Jammisetty Yedukondalu
Research Subjects
Jammisetty Yedukondalu has a total of 33 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 - Karumuri Srinivasa Rao
VLSI-Microelectronics Research Lab, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation (Deemed to be University), Vaddeswaram, India
3 shared publications - Diksha Sharma
Department of Electronics and Communication Engineering, Indian Institute of Information Technology, Sri City, Chittoor, India
2 shared publications - Krishna Chaitanya Mekala
Department of Electronics and Communication Engineering, Sreyas Institute of Engineering and Technology, Hyderabad, India
2 shared publications - Sahebgoud Hanamantray Karaddi
School of Electronics Engineering, VIT-AP University, Amaravati, India
2 shared publications - Achintya Kumar Sarkar
Indian Institute of Information Technology (IIIT) Sri City India
1 shared publication
Latest Publications
- 9 July 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
LDA NET: A Lightweight Dual Assignment Network for Extremely Small-Scale Object Detection in UAV Aerial Imagery
Aerial object detection in aerial imagery is a highly complex task due to challenges such as extremely small objects, densely packed distributions, frequent occlusions and intricate backgrounds. These parameters mostly cause false positives, missed detections and high computational costs in existing models. To address these issues, particularly for the VisDrone dataset, this work proposes an efficient and accurate LDA Network which is designed to handle extremely small and densely clustered objects. Our approach integrates three key innovations: The SCDown module, the Partial Self-Attention (PSA) mechanism, and an NMS-free detection strategy with dual assignment collectively improve both accuracy and efficiency. The SCDown module is a computationally efficient downsampling technique that reduces redundancy while preserving critical spatial details, enabling the model to detect small objects without excessive computational overhead. The PSA mechanism enhances feature extraction by adaptively prioritizing spatially significant regions, thereby improving the detection accuracy of extremely small objects in cluttered and complex visual environments. Finally, the NMS-free detection strategy removes the use of “Non-Maximum Suppression (NMS)” by combining one-to-one and one-to-many predictions, resulting in more precise object localization and faster inference times. Experiments on the VisDrone dataset demonstrate the effectiveness of our model, achieving a “mean average precision” of 54.1%, a “precision” of 78.8%, and a “recall” of 29.8%, outperforming existing YOLO-based models in both accuracy and efficiency. The achieved results indicate the proposed model’s ability to address the challenges of aerial object detection, making it a promising solution for real-world.
- 9 July 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
LDA NET: A Lightweight Dual Assignment Network for Extremely Small-Scale Object Detection in UAV Aerial Imagery
Aerial object detection in aerial imagery is a highly complex task due to challenges such as extremely small objects, densely packed distributions, frequent occlusions and intricate backgrounds. These parameters mostly cause false positives, missed detections and high computational costs in existing models. To address these issues, particularly for the VisDrone dataset, this work proposes an efficient and accurate LDA Network which is designed to handle extremely small and densely clustered objects. Our approach integrates three key innovations: The SCDown module, the Partial Self-Attention (PSA) mechanism, and an NMS-free detection strategy with dual assignment collectively improve both accuracy and efficiency. The SCDown module is a computationally efficient downsampling technique that reduces redundancy while preserving critical spatial details, enabling the model to detect small objects without excessive computational overhead. The PSA mechanism enhances feature extraction by adaptively prioritizing spatially significant regions, thereby improving the detection accuracy of extremely small objects in cluttered and complex visual environments. Finally, the NMS-free detection strategy removes the use of “Non-Maximum Suppression (NMS)” by combining one-to-one and one-to-many predictions, resulting in more precise object localization and faster inference times. Experiments on the VisDrone dataset demonstrate the effectiveness of our model, achieving a “mean average precision” of 54.1%, a “precision” of 78.8%, and a “recall” of 29.8%, outperforming existing YOLO-based models in both accuracy and efficiency. The achieved results indicate the proposed model’s ability to address the challenges of aerial object detection, making it a promising solution for real-world.
- 11 November 2025
- Published by Springer Nature in Cluster Computing
- Vol. 29 (1) , 1-13
Stress detection via EEG signals using Henry gas solubility optimization feature selection
- 11 November 2025
- Published by Springer Nature in Cluster Computing
- Vol. 29 (1) , 1-13
Stress detection via EEG signals using Henry gas solubility optimization feature selection
- 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.
- 1 October 2025
- Published by Springer Nature
- p. 469-478
EEG-Based Cognitive Load Detection Using Pre-trained CNN
- 1 October 2025
- Published by Springer Nature
- p. 469-478
EEG-Based Cognitive Load Detection Using Pre-trained CNN
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (14) , 27485-27494
Automatic Classification of Atrial and Ventricular Arrhythmias Using Scaled Bidirectional LSTM
Cardiac arrhythmia (CA) is a condition of the heart that raises the risk of heart failure, stroke, and mortality. A CA can be quickly detected by an lectrocardiogram (ECG), which analyses heart’s electrical activity. The primary diagnostic procedure, which is typically strenuous and ineffective, is the visual examination of ECG. In this article, a scaled bidirectional long short term memory (SB-LSTM) prototype is designed for the automatic categorization of CAs. The conventional Bidirectional long short term memory (BILSTM) is modified by embedding a scaling layer into it and hence it can able to categorize the CAs automatically and efficiently. After the various pre-processing steps, namely denoising, and normalization, the results show that there is an improvement in accuracy (ACCY). The newly developed prototype is endorsed by popular databases like MIT-BIH atrial fibrillation database (MITBIHAFDB), Creighton University Ventricular Tachyarrhythmia Database (CUVTDB), and MIT-BIH Malignant Ventricular Ectopy database (MITBIHVFDB) the physioNet warehouse, We succeeded in achieving an ACCY of 98.60%. Thus, the technique proposed presents a reliable and accurate procedure for the automatic categorization of CAs.
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (14) , 27485-27494
Automatic Classification of Atrial and Ventricular Arrhythmias Using Scaled Bidirectional LSTM
Cardiac arrhythmia (CA) is a condition of the heart that raises the risk of heart failure, stroke, and mortality. A CA can be quickly detected by an lectrocardiogram (ECG), which analyses heart’s electrical activity. The primary diagnostic procedure, which is typically strenuous and ineffective, is the visual examination of ECG. In this article, a scaled bidirectional long short term memory (SB-LSTM) prototype is designed for the automatic categorization of CAs. The conventional Bidirectional long short term memory (BILSTM) is modified by embedding a scaling layer into it and hence it can able to categorize the CAs automatically and efficiently. After the various pre-processing steps, namely denoising, and normalization, the results show that there is an improvement in accuracy (ACCY). The newly developed prototype is endorsed by popular databases like MIT-BIH atrial fibrillation database (MITBIHAFDB), Creighton University Ventricular Tachyarrhythmia Database (CUVTDB), and MIT-BIH Malignant Ventricular Ectopy database (MITBIHVFDB) the physioNet warehouse, We succeeded in achieving an ACCY of 98.60%. Thus, the technique proposed presents a reliable and accurate procedure for the automatic categorization of CAs.
- 1 December 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (4) , 045258
Early knee osteoarthritis classification using distributed explainable convolutional neural network with local interpretable model-agnostic explanations
Knee Osteoarthritis (KOA) is a type of Knee Arthritis (KA) that causes pain, swelling, and other discomforts to the knee joints, which is quite complicated to classify using previous methods due to its various limitations such as computational cost, over-fitting issues, less reliability and so on. In this research, the classification using a distributed explainable convolutional neural network with local interpretable model-agnostic explanations (LExNN) model is proposed for knee Osteoarthritis. The distributed LExNN model is an ensemble with a distributed mechanism, in which the input vectors are distributed to two explainable CNNs which makes it quite easier for classification and grading. The distributed concepts are blown up with several advantages such as high computation efficiency with less training time, reliability, and develop an efficient model for classification. In addition, the local interpretable model-agnostic explanations (LIME) technique interprets important information from the image and classifies the severity based on two grades namely high and low. This technique provides significant, simple, and understandable information, which is quite reliable for KOA classification. The supremacy of the model can be determined by measuring several parameters such as accuracy, precision, recall, and f1 score that gives 99.25%, 99.25%, 98.42%, and 98.83% compared to other state-of-the-art methods.
- 1 December 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (4) , 045258
Early knee osteoarthritis classification using distributed explainable convolutional neural network with local interpretable model-agnostic explanations
Knee Osteoarthritis (KOA) is a type of Knee Arthritis (KA) that causes pain, swelling, and other discomforts to the knee joints, which is quite complicated to classify using previous methods due to its various limitations such as computational cost, over-fitting issues, less reliability and so on. In this research, the classification using a distributed explainable convolutional neural network with local interpretable model-agnostic explanations (LExNN) model is proposed for knee Osteoarthritis. The distributed LExNN model is an ensemble with a distributed mechanism, in which the input vectors are distributed to two explainable CNNs which makes it quite easier for classification and grading. The distributed concepts are blown up with several advantages such as high computation efficiency with less training time, reliability, and develop an efficient model for classification. In addition, the local interpretable model-agnostic explanations (LIME) technique interprets important information from the image and classifies the severity based on two grades namely high and low. This technique provides significant, simple, and understandable information, which is quite reliable for KOA classification. The supremacy of the model can be determined by measuring several parameters such as accuracy, precision, recall, and f1 score that gives 99.25%, 99.25%, 98.42%, and 98.83% compared to other state-of-the-art methods.
- 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
- Top Cited Papers
- 11 April 2024
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 15 (9) , 4193-4210
EEG-based detection of cognitive load using VMD and LightGBM classifier
- 11 April 2024
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 15 (9) , 4193-4210
Top Cited PapersEEG-based detection of cognitive load using VMD and LightGBM classifier
- 29 November 2023
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 49 (3) , 4445-4457
Subject-Wise Cognitive Load Detection Using Time–Frequency EEG and Bi-LSTM
- 29 November 2023
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 49 (3) , 4445-4457
Subject-Wise Cognitive Load Detection Using Time–Frequency EEG and Bi-LSTM
- Open Access
Circulant Singular Spectrum Analysis and Discrete Wavelet Transform for Automated Removal of EOG Artifacts from EEG Signals
Background: Portable electroencephalogram (EEG) systems are often used in health care applications to record brain signals because their ease of use. An electrooculogram (EOG) is a common, low frequency, high amplitude artifact of the eye blink signal that might confuse disease diagnosis. As a result, artifact removal approaches in single EEG portable devices are in high demand. Materials: Dataset 2a from the BCI Competition IV was employed. It contains the EEG data from nine subjects. To determine the EOG effect, each session starts with 5 min of EEG data. This recording lasted for two minutes with the eyes open, one minute with the eyes closed, and one minute with eye movements. Methodology: This article presents the automated removal of EOG artifacts from EEG signals. Circulant Singular Spectrum Analysis (CiSSA) was used to decompose the EOG contaminated EEG signals into intrinsic mode functions (IMFs). Next, we identified the artifact signal components using kurtosis and energy values and removed them using 4-level discrete wavelet transform (DWT). Results: The proposed approach was evaluated on synthetic and real EEG data and found to be effective in eliminating EOG artifacts while maintaining low frequency EEG information. CiSSA-DWT achieved the best signal to artifact ratio (SAR), mean absolute error (MAE), relative root mean square error (RRMSE), and correlation coefficient (CC) of 1.4525, 0.0801, 18.274, and 0.9883, respectively. Comparison: The developed technique outperforms existing artifact suppression techniques according to performance measures. Conclusions: This advancement is important for brain science and can contribute as an initial pre-processing step for research related to EEG signals.
Open AccessCirculant Singular Spectrum Analysis and Discrete Wavelet Transform for Automated Removal of EOG Artifacts from EEG Signals
Background: Portable electroencephalogram (EEG) systems are often used in health care applications to record brain signals because their ease of use. An electrooculogram (EOG) is a common, low frequency, high amplitude artifact of the eye blink signal that might confuse disease diagnosis. As a result, artifact removal approaches in single EEG portable devices are in high demand. Materials: Dataset 2a from the BCI Competition IV was employed. It contains the EEG data from nine subjects. To determine the EOG effect, each session starts with 5 min of EEG data. This recording lasted for two minutes with the eyes open, one minute with the eyes closed, and one minute with eye movements. Methodology: This article presents the automated removal of EOG artifacts from EEG signals. Circulant Singular Spectrum Analysis (CiSSA) was used to decompose the EOG contaminated EEG signals into intrinsic mode functions (IMFs). Next, we identified the artifact signal components using kurtosis and energy values and removed them using 4-level discrete wavelet transform (DWT). Results: The proposed approach was evaluated on synthetic and real EEG data and found to be effective in eliminating EOG artifacts while maintaining low frequency EEG information. CiSSA-DWT achieved the best signal to artifact ratio (SAR), mean absolute error (MAE), relative root mean square error (RRMSE), and correlation coefficient (CC) of 1.4525, 0.0801, 18.274, and 0.9883, respectively. Comparison: The developed technique outperforms existing artifact suppression techniques according to performance measures. Conclusions: This advancement is important for brain science and can contribute as an initial pre-processing step for research related to EEG signals.