Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
Evolutionary Computation Meets Deep Learning
applsci-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Evolutionary Computation Meets Deep Learning

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 31 January 2025 | Viewed by 11681

Special Issue Editors

Prof. Dr. Yuejiao Gong

E-Mail Website
Guest Editor
School of Computer Science and Technology, South China University of Technology, Guangzhou 510006, China
Interests: evolutionary computation; deep reinforcement learning
Special Issues, Collections and Topics in MDPI journals
Dr. Qiang Yang

E-Mail Website
Guest Editor
School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China
Interests: neural architecture search; swarm intelligence; evolutionary computation
Dr. Ting Huang

E-Mail Website
Guest Editor
Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, China
Interests: evolutionary computation; graph neural network
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Evolutionary computation and deep learning are two mainstream technologies of modern artificial intelligence. They are both biology-inspired computational methods but are engaged in different tasks. Usually, evolutionary algorithms are designed to solve complex optimization problems, whereas deep learning models are built to complete complex learning tasks. Recently, many studies have found that the appropriate combination of these two methods provides rich and flexible ways for the two mature paradigms to boost each other.

The purpose of this Special Issue is to gather a collection of the latest studies on the interplay of evolutionary computation and deep learning, from either theoretical or practical perspectives. We welcome new methods that incorporate different deep learning methods to assist evolutionary algorithms in algorithm configuration, evaluation substitution, etc., as well as the methods that apply different evolutionary algorithms to improve deep learning models in terms of the architectures, training procedures, etc. We invite authors to submit research articles and/or review articles that fit this purpose.

Prof. Dr. Yuejiao Gong
Dr. Qiang Yang
Dr. Ting Huang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • evolutionary computation
  • swarm intelligence
  • deep learning
  • deep reinforcement learning
  • graph neural network
  • neural architecture search

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (7 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

0 pages, 1778 KiB  
Article
Crested Porcupine Optimizer-Optimized CNN-BiLSTM-Attention Model for Predicting Main Girder Temperature in Bridges
by Yan Gao, Jianxun Wang, Wenhao Yu, Lu Yi and Fengqi Guo
Appl. Sci. 2024, 14(16), 7356; https://doi.org/10.3390/app14167356 - 20 Aug 2024
Viewed by 506
Abstract
Stage-built long-span bridges deform with temperature, affecting alignment to design needs. In this paper, a model for predicting temperature time series is proposed, which can predict temperatures in engineering practice and utilize the predicted results to adjust the elevation of stage construction. The [...] Read more.
Stage-built long-span bridges deform with temperature, affecting alignment to design needs. In this paper, a model for predicting temperature time series is proposed, which can predict temperatures in engineering practice and utilize the predicted results to adjust the elevation of stage construction. The model employs convolutional neural networks (CNNs) for initial feature extraction, followed by bidirectional long short-term memory (BiLSTM) layers to capture temporal dependencies. An attention mechanism is applied to the LSTM output, enhancing the model’s ability to focus on the most relevant parts of the sequence. The Crested Porcupine Optimizer (CPO) is used to fine-tune parameters like the number of LSTM units, dropout rate, and learning rate. The experiments on the measured temperature data of an under-construction cable-stayed bridge are conducted to validate our model. The results indicate that our model outperforms the other five models in comparison, with all the R2 values exceeding 0.97. The average of the mean absolute error (MAE) on the 30 measure points is 0.19095, and the average of the root mean square error (RMSE) is 0.28283. Furthermore, the model’s low sensitivity to data makes it adaptable and effective for predicting temperatures and adjusting the elevation in large-span bridge construction. Full article
(This article belongs to the Special Issue Evolutionary Computation Meets Deep Learning)
►▼ Show Figures

Figure 1

24 pages, 1149 KiB  
Article
Multi-Objective Evolutionary Neural Architecture Search with Weight-Sharing Supernet
by Junchao Liang, Ke Zhu, Yuan Li, Yun Li and Yuejiao Gong
Appl. Sci. 2024, 14(14), 6143; https://doi.org/10.3390/app14146143 - 15 Jul 2024
Viewed by 660
Abstract
Deep neural networks have played a crucial role in the field of deep learning, achieving significant success in practical applications. The architecture of neural networks is key to their performance. In the past few years, these architectures have been manually designed by experts [...] Read more.
Deep neural networks have played a crucial role in the field of deep learning, achieving significant success in practical applications. The architecture of neural networks is key to their performance. In the past few years, these architectures have been manually designed by experts with rich domain knowledge. Additionally, the optimal neural network architecture can vary depending on specific tasks and data distributions. Neural Architecture Search (NAS) is a class of techniques aimed at automatically searching for and designing neural network architectures according to the given tasks and data. Specifically, evolutionary-computation-based NAS methods are known for their strong global search capability and have aroused widespread interest in recent years. Although evolutionary-computation-based NAS has achieved success in a wide range of research and applications, it still faces bottlenecks in training and evaluating a large number of individuals during optimization. In this study, we first devise a multi-objective evolutionary NAS framework based on a weight-sharing supernet to improve the search efficiency of traditional evolutionary-computation-based NAS. This framework combines the population optimization characteristic of evolutionary algorithms with the weight-sharing ideas in one-shot models. We then design a bi-population MOEA/D algorithm based on the proposed framework to effectively solve the NAS problem. By constructing two sub-populations with different optimization objectives, the algorithm can effectively explore network architectures of various sizes in complex search spaces. An inter-population communication mechanism further enhances the algorithm’s exploratory capability, enabling it to find network architectures with uniform distribution and high diversity. Finally, we conduct performance comparison experiments on image classification datasets of different scales and complexities. Experimental results demonstrate the effectiveness of the proposed multi-objective evolutionary NAS framework and the practicality and transferability of the introduced bi-population MOEA/D-based NAS method compared to existing state-of-the-art NAS methods. Full article
(This article belongs to the Special Issue Evolutionary Computation Meets Deep Learning)
►▼ Show Figures

Figure 1

16 pages, 2210 KiB  
Article
Long 3D-POT: A Long-Term 3D Drosophila-Tracking Method for Position and Orientation with Self-Attention Weighted Particle Filters
by Chengkai Yin, Xiang Liu, Xing Zhang, Shuohong Wang and Haifeng Su
Appl. Sci. 2024, 14(14), 6047; https://doi.org/10.3390/app14146047 - 11 Jul 2024
Viewed by 552
Abstract
The study of the intricate flight patterns and behaviors of swarm insects, such as drosophilas, has long been a subject of interest in both the biological and computational realms. Tracking drosophilas is an essential and indispensable method for researching drosophilas’ behaviors. Still, it [...] Read more.
The study of the intricate flight patterns and behaviors of swarm insects, such as drosophilas, has long been a subject of interest in both the biological and computational realms. Tracking drosophilas is an essential and indispensable method for researching drosophilas’ behaviors. Still, it remains a challenging task due to the highly dynamic nature of these drosophilas and their partial occlusion in multi-target environments. To address these challenges, particularly in environments where multiple targets (drosophilas) interact and overlap, we have developed a long-term Trajectory 3D Position and Orientation Tracking Method (Long 3D-POT) that combines deep learning with particle filtering. Our approach employs a detection model based on an improved Mask-RCNN to accurately detect the position and state of drosophilas from frames, even when they are partially occluded. Following detection, improved particle filtering is used to predict and update the motion of the drosophilas. To further enhance accuracy, we have introduced a prediction module based on the self-attention backbone that predicts the drosophila’s next state and updates the particles’ weights accordingly. Compared with previous methods by Ameni, Cheng, and Wang, our method has demonstrated a higher degree of accuracy and robustness in tracking the long-term trajectories of drosophilas, even those that are partially occluded. Specifically, Ameni employs the Interacting Multiple Model (IMM) combined with the Global Nearest Neighbor (GNN) assignment algorithm, primarily designed for tracking larger, more predictable targets like aircraft, which tends to perform poorly with small, fast-moving objects like drosophilas. The method by Cheng then integrates particle filtering with LSTM networks to predict particle weights, enhancing trajectory prediction under kinetic uncertainties. Wang’s approach builds on Cheng’s by incorporating an estimation of the orientation of drosophilas in order to refine tracking further. Compared with those methods, our method performs with higher accuracy on detection, which increases by more than 10% on the F1 Score, and tracks more long-term trajectories, showing stability. Full article
(This article belongs to the Special Issue Evolutionary Computation Meets Deep Learning)
►▼ Show Figures

Figure 1

16 pages, 3934 KiB  
Article
Research on Gearbox Fault Diagnosis Method Based on VMD and Optimized LSTM
by Bang-Cheng Zhang, Shi-Qi Sun, Xiao-Jing Yin, Wei-Dong He and Zhi Gao
Appl. Sci. 2023, 13(21), 11637; https://doi.org/10.3390/app132111637 - 24 Oct 2023
Cited by 3 | Viewed by 1245
Abstract
The reliability of gearboxes is extremely important for the normal operation of mechanical equipment. This paper proposes an optimized long short-term memory (LSTM) neural network fault diagnosis method. Additionally, a feature extraction method is employed, utilizing variational mode decomposition (VMD) and permutation entropy [...] Read more.
The reliability of gearboxes is extremely important for the normal operation of mechanical equipment. This paper proposes an optimized long short-term memory (LSTM) neural network fault diagnosis method. Additionally, a feature extraction method is employed, utilizing variational mode decomposition (VMD) and permutation entropy (PE). Firstly, the gear vibration signal is subjected to feature decomposition using VMD. Secondly, PE is calculated as a feature quantity output. Next, it is input into the improved LSTM fault diagnosis model, and the LSTM parameters are iteratively optimized using the chameleon search algorithm (CSA). Finally, the output of the fault diagnosis results is obtained. The experimental results show that the accuracy of the method exceeds 97.8%. Full article
(This article belongs to the Special Issue Evolutionary Computation Meets Deep Learning)
►▼ Show Figures

Figure 1

19 pages, 706 KiB  
Article
A Local Information Perception Enhancement–Based Method for Chinese NER
by Miao Zhang and Ling Lu
Appl. Sci. 2023, 13(17), 9948; https://doi.org/10.3390/app13179948 - 3 Sep 2023
Cited by 1 | Viewed by 1354
Abstract
Integrating lexical information into Chinese character embedding is a valid method to figure out the Chinese named entity recognition (NER) issue. However, most existing methods focus only on the discovery of named entity boundaries, considering only the words matched by the Chinese characters. [...] Read more.
Integrating lexical information into Chinese character embedding is a valid method to figure out the Chinese named entity recognition (NER) issue. However, most existing methods focus only on the discovery of named entity boundaries, considering only the words matched by the Chinese characters. They ignore the association between Chinese characters and their left and right matching words. They ignore the local semantic information of the character’s neighborhood, which is crucial for Chinese NER. The Chinese language incorporates a significant number of polysemous words, meaning that a single word can possess multiple meanings. Consequently, in the absence of sufficient contextual information, individuals may encounter difficulties in comprehending the intended meaning of a text, leading to the emergence of ambiguity. We consider how to handle the issue of entity ambiguity because of polysemous words in Chinese texts in different contexts more simply and effectively. We propose in this paper the use of graph attention networks to construct relatives among matching words and neighboring characters as well as matching words and adding left- and right-matching words directly using semantic information provided by the local lexicon. Moreover, this paper proposes a short-sequence convolutional neural network (SSCNN). It utilizes the generated shorter subsequence encoded with the sliding window module to enhance the perception of local information about the character. Compared with the widely used Chinese NER models, our approach achieves 1.18%, 0.29%, 0.18%, and 1.1% improvement on the four benchmark datasets Weibo, Resume, OntoNotes, and E-commerce, respectively, and proves the effectiveness of the model. Full article
(This article belongs to the Special Issue Evolutionary Computation Meets Deep Learning)
►▼ Show Figures

Figure 1

15 pages, 3369 KiB  
Article
Deep Reinforcement Learning for Intelligent Penetration Testing Path Design
by Junkai Yi and Xiaoyan Liu
Appl. Sci. 2023, 13(16), 9467; https://doi.org/10.3390/app13169467 - 21 Aug 2023
Cited by 2 | Viewed by 3608
Abstract
Penetration testing is an important method to evaluate the security degree of a network system. The importance of penetration testing attack path planning lies in its ability to simulate attacker behavior, identify vulnerabilities, reduce potential losses, and continuously improve security strategies. By systematically [...] Read more.
Penetration testing is an important method to evaluate the security degree of a network system. The importance of penetration testing attack path planning lies in its ability to simulate attacker behavior, identify vulnerabilities, reduce potential losses, and continuously improve security strategies. By systematically simulating various attack scenarios, it enables proactive risk assessment and the development of robust security measures. To address the problems of inaccurate path prediction and difficult convergence in the training process of attack path planning, an algorithm which combines attack graph tools (i.e., MulVAL, multi-stage vulnerability analysis language) and the double deep Q network is proposed. This algorithm first constructs an attack tree, searches paths in the attack graph, and then builds a transfer matrix based on depth-first search to obtain all reachable paths in the target system. Finally, the optimal path for target system attack path planning is obtained by using the deep double Q network (DDQN) algorithm. The MulVAL double deep Q network(MDDQN) algorithm is tested in different scale penetration testing environments. The experimental results show that, compared with the traditional deep Q network (DQN) algorithm, the MDDQN algorithm is able to reach convergence faster and more stably and improve the efficiency of attack path planning. Full article
(This article belongs to the Special Issue Evolutionary Computation Meets Deep Learning)
►▼ Show Figures

Figure 1

23 pages, 1978 KiB  
Article
Prevention of Controller Area Network (CAN) Attacks on Electric Autonomous Vehicles
by Salah Adly, Ahmed Moro, Sherif Hammad and Shady A. Maged
Appl. Sci. 2023, 13(16), 9374; https://doi.org/10.3390/app13169374 - 18 Aug 2023
Cited by 2 | Viewed by 2153
Abstract
The importance of vehicle security has increased in recent years in the automotive field, drawing the attention of both the industry and academia. This is due to the rise in cybersecurity threats caused by (1) the increase in vehicle connectivity schemes, such as [...] Read more.
The importance of vehicle security has increased in recent years in the automotive field, drawing the attention of both the industry and academia. This is due to the rise in cybersecurity threats caused by (1) the increase in vehicle connectivity schemes, such as the Internet of Things, vehicle-to-x communication, and over-the-air updates, and (2) the increased impact of such threats because of the added functionalities that are controlled by vehicle software. These causes and threats are further amplified in autonomous vehicles, which are generally equipped with more electronic control units (ECUs) that are connected through controller area networks (CANs). Due to the holistic nature of CANs, attacks on the networks can affect the functionality of all vehicle ECUs and the whole system. This can lead to a breach of privacy, denial of services, alteration of vehicle performance, and exposure to safety threats. Although cryptographic encryption and authentication algorithms and intrusion detection systems (IDS) are currently being used to detect and prevent CAN bus attacks, they have certain limitations. Therefore, this study proposed a mitigation scheme that can detect and prevent such attacks at the ECU level, which could address the limitations of existing algorithms. This study proposed the usage of a secure boot scheme to detect and prevent the execution of malicious codes, as the presence of one or more ECUs with a malicious code is the root cause of most CAN bus attacks. Secure boot schemes apply cryptographic data integrity algorithms to ensure that only authentic and untampered software can run on the vehicle’s ECUs. The selection of an appropriate cryptographic algorithm is important because it affects the secure boot schemes’ security level and performance. Therefore, this study also tested and compared the performance of the proposed secure boot scheme with five different data security algorithms implemented using the hardware security module (HSM) of the TC399 32-bit AURIX™ TriCore™ microcontroller through an electric autonomous vehicle’s control unit. The tests showed that the two most favorable schemes with the selected hardware are the secure boot scheme with the cipher-based message authentication code (CMAC), because it possesses the highest performance with an execution rate of 26.07 (ms/MB), and the secure boot scheme with the elliptic curve digital signature algorithm (ECDSA), because it provides a higher security level with an acceptable compromise in speed. This study also introduced and tested a novel variation of the ECDSA algorithm based on the CMAC algorithm, which was found to have a 19% performance gain over the standard ECDSA-based secure boot scheme. Full article
(This article belongs to the Special Issue Evolutionary Computation Meets Deep Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-7
Back to TopTop