Sahebgoud Hanamantray Karaddi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sahebgoud Hanamantray Karaddi has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Lakhan Dev Sharma
School of Electronics Engineering, VIT-AP University
6 shared publications - Gogulamudi Pradeep Reddy
Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, Karnataka, India
2 shared publications - Jammisetty Yedukondalu
Department of ECE, PACE Institute of Technology and Sciences, Ongole, Andhra Pradesh, India
2 shared publications - Abhijit Bhattacharyya
Discipline of Electrical Engineering, Indian Institute of Technology Indore, Indore, India
1 shared publication Abhilasha Joshi
1 shared publication- Achintya Kumar Sarkar
Indian Institute of Information Technology (IIIT) Sri City India
1 shared publication
Latest Publications
- Open Access
- 1 December 2025
- Published by Elsevier in Alexandria Engineering Journal
- Vol. 133, 615-626
Coronary artery disease detection using deep integration of vision transformer and extended LSTM from cardiac multi-modal images
- 1 December 2025
- Published by Elsevier in Alexandria Engineering Journal
- Vol. 133, 615-626
Open AccessCoronary artery disease detection using deep integration of vision transformer and extended LSTM from cardiac multi-modal images
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (4) , 9557-9568
Deep Fusion of VGG19 and ConvMixer With Superlet Transform for Cognitive Load Detection
The cognitive load triggers neural activity, which is crucial for understanding the brain’s response to mental stress or stimuli that induce stress. Electroencephalogram (EEG) signals were collected from a mental arithmetic task (MAT), simultaneous task EEG workload datasets and segmented into 4-second intervals. These segmented signals were then transformed into images using various time-frequency conversion methods (TF), including the Short-Time Fourier Transform (STFT), Continuous Wavelet Transform (CWT), Q Transform (QT), and Superlet Transform (SLT). The resulting TF images were fed into convolutional neural networks (CNNs), such as VGG19, ConvMixer, and a fusion of VGG19+ConvMixer. CNN models were trained using the Adam optimizer to detect cognitive load. The preprocessing involved normalization, and scaling in both phases. Among the models tested, the SLT-based TF-EEG with the fusion of the VGG19 and ConvMixer model outperformed other TF conversion methods and CNN architectures. The VGG19+ConvMixer utilizes the individual advantages of both VGG19 and ConvMixer models. It helps reduce overfitting and vanishing gradients, enhances performance with new data, improves GPU acceleration, and reduces computational cost due to its simpler architecture. However, the SLT effectively handles non-stationary data through its adaptive multi-resolution approach, making it ideal for EEG analysis. The SLT + VGG19 + ConvMixer model achieved accuracies of 97.26% on the MAT dataset and 96.04% on the STEW dataset, with all other evaluation metrics such as precision, sensitivity, specificity, F-score, MCC, Jaccard index, and Cohen’s kappa exceeding 94%. These findings can enhance real-time cognitive load monitoring, benefiting areas such as personalized learning, mental health, and stress management by detecting cognitive load to improve performance and reduce stress in critical situations.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (4) , 9557-9568
Deep Fusion of VGG19 and ConvMixer With Superlet Transform for Cognitive Load Detection
The cognitive load triggers neural activity, which is crucial for understanding the brain’s response to mental stress or stimuli that induce stress. Electroencephalogram (EEG) signals were collected from a mental arithmetic task (MAT), simultaneous task EEG workload datasets and segmented into 4-second intervals. These segmented signals were then transformed into images using various time-frequency conversion methods (TF), including the Short-Time Fourier Transform (STFT), Continuous Wavelet Transform (CWT), Q Transform (QT), and Superlet Transform (SLT). The resulting TF images were fed into convolutional neural networks (CNNs), such as VGG19, ConvMixer, and a fusion of VGG19+ConvMixer. CNN models were trained using the Adam optimizer to detect cognitive load. The preprocessing involved normalization, and scaling in both phases. Among the models tested, the SLT-based TF-EEG with the fusion of the VGG19 and ConvMixer model outperformed other TF conversion methods and CNN architectures. The VGG19+ConvMixer utilizes the individual advantages of both VGG19 and ConvMixer models. It helps reduce overfitting and vanishing gradients, enhances performance with new data, improves GPU acceleration, and reduces computational cost due to its simpler architecture. However, the SLT effectively handles non-stationary data through its adaptive multi-resolution approach, making it ideal for EEG analysis. The SLT + VGG19 + ConvMixer model achieved accuracies of 97.26% on the MAT dataset and 96.04% on the STEW dataset, with all other evaluation metrics such as precision, sensitivity, specificity, F-score, MCC, Jaccard index, and Cohen’s kappa exceeding 94%. These findings can enhance real-time cognitive load monitoring, benefiting areas such as personalized learning, mental health, and stress management by detecting cognitive load to improve performance and reduce stress in critical situations.
- Open Access
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 117224-117238
Sleep Stage Classification Using Variational Mode Decomposition and Wrapper-Based Feature Selection From the Single Channel EEG
Sleep stage classification can diagnose various sleep disorders and sleep patterns. The classification model classifies many stages of sleep, including wakefulness, non-rapid eye movement (NREM) sleep, and rapid eye movement (REM) sleep. Precise and reliable sleep stage classification is crucial for clinical applications and research studies. Diagnosing sleep disorders without an accurate automated classification model is laborious and susceptible to inaccuracies.This may lead to delayed or ineffective treatments. Manual scoring is tiresome and inconsistent, making it difficult to provide personalized treatments to treat sleep diseases efficiently. Sleep disorders, including narcolepsy, insomnia, and sleep apnea, can be identified and monitored by automatic sleep classification. The proposed framework uses variational mode decomposition (VMD). The electroencephalogram (EEG) is processed into band-limited intrinsic mode functions (IMFs) by VMD. Each IMF signal in EEG was broken down into 15 features based on time, frequency, and information theory. Furthermore, the optimum feature subset was selected using the Wrapper-Based Feature Selector (WBFS). Finally, well-known classifiers used to classify the EEG signal into five distinct sleep stages. This study achieves accuracies of 94.84% and 95.20%on the Sleep-EDF database, and 95.60% and 96.17% on the ISRUC-Sleep dataset, for the balanced and unbalanced cases, respectively.
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 117224-117238
Open AccessSleep Stage Classification Using Variational Mode Decomposition and Wrapper-Based Feature Selection From the Single Channel EEG
Sleep stage classification can diagnose various sleep disorders and sleep patterns. The classification model classifies many stages of sleep, including wakefulness, non-rapid eye movement (NREM) sleep, and rapid eye movement (REM) sleep. Precise and reliable sleep stage classification is crucial for clinical applications and research studies. Diagnosing sleep disorders without an accurate automated classification model is laborious and susceptible to inaccuracies.This may lead to delayed or ineffective treatments. Manual scoring is tiresome and inconsistent, making it difficult to provide personalized treatments to treat sleep diseases efficiently. Sleep disorders, including narcolepsy, insomnia, and sleep apnea, can be identified and monitored by automatic sleep classification. The proposed framework uses variational mode decomposition (VMD). The electroencephalogram (EEG) is processed into band-limited intrinsic mode functions (IMFs) by VMD. Each IMF signal in EEG was broken down into 15 features based on time, frequency, and information theory. Furthermore, the optimum feature subset was selected using the Wrapper-Based Feature Selector (WBFS). Finally, well-known classifiers used to classify the EEG signal into five distinct sleep stages. This study achieves accuracies of 94.84% and 95.20%on the Sleep-EDF database, and 95.60% and 96.17% on the ISRUC-Sleep dataset, for the balanced and unbalanced cases, respectively.
- 1 October 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (24) , 28667-28691
Classification of lung disorders in chest multi-modal images using hyper-Parameter tuning and modified ResNet50
- 1 October 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (24) , 28667-28691
Classification of lung disorders in chest multi-modal images using hyper-Parameter tuning and modified ResNet50
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (20) , 32566-32576
Softflatten-Net: A Deep Convolutional Neural Network Design for Monkeypox Classification From Digital Skin Lesions Images
In scenarios where smallpox has been eradicated, the most important human orthopoxvirus pandemic is monkeypox (MP), which is a zoonotic disease that spreads more often. MP is difficult to diagnose, as it has characteristics similar to smallpox, chickenpox (CP), and measles (MS). Polymerise chain reaction (PCR), computerized histopathological nucleic acid amplification test (NAAT), immuno-histo-chemistry, enzyme-linked immunosorbent assay (ELISA) and electron microscope-based skin lesion testing are used for MP detection. But these tests are time consuming and may lead to false decision. Therefore, automation in MP detection using skin lesions images is needed for developing affordable and fast solutions. In this work, we have proposed a deep convolutional neural network architecture named the Softflatten-Net to identify and categorize MP using skin lesions. This architecture helps to avoid gradient vanishing and over-fitting problems. Classification has been conducted in seven distinct scenarios: MP vs normal (NH), MP vs. MS, MP vs. CP, MP vs. other, MP vs. CP vs. NH, MP vs. CP vs. MS, and MP vs. CP vs. MS vs. NH. Among binary classification tasks, the Softflatten-Net achieved the maximum classification accuracy (Ac) of 97.25%, sensitivity (Sen) of 92.94%, and precision (Pr) of 96.48% in classifying MP from other categories of skin images. In the three-class classification task (MP vs CP vs NH), the proposed network achieved an Ac of 94.71%, Pr of 92.11%, and Sen of 87.87%. In the four-class classification scenario, namely MP vs CP vs MS vs NH, the proposed model achieved Ac, Pr, and Sen values of 90. 73%, 84. 21% and 69. 38%, respectively. Furthermore, we have considered 4,241 skin images from IEEE data-port for nine class classification and 28,771 images from Dermnet for twenty-one class classification to validate the performance of proposed Softflatten-Net architecture. The proposed architecture performed satisfactorily on all the three datasets considered in this work and outperformed the existing state-of-the-art models in the literature. Post-image analysis is performed via local interpretable model-agnostic explanations (LIME), gradient class activation maps (G-CAM) and occlusion sensitivity (OS) approaches. In addition, to analyze misclassification, the stochastic neighbor embedding distributed with t (t-SNE) is employed. Visualization techniques aided in identifying the image regions most pertinent for classification. he proposed network can be utilized for early and reliable detection of MP using images of skin lesions.
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (20) , 32566-32576
Softflatten-Net: A Deep Convolutional Neural Network Design for Monkeypox Classification From Digital Skin Lesions Images
In scenarios where smallpox has been eradicated, the most important human orthopoxvirus pandemic is monkeypox (MP), which is a zoonotic disease that spreads more often. MP is difficult to diagnose, as it has characteristics similar to smallpox, chickenpox (CP), and measles (MS). Polymerise chain reaction (PCR), computerized histopathological nucleic acid amplification test (NAAT), immuno-histo-chemistry, enzyme-linked immunosorbent assay (ELISA) and electron microscope-based skin lesion testing are used for MP detection. But these tests are time consuming and may lead to false decision. Therefore, automation in MP detection using skin lesions images is needed for developing affordable and fast solutions. In this work, we have proposed a deep convolutional neural network architecture named the Softflatten-Net to identify and categorize MP using skin lesions. This architecture helps to avoid gradient vanishing and over-fitting problems. Classification has been conducted in seven distinct scenarios: MP vs normal (NH), MP vs. MS, MP vs. CP, MP vs. other, MP vs. CP vs. NH, MP vs. CP vs. MS, and MP vs. CP vs. MS vs. NH. Among binary classification tasks, the Softflatten-Net achieved the maximum classification accuracy (Ac) of 97.25%, sensitivity (Sen) of 92.94%, and precision (Pr) of 96.48% in classifying MP from other categories of skin images. In the three-class classification task (MP vs CP vs NH), the proposed network achieved an Ac of 94.71%, Pr of 92.11%, and Sen of 87.87%. In the four-class classification scenario, namely MP vs CP vs MS vs NH, the proposed model achieved Ac, Pr, and Sen values of 90. 73%, 84. 21% and 69. 38%, respectively. Furthermore, we have considered 4,241 skin images from IEEE data-port for nine class classification and 28,771 images from Dermnet for twenty-one class classification to validate the performance of proposed Softflatten-Net architecture. The proposed architecture performed satisfactorily on all the three datasets considered in this work and outperformed the existing state-of-the-art models in the literature. Post-image analysis is performed via local interpretable model-agnostic explanations (LIME), gradient class activation maps (G-CAM) and occlusion sensitivity (OS) approaches. In addition, to analyze misclassification, the stochastic neighbor embedding distributed with t (t-SNE) is employed. Visualization techniques aided in identifying the image regions most pertinent for classification. he proposed network can be utilized for early and reliable detection of MP using images of skin lesions.
- 26 June 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (4) , 2795-2806
Automated Metal Surface Flaws Detection Using Convolutional Neural Network and Deep Visualization Analysis
- 26 June 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (4) , 2795-2806
Automated Metal Surface Flaws Detection Using Convolutional Neural Network and Deep Visualization Analysis
- 27 August 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 211
Automated multi-class classification of lung diseases from CXR-images using pre-trained convolutional neural networks
- 27 August 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 211
Automated multi-class classification of lung diseases from CXR-images using pre-trained convolutional neural networks