Emerging Applications of Machine Learning in Smart Systems Symmetry

A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".

Deadline for manuscript submissions: 30 June 2024 | Viewed by 4461

Special Issue Editors

School of Computer Science, The University of Sydney, Darlington, NSW 2008, Australia
Interests: network and communications; cyber security; IoT; machine learning; technology for developing country
Special Issues, Collections and Topics in MDPI journals
School of Computer, Data and Mathematical Sciences, Western Sydney University, Kingswood, NSW 2747, Australia
Interests: networking; internet of things; cybersecurity; machine learning; smart aging
Special Issues, Collections and Topics in MDPI journals
School of Engineering and Technology, Central Queensland University, Sydney, NSW 2000, Australia
Interests: information systems; artificial intelligence and image processing; computer software; communications technologies
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In the wave of the third Artificial Intelligence (AI) revolution, smart systems have become a norm in our day to day life. Machine learning, a subset of AI, is one of the most influential enablers behind these smart systems. On the other hand, the symmetry concept in machine learning models is gaining momentum. Machine learning is bringing both positive and negative emotions and concerns to the research community. Consequently, human-centred Artificial Intelligence is in the spotlight. The ethical concern related by machine learning is of paramount importance in smart healthcare, autonomous, and other intelligent systems. Machine learning has also become a critical technology to enable contemporary cybersecurity systems.

This Special Issue of Symmetry features emerging smart systems, along with state-of-the-art machine learning and applied symmetrical methods in developing models and their applications. We are seeking contributions around this theme. The researchers are encouraged to submit their original works that cover some novel aspects of machine learning in the context of smart systems.

The journal focuses on the following, however, are not limited to innovative applications of:

  • machine learning and cyber-physical systems;
  • intelligent healthcare;
  • predictive models in healthcare;
  • applied machine learning in cybersecurity;
  • Society 5.0 and smart aging;
  • human in the loop;
  • machine learning and environment;
  • machine learning and Industry 4.0 

Submit your paper and select the Journal “Symmetry” and the Special Issue “Emerging Applications of Machine Learning in Smart Systems Symmetry” via: MDPI submission system. Our papers will be published on a rolling basis and we will be pleased to receive your submission once you have finished it.

Dr. Farnaz Farid 
Dr. Farhad Ahamed
Dr. Mahmoud Elkhodr 
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. Symmetry is an international peer-reviewed open access monthly 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.

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

18 pages, 8554 KiB  
Article
An Efficient Trajectory Planning Approach for Autonomous Ground Vehicles Using Improved Artificial Potential Field
by Xianjian Jin, Zhiwei Li, Nonsly Valerienne Opinat Ikiela, Xiongkui He, Zhaoran Wang, Yinchen Tao and Huaizhen Lv
Symmetry 2024, 16(1), 106; https://doi.org/10.3390/sym16010106 - 15 Jan 2024
Viewed by 693
Abstract
In this paper, the concept of symmetry is utilized in the promising trajectory planning design of autonomous ground vehicles—that is, the construction and the solution of improved artificial potential field-based trajectory planning approach are symmetrical. Despite existing artificial potential fields (APF) achievements on [...] Read more.
In this paper, the concept of symmetry is utilized in the promising trajectory planning design of autonomous ground vehicles—that is, the construction and the solution of improved artificial potential field-based trajectory planning approach are symmetrical. Despite existing artificial potential fields (APF) achievements on trajectory planning in autonomous ground vehicles (AGV), applying the traditional approach to dynamic traffic scenarios is inappropriate without considering vehicle dynamics environment and road regulations. This paper introduces a highly efficient approach for planning trajectories using improved artificial potential fields (IAPF) to handle dynamic road participants and address the issue of local minima in artificial potential fields. To begin with, potential fields are created with data obtained from other sensors. By incorporating rotational factors, the potential field will spin when the obstacle executes a maneuver; then, a safety distance model is also developed to limit the range of influence in order to minimize the computational burden. Furthermore, during the planning process, virtual forces using the gradient descent method are generated to direct the vehicle’s movement. During each timestep, the vehicle will assess whether it is likely to encounter a local minimum in the future. Once a local minimum is discovered, the method will create multiple temporary objectives to guide the vehicle toward the global minimum. Consequently, a trajectory that is both collision-free and feasible is planned. Traffic scenarios are carried out to validate the effectiveness of the proposed approach. The simulation results demonstrate that the improved artificial potential field approach is capable of generating a secure trajectory with both comfort and stability. Full article
(This article belongs to the Special Issue Emerging Applications of Machine Learning in Smart Systems Symmetry)
Show Figures

Figure 1

22 pages, 5803 KiB  
Article
Discriminant Analysis Based on the Patch Length and Crack Depth to Determine the Convergence of Global–Local Non-Intrusive Analysis with 1D-to-3D Coupling
by Matías Jaque-Zurita, Jorge Hinojosa, Emilio Castillo-Ibarra and Ignacio Fuenzalida-Henríquez
Symmetry 2023, 15(11), 2068; https://doi.org/10.3390/sym15112068 - 15 Nov 2023
Viewed by 542
Abstract
Reducing the time spent on computational simulations is an active area in solid mechanics, and efforts are being made to implement novel techniques and apply them to time-sensitive areas in the industry and research. One of these techniques is called global–local non-intrusive analysis, [...] Read more.
Reducing the time spent on computational simulations is an active area in solid mechanics, and efforts are being made to implement novel techniques and apply them to time-sensitive areas in the industry and research. One of these techniques is called global–local non-intrusive analysis, a methodology that enriches a local patch model using 3D elements with non-linear behavior (such as crack propagation), coupled with a linear, global 1D frame model that solves iteratively, thereby reducing overall times compared to a monolithic solution. However, engineers do not know the length of the local model (also known as the patch model) to be considered, which affects the convergence, computational time, and overall quality of the solution. Therefore, this study considered the use of categorical analyses for performing linear and quadratic discriminant solvers for a given set of simple cases with symmetric crack propagation within the local model and defining the convergence boundary with a certain probability of a successful convergence. In addition, a practical case was analyzed for different lengths of the local model, giving strong correlations to the results of the discriminant analysis. The solution of all the cases was also analyzed, considering the number of degrees of freedom, computational times, and the number of iterations for convergence. This aimed to establish a functional relation for engineering practice, enabling the determination of a suitable patch length for performing global–local non-intrusive analysis with crack propagation in doubly symmetric steel sections. Full article
(This article belongs to the Special Issue Emerging Applications of Machine Learning in Smart Systems Symmetry)
Show Figures

Figure 1

15 pages, 579 KiB  
Article
Modifications for the Differential Evolution Algorithm
by Vasileios Charilogis, Ioannis G. Tsoulos, Alexandros Tzallas and Evangelos Karvounis
Symmetry 2022, 14(3), 447; https://doi.org/10.3390/sym14030447 - 23 Feb 2022
Cited by 4 | Viewed by 2104
Abstract
Differential Evolution (DE) is a method of optimization used in symmetrical optimization problems and also in problems that are not even continuous, and are noisy and change over time. DE optimizes a problem with a population of candidate solutions and creates new candidate [...] Read more.
Differential Evolution (DE) is a method of optimization used in symmetrical optimization problems and also in problems that are not even continuous, and are noisy and change over time. DE optimizes a problem with a population of candidate solutions and creates new candidate solutions per generation in combination with existing rules according to discriminatory rules. The present work proposes two variations for this method. The first significantly improves the termination of the method by proposing an asymptotic termination rule, which is based on the differentiation of the average of the function values in the population of DE. The second modification proposes a new scheme for a critical parameter of the method, which improves the method’s ability to better explore the search space of the objective function. The proposed variations have been tested on a number of problems from the current literature, and from the experimental results, it appears that the proposed modifications render the method quite robust and faster even in large-scale problems. Full article
(This article belongs to the Special Issue Emerging Applications of Machine Learning in Smart Systems Symmetry)
Show Figures

Figure 1

Back to TopTop