Vimal Kumar Shrivastava
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Vimal Kumar Shrivastava has a total of 64 co-authors. Here are the top co-authors by number of shared publications:
- Jasjit S. Suri
Department of ECE, Idaho State University, Pocatello, ID 83209, USA
7 shared publications Narendra D. Londhe
Department of Electrical Engineering, NIT Raipur, Chhattisgarh, India
7 shared publications- Narendra Digambar Londhe
Electrical Engineering Department, National Institute of Technology Raipur
5 shared publications - Rajendra S. Sonawane
Psoriasis Clinic and Research Centre, Psoriatreat, Pune, Maharashtra, India
5 shared publications Andrew Nicolaides
Vascular Screening and Diagnostic Centre, London, England; Vascular Diagnostic Centre, University of Cyprus, Nicosia, Cyprus
3 shared publicationsJasjit S. Suri
3 shared publications
Latest Publications
- 26 May 2025
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 35 (3)
Enhancing Melanoma Detection With Anisotropic Median Filtering and Multinomial Classification Vision Transformer
Skin cancer is one of the most prevalent and dangerous types of cancer globally, caused by unrepaired DNA damage leading to abnormal cell growth in the epidermis. Melanoma, in particular, is one of the most hazardous forms, requiring early and precise diagnosis to improve patient outcomes. Early detection and diagnosis are vital for reducing the mortality rates associated with this aggressive cancer. In this paper, we propose a novel approach that combines an anisotropic median filter (AMF) with a modified vision transformer, termed the Multinomial Classification Vision Transformer (MCVT) for skin cancer classification. The AMF is used as pre‐processing to effectively remove noise and enhance image quality, preserving critical features essential for accurate classification. On the other hand, the MCVT leverages its robust feature extraction capabilities to classify melanoma with high accuracy. We utilized the HAM10000 dataset for training and evaluation. Our proposed method outperforms existing state‐of‐the‐art techniques, achieving an overall classification accuracy of 91% and a melanoma classification accuracy of 89%. These results demonstrate the potential of integrating AMF and MCVT to enhance skin cancer classification, with a particular focus on improving melanoma detection.
- 26 May 2025
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 35 (3)
Enhancing Melanoma Detection With Anisotropic Median Filtering and Multinomial Classification Vision Transformer
Skin cancer is one of the most prevalent and dangerous types of cancer globally, caused by unrepaired DNA damage leading to abnormal cell growth in the epidermis. Melanoma, in particular, is one of the most hazardous forms, requiring early and precise diagnosis to improve patient outcomes. Early detection and diagnosis are vital for reducing the mortality rates associated with this aggressive cancer. In this paper, we propose a novel approach that combines an anisotropic median filter (AMF) with a modified vision transformer, termed the Multinomial Classification Vision Transformer (MCVT) for skin cancer classification. The AMF is used as pre‐processing to effectively remove noise and enhance image quality, preserving critical features essential for accurate classification. On the other hand, the MCVT leverages its robust feature extraction capabilities to classify melanoma with high accuracy. We utilized the HAM10000 dataset for training and evaluation. Our proposed method outperforms existing state‐of‐the‐art techniques, achieving an overall classification accuracy of 91% and a melanoma classification accuracy of 89%. These results demonstrate the potential of integrating AMF and MCVT to enhance skin cancer classification, with a particular focus on improving melanoma detection.
- Open Access
- 16 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 72087-72103
Sb-PiPLU: A Novel Parametric Activation Function for Deep Learning
The choice of activation function—particularly non-linear ones—plays a vital role in enhancing the classification performance of deep neural networks. In recent years, a variety of non-linear activation functions have been proposed. However, many of these suffer from drawbacks that limit the effectiveness of deep learning models. Common issues include the dying neuron problem, bias shift, gradient explosion, and vanishing gradients. To address these challenges, we introduce a new activation function: Softsign-based Piecewise Parametric Linear Unit (Sb-PiPLU). This function offers improved non-linear approximation capabilities for neural networks. Its piecewise, parametric design allows for greater adaptability and flexibility, which in turn enhances overall model performance. We evaluated Sb-PiPLU through a series of image classification experiments across various Convolutional Neural Network (CNN) architectures. Additionally, we assessed its memory usage and computational cost, demonstrating that Sb-PiPLU is both stable and efficient in practical applications. Our experimental results show that Sb-PiPLU consistently outperforms conventional activation functions in both classification accuracy and computational efficiency. It achieved higher accuracy on multiple benchmark datasets, including CIFAR-10, CINIC-10, MWD, Brain Tumor, and SVHN, surpassing widely-used functions such as ReLU and Tanh. Due to its flexibility and robustness, Sb-PiPLU is particularly well-suited for complex image classification tasks.
- 16 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 72087-72103
Open AccessSb-PiPLU: A Novel Parametric Activation Function for Deep Learning
The choice of activation function—particularly non-linear ones—plays a vital role in enhancing the classification performance of deep neural networks. In recent years, a variety of non-linear activation functions have been proposed. However, many of these suffer from drawbacks that limit the effectiveness of deep learning models. Common issues include the dying neuron problem, bias shift, gradient explosion, and vanishing gradients. To address these challenges, we introduce a new activation function: Softsign-based Piecewise Parametric Linear Unit (Sb-PiPLU). This function offers improved non-linear approximation capabilities for neural networks. Its piecewise, parametric design allows for greater adaptability and flexibility, which in turn enhances overall model performance. We evaluated Sb-PiPLU through a series of image classification experiments across various Convolutional Neural Network (CNN) architectures. Additionally, we assessed its memory usage and computational cost, demonstrating that Sb-PiPLU is both stable and efficient in practical applications. Our experimental results show that Sb-PiPLU consistently outperforms conventional activation functions in both classification accuracy and computational efficiency. It achieved higher accuracy on multiple benchmark datasets, including CIFAR-10, CINIC-10, MWD, Brain Tumor, and SVHN, surpassing widely-used functions such as ReLU and Tanh. Due to its flexibility and robustness, Sb-PiPLU is particularly well-suited for complex image classification tasks.
- 11 March 2025
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
- Vol. 29 (6) , 1549-1567
Improved performance on melanoma skin cancer classification using deep learning based ensemble technique
Skin cancer, particularly melanoma, arises from DNA damage that leads to abnormal cell growth in the epidermis. Early detection is crucial as melanoma can spread rapidly, but it is highly curable if identified promptly. Detecting and diagnosing melanoma early are essential to reduce mortality rates associated with this type of cancer. In the literature, various ensemble techniques have been proposed to improve the performance. This paper introduces a deep learning based ensemble method aimed at enhancing the accuracy of melanoma skin cancer detection. Additionally, it presents a thorough performance evaluation of five ensemble techniques. Initially, the dataset underwent pre-processing, involving the removal of artifacts through hair removal, and achieving a balance in the distribution of images for each class through image augmentation techniques. Then, the architecture of 16 pre-trained models was modified by adding additional layers to improve their performance. The models that achieved the highest melanoma accuracy were selected for ensembling. Since VGG16, MobileNetV2, and DenseNet169 achieved the highest melanoma accuracy, they were chosen for ensembling. Five ensemble techniques, namely, weighted average, voting, bagging, boosting, and stacking, were applied to the modified architectures of fine-tuned pre-trained models such as VGG16, MobileNetV2, and DenseNet169 to classify skin cancer images. The experiments were performed on a combined dataset of HAM10000 and ISIC2019, which contains images of seven skin lesion classes. The results demonstrate that the weighted average ensemble model achieves highest overall accuracy of 81.99% and melanoma classification accuracy of 89.85%. The positive outcomes affirm that employing ensemble techniques with adjusted model architectures enhances performance, thereby demonstrating their potential utility in the classification of skin cancer images.
- 11 March 2025
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
- Vol. 29 (6) , 1549-1567
Improved performance on melanoma skin cancer classification using deep learning based ensemble technique
Skin cancer, particularly melanoma, arises from DNA damage that leads to abnormal cell growth in the epidermis. Early detection is crucial as melanoma can spread rapidly, but it is highly curable if identified promptly. Detecting and diagnosing melanoma early are essential to reduce mortality rates associated with this type of cancer. In the literature, various ensemble techniques have been proposed to improve the performance. This paper introduces a deep learning based ensemble method aimed at enhancing the accuracy of melanoma skin cancer detection. Additionally, it presents a thorough performance evaluation of five ensemble techniques. Initially, the dataset underwent pre-processing, involving the removal of artifacts through hair removal, and achieving a balance in the distribution of images for each class through image augmentation techniques. Then, the architecture of 16 pre-trained models was modified by adding additional layers to improve their performance. The models that achieved the highest melanoma accuracy were selected for ensembling. Since VGG16, MobileNetV2, and DenseNet169 achieved the highest melanoma accuracy, they were chosen for ensembling. Five ensemble techniques, namely, weighted average, voting, bagging, boosting, and stacking, were applied to the modified architectures of fine-tuned pre-trained models such as VGG16, MobileNetV2, and DenseNet169 to classify skin cancer images. The experiments were performed on a combined dataset of HAM10000 and ISIC2019, which contains images of seven skin lesion classes. The results demonstrate that the weighted average ensemble model achieves highest overall accuracy of 81.99% and melanoma classification accuracy of 89.85%. The positive outcomes affirm that employing ensemble techniques with adjusted model architectures enhances performance, thereby demonstrating their potential utility in the classification of skin cancer images.
- 13 September 2024
- Published by Springer Nature in Journal of the Indian Society of Remote Sensing
- Vol. 53 (2) , 405-419
Improved Building Extraction from Remotely Sensed Images by Integration of Encode–Decoder and Edge Enhancement Models
- 13 September 2024
- Published by Springer Nature in Journal of the Indian Society of Remote Sensing
- Vol. 53 (2) , 405-419
Improved Building Extraction from Remotely Sensed Images by Integration of Encode–Decoder and Edge Enhancement Models
- 5 July 2024
- Published by Springer Nature
- p. 541-550
Loss Function Analysis for Building Extraction from Remote Sensing Images
- 5 July 2024
- Published by Springer Nature
- p. 541-550
Loss Function Analysis for Building Extraction from Remote Sensing Images
- 30 September 2023
- Published by Springer Nature
- p. 121-131
Effect of Dropout on Convolutional Neural Network for Hyperspectral Image Classification
- 30 September 2023
- Published by Springer Nature
- p. 121-131
Effect of Dropout on Convolutional Neural Network for Hyperspectral Image Classification
- 14 October 2022
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 150, 106183
A novel Parametric Flatten-p Mish activation function based deep CNN model for brain tumor classification
- 14 October 2022
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 150, 106183
A novel Parametric Flatten-p Mish activation function based deep CNN model for brain tumor classification
- 2 June 2022
- Published by Springer Nature
- p. 539-549
A BERT Model-Based Sentiment Analysis on COVID-19 Tweets
- 2 June 2022
- Published by Springer Nature
- p. 539-549
A BERT Model-Based Sentiment Analysis on COVID-19 Tweets
- 9 March 2022
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 16 (3) , 729-738
Diagnosis of COVID-19 using chest X-ray images based on modified DarkCovidNet model
Coronavirus disease, also known as COVID-19, is an infectious disease caused by SARS-CoV-2. It has a direct impact on the upper and lower respiratory tract and threatened the health of many people around the world. The latest statistics show that the number of people diagnosed with COVID-19 is growing exponentially. Diagnosing positive cases of COVID-19 is important for preventing further spread of the disease. Currently, Coronavirus is a serious threat to scientists, medical experts and researchers around the world from its detection to its treatment. It is currently detected using reverse transcription polymerase chain reaction (RT-PCR) analysis at the most test centers around the world. Yet, knowing the reliability of a deep learning based medical diagnosis is important for doctors to build confidence in the technology and improve treatment. The goal of this study is to develop a model that automatically identifies COVID-19 by using chest X-ray images. To achieve this, we modified the DarkCovidNet model which is based on a convolutional neural network (CNN) and plotted the experimental results for two scenarios: binary classification (COVID-19 versus No-findings) and multi-class classification (COVID-19 versus pneumonia versus No-findings). The model is trained on more than 10 thousand X-ray images and achieved an average accuracy of 99.53% and 94.18% for binary and multi-class classification, respectively. Therefore, the proposed method demonstrates the effectiveness of COVID-19 detection using X-ray images. Our model can be used to test the patient via cloud and also be used in situations where RT-PCR tests and other options aren't available.
- 9 March 2022
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 16 (3) , 729-738
Diagnosis of COVID-19 using chest X-ray images based on modified DarkCovidNet model
Coronavirus disease, also known as COVID-19, is an infectious disease caused by SARS-CoV-2. It has a direct impact on the upper and lower respiratory tract and threatened the health of many people around the world. The latest statistics show that the number of people diagnosed with COVID-19 is growing exponentially. Diagnosing positive cases of COVID-19 is important for preventing further spread of the disease. Currently, Coronavirus is a serious threat to scientists, medical experts and researchers around the world from its detection to its treatment. It is currently detected using reverse transcription polymerase chain reaction (RT-PCR) analysis at the most test centers around the world. Yet, knowing the reliability of a deep learning based medical diagnosis is important for doctors to build confidence in the technology and improve treatment. The goal of this study is to develop a model that automatically identifies COVID-19 by using chest X-ray images. To achieve this, we modified the DarkCovidNet model which is based on a convolutional neural network (CNN) and plotted the experimental results for two scenarios: binary classification (COVID-19 versus No-findings) and multi-class classification (COVID-19 versus pneumonia versus No-findings). The model is trained on more than 10 thousand X-ray images and achieved an average accuracy of 99.53% and 94.18% for binary and multi-class classification, respectively. Therefore, the proposed method demonstrates the effectiveness of COVID-19 detection using X-ray images. Our model can be used to test the patient via cloud and also be used in situations where RT-PCR tests and other options aren't available.