance on the BraTS2020 dataset, having an accuracy of 98.44, precision of 98.43, recall of 98.44, and F1-score of 98.43. VGG16 and ResNet50 have the highest accuracy of 93.31 on the Figshare dataset, which means that they have good classification by structured MRI data. The high accuracy of the suggested model makes the focus of attention-based channel recalibration efficient in capturing discriminative tumor features without a significant sacrifice in computational efficiency. The proposed framework has great potential in improving the robustness, generalization, and interpretability of brain tumor classification that can be utilized as a reliable method of classifying medical images.
The Synergistic Effect of SSO with CNN Using Five Dense Layers Iaeng International Journal of Computer Science, 2025
Big Data Time Series Forecasting Using Pattern Sequencing Similarity , Gaurav Sharma, Kailash Chandra Bandhu International Journal of Computer Network and Information Security, 2025 Time series forecasting in big data analytics is crucial for making decisions in a variety of fields. but faces challenges due to high dimensionality, non-stationarity, and dynamic patterns. Conventional approaches frequently produce inaccurate results because they are unable to capture sudden variations and intricate temporal connections. This study proposes a Multi-scale Dynamic Time Warping-based Hierarchical Clustering (MDTWbH) approach to improve forecasting accuracy and scalability. Multi-scale Dynamic Time Warping (MDTW) transforms time series data into multi-scale representations, preserving local and global patterns, while Hierarchical Clustering groups similar sequences for enhanced predictive performance. The proposed framework integrates data preprocessing, outlier detection, and missing value interpolation to refine input data. It employs Apache Hadoop and Spark for efficient big data processing. Long Short Term Memory (LSTM) is applied within each cluster for accurate forecasting, and accuracy, precision, recall, F1-score, MAE, and RMSE are used to assess the performance of the model. Experimental results on electricity demand, wind speed, and taxi demand datasets demonstrate superior performance compared to existing techniques. MDTWbH provides a scalable and interpretable solution for large-scale time series forecasting by efficiently capturing evolving temporal patterns.
GLCM and CCV Based Texture Filtering in Association with Machine Learning for Detection of Cervical Cancer Manish Korde, Kailash Chandra Bandhu 2025 IEEE International Conference on Advances in Computing Research on Science Engineering and Technology Acroset 2025, 2025 HPV and various associated factors responsible for the development of cervical cancer in women. The only way to address the issue is through early screening and diagnosis for predicting cancer. The purpose of this study is to find approaches for forecasting the risk factors related with early-stage cervical cancer and the potential for deception, leveraging machine learning models. We chose images of cervical cancer cases and reduced the unnecessary features through PCA. Next, we employed GLCM for feature extraction, and finally, confusion matrices were created using both Random Forest and Support Vector Machine methods of machine learning. This process achieved a maximum accuracy of 85%. To enhance accuracy, utilize a combination of GLCM and CCV along with the Bhattacharyya distance matrix method, resulting in an accuracy improvement of up to 91%.
A consumer behaviour assessment using dimension reduction and deep learning classification Pragya Pandey, Kailash Chandra Bandhu International Journal of Information and Decision Sciences, 2025 Consumer behaviour assessment is extremely important for online communities to finding out mindset of customer and changes their views about specific products and services. Customers share their experiences with particular goods, and services on channels and social media, empowered by artificial intelligence for consumer knowledge sharing and acquire new information. In this proposed work, a deep learning model has been developed for statistical tests, statistical analysis using correlation and association testing are performed. The ordinary dimension reduction with principal component analysis and module eigenvalues, followed by a second normalisation phase that maximises the coefficient's size using possible values. The keras library was used on the third layer of the deep learning classification hierarchy with the rectified linear unit and sigmoid activation functions. The average F1-score was 98% accurate and according to the statistics, the proposed strategy had an accuracy of 84% and a recall of 100%.
A Review on Security and Privacy Enhancement of Patient Data using Hyperledger Fabric Rashmi Vijaywargiya, Kailash Chandra Bandhu 2025 IEEE International Conference on Advances in Computing Research on Science Engineering and Technology Acroset 2025, 2025 In healthcare blockchain technology's ability is recognizable for enhancing data privacy [1]. This paper looks at recent developments in the blockchain, with a particular significance on the Hyperledger Fabric framework [2]. The review shows away the rising trend of engaging blockchain to upgrade healthcare data governance, ensure data exchange in cyberphysical systems, and consolidate supply chain security by means of smart contracts [3] [4]. The review emphasizes the productiveness of Hyperledger Fabric, with its resilient and authorized architecture, in establish data integrity, confidentiality, and interoperability [5] [6]. The survey shows that blockchain, specifically Hyperledger Fabric, has an abundant dormant for making data management systems that are safe and protect privacy [7]. This imply that it could be used in many other areas as well.
Predictive Modeling of Customer Churn in Telecommunications Suhani Sharma, Kailash Chandra Bandhu 2025 World Conference on Cutting Edge Science and Technology Wccest 2025, 2025 Customer churn in telecom makes a substantial hazard to the financial success and sustainability of telecom companies, with earning new customers being more expensive than saving current ones. This paper presents a data-oriented approach to predicting customer churn for telecommunication using advanced machine learning (ML) algorithms, including Logistic Regression (LR), Random Forest (RF), Decision Trees (DT)-Tree Model, Gradient Boosting (GBM), and Artificial Neural Networks. The study utilizes a real-world telecom dataset with various customer attributes, including service usage patterns, billing information, and customer demographics. Feature engineering techniques and data preprocessing strategies were employed to enhance model accuracy and robustness. The evaluation of Model performance was done using key metrics such as precision Metrics, accuracy, recall, ROC-AUC and F1-score, Among the evaluated models, Gradient Boosting and Random Forest proved to have better performance in identifying high-risk churn customers. The paper also explores the interpretability of models using SHAP values and presents actionable insights for churn mitigation strategies. This research paper helps in the field by highlighting the effectiveness of ensemble methods and interpretable AI techniques in customer churn prediction, supporting proactive decision-making for telecom providers.
An In-depth Review of Methods and Approaches for the Early Monitoring of Alzheimer's Illness Garima Gole, Kailash Chandra Bandhu 2025 IEEE International Conference on Advances in Computing Research on Science Engineering and Technology Acroset 2025, 2025 Health care research is always evolving, exploring basic health, medicine, and wellness concerns. It includes multidisciplinary studies on health care policy, practice, and delivery. Researchers aim to improve patient-centred, safe, and effective health care. Researchers study area, socioeconomic status, race, and ethnicity differences. They want everyone to have inexpensive healthcare. Assessing the effects of telemedicine, digital health tools, and other medical innovations on individuals. Investigations are underway into how wearable technologies and electronic health records can improve patient health. Investigating sickness trends, risks, and preventative medication. Alzheimer's diagnosis is the healthcare system's biggest challenge. A neurodegenerative illness, Alzheimer's disease (AD) grows with time. It is the main reason of dementia, a group of symptoms that affect memory, thinking, and behaviour. Alzheimer's disease has three phases: mild, moderate, and severe. Age, inheritance, mild cognitive impairment, brain infections, and head trauma may cause it. Alzheimer's detection has been extensively studied. After reviewing the literature, this study discovered that different studies used different diagnostic criteria to detect early Alzheimer's disease. There were many restrictions. Based on a review of many research, this study demonstrated that many diagnostic methods for one patient allowed diagnosing disease of Alzheimer at an early stage. Machine Learning can help to identify Alzheimer's disease early from MRI, PET, and EEG pictures. simultaneously Building a hybrid model and hyper-tuning it with many diagnosis approaches can improve Alzheimer's Medical conditions detection.
Deepfake Detection in the Era of AI: State-Of-the-art Methods and Open Challenges Divya Samad, Kailash Chandra Bandhu 2025 IEEE International Conference on Advances in Computing Research on Science Engineering and Technology Acroset 2025, 2025 Deepfake technology, fueled by advances in artificial intelligence technology, has been a revolutionary assistant as well as a tremendous security threat. Deepfakes have new uses in media, entertainment, and digital communication, their abuse can cause dangers such as misinformation, identity fraud, and political deception. This review discusses recent developments in deepfake detection methods and presents the contributions of deep learning, blockchain, and hybrid AI models. We discuss different methodologies ranging from convolutional neural networks (CNNs) and graph neural networks (GNNs) to federated learning and adversarial defense techniques. Despite significant advancements, major challenges persist, such as dataset biases, changing deep fake generation habits, and the requirement of real-time detection systems. This paper offers current research lacunae and proposes future avenues, pointing out the explainability requirements, privacy protection, and multimodal detection paradigms. Through the integration of results from different studies, this review presents an extensive view of the field and determines essential areas for future research.
Unveiling Oral Cancer: Deep Learning's Diagnostic Eye Vandana Tank, Kailash Chandra Bandhu, Ratnesh Litoriya 2025 IEEE International Conference on Advances in Computing Research on Science Engineering and Technology Acroset 2025, 2025
Enhanced Security Measures through Video using Inception v3 with Bidirectional Long Short-Term Memory Networks: A Method for Crime Prevention 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
A Survey on Big Data and Time-Series Analysis 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
SummaGen: Next-Generation Seq-to-Seq Model for Summarizing Unstructured Text International Journal of Intelligent Systems and Applications in Engineering, 2024
Machine Learning Based Crop Recommendation System Arpit Deo, Kailash Chandra Bandhu, Ratnesh Litoriya, Abhay Gupta, Purvi Chelawat, Purvi Gohade 2024 International Conference on Advances in Computing Research on Science Engineering and Technology Acroset 2024, 2024
Performance Analysis of Cloud and Fog Computing at Emporium. D BV, D BN, V BR, S Mubeen International Journal of Distributed & Cloud Computing 12 (1) , 2024 2024.0
Game Theory Approach: Profit Calculation in Business. S Mubeen, AS Krishna, B BS, B MS Journal of Applied Information Science 12 (1) , 2024 2024.0
Design and Implementation using of B2B Bot using Game and Queuing Theory. T Mansoor, V BR, YA Bhat, V Srinivasan, S Mubeen Journal of Network and Information Security 10 (2), 21-25 , 2022 2022.0 Citations: 1
Reliability checking and performance analysis of stake holder of E-SCM using machine learning and petrinets S Johar, S Mubeen IJECS 4 (1), 15-25 , 2022 2022.0
Customer Reviews for Product Recommendation using Machine Learning JM Abhishek, SS Jois, AK Pastay, P Chiranthan, S Mubeen Journal of Network and Information Security 10 (2), 08-14 , 2022 2022.0
Find_S Algorithm: To Detect Node Behaviour in Ad Hoc Network. S Mubeen International Journal of Knowledge Based Computer Systems 10 (1) , 2022 2022.0
Designing A Learning System Using Machine Learning S Mubeen Pensee 51 (2), 275-278 , 2021 2021.0
Sentiment Analysis on Large Scale Amazon Product Reviews SM Syed Johar International Journal of Scientific Research in Computer Science and … , 2020 2020.0 Citations: 11
Performance Analysis of AODV and DSR Routing Protocols in Mobile Ad-Hoc Network AGSAM Samara Mubeen, Bibi Zahera , Ishwarya R International Journal of Knowledge Based Computer Systems 7 (2), 8-13 , 2019 2019.0
Detection and Elimination of the Selfish Node in Ad-Hoc Network Using Energy Credit Based System SJ Samara Mubeen Journal of Network and Information Security 7 (2), 18-22 , 2019 2019.0 Citations: 3
Isolating Selfish Nodes and Analyzing Performance of Ad-Hoc Network Using Perfect Information Game Theory S Mubeen International Journal of Knowledge Based Computer System 6 (2), 31-17 , 2018 2018.0 Citations: 1
Game Theoretic Approach for Selection of Retailers in B2B E-Commerce S Mubeen, KN Subramanya, NK Srinath 2017 2nd International Conference on Computational Systems and Information … , 2017 2017.0 Citations: 1
Double Securing from Hackers in B2B E-commerce S Mubeen, NK Srinath, KN Subramanya International Journal of Information Technology and Computer Science 1 (8 … , 2016 2016.0 Citations: 3
Selection of Supplier in B2B E-commerce using Work Flow Petri net S Mubeen, KN Subramanya International Journal of Managing Value and Supply Chains 5 (3), 91 , 2014 2014.0 Citations: 4
Performance analysis of e-supply chain using M/M/1 queue in business to business S Mubeen, N Srinath, K Subramanya International Journal of Latest Trends in Engineering and Technology 4 (4 … , 2014 2014.0 Citations: 1
Analyzing of Node Behavior in Ad hoc Network Using Finds Algorithm a concept of Machine Learning SAA Samara Mubeen lino, 1-11 , 0
Stabilizing the network in presence of agents using flow graph and Shapely value in B2B E-commerce S Mubeen, KN Subramanya
MATCH MAKINGIN B2B USING EXTENSIVE GAMES WITH PERFECT INFORMATION S Mubeen, NK Srinath, KN Subramanya
MOST CITED SCHOLAR PUBLICATIONS
Sentiment Analysis on Large Scale Amazon Product Reviews SM Syed Johar International Journal of Scientific Research in Computer Science and … , 2020 2020.0 Citations: 11
Selection of Supplier in B2B E-commerce using Work Flow Petri net S Mubeen, KN Subramanya International Journal of Managing Value and Supply Chains 5 (3), 91 , 2014 2014.0 Citations: 4
Detection and Elimination of the Selfish Node in Ad-Hoc Network Using Energy Credit Based System SJ Samara Mubeen Journal of Network and Information Security 7 (2), 18-22 , 2019 2019.0 Citations: 3
Double Securing from Hackers in B2B E-commerce S Mubeen, NK Srinath, KN Subramanya International Journal of Information Technology and Computer Science 1 (8 … , 2016 2016.0 Citations: 3
Design and Implementation using of B2B Bot using Game and Queuing Theory. T Mansoor, V BR, YA Bhat, V Srinivasan, S Mubeen Journal of Network and Information Security 10 (2), 21-25 , 2022 2022.0 Citations: 1
Isolating Selfish Nodes and Analyzing Performance of Ad-Hoc Network Using Perfect Information Game Theory S Mubeen International Journal of Knowledge Based Computer System 6 (2), 31-17 , 2018 2018.0 Citations: 1
Game Theoretic Approach for Selection of Retailers in B2B E-Commerce S Mubeen, KN Subramanya, NK Srinath 2017 2nd International Conference on Computational Systems and Information … , 2017 2017.0 Citations: 1
Performance analysis of e-supply chain using M/M/1 queue in business to business S Mubeen, N Srinath, K Subramanya International Journal of Latest Trends in Engineering and Technology 4 (4 … , 2014 2014.0 Citations: 1
Performance Analysis of Cloud and Fog Computing at Emporium. D BV, D BN, V BR, S Mubeen International Journal of Distributed & Cloud Computing 12 (1) , 2024 2024.0
Game Theory Approach: Profit Calculation in Business. S Mubeen, AS Krishna, B BS, B MS Journal of Applied Information Science 12 (1) , 2024 2024.0
Reliability checking and performance analysis of stake holder of E-SCM using machine learning and petrinets S Johar, S Mubeen IJECS 4 (1), 15-25 , 2022 2022.0
Customer Reviews for Product Recommendation using Machine Learning JM Abhishek, SS Jois, AK Pastay, P Chiranthan, S Mubeen Journal of Network and Information Security 10 (2), 08-14 , 2022 2022.0
Find_S Algorithm: To Detect Node Behaviour in Ad Hoc Network. S Mubeen International Journal of Knowledge Based Computer Systems 10 (1) , 2022 2022.0
Designing A Learning System Using Machine Learning S Mubeen Pensee 51 (2), 275-278 , 2021 2021.0
Performance Analysis of AODV and DSR Routing Protocols in Mobile Ad-Hoc Network AGSAM Samara Mubeen, Bibi Zahera , Ishwarya R International Journal of Knowledge Based Computer Systems 7 (2), 8-13 , 2019 2019.0
Analyzing of Node Behavior in Ad hoc Network Using Finds Algorithm a concept of Machine Learning SAA Samara Mubeen lino, 1-11 , 0
Stabilizing the network in presence of agents using flow graph and Shapely value in B2B E-commerce S Mubeen, KN Subramanya
MATCH MAKINGIN B2B USING EXTENSIVE GAMES WITH PERFECT INFORMATION S Mubeen, NK Srinath, KN Subramanya
