Siva Sangari Mani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Siva Sangari Mani has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Aliya Aleryani
Department of Computer Science, College of Computer Science, King Khalid University, Abha, Saudi Arabia
1 shared publication - Areej Alasiry
College of Computer Science, King Khalid University, Abha, Saudi Arabia
1 shared publication - Chandru Vignesh Chinnappan
School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India
1 shared publication - Ihtiram Raza Khan
Jamia Hamdard
1 shared publication Kokilavani Krishnan
Department of Computer Science and Engineering, KPR Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India
1 shared publication- Monia Turki-Hadj Alouane
College of Computer Science, King Khalid University, Abha, Saudi Arabia
1 shared publication
Latest Publications
- 25 April 2025
- Published by Springer Nature
- p. 250-260
Effective Heart Disease Prediction Using Machine Learning Algorithm with Cardiovascular Health Monitoring System
- 25 April 2025
- Published by Springer Nature
- p. 250-260
Effective Heart Disease Prediction Using Machine Learning Algorithm with Cardiovascular Health Monitoring System
- Open Access
- 19 September 2023
- Published by MDPI AG in Biomimetics
- Vol. 8 (5) , 438
An Automatic-Segmentation- and Hyper-Parameter-Optimization-Based Artificial Rabbits Algorithm for Leaf Disease Classification
In recent years, disease attacks have posed continuous threats to agriculture and caused substantial losses in the economy. Thus, early detection and classification could minimize the spread of disease and help to improve yield. Meanwhile, deep learning has emerged as the significant approach to detecting and classifying images. The classification performed using the deep learning approach mainly relies on large datasets to prevent overfitting problems. The Automatic Segmentation and Hyper Parameter Optimization Artificial Rabbits Algorithm (AS-HPOARA) is developed to overcome the above-stated issues. It aims to improve plant leaf disease classification. The Plant Village dataset is used to assess the proposed AS-HPOARA approach. Z-score normalization is performed to normalize the images using the dataset’s mean and standard deviation. Three augmentation techniques are used in this work to balance the training images: rotation, scaling, and translation. Before classification, image augmentation reduces overfitting problems and improves the classification accuracy. Modified UNet employs a more significant number of fully connected layers to better represent deeply buried characteristics; it is considered for segmentation. To convert the images from one domain to another in a paired manner, the classification is performed by HPO-based ARA, where the training data get increased and the statistical bias is eliminated to improve the classification accuracy. The model complexity is minimized by tuning the hyperparameters that reduce the overfitting issue. Accuracy, precision, recall, and F1 score are utilized to analyze AS-HPOARA’s performance. Compared to the existing CGAN-DenseNet121 and RAHC_GAN, the reported results show that the accuracy of AS-HPOARA for ten classes is high at 99.7%.
- 19 September 2023
- Published by MDPI AG in Biomimetics
- Vol. 8 (5) , 438
Open AccessAn Automatic-Segmentation- and Hyper-Parameter-Optimization-Based Artificial Rabbits Algorithm for Leaf Disease Classification
In recent years, disease attacks have posed continuous threats to agriculture and caused substantial losses in the economy. Thus, early detection and classification could minimize the spread of disease and help to improve yield. Meanwhile, deep learning has emerged as the significant approach to detecting and classifying images. The classification performed using the deep learning approach mainly relies on large datasets to prevent overfitting problems. The Automatic Segmentation and Hyper Parameter Optimization Artificial Rabbits Algorithm (AS-HPOARA) is developed to overcome the above-stated issues. It aims to improve plant leaf disease classification. The Plant Village dataset is used to assess the proposed AS-HPOARA approach. Z-score normalization is performed to normalize the images using the dataset’s mean and standard deviation. Three augmentation techniques are used in this work to balance the training images: rotation, scaling, and translation. Before classification, image augmentation reduces overfitting problems and improves the classification accuracy. Modified UNet employs a more significant number of fully connected layers to better represent deeply buried characteristics; it is considered for segmentation. To convert the images from one domain to another in a paired manner, the classification is performed by HPO-based ARA, where the training data get increased and the statistical bias is eliminated to improve the classification accuracy. The model complexity is minimized by tuning the hyperparameters that reduce the overfitting issue. Accuracy, precision, recall, and F1 score are utilized to analyze AS-HPOARA’s performance. Compared to the existing CGAN-DenseNet121 and RAHC_GAN, the reported results show that the accuracy of AS-HPOARA for ten classes is high at 99.7%.
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2764 (1) , 060009
Hybrid coalitional game-theory model for coordinated wireless sensor networks
Coordinated Multipoint Transmission (CMT) is critical in obtaining faster data transfer speeds than other systems during the Advanced Long-Term Evolution (LTE-A) of networks and 5G data transmission. Additionally, the Radio Access Network (RAN) requires more transmission points (TP) for data transfer in smaller groups. This article proposes a unique architecture for sending data from the sensor node to the receiver via cluster creation and data aggregation techniques. With the models mentioned above, the implementation of a game-theoretic energy-efficient clustering mechanism. The clustering model utilized in this work is a load-aware model based on a coalitional game with merge/split operations for maximizing Spectral Efficiency (SE) of the network and load balancing (LB). Suggested hybrid algorithm’s simulation results indicate that the supplied model beats the greedy clustering model by 71.6 percent energy efficiency in over-load scenarios. Thus, the network may run without backlogs even under high load situations, such as those associated with hotspots. Thus, the number of dissatisfied users under the given overload state is substantially lower than conventional clustering techniques.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2764 (1) , 060009
Open AccessHybrid coalitional game-theory model for coordinated wireless sensor networks
Coordinated Multipoint Transmission (CMT) is critical in obtaining faster data transfer speeds than other systems during the Advanced Long-Term Evolution (LTE-A) of networks and 5G data transmission. Additionally, the Radio Access Network (RAN) requires more transmission points (TP) for data transfer in smaller groups. This article proposes a unique architecture for sending data from the sensor node to the receiver via cluster creation and data aggregation techniques. With the models mentioned above, the implementation of a game-theoretic energy-efficient clustering mechanism. The clustering model utilized in this work is a load-aware model based on a coalitional game with merge/split operations for maximizing Spectral Efficiency (SE) of the network and load balancing (LB). Suggested hybrid algorithm’s simulation results indicate that the supplied model beats the greedy clustering model by 71.6 percent energy efficiency in over-load scenarios. Thus, the network may run without backlogs even under high load situations, such as those associated with hotspots. Thus, the number of dissatisfied users under the given overload state is substantially lower than conventional clustering techniques.