Guman Singh Chauhan
Research Subjects
Guman Singh Chauhan has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Rahul Jadon
CarGurus Inc, Boston, USA
8 shared publications - Kannan Srinivasan
Saiana Technologies Inc, Piscataway, USA
7 shared publications - Rajababu Budda
IBM, San Francisco, USA
6 shared publications - Venkata Surya Teja Gollapalli
Centene Management Company LLC, Clayton, USA
5 shared publications - Joseph Bamidele Awotunde
University of Ilorin
3 shared publications - Joseph Bamidele Awotunde
University of Ilorin, Ilorin 240003, Kwara State, Nigeria
2 shared publications
Latest Publications
- 1 April 2026
- Published by Springer Nature
- p. 513-527
Optimizing IoT Security: Tunicate Swarm Algorithm Integrated with Stacked Deep Learning Models
- 1 April 2026
- Published by Springer Nature
- p. 513-527
Optimizing IoT Security: Tunicate Swarm Algorithm Integrated with Stacked Deep Learning Models
- 17 February 2026
- Published by Springer Nature in Soft Computing
- Vol. 30 (4) , 2909-2923
An innovative framework for brain tumor detection and types classification using ScLe2 LU–DNN and GaPL-MOA
- 17 February 2026
- Published by Springer Nature in Soft Computing
- Vol. 30 (4) , 2909-2923
An innovative framework for brain tumor detection and types classification using ScLe2 LU–DNN and GaPL-MOA
- 11 November 2025
- Published by Springer Nature in Cluster Computing
- Vol. 29 (1) , 1-15
Performance optimization in cloud data warehouse based on blockchain and data security using AC-AKDES approach
- 11 November 2025
- Published by Springer Nature in Cluster Computing
- Vol. 29 (1) , 1-15
Performance optimization in cloud data warehouse based on blockchain and data security using AC-AKDES approach
- 9 October 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (15) , 1-17
Federated meta heuristic cryptography algorithm with fuzzy logic model in cloud secure data migration
- 9 October 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (15) , 1-17
Federated meta heuristic cryptography algorithm with fuzzy logic model in cloud secure data migration
- 24 July 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (6) , 1-16
Phishing Detection and Zero-Trust Verification with Spiking Neural Networks Auto Encoder and Selu Activation
- 24 July 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (6) , 1-16
Phishing Detection and Zero-Trust Verification with Spiking Neural Networks Auto Encoder and Selu Activation
- Open Access
- 16 June 2025
- Published by Chinese Institute of Automation Engineers in International Journal of Automation and Smart Technology
- Vol. 15 (1)
Advanced Defect Localization Using Principal Component Analysis (PCA) and Bilateral Filtering in Robotics Systems
Defect localization is critical for maintaining system performance in robotics, especially when it comes to high-precision tasks. Traditional methods often struggle to handle noisy data and subtle defects; thus, more advanced solutions are required to achieve higher accuracy and dependability in defect detection. This work focuses on both error reduction and defect detection. They tried to use a hybrid defect localization algorithm that they referred to as PCA and Bilateral Filtering, by using their method can increase the accuracy, precision, and robustness of real-time robotic systems. The proposed approach integrated PCA and bilateral filtering for edge preservation and noise reduction of point cloud data for feature extraction. The hybrid method is compared with the state-of-the-art methods using key performance indicators like accuracy, precision, and recall. As compared to the state-of-the-art defect localization algorithms (in terms of accuracy, precision, and recall), the suggested approach achieves the best RME (5%) and accuracy (95%), precision (93%) and recall (91%) demonstrating its robustness in identifying the robotic defect. Since the proposed solution achieves significant improvements in problem locality, it establishes new state-of-the-art for defect detection in difficult conditions by combining PCA with bilateral filtering. It also provides a robust and efficient approach to real-time applications in robotic systems.
- 16 June 2025
- Published by Chinese Institute of Automation Engineers in International Journal of Automation and Smart Technology
- Vol. 15 (1)
Open AccessAdvanced Defect Localization Using Principal Component Analysis (PCA) and Bilateral Filtering in Robotics Systems
Defect localization is critical for maintaining system performance in robotics, especially when it comes to high-precision tasks. Traditional methods often struggle to handle noisy data and subtle defects; thus, more advanced solutions are required to achieve higher accuracy and dependability in defect detection. This work focuses on both error reduction and defect detection. They tried to use a hybrid defect localization algorithm that they referred to as PCA and Bilateral Filtering, by using their method can increase the accuracy, precision, and robustness of real-time robotic systems. The proposed approach integrated PCA and bilateral filtering for edge preservation and noise reduction of point cloud data for feature extraction. The hybrid method is compared with the state-of-the-art methods using key performance indicators like accuracy, precision, and recall. As compared to the state-of-the-art defect localization algorithms (in terms of accuracy, precision, and recall), the suggested approach achieves the best RME (5%) and accuracy (95%), precision (93%) and recall (91%) demonstrating its robustness in identifying the robotic defect. Since the proposed solution achieves significant improvements in problem locality, it establishes new state-of-the-art for defect detection in difficult conditions by combining PCA with bilateral filtering. It also provides a robust and efficient approach to real-time applications in robotic systems.
- Open Access
- 16 June 2025
- Published by Chinese Institute of Automation Engineers in International Journal of Automation and Smart Technology
- Vol. 15 (1)
Advanced Robotic Automation with Transformer-Guided GNNs, Hybrid Neural Architectures, and Fuzzy Decision Frameworks for Accurate and Scalable Breast Cancer Prediction
Breast cancer still contributes a major portion of the world deaths due to such diseases, and innovative methods to diagnose are needed. There is a lack of novel diagnostic solutions, which present limited accuracy, scalability issues, and lack of interpretability in dealing with complex medical data. This work is designed to improve the system's accuracy, scalability, and interpretability in predicting breast cancer, through an integrated system involving robotic automation, Transformer-guided graph neural networks, hybrid neural models, and fuzzy decision frameworks. The objective is to design a robust platform that can make reliable, real-time predictions relevant to clinical practice. The framework proposed was based on graph neural networks for analyzing relational information, hybrid architectures to extract spatial and temporal patterns, and fuzzy logic in dealing with uncertainty. The robotic processes dealt with the multi-modal datasets, images, and records efficiently and scalably. Benchmarking measured performance against state-of-the-art methods by metrics like precision, recall, and processing speed. The proposed method achieved 95.3% accuracy and 96.7% recall with the processing time reduced to 180 milliseconds, which was better than other models tested. Its high scalability and interpretability validate its applicability to real-world clinical implementations. This reliable scalable prediction platform for breast cancer shall be a game-changing source of innovation through this state-of-the-art fusion of advance techniques.
- 16 June 2025
- Published by Chinese Institute of Automation Engineers in International Journal of Automation and Smart Technology
- Vol. 15 (1)
Open AccessAdvanced Robotic Automation with Transformer-Guided GNNs, Hybrid Neural Architectures, and Fuzzy Decision Frameworks for Accurate and Scalable Breast Cancer Prediction
Breast cancer still contributes a major portion of the world deaths due to such diseases, and innovative methods to diagnose are needed. There is a lack of novel diagnostic solutions, which present limited accuracy, scalability issues, and lack of interpretability in dealing with complex medical data. This work is designed to improve the system's accuracy, scalability, and interpretability in predicting breast cancer, through an integrated system involving robotic automation, Transformer-guided graph neural networks, hybrid neural models, and fuzzy decision frameworks. The objective is to design a robust platform that can make reliable, real-time predictions relevant to clinical practice. The framework proposed was based on graph neural networks for analyzing relational information, hybrid architectures to extract spatial and temporal patterns, and fuzzy logic in dealing with uncertainty. The robotic processes dealt with the multi-modal datasets, images, and records efficiently and scalably. Benchmarking measured performance against state-of-the-art methods by metrics like precision, recall, and processing speed. The proposed method achieved 95.3% accuracy and 96.7% recall with the processing time reduced to 180 milliseconds, which was better than other models tested. Its high scalability and interpretability validate its applicability to real-world clinical implementations. This reliable scalable prediction platform for breast cancer shall be a game-changing source of innovation through this state-of-the-art fusion of advance techniques.
- 3 June 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (5) , 1-15
Adaptive Hellinger Distance CS and GELU-RNN: Advanced Solutions for Feature Optimization and Cloud Threat Detection
- 3 June 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (5) , 1-15
Adaptive Hellinger Distance CS and GELU-RNN: Advanced Solutions for Feature Optimization and Cloud Threat Detection
- 31 December 2024
- Published by Inventive Research Organization in Journal of Ubiquitous Computing and Communication Technologies
- Vol. 6 (4) , 377-396
Advanced-Data Processing in IoT using MQTT and OPTICS with Spiking Neural Networks and Mist Computing for Real-Time Analytics
The proposed combination of Message Queuing Telemetry Transport (MQTT), Ordering points to identify the clustering structure (OPTICS), Spiking Neural Networks (SNNs), and Mist computing improves real-time processing of IoT data by tackling issues with event-driven analytics, communication, and clustering. Effective clustering and anomaly detection in big, dynamic datasets are made possible by OPTICS, while MQTT guarantees effective, low-latency communication. Biological neuron-inspired SNNs offer energy-efficient real-time event detection, while Mist Computing decentralizes computing to lower latency and bandwidth consumption. 90% energy efficiency, 92% data throughput, 95% latency reduction, and 97% anomaly detection accuracy are among the notable performance gains the system makes. Smart cities, industrial IoT, and healthcare systems are just a few examples of the sophisticated IoT applications that benefit from this all-inclusive framework's great scalability and efficiency. Through the integration of sophisticated communication protocols, clustering techniques, and real-time processing capabilities, it guarantees accurate, scalable, and energy-efficient answers to contemporary IoT problems.
- 31 December 2024
- Published by Inventive Research Organization in Journal of Ubiquitous Computing and Communication Technologies
- Vol. 6 (4) , 377-396
Advanced-Data Processing in IoT using MQTT and OPTICS with Spiking Neural Networks and Mist Computing for Real-Time Analytics
The proposed combination of Message Queuing Telemetry Transport (MQTT), Ordering points to identify the clustering structure (OPTICS), Spiking Neural Networks (SNNs), and Mist computing improves real-time processing of IoT data by tackling issues with event-driven analytics, communication, and clustering. Effective clustering and anomaly detection in big, dynamic datasets are made possible by OPTICS, while MQTT guarantees effective, low-latency communication. Biological neuron-inspired SNNs offer energy-efficient real-time event detection, while Mist Computing decentralizes computing to lower latency and bandwidth consumption. 90% energy efficiency, 92% data throughput, 95% latency reduction, and 97% anomaly detection accuracy are among the notable performance gains the system makes. Smart cities, industrial IoT, and healthcare systems are just a few examples of the sophisticated IoT applications that benefit from this all-inclusive framework's great scalability and efficiency. Through the integration of sophisticated communication protocols, clustering techniques, and real-time processing capabilities, it guarantees accurate, scalable, and energy-efficient answers to contemporary IoT problems.