Arpit Kumar Sharma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Arpit Kumar Sharma has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Amita Nandal
Department of IOT & IS, Manipal University Jaipur, Jaipur, India
4 shared publications - Arvind Dhaka
Department of Computer and Communication Engineering, Manipal University Jaipur, Jaipur, India
3 shared publications - Akanksha Chaturvedi
Department of Computer and Communication Engineering, Manipal University Jaipur, Jaipur, India
2 shared publications - Arpana Sinhal
Manipal University Jaipur, Jaipur, India
2 shared publications - Arvind Dhaka
Department of Computer and Communication Engineering, Manipal University Jaipur, Jaipur, India
2 shared publications - Amit Sinhal
JK Lakshmipat University
1 shared publication
Latest Publications
- Open Access
- 4 September 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1) , 334
An Efficient Video Steganography Approach for Secure and Low-distortion Data Embedding and Extraction
The growing requirement for secure multimedia communication has tested typical video steganography methods, which often trade off embedding capacity, visual quality, and signal-processing robustness. This study proposes an adaptive Discrete Wavelet Transform (DWT)-based video steganography architecture that uses key-based pseudo-random frame selection and adaptive coefficient embedding to hide data safely and undetected. Two layers of Haar DWT deconstruct selected video frames, and a dynamic scaling factor based on local and global statistical parameters encodes hidden information in LH and HL sub-bands. We test the proposed system on the UCF101 dataset of human action videos under Gaussian noise, JPEG compression, filtering, and frame dropping. Experimental results demonstrate that the recommended approach generates a high peak signal to noise ratio (PSNR) of 43.85 dB and a low MSE of 4.12, resulting in excellent visual clarity with reduced distortion. The suggested framework has a maximum embedding capacity of 0.58 bpp, outperforming LSB, DCT, and DWT. Robustness analysis shows a bit error rate < 0.02 with common attacks, ensuring data recovery and signal resilience. Results reveal that the adaptive DWT design balances security, embedding efficiency, and visual quality, making it suitable for secure multimedia transmission and digital content protection.
- 4 September 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1) , 334
Open AccessAn Efficient Video Steganography Approach for Secure and Low-distortion Data Embedding and Extraction
The growing requirement for secure multimedia communication has tested typical video steganography methods, which often trade off embedding capacity, visual quality, and signal-processing robustness. This study proposes an adaptive Discrete Wavelet Transform (DWT)-based video steganography architecture that uses key-based pseudo-random frame selection and adaptive coefficient embedding to hide data safely and undetected. Two layers of Haar DWT deconstruct selected video frames, and a dynamic scaling factor based on local and global statistical parameters encodes hidden information in LH and HL sub-bands. We test the proposed system on the UCF101 dataset of human action videos under Gaussian noise, JPEG compression, filtering, and frame dropping. Experimental results demonstrate that the recommended approach generates a high peak signal to noise ratio (PSNR) of 43.85 dB and a low MSE of 4.12, resulting in excellent visual clarity with reduced distortion. The suggested framework has a maximum embedding capacity of 0.58 bpp, outperforming LSB, DCT, and DWT. Robustness analysis shows a bit error rate < 0.02 with common attacks, ensuring data recovery and signal resilience. Results reveal that the adaptive DWT design balances security, embedding efficiency, and visual quality, making it suitable for secure multimedia transmission and digital content protection.
- Open Access
- 10 July 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Joint semantic segmentation and steganography for scene understanding and secure data hiding in remote sensing images
- 10 July 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Open AccessJoint semantic segmentation and steganography for scene understanding and secure data hiding in remote sensing images
- 2 July 2026
- Published by Springer Nature
- p. 537-552
Performance Comparison of Lightweight Cryptographic Algorithms for IoT Security
- 2 July 2026
- Published by Springer Nature
- p. 537-552
Performance Comparison of Lightweight Cryptographic Algorithms for IoT Security
- Open Access
- 30 June 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 406
Energy–lifetime aware cluster head selection in wireless sensor networks using an adaptive hybrid GWO–PSO framework
- 30 June 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 406
Open AccessEnergy–lifetime aware cluster head selection in wireless sensor networks using an adaptive hybrid GWO–PSO framework
- Open Access
- 29 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
An attention-guided multimodal deep learning framework by integrating CT-PET imaging and clinical data for lung cancer detection
The proposed multi-modal deep learning system for lung cancer diagnosis and characterisation uses structural (CT), functional (PET), and clinical (EHR) data. The heterogeneous information fusion technique uses a clinical data encoder, an attention-based fusion mechanism, and a convolutional neural network backbone for image feature extraction. Multi-task learning combines tumor categorization and characterization. Optimal hyperparameters for model training are 0.001 learning rate, 32 batch size, and 0.3 dropout rate for steady convergence and enhanced generalization. The ablation investigation’s 9% accuracy gain over the baseline model is mostly due to the attention mechanism. As model components are added, the ablation research shows a continuous and considerable performance increase. From the basic setup, adding PET data, EHR-based clinical characteristics, and enhanced fusion techniques improves all assessment measures. Attention-based fusion improves the most by adaptively weighting modalities. Compared with the baseline CT-only CNN model, the proposed attention-guided multimodal framework achieved consistent improvements across all evaluation metrics. Specifically, classification accuracy increased from 88.2% to 96.5%, corresponding to an absolute improvement of 8.3 percentage points. Precision improved from 87.5% to 95.8% (+ 8.3 percentage points), recall increased from 86.9% to 96.2% (+ 9.3 percentage points), and the F1-score increased from 87.2% to 96.0% (+ 8.8 percentage points). Similarly, the AUC-ROC improved from 0.901 to 0.982, representing an absolute increase of 0.081. These results demonstrate that the proposed multimodal attention-based framework substantially enhances classification performance and discrimination capability compared with the baseline model. According to five-fold cross-validation, the proposed model achieved an average accuracy of 96.5 ± 0.23%, precision of 95.8 ± 0.26%, recall of 96.2 ± 0.21%, F1-score of 96.0 ± 0.24%, and AUC of 0.982 ± 0.003. The performance gains were statistically significant (p < 0.05) compared with competing configurations and baseline models, confirming the robustness and effectiveness of the proposed framework.
- 29 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessAn attention-guided multimodal deep learning framework by integrating CT-PET imaging and clinical data for lung cancer detection
The proposed multi-modal deep learning system for lung cancer diagnosis and characterisation uses structural (CT), functional (PET), and clinical (EHR) data. The heterogeneous information fusion technique uses a clinical data encoder, an attention-based fusion mechanism, and a convolutional neural network backbone for image feature extraction. Multi-task learning combines tumor categorization and characterization. Optimal hyperparameters for model training are 0.001 learning rate, 32 batch size, and 0.3 dropout rate for steady convergence and enhanced generalization. The ablation investigation’s 9% accuracy gain over the baseline model is mostly due to the attention mechanism. As model components are added, the ablation research shows a continuous and considerable performance increase. From the basic setup, adding PET data, EHR-based clinical characteristics, and enhanced fusion techniques improves all assessment measures. Attention-based fusion improves the most by adaptively weighting modalities. Compared with the baseline CT-only CNN model, the proposed attention-guided multimodal framework achieved consistent improvements across all evaluation metrics. Specifically, classification accuracy increased from 88.2% to 96.5%, corresponding to an absolute improvement of 8.3 percentage points. Precision improved from 87.5% to 95.8% (+ 8.3 percentage points), recall increased from 86.9% to 96.2% (+ 9.3 percentage points), and the F1-score increased from 87.2% to 96.0% (+ 8.8 percentage points). Similarly, the AUC-ROC improved from 0.901 to 0.982, representing an absolute increase of 0.081. These results demonstrate that the proposed multimodal attention-based framework substantially enhances classification performance and discrimination capability compared with the baseline model. According to five-fold cross-validation, the proposed model achieved an average accuracy of 96.5 ± 0.23%, precision of 95.8 ± 0.26%, recall of 96.2 ± 0.21%, F1-score of 96.0 ± 0.24%, and AUC of 0.982 ± 0.003. The performance gains were statistically significant (p < 0.05) compared with competing configurations and baseline models, confirming the robustness and effectiveness of the proposed framework.
- Top Cited PapersOpen Access
- 19 April 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 217
Large language model based machine translation for universal multilingual understanding and translation quality enhancement
- 19 April 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 217
Top Cited PapersOpen AccessLarge language model based machine translation for universal multilingual understanding and translation quality enhancement
- Open Access
- 10 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Real-time medical images enhancement technique using Adaptive Histogram Equalization model
In low-contrast modalities like magnetic resonance imaging, medical image augmentation helps reveal anatomical structures and diseased locations. This paper presents an adaptive histogram-based contrast enhancement technique to improve medical picture quality while conserving structure. The suggested approach enhances tumor areas and tissue borders without artifacts using statistical normalization, adaptive histogram modeling, Gaussian-based intensity redistribution, and brightness-preserving contrast modification. T1, T2, FLAIR, and contrast-enhanced T1 MRI scans from the BraTS 2020 Brain Tumor Segmentation Dataset were used in experiments. The proposed method was compared to five state-of-the-art contrast enhancement methods: Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gamma Correction (GC), Retinex-based enhancement, and Adaptive Gamma Correction. Quantitative metrics like PSNR, MSE, SSIM, and entropy were used to evaluate the method’s performance. The suggested technique outperforms HE (31.46 dB), CLAHE (34.15 dB), Gamma Correction (32.74 dB), Retinex (35.21 dB), and Adaptive Gamma Correction (36.04 dB) in experimental PSNR (37.82 dB). The suggested technique has an SSIM of 0.962, compared to 0.891, 0.915, 0.902, 0.934, and 0.947 for the competing approaches. The approach decreases reconstruction error with an MSE of 18.4, lower than HE (42.7) and CLAHE (29.6). Qualitative analysis shows better contrast and tumor borders without brightness amplification. These findings show that the adaptive histogram approach enhances medical image analysis and diagnostic assistance systems robustly and efficiently.
- 10 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessReal-time medical images enhancement technique using Adaptive Histogram Equalization model
In low-contrast modalities like magnetic resonance imaging, medical image augmentation helps reveal anatomical structures and diseased locations. This paper presents an adaptive histogram-based contrast enhancement technique to improve medical picture quality while conserving structure. The suggested approach enhances tumor areas and tissue borders without artifacts using statistical normalization, adaptive histogram modeling, Gaussian-based intensity redistribution, and brightness-preserving contrast modification. T1, T2, FLAIR, and contrast-enhanced T1 MRI scans from the BraTS 2020 Brain Tumor Segmentation Dataset were used in experiments. The proposed method was compared to five state-of-the-art contrast enhancement methods: Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gamma Correction (GC), Retinex-based enhancement, and Adaptive Gamma Correction. Quantitative metrics like PSNR, MSE, SSIM, and entropy were used to evaluate the method’s performance. The suggested technique outperforms HE (31.46 dB), CLAHE (34.15 dB), Gamma Correction (32.74 dB), Retinex (35.21 dB), and Adaptive Gamma Correction (36.04 dB) in experimental PSNR (37.82 dB). The suggested technique has an SSIM of 0.962, compared to 0.891, 0.915, 0.902, 0.934, and 0.947 for the competing approaches. The approach decreases reconstruction error with an MSE of 18.4, lower than HE (42.7) and CLAHE (29.6). Qualitative analysis shows better contrast and tumor borders without brightness amplification. These findings show that the adaptive histogram approach enhances medical image analysis and diagnostic assistance systems robustly and efficiently.
- Open Access
- 2 October 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-20
Advanced deep learning approach for the fault severity classification of rolling-element bearings
A hybrid methodology for bearing fault and severity analysis using param, eter-optimized variational mode decomposition (VMD) and deep learning (DL) algorithms is presented in this study. Different localized defects are artificially seeded at the contacting surfaces of a self-aligning bearings, and vibration data is generated (Case study II) under various radial-load and speed conditions for DL algorithm development. This data is pre-processed using the parameter-optimized VMD, where the intrinsic mode function with the highest kurtosis is processed using a deep learning (DL) algorithm. Particle swarm optimization is used for optimizing two VMD parameters. Further, seven different DL algorithms are implemented to classify various fault severity of rolling-element bearings. These algorithms are validated against the standard repository dataset of Case Western Reserve University (Case study I). The reliability of these algorithms is also tested using the generated dataset (Case study II) and the results show that 1D-CNN, WaveNet and gated recurrent unit have outperformed all other algorithms by achieving accuracies of 99.65%, 97.05% and 97.33%, respectively.
- 2 October 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-20
Open AccessAdvanced deep learning approach for the fault severity classification of rolling-element bearings
A hybrid methodology for bearing fault and severity analysis using param, eter-optimized variational mode decomposition (VMD) and deep learning (DL) algorithms is presented in this study. Different localized defects are artificially seeded at the contacting surfaces of a self-aligning bearings, and vibration data is generated (Case study II) under various radial-load and speed conditions for DL algorithm development. This data is pre-processed using the parameter-optimized VMD, where the intrinsic mode function with the highest kurtosis is processed using a deep learning (DL) algorithm. Particle swarm optimization is used for optimizing two VMD parameters. Further, seven different DL algorithms are implemented to classify various fault severity of rolling-element bearings. These algorithms are validated against the standard repository dataset of Case Western Reserve University (Case study I). The reliability of these algorithms is also tested using the generated dataset (Case study II) and the results show that 1D-CNN, WaveNet and gated recurrent unit have outperformed all other algorithms by achieving accuracies of 99.65%, 97.05% and 97.33%, respectively.
- Open Access
- 2 July 2025
- Published by Academic Science Publications and Distributions in International Journal of Environmental Sciences
- p. 1227-1240
A Novel layers-based Framework for Edge Computing in Healthcare Applications
New technologies have greatly impacted the healthcare sector and increased the need for vital problem-solving solutions like edge computing. Edge computing processes data near the source to avoid high latency, band- width constraints, and inefficient systems that are unsuitable for real-time health care. In this paper, a novel framework is proposed that introduces edge computing layers for health care data management, privacy, and system reliability. The proposed framework has five layers: device, edge, fog, cloud, and application layers. Every system layer does data mining, cleansing, real-time processing, analysis, and decision making. A detailed simulation assessed the framework’s efficacy. Signal filtering, averaging, feature extraction, and classification were done using the edge layer approach before and after physiological signal simulation. Performance was compared to a noise-free reference technique. The simulation results showed that the suggested edge layer technique improved data quality and classification accuracy for real-time healthcare applications. This study discusses edge computing’s minimal delay, privacy, expandability, and reliability benefits in healthcare. Simulations showed that the framework improved data processing and decision-making over conventional methods. This research work is aligned with the SDG 3 – Good Health and Wellbeing. The study advises healthcare practitioners and policymakers to use edge computing for improved management, diagnosis, and treatment to im- prove healthcare delivery.
- 2 July 2025
- Published by Academic Science Publications and Distributions in International Journal of Environmental Sciences
- p. 1227-1240
Open AccessA Novel layers-based Framework for Edge Computing in Healthcare Applications
New technologies have greatly impacted the healthcare sector and increased the need for vital problem-solving solutions like edge computing. Edge computing processes data near the source to avoid high latency, band- width constraints, and inefficient systems that are unsuitable for real-time health care. In this paper, a novel framework is proposed that introduces edge computing layers for health care data management, privacy, and system reliability. The proposed framework has five layers: device, edge, fog, cloud, and application layers. Every system layer does data mining, cleansing, real-time processing, analysis, and decision making. A detailed simulation assessed the framework’s efficacy. Signal filtering, averaging, feature extraction, and classification were done using the edge layer approach before and after physiological signal simulation. Performance was compared to a noise-free reference technique. The simulation results showed that the suggested edge layer technique improved data quality and classification accuracy for real-time healthcare applications. This study discusses edge computing’s minimal delay, privacy, expandability, and reliability benefits in healthcare. Simulations showed that the framework improved data processing and decision-making over conventional methods. This research work is aligned with the SDG 3 – Good Health and Wellbeing. The study advises healthcare practitioners and policymakers to use edge computing for improved management, diagnosis, and treatment to im- prove healthcare delivery.
- Open Access
- 1 January 2025
- Published by Sakun Publishing House
- Vol. 24 (3s) , 372-386
LoRA-Tuned Segment Anything Model for Few-Shot Polyp Segmentation in Colonoscopy Images
Colorectal cancer is a leading cause of cancer mortality, and automated polyp segmentation in colonoscopy images is vital for early detection. However, deep segmentation models often require large, annotated datasets, which are scarce in medicine. We explore whether vision foundation models like the Segment Anything Model (SAM) can be adapted for accurate polyp segmentation with minimal labeled samples. We leverage SAM’s pre-trained ViT-H encoder, injecting lightweight LoRA adapters for fine-tuning on Kvasir-SEG (1,000 polyp images) with only 5–50 labeled examples. We also evaluated zero-shot MedSAM (a SAM model fine-tuned on 1.57M medical images) and a classic CNN (UNet++) for comparison. With only 2–5% of labels, our SAM-LoRA approach achieves a Dice score of 0.88–0.90, approaching the 0.91 Dice of a fully-supervised UNet++ trained on 100% data. It significantly outperforms both UNet++ with 20 labels (0.73 Dice) and zero-shot SAM variants. Adapter-tuned SAM retains strong segmentation capability with minimal annotated images, offering a compelling solution to label scarcity. We discuss failure modes on tiny polyps and the trade-off between SAM’s higher computational cost and its superior data efficiency. These findings highlight the promise of foundation models in few-shot medical image segmentation.
- 1 January 2025
- Published by Sakun Publishing House
- Vol. 24 (3s) , 372-386
Open AccessLoRA-Tuned Segment Anything Model for Few-Shot Polyp Segmentation in Colonoscopy Images
Colorectal cancer is a leading cause of cancer mortality, and automated polyp segmentation in colonoscopy images is vital for early detection. However, deep segmentation models often require large, annotated datasets, which are scarce in medicine. We explore whether vision foundation models like the Segment Anything Model (SAM) can be adapted for accurate polyp segmentation with minimal labeled samples. We leverage SAM’s pre-trained ViT-H encoder, injecting lightweight LoRA adapters for fine-tuning on Kvasir-SEG (1,000 polyp images) with only 5–50 labeled examples. We also evaluated zero-shot MedSAM (a SAM model fine-tuned on 1.57M medical images) and a classic CNN (UNet++) for comparison. With only 2–5% of labels, our SAM-LoRA approach achieves a Dice score of 0.88–0.90, approaching the 0.91 Dice of a fully-supervised UNet++ trained on 100% data. It significantly outperforms both UNet++ with 20 labels (0.73 Dice) and zero-shot SAM variants. Adapter-tuned SAM retains strong segmentation capability with minimal annotated images, offering a compelling solution to label scarcity. We discuss failure modes on tiny polyps and the trade-off between SAM’s higher computational cost and its superior data efficiency. These findings highlight the promise of foundation models in few-shot medical image segmentation.