Hemant Kumar

Dr. Hemant Kumar

Computing and Information Science, Chandigrah University, Lucknow, India
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2024 in MethodsX
Verified
Journal Article
Open access
VAVishal Awasthi
Vishal Awasthi
NANamita Awasthi
Namita Awasthi
Hemant KumarHemant Kumar
Hemant Kumar
SSShubhendra Singh
Shubhendra Singh
PSPrabal Pratap Singh
Prabal Pratap Singh
RARashi Agarwal
Rashi Agarwal
Diabetic retinopathy (DR) is a significant cause of vision impairment globally, emphasizing the importance of timely and precise detection to prevent severe consequences. This study presents an optimized Vision Transformer (ViT) model that incorporates Harris Hawk Optimization (HHO) to improve the automated detection of diabetic retinopathy (DR). The ViT architecture utilizes self-attention mechanisms to capture local and global features in retinal images. Additionally, HHO optimizes key hyperparameters to maximize the performance of the model. The proposed ViT-HHO model achieved exceptional performance on the APTOS-2019 and IDRiD datasets. Specifically, it achieved 99.83 % accuracy, 99.78 % sensitivity, 99.85 % specificity, and 99.80 % AUC-ROC on the APTOS-2019 dataset, surpassing traditional CNNs and alternative optimization techniques. The model exhibited strong generalization on the IDRiID dataset, achieving an accuracy of 99.11 % and an AUC-ROC of 99.12 %. The ViT-HHO model demonstrates the potential for enhancing the clinical detection of diabetic retinopathy (DR), providing high precision and reliability. • An optimized Vision Transformer (ViT) model was developed using HHO for improved detection of Diabetic Retinopathy (DR). • The model was validated on the APTOS-2019 and IDRiID datasets, demonstrating superior accuracy and AUC-ROC metrics. • The model's generalization and robustness were demonstrated through comprehensive performance evaluations.

11 February 2025 in Journal of Electronics, Electromedical Engineering, and Medical Informatics
Verified
Journal Article
Open access
PDF file
Hemant KumarHemant Kumar
Hemant Kumar
RSRishabh Sachan
Rishabh Sachan
MTMamta Tiwari
Mamta Tiwari
AKAmit Kumar Katiyar
Amit Kumar Katiyar
NANamita Awasthi
Namita Awasthi
PMPuspha Mamoria
Puspha Mamoria
Sign-language recognition (SLR) plays a pivotal role in enhancing communication accessibility and fostering the inclusion of deaf communities. Despite significant advancements in SLR systems, challenges such as variability in sign language gestures, the need for real-time processing, and the complexity of capturing spatiotemporal dependencies remain unresolved. This study aims to address these limitations by proposing an advanced framework that integrates deep learning and machine learning techniques to optimize sign language recognition systems, with a focus on the Indian Sign Language (ISL) dataset. The framework leverages MobileNetV3 for feature extraction, which is selected after rigorous evaluation against VGG16, ResNet50, and EfficientNet-B0. MobileNetV3 demonstrates superior accuracy and efficiency, making it optimal for this task. To enhance the model's ability to capture complex dependencies and contextual information, multi-head self-attention (MHSA) was incorporated. This process enriches the extracted features, enabling a better understanding of sign language gestures. Finally, LightGBM, a gradient-boosting algorithm that is efficient for large-scale datasets, was employed for classification. The proposed framework achieved remarkable results, with a test accuracy of 98.42%, precision of 98.19%, recall of 98.81%, and an F1-score of 98.15%. The integration of MobileNetV3, MHSA, and LightGBM offers a robust and adaptable solution that outperforms the existing methods, demonstrating its potential for real-world deployment. In conclusion, this study advances precise and accessible communication technologies for deaf individuals, contributing to more inclusive and effective human-computer interaction systems. The proposed framework represents a significant step forward in SLR research by addressing the challenges of variability, real-time processing, and spatiotemporal dependency. Future work will expand the dataset to include more diverse gestures and environmental conditions and explore cross-lingual adaptations to enhance the model’s applicability and impact.

3 July 2024 in MethodsX
Verified
Journal Article
Open access
Hemant KumarHemant Kumar
Hemant Kumar
ADAbhishek Dwivedi
Abhishek Dwivedi
AMAbhishek Kumar Mishra
Abhishek Kumar Mishra
ASArvind Kumar Shukla
Arvind Kumar Shukla
BSBrajesh Kumar Sharma
Brajesh Kumar Sharma
SKSunil Kumar
Sunil Kumar
Melanoma is a type of skin cancer that poses significant health risks and requires early detection for effective treatment. This study proposing a novel approach that integrates a transformer-based model with hand-crafted texture features and Gray Wolf Optimization, aiming to enhance efficiency of melanoma classification. Preprocessing involves standardizing image dimensions and enhancing image quality through median filtering techniques. Texture features, including GLCM and LBP, are extracted to capture spatial patterns indicative of melanoma. The GWO algorithm is applied to select the most discriminative features. A transformer-based decoder is then employed for classification, leveraging attention mechanisms to capture contextual dependencies. The experimental validation on the HAM10000 dataset and ISIC2019 dataset showcases the effectiveness of the proposed methodology. The transformer-based model, integrated with hand-crafted texture features and guided by Gray Wolf Optimization, achieves outstanding results. The results showed that the proposed method performed well in melanoma detection tasks, achieving an accuracy and F1-score of 99.54% and 99.11% on the HAM10000 dataset, and an accuracy of 99.47%, and F1-score of 99.25% on the ISIC2019 dataset.

6 March 2025 in MethodsX
Verified
Journal Article
Open access
VAVishal Awasthi
Vishal Awasthi
MTMamta Tiwari
Mamta Tiwari
AYAmit Yadav
Amit Yadav
GTGesu Thakur
Gesu Thakur
MPMamata Mayee Panda
Mamata Mayee Panda
STShivneet Tripathi
Shivneet Tripathi
This study presents an automated framework for brain tumor classification aimed at accurately distinguishing tumor types in MRI images. The proposed model integrates InceptionResNetV2 for feature extraction with Deep Stacked Autoencoders (DSAEs) for classification, enhanced by sparsity regularization and the SwiGLU activation function. InceptionResNetV2, pre-trained on ImageNet, was fine-tuned to extract multi-scale features, while the DSAE structure compressed these features to highlight critical attributes essential for classification. The approach achieved high performance, reaching an overall accuracy of 99.53 %, precision of 98.27 %, recall of 99.21 %, specificity of 98.73 %, and an F1-score of 98.74 %. These results demonstrate the model's efficacy in accurately categorizing glioma, meningioma, pituitary tumors, and non-tumor cases, with minimal misclassifications. Despite its success, limitations include the model's dependency on pre-trained weights and significant computational resources. Future studies should address these limitations by enhancing interpretability, exploring domain-specific transfer learning, and validating on diverse datasets to strengthen the model's utility in real-world settings. Overall, the InceptionResNetV2 integrated with DSAEs, sparsity regularization, and SwiGLU offers a promising solution for reliable and efficient brain tumor diagnosis in clinical environments.•Leveraging a pre-trained InceptionResNetV2 model to capture multi-scale features from MRI data.•Utilizing Deep Stacked Autoencoders with sparsity regularization to emphasize critical attributes for precise classification.•Incorporating the SwiGLU activation function to capture complex, non-linear patterns within the data.


28 June 2024
Verified
Book Chapter
Closed access
BKBrajesh Kumar Khare
Brajesh Kumar Khare
DSDeshraj Sahu
Deshraj Sahu
DPDIGVIJAY PANDEY
DIGVIJAY PANDEY
MTMamta Tiwari
Mamta Tiwari
Hemant KumarHemant Kumar
Hemant Kumar
NSNigar Siddiqui
Nigar Siddiqui
The chapter explores the use of machine learning (ML) in detecting and addressing anomalies in advanced 6G communication systems. It emphasizes the drawbacks of conventional approaches and delves into ML algorithms that are appropriate for identifying anomalies, such as clustering, classification, and deep learning. The study focuses on the difficulties of choosing important features from various data sources in 6G networks, including network traffic and device behavior. It also explores possible attacks on ML models and suggests ways to improve their resilience. Exploring integration with network slicing and highlighting the adaptability of ML to dynamic virtualized networks. The chapter highlights the importance of ML-based anomaly detection in strengthening 6G network security and suggests areas for future research.