Hadi Soltanizadeh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hadi Soltanizadeh has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
Zeynab Imani
Electrical and Computer Engineering Faculty
4 shared publications- Masoume Gholizade
Faculty of Electrical and Computer Engineering, Semnan University, Semnan, Iran
3 shared publications - Mohammad Rahmanimanesh
Faculty of Electrical and Computer Engineering, Semnan University, Semnan, Iran
3 shared publications - Mohammad Zahraei
Medical Nanotechnology and Tissue Engineering Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran
3 shared publications Seyyed Ali Asghar Shahidian
3 shared publications- Ali Asghar Orouji
Department of Electrical and Computer Engineering, Semnan University, Semnan 35131-19111, Iran
2 shared publications
Latest Publications
- 17 August 2026
- Published by Springer Nature in Human-Intelligent Systems Integration
- p. 1-21
Measurement of plantar-pressure in clinical and analytical applications: a systematic review
- 17 August 2026
- Published by Springer Nature in Human-Intelligent Systems Integration
- p. 1-21
Measurement of plantar-pressure in clinical and analytical applications: a systematic review
- 4 February 2026
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 42 (1) , 6
Automated hip joint mobility assessment using fuzzy algorithms, kinect sensor and clinical expertise
- 4 February 2026
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 42 (1) , 6
Automated hip joint mobility assessment using fuzzy algorithms, kinect sensor and clinical expertise
- 6 January 2026
- Published by Springer Nature in Cluster Computing
- Vol. 29 (2) , 95
Multi-source transfer learning with limited data access: a neural networks and fuzzy rules approach for regression problems
- 6 January 2026
- Published by Springer Nature in Cluster Computing
- Vol. 29 (2) , 95
Multi-source transfer learning with limited data access: a neural networks and fuzzy rules approach for regression problems
- 27 December 2025
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 29 (1) , 12
Partial derivative regularized knowledge transformation for deep neural networks generalization
- 27 December 2025
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 29 (1) , 12
Partial derivative regularized knowledge transformation for deep neural networks generalization
- Open Access
- 7 March 2025
- Published by Elsevier in Medicine in Novel Technology and Devices
- Vol. 26
A review of evaluation methods for Duchenne muscular dystrophy
- 7 March 2025
- Published by Elsevier in Medicine in Novel Technology and Devices
- Vol. 26
Open AccessA review of evaluation methods for Duchenne muscular dystrophy
- Top Cited Papers
- 21 February 2025
- Published by Springer Nature in International Journal of System Assurance Engineering and Management
- Vol. 16 (3) , 1123-1162
A review of recent advances and strategies in transfer learning
- 21 February 2025
- Published by Springer Nature in International Journal of System Assurance Engineering and Management
- Vol. 16 (3) , 1123-1162
Top Cited PapersA review of recent advances and strategies in transfer learning
- Open Access
- 24 January 2024
- Published by Springer Nature in Research Square
Robust graph representation learning via out-of-distribution detection approach
Graph neural networks (GNNs) are powerful models capable of learning from graph-structured data and performing various tasks. GNNs are susceptible to poisoning attacks, in which sophisticated attackers inject malicious nodes or edges into the graph topology to degrade their performance. The existing defense mechanisms, such as adversarial training, are ineffective in improving the robustness of GNN models. Fake nodes can be utilized creatively to deceive traditional GNN neural functions. In this paper, we propose a robust GNN model empowered by a reliable aggregation function based on the OOD detection concept and a novel method. A key idea of RGRO is to train a model that maps the nodes to a latent space in which we can measure the distance between the nodes and their distribution. The Mahalanobis distance is proposed as a superior alternative to cosine distance in order to exploit the homophily rule better and to consider the contextual information of the nodes. The Mahalanobis distance, which considers the covariance of the data and is scale-invariant, allows for a more effective application of the homophily rule. Mahalanobis distance is explored in this study to enhance the robustness and accuracy of outlier detection in graph data, thus contributing to a better understanding of homophily. The RGRO model can improve accuracy by removing poisoned data without knowing any types of poisoning attacks or GNN algorithms. RGRO is evaluated with four typical defense strategies based on two types of poisoning attacks implemented on different realistic datasets. Based on the results, RGRO can detect poisoned data against attacks effectively and efficiently. In the best scenario, RGRO improves the accuracy of the GNN model by 0.86.
- 24 January 2024
- Published by Springer Nature in Research Square
Open AccessRobust graph representation learning via out-of-distribution detection approach
Graph neural networks (GNNs) are powerful models capable of learning from graph-structured data and performing various tasks. GNNs are susceptible to poisoning attacks, in which sophisticated attackers inject malicious nodes or edges into the graph topology to degrade their performance. The existing defense mechanisms, such as adversarial training, are ineffective in improving the robustness of GNN models. Fake nodes can be utilized creatively to deceive traditional GNN neural functions. In this paper, we propose a robust GNN model empowered by a reliable aggregation function based on the OOD detection concept and a novel method. A key idea of RGRO is to train a model that maps the nodes to a latent space in which we can measure the distance between the nodes and their distribution. The Mahalanobis distance is proposed as a superior alternative to cosine distance in order to exploit the homophily rule better and to consider the contextual information of the nodes. The Mahalanobis distance, which considers the covariance of the data and is scale-invariant, allows for a more effective application of the homophily rule. Mahalanobis distance is explored in this study to enhance the robustness and accuracy of outlier detection in graph data, thus contributing to a better understanding of homophily. The RGRO model can improve accuracy by removing poisoned data without knowing any types of poisoning attacks or GNN algorithms. RGRO is evaluated with four typical defense strategies based on two types of poisoning attacks implemented on different realistic datasets. Based on the results, RGRO can detect poisoned data against attacks effectively and efficiently. In the best scenario, RGRO improves the accuracy of the GNN model by 0.86.
- 17 June 2023
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 79 (18) , 20899-20922
Improving generalization in deep neural network using knowledge transformation based on fisher criterion
- 17 June 2023
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 79 (18) , 20899-20922
Improving generalization in deep neural network using knowledge transformation based on fisher criterion
- 6 December 2022
- Published by Springer Nature in Optical and Quantum Electronics
- Vol. 55 (1) , 1-28
Refractive index optical sensor using gold-walled silicon nanowire
- 6 December 2022
- Published by Springer Nature in Optical and Quantum Electronics
- Vol. 55 (1) , 1-28
Refractive index optical sensor using gold-walled silicon nanowire