Overview of the Special Issue on “Deep Neural Networks and Optimization Algorithms”
1
School of Mathematics and Physics, Anhui Jianzhu University, Hefei 230601, China
2
Department of Mathematics, COMSATS University Islamabad, Lahore Campus, Lahore 54000, Pakistan
3
Department of Computer and Information Sciences, Northumbria University, Newcastle NE1 8ST, UK
*
Author to whom correspondence should be addressed.
Algorithms 2023, 16(11), 497; https://doi.org/10.3390/a16110497
Submission received: 20 October 2023
/
Accepted: 23 October 2023
/
Published: 26 October 2023
(This article belongs to the Special Issue Deep Neural Networks and Optimization Algorithms)
1. Introduction
Deep Neural Networks and Optimization Algorithms have many applications in engineering problems and scientific research [1,2]. This Special Issue of Algorithms is dedicated to recent developments related to the title topic, namely “Deep Neural Networks and Optimization Algorithms”. For this Special Issue, high-quality papers were solicited to address both theoretical and practical issues in the wide area of “Deep Neural Networks and Optimization Algorithms”. After a careful vetting process, seven papers were selected for publication in this Special Issue. As a rule, all submissions have been reviewed by two or three experts in the corresponding area.
2. Special Issue
The first accepted paper presents the problem of preprocessing pregnancy examination data and proposes an improved bi-LSTM-based missing value imputation approach, significantly enhancing the accuracy of predictions of hypertensive disorder in pregnancy (HDP) using the examination data.
The second paper explores the importance of sampling in neural network training to accelerate convergence and improve generalization, especially in imbalanced data scenarios.
In the third paper, a neural network boosting methodology for logistic regression is discussed, exploring various neural network-based models and advanced approaches applied to a binary classification task in a motor insurance portfolio while addressing model interpretability using a specific approach.
In the fourth paper published in this Special Issue, a task-driven method using CWGAN is proposed to generate high-quality artificial EEG data for emotion recognition tasks, resulting in improved performance and clearer classifications compared to real data.
Tsai M. et al. have investigated computer vision and pre-trained CNN models to enhance QR code source printer identification for digital forensics, with the customized CNN model outperforming others in terms of grayscale and color QR codes.
Lang J. proposes a gas tracking network by utilizing traceability technology and distributed sensors in chemical industry parks to monitor hazardous gas diffusion. The model, which was trained using a hybrid strategy, effectively and robustly traces leaking sources with a final classification accuracy of 99.14%, even in complex urban terrain and varying weather conditions.
Navid Nourian et al. apply the benefits of graph representation to develop a GNN-based surrogate model integrated with a particle swarm optimization (PSO) algorithm.
3. Conclusions
In conclusion, we observed that AI [3,4] is increasingly being used in cybersecurity, with three main directions of research: (1) new areas of cybersecurity are addressed, such as CPS security and threat intelligence; (2) more stable and consistent results are being presented, sometimes with surprising accuracy and effectiveness; and (3) the presence of an AI-aware adversary is recognized and analyzed, enabling more robust and reliable solutions.
Author Contributions
Special issue editorial by J.-B.L., M.F.N. and Y.S. All authors have read and agreed to the published version of the manuscript.
Acknowledgments
The Guest Editors would like to thank all the authors and referees, as well as the Editorial Office of Algorithms, for the precious help given.
Conflicts of Interest
The authors declare no conflict of interest.
List of Contributions
- Lu X., Yuan L., Li R., Xing Z., Yao N., Yu Y., An Improved Bi-LSTM-Based Missing Value Imputation Approach for Pregnancy Examination Data. Algorithms 2023, 16, 12. https://doi.org/10.3390/a16010012.
- Ioannou G., Alexandridis G., Stafylopatis A. Online Batch Selection for Enhanced Generalization in Imbalanced Datasets. Algorithms 2023, 16, 65. https://doi.org/10.3390/a16020065.
- Tzougas G, Kutzkov K. Enhancing Logistic Regression Using Neural Networks for Classification in Actuarial Learning. Algorithms 2023, 16, 99. https://doi.org/10.3390/a16020099.
- Liu Q., Hao J., Guo Y. EEG Data Augmentation for Emotion Recognition with a Task-Driven GAN. Algorithms 2023, 16, 118. https://doi.org/10.3390/a16020118.
- Tsai M., Lee Y, Chen T. Implementing Deep Convolutional Neural Networks for QR Code-Based Printed Source Identification. Algorithms 2023, 16, 160. https://doi.org/10.3390/a16030160.
- Lang J., Zeng Z., Ma T., He S., Leaking Gas Source Tracking for Multiple Chemical Parks within an Urban City. Algorithms 2023, 16, 342. https://doi.org/10.3390/a16070342.
- Navid Nourian, Mamdouh El-Badry, and Maziar Jamshidi, Design Optimization of Truss Structures Using a Graph Neural Network-Based Surrogate Model. Algorithms 2023, 16, 380. https://doi.org/10.3390/a16080380.
References
- Bahadori, M.T.; Liu, Y.; Zhang, D. A general framework for scalable transductive transfer learning. Knowl. Inf. Syst. 2014, 38, 61–83. [Google Scholar] [CrossRef]
- Day, O.; Khoshgoftaar, T.M. A survey on heterogeneous transfer learning. J. Big Data 2017, 4, 29. [Google Scholar] [CrossRef]
- Azucar, D.; Marengo, D.; Settanni, M. Predicting the Big 5 personality traits from digital footprints on social media: A meta-analysis. Personal. Individ. Differ. 2018, 124, 150–159. [Google Scholar] [CrossRef]
- Han, S.; Huang, H.; Tang, Y. Knowledge of words: An interpretable approach for personality recognition from social media. Knowl. Based Syst. 2020, 194, 105550. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
MDPI and ACS Style
Liu, J.-B.; Nadeem, M.F.; Shang, Y. Overview of the Special Issue on “Deep Neural Networks and Optimization Algorithms”. Algorithms 2023, 16, 497. https://doi.org/10.3390/a16110497
AMA Style
Liu J-B, Nadeem MF, Shang Y. Overview of the Special Issue on “Deep Neural Networks and Optimization Algorithms”. Algorithms. 2023; 16(11):497. https://doi.org/10.3390/a16110497
Chicago/Turabian StyleLiu, Jia-Bao, Muhammad Faisal Nadeem, and Yilun Shang. 2023. "Overview of the Special Issue on “Deep Neural Networks and Optimization Algorithms”" Algorithms 16, no. 11: 497. https://doi.org/10.3390/a16110497
APA StyleLiu, J. -B., Nadeem, M. F., & Shang, Y. (2023). Overview of the Special Issue on “Deep Neural Networks and Optimization Algorithms”. Algorithms, 16(11), 497. https://doi.org/10.3390/a16110497
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.
