Gaurav Kumar Ameta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Gaurav Kumar Ameta has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Ganesh Khekare
Vellore Institute of Technology
3 shared publications - Ajay Kumar Phulre
School of Computing Science and Artificial Intelligence, VIT Bhopal University,Bhopal,Madhya Pradesh,India
2 shared publications - Priya Dasarwar
Department of Computer Science and Engineering, Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune, India
2 shared publications - Pushpendra Singh Sisodia
Topia Life Sciences, Ahmedabad, India
2 shared publications Urvashi Khekare
Vellore Institute of Technology, India
2 shared publicationsAditi Aditi
1 shared publication
Latest Publications
- Open Access
- 1 October 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (5) , 3923-3934
Hybrid 3D CNN–transformer model for early brain tumor detection with multi-modal magnetic resonance imaging
Accurate and early diagnosis of brain tumors using multi-modal magnetic resonance imaging (MRI) remains a critical challenge due to tumor heterogeneity and complex spatial representation. This study proposes a novel hybrid deep learning framework that integrates a 3D convolutional neural network (3D CNN) with swin transformer blocks and an attention-based feature fusion module (ABFFM). The model leverages multi-modal MRI inputs—T1, T1Gd, T2, and fluid-attenuated inversion recovery (FLAIR)—and features a dual-branch classification head for binary tumor detection and multi-label tumor sub-region classification: enhancing tumor (ET), tumor core (TC), and whole tumor (WT). Experiments conducted on the BraTS2023-GLI dataset demonstrate that the proposed model achieves a superior classification accuracy of 96.51%, with precision of 97.98%, recall of 97.04%, and F1-score of 97.61%, outperforming state-of-the-art methods. Furthermore, intrinsic attention weights offer interpretability by highlighting modality-specific contributions. The proposed model establishes a clinically promising approach for brain tumor analysis, with strong implications for early diagnosis and treatment planning.
- 1 October 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (5) , 3923-3934
Open AccessHybrid 3D CNN–transformer model for early brain tumor detection with multi-modal magnetic resonance imaging
Accurate and early diagnosis of brain tumors using multi-modal magnetic resonance imaging (MRI) remains a critical challenge due to tumor heterogeneity and complex spatial representation. This study proposes a novel hybrid deep learning framework that integrates a 3D convolutional neural network (3D CNN) with swin transformer blocks and an attention-based feature fusion module (ABFFM). The model leverages multi-modal MRI inputs—T1, T1Gd, T2, and fluid-attenuated inversion recovery (FLAIR)—and features a dual-branch classification head for binary tumor detection and multi-label tumor sub-region classification: enhancing tumor (ET), tumor core (TC), and whole tumor (WT). Experiments conducted on the BraTS2023-GLI dataset demonstrate that the proposed model achieves a superior classification accuracy of 96.51%, with precision of 97.98%, recall of 97.04%, and F1-score of 97.61%, outperforming state-of-the-art methods. Furthermore, intrinsic attention weights offer interpretability by highlighting modality-specific contributions. The proposed model establishes a clinically promising approach for brain tumor analysis, with strong implications for early diagnosis and treatment planning.
- 5 February 2025
- Published by IGI Global Scientific Publishing
- p. 209-230
Advanced LSTM Neural Networks for Predicting Hospital Readmissions in Diabetic Patients
The development of the predictive model for forecasting hospital readmissions among diabetic patients represents a remarkable footstep in applying machine learning techniques. These are responsible for enhancing healthcare delivery. Ethical considerations, such as transparent judgment and bias monitoring, must be precisely addressed to uphold fairness and convince the therapist. The proposed model utilizes Long Short-Term Memory (LSTM) neural networks. The model has indicated a magnificent accuracy rate of 83% during pilot testing, this development results in a 39% reduction in the 30-day readmission rate with cost effective and enhanced diagnosis solutions. Ongoing research efforts should enhance model interpretability, explore new data sources, and maintain relevance through evolving architectures and methodologies. By addressing these multifaceted challenges through a comprehensive and iterative approach, this predictive model can potentially revolutionize chronic illness management, leading to improved patient outcomes and reduced operational costs within healthcare systems.
- 5 February 2025
- Published by IGI Global Scientific Publishing
- p. 209-230
Advanced LSTM Neural Networks for Predicting Hospital Readmissions in Diabetic Patients
The development of the predictive model for forecasting hospital readmissions among diabetic patients represents a remarkable footstep in applying machine learning techniques. These are responsible for enhancing healthcare delivery. Ethical considerations, such as transparent judgment and bias monitoring, must be precisely addressed to uphold fairness and convince the therapist. The proposed model utilizes Long Short-Term Memory (LSTM) neural networks. The model has indicated a magnificent accuracy rate of 83% during pilot testing, this development results in a 39% reduction in the 30-day readmission rate with cost effective and enhanced diagnosis solutions. Ongoing research efforts should enhance model interpretability, explore new data sources, and maintain relevance through evolving architectures and methodologies. By addressing these multifaceted challenges through a comprehensive and iterative approach, this predictive model can potentially revolutionize chronic illness management, leading to improved patient outcomes and reduced operational costs within healthcare systems.
- 10 January 2025
- Published by IGI Global Scientific Publishing
- p. 137-160
Advanced Fuzzy Logic for Predicting Hospital Readmissions in Diabetic Patients
The development of the predictive model for forecasting hospital readmissions among diabetic patients represents a remarkable footstep in applying fuzzy logic techniques. The proposed model Utilizing Long Short-Term Memory (LSTM) neural networks, the model has indicated a magnificent accuracy rate of 83% during pilot testing, this development results in a 39% reduction in the 30-day readmission rate. Although the model's current state is promising, several areas need focused attention for the establishment of its successful deployment in realistic situations and long-term sustainability. Ongoing research efforts should enhance model interpretability, explore new data sources, and maintain relevance through evolving architectures and methodologies. By addressing these multifaceted challenges through a comprehensive and iterative approach, this predictive model can potentially revolutionize chronic illness management, leading to improved patient outcomes and reduced operational costs within healthcare systems.
- 10 January 2025
- Published by IGI Global Scientific Publishing
- p. 137-160
Advanced Fuzzy Logic for Predicting Hospital Readmissions in Diabetic Patients
The development of the predictive model for forecasting hospital readmissions among diabetic patients represents a remarkable footstep in applying fuzzy logic techniques. The proposed model Utilizing Long Short-Term Memory (LSTM) neural networks, the model has indicated a magnificent accuracy rate of 83% during pilot testing, this development results in a 39% reduction in the 30-day readmission rate. Although the model's current state is promising, several areas need focused attention for the establishment of its successful deployment in realistic situations and long-term sustainability. Ongoing research efforts should enhance model interpretability, explore new data sources, and maintain relevance through evolving architectures and methodologies. By addressing these multifaceted challenges through a comprehensive and iterative approach, this predictive model can potentially revolutionize chronic illness management, leading to improved patient outcomes and reduced operational costs within healthcare systems.
- 1 January 2025
- Published by American Scientific Publishing Group (ASPG) LLC
- Vol. 19 (1) , 50-56
Gated Recurrent Fusion in Long Short-Term Memory Fusion
Fusion techniques on enhancing the efficiency of Long Short-Term Memory (LSTM) networks are dominating across a variety of domains. To handle sequential data while integrating from various sources is often challenging using LSTM techniques. Fusion methods that integrate different models enhances LSTM’ ability to handle complex correlations in the data. This paper examines early, late and hybrid fusion techniques. The study provides fusion approaches to enhance LSTM networks to efficiently handle complex multimodal data across self-navigating models. The findings reveal that the hybrid fusion techniques outperform traditional methods in terms of accuracy and generalization of various tasks. This paper proposes the Gated Recurrent Fusion (GRF) approach to demonstrate its performance to handle multimodal and temporal models in a supervised recurrence. The findings report 10% enhancement in terms of precision rate
- 1 January 2025
- Published by American Scientific Publishing Group (ASPG) LLC
- Vol. 19 (1) , 50-56
Gated Recurrent Fusion in Long Short-Term Memory Fusion
Fusion techniques on enhancing the efficiency of Long Short-Term Memory (LSTM) networks are dominating across a variety of domains. To handle sequential data while integrating from various sources is often challenging using LSTM techniques. Fusion methods that integrate different models enhances LSTM’ ability to handle complex correlations in the data. This paper examines early, late and hybrid fusion techniques. The study provides fusion approaches to enhance LSTM networks to efficiently handle complex multimodal data across self-navigating models. The findings reveal that the hybrid fusion techniques outperform traditional methods in terms of accuracy and generalization of various tasks. This paper proposes the Gated Recurrent Fusion (GRF) approach to demonstrate its performance to handle multimodal and temporal models in a supervised recurrence. The findings report 10% enhancement in terms of precision rate
- 13 November 2024
- Published by Taylor & Francis
- p. 252-262
Artificial Intelligence Algorithms for Better Decision-Making
To provide a better understanding of digital data, there is an ever-growing need for a product that not only analyses big data sets but also provides high accuracy in doing so. In this chapter, the authors aim to provide a platform that gives users crucial information from their existing data for better understanding customers. Machine learning algorithms are also being used to improve business decision-making and being studied in both industry and research. Digital data analysis has always been a challenge, and determining a suitable algorithm and model has been an intricate task. The authors of this research propose a novel platform for empirically determining the optimal algorithm for analyzing a given data set. Comparing algorithms for features such as accuracy and response times from the server helps to eliminate using trial and error to select the most appropriate algorithms. The authors test the developed interface using two distinct data sets: for binary classification (city vs. sell) and for multiclass classification of cell types. The work is carried out via the Python language and pytorch libraries with deep learning. This novel interface provides improved empirical analysis with better accuracy.
- 13 November 2024
- Published by Taylor & Francis
- p. 252-262
Artificial Intelligence Algorithms for Better Decision-Making
To provide a better understanding of digital data, there is an ever-growing need for a product that not only analyses big data sets but also provides high accuracy in doing so. In this chapter, the authors aim to provide a platform that gives users crucial information from their existing data for better understanding customers. Machine learning algorithms are also being used to improve business decision-making and being studied in both industry and research. Digital data analysis has always been a challenge, and determining a suitable algorithm and model has been an intricate task. The authors of this research propose a novel platform for empirically determining the optimal algorithm for analyzing a given data set. Comparing algorithms for features such as accuracy and response times from the server helps to eliminate using trial and error to select the most appropriate algorithms. The authors test the developed interface using two distinct data sets: for binary classification (city vs. sell) and for multiclass classification of cell types. The work is carried out via the Python language and pytorch libraries with deep learning. This novel interface provides improved empirical analysis with better accuracy.
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3107 (1) , 050009
Analysis & prediction of cardiac arrhythmia using deep learning techniques
Automated diagnosis of the cardiovascular disease from heartbeats of an individual is a difficult and challenging task. Essentially, it requires continuous moni Automated diagnosis of the cardiovascular disease from heartbeats of an individual is a difficult and challenging task. Essentially, it requires continuous moni
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3107 (1) , 050009
Analysis & prediction of cardiac arrhythmia using deep learning techniques
Automated diagnosis of the cardiovascular disease from heartbeats of an individual is a difficult and challenging task. Essentially, it requires continuous moni Automated diagnosis of the cardiovascular disease from heartbeats of an individual is a difficult and challenging task. Essentially, it requires continuous moni
- 29 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 1-6
AI-Powered Computer Vision for Early Skin Cancer Detection with IoT-Connected Dermascopes
This research combines AI-powered computer vision with the Internet of Things-connected dermascopes in order to offer a novel method for early skin cancer detection. The developed AI algorithm shows promise for identifying subtle signs of skin cancer in dermatoscopic image analysis, as evidenced by its high accuracy rate. Real-time collection and analysis of data are made possible by seamless integration with IoT-connected dermascopes, which solves issues with conventional workflows. The system's effectiveness, shorter diagnostic times, as well as versatility in various clinical situations are demonstrated by the evaluation results. This integrated system's revolutionary effect places it in a position to revolutionize dermatological diagnostics, with implications for better patient outcomes alongside the potential to reduce the demand for healthcare resources. Algorithm improvement, validation research, and integration into actual clinical settings are all part of the upcoming work.
- 29 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 1-6
AI-Powered Computer Vision for Early Skin Cancer Detection with IoT-Connected Dermascopes
This research combines AI-powered computer vision with the Internet of Things-connected dermascopes in order to offer a novel method for early skin cancer detection. The developed AI algorithm shows promise for identifying subtle signs of skin cancer in dermatoscopic image analysis, as evidenced by its high accuracy rate. Real-time collection and analysis of data are made possible by seamless integration with IoT-connected dermascopes, which solves issues with conventional workflows. The system's effectiveness, shorter diagnostic times, as well as versatility in various clinical situations are demonstrated by the evaluation results. This integrated system's revolutionary effect places it in a position to revolutionize dermatological diagnostics, with implications for better patient outcomes alongside the potential to reduce the demand for healthcare resources. Algorithm improvement, validation research, and integration into actual clinical settings are all part of the upcoming work.
- 3 January 2023
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 30 (4) , 2409-2429
A Review of Deep Transfer Learning Approaches for Class-Wise Prediction of Alzheimer’s Disease Using MRI Images
- 3 January 2023
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 30 (4) , 2409-2429
A Review of Deep Transfer Learning Approaches for Class-Wise Prediction of Alzheimer’s Disease Using MRI Images
- RetractedOpen Access
- 1 January 2022
- Published by Wiley in BioMed Research International
- Vol. 2022 (1) , 1467070
[Retracted] Prediction Performance of Deep Learning for Colon Cancer Survival Prediction on SEER Data
Colon and rectal cancers are the most common kinds of cancer globally. Colon cancer is more prevalent in men than in women. Early detection increases the likelihood of survival, and treatment significantly increases the likelihood of eradicating the disease. The Surveillance, Epidemiology, and End Results (SEER) programme is an excellent source of domestic cancer statistics. SEER includes nearly 30% of the United States population, covering various races and geographic locations. The data are made public via the SEER website when a SEER limited‐use data agreement form is submitted and approved. We investigate data from the SEER programme, specifically colon cancer statistics, in this study. Our objective is to create reliable colon cancer survival and conditional survival prediction algorithms. In this study, we have presented an overview of cancer diagnosis methods and the treatments used to cure cancer. This paper presents an analysis of prediction performance of multiple deep learning approaches. The performance of multiple deep learning models is thoroughly examined to discover which algorithm surpasses the others, followed by an investigation of the network’s prediction accuracy. The simulation outcomes indicate that automated prediction models can predict colon cancer patient survival. Deep autoencoders displayed the best performance outcomes attaining 97% accuracy and 95% area under curve‐receiver operating characteristic (AUC‐ROC).
- 1 January 2022
- Published by Wiley in BioMed Research International
- Vol. 2022 (1) , 1467070
RetractedOpen Access[Retracted] Prediction Performance of Deep Learning for Colon Cancer Survival Prediction on SEER Data
Colon and rectal cancers are the most common kinds of cancer globally. Colon cancer is more prevalent in men than in women. Early detection increases the likelihood of survival, and treatment significantly increases the likelihood of eradicating the disease. The Surveillance, Epidemiology, and End Results (SEER) programme is an excellent source of domestic cancer statistics. SEER includes nearly 30% of the United States population, covering various races and geographic locations. The data are made public via the SEER website when a SEER limited‐use data agreement form is submitted and approved. We investigate data from the SEER programme, specifically colon cancer statistics, in this study. Our objective is to create reliable colon cancer survival and conditional survival prediction algorithms. In this study, we have presented an overview of cancer diagnosis methods and the treatments used to cure cancer. This paper presents an analysis of prediction performance of multiple deep learning approaches. The performance of multiple deep learning models is thoroughly examined to discover which algorithm surpasses the others, followed by an investigation of the network’s prediction accuracy. The simulation outcomes indicate that automated prediction models can predict colon cancer patient survival. Deep autoencoders displayed the best performance outcomes attaining 97% accuracy and 95% area under curve‐receiver operating characteristic (AUC‐ROC).
- 24 September 2021
- Published by ASME International in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B. Mechanical Engineering
- Vol. 8 (1)
On Characterizing Uncertainty Sources in Laser Powder-Bed Fusion Additive Manufacturing Models
Tremendous efforts have been made to use computational and simulation models of additive manufacturing (AM) processes. The goals of these efforts are to better understand process complexities and to realize better high-quality parts. However, understanding whether any model is a correct representation for a given scenario is a difficult proposition. For example, when using metal powders, the laser powder-bed fusion (L-PBF) process involves complex physical phenomena such as powder morphology, heat transfer, phase transformation, and fluid flow. Models based on these phenomena will possess different degrees of fidelity since they often rely on assumptions that may neglect or simplify process physics, resulting in uncertainties in their prediction accuracy. Prediction accuracy and its characterization can vary greatly between models due to their uncertainties. This paper characterizes several sources of L-PBF model uncertainty for low, medium, and high-fidelity thermal models including modeling assumptions (model-form uncertainty), numerical approximations (numerical uncertainty), and input parameters (parameter uncertainty). This paper focuses on the input uncertainty sources, which we model in terms of a probability density function (PDF), and its propagation through all other L-PBF models. We represent uncertainty sources using the webontologylanguage, which allows us to capture the relevant knowledge used for interoperability and reusability. The topology and mapping of the uncertainty sources establish fundamental requirements for measuring model fidelity and for guiding the selection of a model suitable for its intended purpose.
- 24 September 2021
- Published by ASME International in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B. Mechanical Engineering
- Vol. 8 (1)
On Characterizing Uncertainty Sources in Laser Powder-Bed Fusion Additive Manufacturing Models
Tremendous efforts have been made to use computational and simulation models of additive manufacturing (AM) processes. The goals of these efforts are to better understand process complexities and to realize better high-quality parts. However, understanding whether any model is a correct representation for a given scenario is a difficult proposition. For example, when using metal powders, the laser powder-bed fusion (L-PBF) process involves complex physical phenomena such as powder morphology, heat transfer, phase transformation, and fluid flow. Models based on these phenomena will possess different degrees of fidelity since they often rely on assumptions that may neglect or simplify process physics, resulting in uncertainties in their prediction accuracy. Prediction accuracy and its characterization can vary greatly between models due to their uncertainties. This paper characterizes several sources of L-PBF model uncertainty for low, medium, and high-fidelity thermal models including modeling assumptions (model-form uncertainty), numerical approximations (numerical uncertainty), and input parameters (parameter uncertainty). This paper focuses on the input uncertainty sources, which we model in terms of a probability density function (PDF), and its propagation through all other L-PBF models. We represent uncertainty sources using the webontologylanguage, which allows us to capture the relevant knowledge used for interoperability and reusability. The topology and mapping of the uncertainty sources establish fundamental requirements for measuring model fidelity and for guiding the selection of a model suitable for its intended purpose.