Atul Kumar Agnihotri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Atul Kumar Agnihotri has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Fateh Bahadur Kunwar
Rajasthan Technical University, India
1 shared publication - Hazra Imran
School of Computing Science, Simon Fraser University, Burnaby, BC V5A 1S6, Canada
1 shared publication Jagendra Singh
Bennett University, India
1 shared publication- Kotha Sinduja
Jawaharlal Nehru Technological University, Kakinada, India
1 shared publication - Pongkit Ekvitayavetchanukul
The Board of Khon Kaen University Affairs, Khon Kaen University, Thailand
1 shared publication - Rakshit Kothari
College of Technology and Engineering, Maharana Pratap University of Agriculture and Technology, India
1 shared publication
Latest Publications
- 6 December 2024
- Published by IGI Global Scientific Publishing
- p. 313-330
Enhancing Heart Disease Diagnosis Through Particle Swarm Optimization and Ensemble Deep Learning Models
The present research focused on combining Particle Swarm Optimization (PSO) based hybrid deep learning models to classify heart disease images and patient sequences. This study employs Convolutional Neural Networks (CNNs), including VGG 16, VGG 19 and ResNet 50, as well as Recurrent Neu-ral Networks (RNNs), whereby their performance is optimized by PSO to im-prove the accuracy in diagnosing heart disease from CT images together with associated medical history. The models experienced a significant increase in classification performance, using manual hyperparameters tuning by PSO. The combined algorithm PSO with VGG 19 and the RNN model performed best, achieving a precision of 97.78% and becoming the highest recall on testing. The model that we propose uses the modern feature extraction of VGG 19 and an RNN to take into consideration the sequential nature of data, making it very accurate while keeping loss minimal. PSO with VGG 16 and RNN model is also another robust performance with an accuracy of 94.5%.
- 6 December 2024
- Published by IGI Global Scientific Publishing
- p. 313-330
Enhancing Heart Disease Diagnosis Through Particle Swarm Optimization and Ensemble Deep Learning Models
The present research focused on combining Particle Swarm Optimization (PSO) based hybrid deep learning models to classify heart disease images and patient sequences. This study employs Convolutional Neural Networks (CNNs), including VGG 16, VGG 19 and ResNet 50, as well as Recurrent Neu-ral Networks (RNNs), whereby their performance is optimized by PSO to im-prove the accuracy in diagnosing heart disease from CT images together with associated medical history. The models experienced a significant increase in classification performance, using manual hyperparameters tuning by PSO. The combined algorithm PSO with VGG 19 and the RNN model performed best, achieving a precision of 97.78% and becoming the highest recall on testing. The model that we propose uses the modern feature extraction of VGG 19 and an RNN to take into consideration the sequential nature of data, making it very accurate while keeping loss minimal. PSO with VGG 16 and RNN model is also another robust performance with an accuracy of 94.5%.
- 28 May 2024
- Published by IGI Global Scientific Publishing
- p. 117-137
Human-Centric AI Applications for Remote Patient Monitoring
This research analyses the deployment of a human-centric IoT gadget for remote impacted person monitoring, employing sophisticated technology to beautify healthcare operations. The suggested approach incorporates a community of sensors, together with temperature, stress, coronary heart charge, and oxygen sensors, strategically situated at the afflicted person's frame. These sensors capture actual-time physiological information, which is processed via a signal converter, delivered to character controllers, and consolidated within the cloud for complete analysis. Subsequently, machine studying styles, including artificial neural network (ANN), decision tree (DT), random forest (RF), and naive bayes (NB), are used to anticipate impacted person fitness outcomes based at the accumulated dataset. The analysis assesses each version's performance using a dataset of 3233 items, of which 70% are designated for learning and 30% for experimentation. Results suggest that the proposed ANN model achieves an outstanding accuracy of 97.5%, outperforming DT, RF, and NB. Decision tree and random forest comply closely with accuracies of 92.33% and 91.22%, correspondingly, while naive bayes demonstrates a superb accuracy of 86.5%. These outcomes underline the potential of sophisticated machine learning models, notably ANN, within the field of remote affected person monitoring, giving a transformational method to healthcare. The merger of human-centric layout ideas, IoT technologies, and device learning contributes to the continuous dialogue on improving affected person care, opening the way for extra proactive, customized, and successful healthcare treatments. This investigation suggests a leap forward in utilising generation to alter healthcare practices, highlighting the crucial significance of facts-driven decision-making in making sure best patient impacts.
- 28 May 2024
- Published by IGI Global Scientific Publishing
- p. 117-137
Human-Centric AI Applications for Remote Patient Monitoring
This research analyses the deployment of a human-centric IoT gadget for remote impacted person monitoring, employing sophisticated technology to beautify healthcare operations. The suggested approach incorporates a community of sensors, together with temperature, stress, coronary heart charge, and oxygen sensors, strategically situated at the afflicted person's frame. These sensors capture actual-time physiological information, which is processed via a signal converter, delivered to character controllers, and consolidated within the cloud for complete analysis. Subsequently, machine studying styles, including artificial neural network (ANN), decision tree (DT), random forest (RF), and naive bayes (NB), are used to anticipate impacted person fitness outcomes based at the accumulated dataset. The analysis assesses each version's performance using a dataset of 3233 items, of which 70% are designated for learning and 30% for experimentation. Results suggest that the proposed ANN model achieves an outstanding accuracy of 97.5%, outperforming DT, RF, and NB. Decision tree and random forest comply closely with accuracies of 92.33% and 91.22%, correspondingly, while naive bayes demonstrates a superb accuracy of 86.5%. These outcomes underline the potential of sophisticated machine learning models, notably ANN, within the field of remote affected person monitoring, giving a transformational method to healthcare. The merger of human-centric layout ideas, IoT technologies, and device learning contributes to the continuous dialogue on improving affected person care, opening the way for extra proactive, customized, and successful healthcare treatments. This investigation suggests a leap forward in utilising generation to alter healthcare practices, highlighting the crucial significance of facts-driven decision-making in making sure best patient impacts.
- Open Access
- 11 June 2023
- Published by Edtech Publishers (OPC) Private Limited in International Journal of Scientific Research in Engineering and Management
- Vol. 07 (06)
A Review & Analysis on Designing issues for Optimizing a Wireless Sensor Network
A Review & Analysis on Designing issues for Optimizing a Wireless Sensor Network Atul Kumar Agnihotri, Dr.Vishal Awasthi U.I.E.T. (E.C.E DEPARTMENT) […]
- 11 June 2023
- Published by Edtech Publishers (OPC) Private Limited in International Journal of Scientific Research in Engineering and Management
- Vol. 07 (06)
Open AccessA Review & Analysis on Designing issues for Optimizing a Wireless Sensor Network
A Review & Analysis on Designing issues for Optimizing a Wireless Sensor Network Atul Kumar Agnihotri, Dr.Vishal Awasthi U.I.E.T. (E.C.E DEPARTMENT) […]