Arpit Kumar Sharma

Arpit Kumar Sharma

Auto-generated profile, based on publicly available information

Arpit Kumar Sharma

Department of Computer and Communication Engineering, Manipal University Jaipur, Jaipur, India

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

19 April 2026 in Discover Computing
Verified
Journal Article
Open access
PDF file
PSPriyanka Suram
Priyanka Suram
DBDebajyoty Banik
Debajyoty Banik
ASArpit Kumar Sharma
Arpit Kumar Sharma
Large language models based machine translation has significantly improved the fluency, adequacy, and context awareness of translations across various languages and domains. This enhancement has been achieved through comprehensive research efforts. The primary objective of this paper is to present a detailed analysis of large language model-based machine translation. We also accomplished the comprehensive compilation of different large language model-based machine translation approaches, datasets, and assessment criteria. Along with the comparative analysis with the contextual behaviors, we also identified different research gaps that may be useful for the future research of the natural language processing research community. The primary objective of this study is to determine suitable methods for enhancing translation adequacy and fluency based on the situations. In this context, three research questions are raised in the study with three objectives. One issue is whether the use of large language models (LLM) in machine translation (MT) can improve the adequacy, fluency, and ambiguity resolution. We also analysed different multimodal machine translation approaches with large language models.

29 June 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
RDRitika Dubey
Ritika Dubey
ADArvind Dhaka
Arvind Dhaka
ANAmita Nandal
Amita Nandal
ASArpit Kumar Sharma
Arpit Kumar Sharma
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.

2 October 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
VPVivek Parmar
Vivek Parmar
SLShirshendu Layek
Shirshendu Layek
MBMegha Bhushan
Megha Bhushan
SMShaswat Singh Mehta
Shaswat Singh Mehta
SHS. P. Harsha
S. P. Harsha
ASArpit Kumar Sharma
Arpit Kumar Sharma
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 July 2025 in International Journal of Environmental Sciences
Verified
Journal Article
Open access
PDF file
ASArpit Sharma
Arpit Sharma
SCSunita Choudhary
Sunita Choudhary
ASArpana Sinhal
Arpana Sinhal
KGKamlesh Gautam
Kamlesh Gautam
ASArvind Sharma
Arvind Sharma
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.

10 April 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
ADArvind Dhaka
Arvind Dhaka
ASArpit Kumar Sharma
Arpit Kumar Sharma
ANAmita Nandal
Amita Nandal
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.