Raghavendra M Ichangi

@cuk.ac.in

Assistant Professor Department of Artificial Intelligence and Machine Learning
Central University of Karnataka

Raghavendra M Ichangi


                     Download Compact PDF  
https://researchid.co/rmichangi

EDUCATION

B.E. M.Tech (

RESEARCH, TEACHING, or OTHER INTERESTS

Engineering, Artificial Intelligence, Multidisciplinary, Management Information Systems
9

Scopus Publications

3

Scholar Citations

1

Scholar h-index

Scopus Publications

  • Automated Brain Tumour Classification and Segmentation using Deep Neural Networks
    Sudheesh K V, Manu H M, Raghavendra M Ichangi, Prabhavathi K, Dayanand Ram, Sunil Kumar D S
    Proceedings of the 2026 6th International Conference on Image Processing and Capsule Networks Icipcn 2026, 2026
    Brain tumours are one of the deadliest forms of cancer, and as all cancer types, early detection is very important and can save lives. By the time symptoms appear, cancer may have begun to spread and be harder to treat. The screening process (the process of performing MRI or CT scans to detect tumours) can be divided into two main tasks. The first task is the classification task, doctors need to identify the type of the brain tumour. There are three types of brain tumours meningioma, pituitary and glioma. The type of the tumour can be an indication of the tumor`s aggressiveness, however to estimate the tumour's stage (the size of the cancer and how far it's spread) an expert needs to segment the tumor first in order to measure it in an accurate way. This lead to the second and more time-consuming task of segmenting the brain tumors which doctors need to separate the infected tissues from the healthy ones by labelling each pixel in the scan. In this work, we propose a deep learning–based approach for automated brain tumor segmentation, leveraging advanced convolutional neural network architectures to improve accuracy and reduce the manual effort required in clinical practice.
  • Transformer-Based Semantic Self-Attention Regression for the Evaluation of Customer Satisfaction in Social Media Data
    Raghavendra M. Ichangi, Shrinivasrao B. Kulkarni
    Engineering Technology and Applied Science Research, 2025
    A website that is optimized and has a high Search Engine Results Page (SERP) ranking is more likely to attract relevant users. As a result, there is a direct relationship between Search Engine Optimization (SEO) and user experience, and poor SEO makes it hard for a user to find the items he is looking for. The proposed Semantic Self-Attention Regression based on Transformer (SSAR-T) model uses four separate layers—tokenizing, embedding, encoding, and fine-tuning—to determine the degree of user experience satisfaction. Sample input text is fed to the tokenizing layer. The cosine Euclidean semantic similarity-based segment embedding is designed to help minimize the prediction error and training time. Self-attention-based encoder transformation is utilized with multiple attention heads, focusing on learning the context of surrounding words accurately and precisely. Non-linear regression-based fine-tuning is used for measuring customer satisfaction. KANO mapping functions are used to assess the model's precision. Compared to previous methods, the proposed SSAR-T model achieved improvements of 19%, 24% and 58% in precision and 9%, 14% and 12% in recall for SEO, Instagram influencer, and Twitter data samples, respectively.
  • Deep Learning Applications for Improving Early Detection and Staging Accuracy in Alzheimer’s Disease
    R Raksha, Jyoti Metan, Raghavendra M. Ichangi, P Suresh, Shazia Sulthana, M N Anusha, K N Bharath
    SN Computer Science, 2025
  • A Discretized Recurrent Deep Learning Classifier based on Stochastic Gradient ChatGPT to Improve Lead Conversion Rate
    Raghavendra M. Ichangi, Shrinivasrao B. Kulkarni
    Engineering Technology and Applied Science Research, 2025
    In the vast domain of digital marketing, lead generation forms the foundation for business development. Business strategies depend on converting the leads into customers. It has become very crucial and challenging to choose an appropriate digital platform for marketing. The proposed method, called Stochastic Gradient ChatGPT-based Discretized Recurrent Deep Learning Classification (SG-CDRDLC), employs an efficient way for lead conversion based on influencing feature keywords. The DL classifier with two hidden layers allows companies to determine the popularity of the keywords in the first layer. The second layer measures the keyword density based on a variety of user queries to evaluate and enhance the conversion rate. The proposed model was trained and tested on three datasets and compared against existing methods using accuracy, precision, recall, and training time.
  • QEMF for spatial domain pre-processing in iris biometrics: advancing accuracy and efficiency in recognition systems
    Prajwalasimha Sindugatta Nagaraja, Naveen Kulkarani, Raghavendra M. Ichangi, Vinitha Varanamkudath, Sharanabasappa Tadkal, Ranjima Parakkal, Deepthika Karuppusamy
    Bulletin of Electrical Engineering and Informatics, 2025
    This article presents a Quantum-Enhanced Median Filtering (QEMF) method for spatial domain pre-processing in iris biometrics, designed to improve image denoising and recognition accuracy. Traditional median filtering often struggles with high noise density, leading to inconsistencies in the denoised image. Our approach enhances the median filtering process by integrating quantum-inspired principles with statistical measures, combining median and average values of neighboring pixels. This hybrid strategy preserves the structural integrity of the original image while effectively reducing noise. Additionally, a quantum-based thresholding step is introduced in the final stage to minimize ambiguities and further enhance image quality. The proposed method is evaluated using approximately one hundred standard iris images from the Chinese University of Hong Kong (CUHK) dataset, considering four types of noise: Impulse, Poisson, Gaussian, and Speckle. Comparative analysis with conventional filters, including Median and Wiener filters, demonstrates that the QEMF method achieves 99.36% similarity to the original images, surpassing Median and Wiener filters by 1.32% and 0.34%, respectively. These results highlight the potential of quantum-enhanced filtering for improved denoising performance and increased efficiency in iris recognition systems.
  • Revolutionizing Brain Tumor Classification with Fusion-Driven Deep Learning Models
    Katepaka Anil Kumar, Gunasundari B, Raghavendra M Ichangi, S Arun Kumar, Jeethu Philip, S Saranya
    Apci 2025 2025 International Conference on Advancements in Power Communication and Intelligent Systems, 2025
    The identification of brain tumors presents a significant medical challenge, as timely and precise diagnosis greatly influences patient survival rates. Brain tumors, caused by abnormal cell growth, vary in severity and often present subtle differences in medical imaging, making manual diagnosis by radiologists Labor-intensive and susceptible to mistakes. Magnetic resonance imaging (MRI) and Computed tomography (CT) scans plays a key role in enhancing tumor visibility and aiding diagnosis. However, the complexity of brain structures and the limitations of manual interpretation highlight the need for automated, efficient, and reliable diagnostic methods to support timely clinical decision-making. Multimodel approaches integrating information from various imaging techniques, including CT and MRI scans, have surfaced as a robust solution to enhance diagnostic accuracy. In this study, we propose a novel multimodel framework leveraging ResNet50, a deep convolutional neural network designed for the detection of brain tumors. Our approach integrates CT and MRI scan data, utilizing their complementary information to achieve superior performance. The proposed system incorporates a late fusion strategy, where features extracted from the CT and MRI scans by independent ResNet50 models are combined for final classification. The model underwent training and evaluation using a comprehensive dataset, achieving an accuracy of 97.5% in tumor detection, significantly outperforming single-modality approaches. This high accuracy emphasizes the potential of multimodel frameworks in enhancing the reliability of brain tumor diagnostics. Our research indicates that multimodal data integration, unified with the advanced feature extraction capabilities of ResNet50, can substantially strengthened the precision of automated brain tumor recognition systems. This research paves the way for more effective diagnostic tools within clinical contexts, it may significantly lower diagnostic error rates and lead to improved health outcomes.
  • Deep Transfer Learning with Dual Attention for Reliable Diabetic Retinopathy Screening
    Gunasundari B, Shaafia Tasneem N, Valli Priyadharshini K, R V V N Bheema Rao, Raghavendra M Ichangi, K S Jayareka
    IC Decon 2025 2025 International Conference on Data Energy and Communication Network Proceedings, 2025
    Diabetic Retinopathy, or DR, shows up as one of the key microvascular complications linked to diabetes mellitus. It remains a leading cause of preventable blindness across the globe. The problem stems from prolonged periods of elevated blood sugar levels. Those levels damage the blood vessels within the retina over time. Eventually, this leads to issues such as microaneurysms, hemorrhages, exudates, and more severe complications in advanced stages. Those might involve retinal detachment or irreversible vision loss. Early detection plays a crucial role in managing the condition. Prompt intervention helps avoid lasting damage as well. Traditional screening typically relies on ophthalmologists manually examining retinal fundus photographs. This process demands significant time and resources. It can also lead to variations in interpretation among different specialists. The proposed approach introduces an innovative Attention-Enhanced Transfer Learning Framework. This combines the VGG19 architecture with a Channel and Spatial Attention Module, known as CSAM. The aim centers on automating the detection of Diabetic Retinopathy through retinal fundus images. The model leverages pre-trained networks for its foundation. It incorporates attention mechanisms to highlight critical retinal features relevant to diagnosis. Overall, this enhances interpretability of the outcomes. It improves classification performance too. On the testing dataset, the framework achieved an accuracy rate of 98 percent. That indicates strong generalization capabilities. It suggests real potential for clinical application in disease detection. Ultimately, these results highlight the framework's viability as a reliable and efficient tool. It could assist in large-scale DR screening programs. In turn, this reduces the burden on healthcare facilities. It also promotes earlier identification of cases.
  • The Role Of AI In Identifying Bearing Faults Of Renewable Energy Systems
    Raghavendra M Ichangi, Ramesh Babu N, Daison Stallon S, Sumalatha Kalakotla, Devanga Dharani Lakshmi, R. Senthamil Selvan
    3rd International Conference on Advances in Computing Communication and Materials Icaccm 2024, 2024
    The increasing complexity and power requirements of communication systems make them impractical for widespread usage. Theoretical systems have been superbly applied to the actual world by artificial intelligence (AI), with less complexity producing greater outcomes. Here, they contrast two kinds of detectors—one based on deep learning and the other on the more conventional maximum likelihood (ML) decoder—and two methods for multiuser Visible Light Communication (VLC) systems: Successive Interference Cancellation (SIC) and Non-Orthogonal Multiple Access (NOMA). Examine the differences and similarities between Index Modulation (IM), Orthogonal Frequency Division Multiplexing (OFDM), and the new Orbital Angular Momentum (OAM) multiplexing. Simulated results for a variety of signal-to-noise ratios (SNRs) reveal that, for both users, deep learning-based structures provide superior decryption at the receiver end, mainly for advanced SNR values, when compared to ML-based systems. By using deep learning, the detection error may be reduced to about 20% for low SNR values and roughly 30% for high SNR values.
  • Exploring Non-convex Optimization in Sparse Signal Recovery: A Comparative Study of Non-convex Dantzig Selector and LASSO
    Raghavendra M. Devadas, Vani Hiremani, Aditi Sharma, Anita Venugopal, Raghavendra M. Ichangi, Naveen Kulkarni, N. Pavithra
    Lecture Notes in Networks and Systems, 2024

RECENT SCHOLAR PUBLICATIONS

  • Deep Transfer Learning with Dual Attention for Reliable Diabetic retinopathy Screening
    G B, S Tasneem N, V Priyadharshini K, RVVNB Rao, RM Ichangi, ...
    2025 International Conference on Data, Energy and Communication Networks (DECoN) , 2026
    2026
  • Automated Brain Tumour Classification and Segmentation using Deep Neural Networks
    RM Ichangi, S K. V., M H. M., P K., D Ram, SK D. S.
    6th International Conference on Image Processing and Capsule Networks (ICIPCN) , 2026
    2026
  • Transformer-Based Semantic Self-Attention Regression for the Evaluation of Customer Satisfaction in Social Media Data
    RM Ichangi, SB Kulkarni
    Engineering, Technology & Applied Science Research 15 (6), 29745-29750 , 2025
    2025
  • Revolutionizing Brain Tumor Classification with Fusion-Driven Deep Learning Models
    RM Ichangi, G B
    IEEE , 2025
    2025
  • Deep Learning Applications for Improving Early Detection and Staging Accuracy in Alzheimer’s Disease
    R Raksha, J Metan, RM Ichangi, P Suresh, S Sulthana, MN Anusha, ...
    SN Computer Science 6 (7), 800 , 2025
    2025
    Citations: 2
  • The Role Of AI In Identifying Bearing Faults Of Renewable Energy Systems
    RM Ichangi, R Babu N, D Stallon S, S Kalakotla, DD Lakshmi, RS Selvan
    IEEE , 2025
    2025
  • A Discretized Recurrent Deep Learning Classifier based on Stochastic Gradient ChatGPT to Improve Lead Conversion Rate
    RM Ichangi, SB Kulkarni
    Engineering, Technology & Applied Science Research 15 (3), 22712-22717 , 2025
    2025
    Citations: 1
  • QEMF for spatial domain pre-processing in iris biometrics: advancing accuracy and efficiency in recognition systems
    PS Nagaraja, N Kulkarani, RM Ichangi, V Varanamkudath, S Tadkal, ...
    Bulletin of Electrical Engineering and Informatics 14 (3), 1959-1968 , 2025
    2025
  • Developing a Wireless Network for Optimum Distance Learning Assistant
    DRSS Dr.M.Prabha, Dr. Sudhir Anakal, Dr.Poornachandran R, Raghavendra M ...
    The Bioscan 19 (1), 351-355 , 2024
    2024
  • Exploring Non-convex Optimization in Sparse Signal Recovery: A Comparative Study of Non-convex Dantzig Selector and LASSO
    NKNP Raghavendra M. Devadas, Vani Hiremani, Aditi Sharma, Anita Venugopal ...
    Lecture Notes in Networks and Systems 1074, 57-67 , 2024
    2024
  • A Comparative Study of Various Digital Marketing Tools for enhancement of customer outreach
    RM Ichangi
    International Journal of Scientific Research in Engineering and Management 6 … , 2022
    2022
  • Analysis of Big Data Analytics for Social Media
    RM Ichangi
    International Journal for Research in Applied Science and Engineering … , 2021
    2021
  • Social Media Analytics – Applications and Tools for Social Media Networks
    RM Ichangi
    International Journal of All Research Education and Scientific Methods 9 (4 … , 2021
    2021
  • A Survey paper on Applications of Data Analytics
    RM Ichangi
    International Journal for Research in Applied Science & Engineering … , 2021
    2021

MOST CITED SCHOLAR PUBLICATIONS

  • Deep Learning Applications for Improving Early Detection and Staging Accuracy in Alzheimer’s Disease
    R Raksha, J Metan, RM Ichangi, P Suresh, S Sulthana, MN Anusha, ...
    SN Computer Science 6 (7), 800 , 2025
    2025
    Citations: 2
  • A Discretized Recurrent Deep Learning Classifier based on Stochastic Gradient ChatGPT to Improve Lead Conversion Rate
    RM Ichangi, SB Kulkarni
    Engineering, Technology & Applied Science Research 15 (3), 22712-22717 , 2025
    2025
    Citations: 1
  • Deep Transfer Learning with Dual Attention for Reliable Diabetic retinopathy Screening
    G B, S Tasneem N, V Priyadharshini K, RVVNB Rao, RM Ichangi, ...
    2025 International Conference on Data, Energy and Communication Networks (DECoN) , 2026
    2026
  • Automated Brain Tumour Classification and Segmentation using Deep Neural Networks
    RM Ichangi, S K. V., M H. M., P K., D Ram, SK D. S.
    6th International Conference on Image Processing and Capsule Networks (ICIPCN) , 2026
    2026
  • Transformer-Based Semantic Self-Attention Regression for the Evaluation of Customer Satisfaction in Social Media Data
    RM Ichangi, SB Kulkarni
    Engineering, Technology & Applied Science Research 15 (6), 29745-29750 , 2025
    2025
  • Revolutionizing Brain Tumor Classification with Fusion-Driven Deep Learning Models
    RM Ichangi, G B
    IEEE , 2025
    2025
  • The Role Of AI In Identifying Bearing Faults Of Renewable Energy Systems
    RM Ichangi, R Babu N, D Stallon S, S Kalakotla, DD Lakshmi, RS Selvan
    IEEE , 2025
    2025
  • QEMF for spatial domain pre-processing in iris biometrics: advancing accuracy and efficiency in recognition systems
    PS Nagaraja, N Kulkarani, RM Ichangi, V Varanamkudath, S Tadkal, ...
    Bulletin of Electrical Engineering and Informatics 14 (3), 1959-1968 , 2025
    2025
  • Developing a Wireless Network for Optimum Distance Learning Assistant
    DRSS Dr.M.Prabha, Dr. Sudhir Anakal, Dr.Poornachandran R, Raghavendra M ...
    The Bioscan 19 (1), 351-355 , 2024
    2024
  • Exploring Non-convex Optimization in Sparse Signal Recovery: A Comparative Study of Non-convex Dantzig Selector and LASSO
    NKNP Raghavendra M. Devadas, Vani Hiremani, Aditi Sharma, Anita Venugopal ...
    Lecture Notes in Networks and Systems 1074, 57-67 , 2024
    2024
  • A Comparative Study of Various Digital Marketing Tools for enhancement of customer outreach
    RM Ichangi
    International Journal of Scientific Research in Engineering and Management 6 … , 2022
    2022
  • Analysis of Big Data Analytics for Social Media
    RM Ichangi
    International Journal for Research in Applied Science and Engineering … , 2021
    2021
  • Social Media Analytics – Applications and Tools for Social Media Networks
    RM Ichangi
    International Journal of All Research Education and Scientific Methods 9 (4 … , 2021
    2021
  • A Survey paper on Applications of Data Analytics
    RM Ichangi
    International Journal for Research in Applied Science & Engineering … , 2021
    2021