Artificial Intelligence and Intelligent Control for Autonomous Systems

A special issue of Systems (ISSN 2079-8954). This special issue belongs to the section "Systems Practice in Engineering".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 11095

Special Issue Editors

Computer Science, Kuwait College of Science & Technology, Doha 35001, Kuwait
Interests: vertical handover management; computer networks; Internet of Things; smart control systems
Special Issues, Collections and Topics in MDPI journals
Amazon Web Services (AWS), Dallas, TX 75240, USA
Interests: wireless communications; signal processing; IoT/M2M

Special Issue Information

Dear Colleagues,

Rising demands, accompanied by a lack of manpower, have accelerated the adaptation of autonomous systems in various industrial sectors. Thus, autonomous systems are receiving enormous attention due to their enhanced performance with less requirement of human support. Autonomous systems are being incorporated into industries, logistics, finance, health care, and every other possible sector. Intelligent control is an amalgamation of artificial intelligence and autonomous systems, which helps in taking crucial decision making steps. However, the model prediction and intelligent decision forecasted by AI have limited applications due to its drawbacks. For the training of AI modules, large datasets are required, which are unavailable for most real-time scenarios. Moreover, the extent of labelling in the training datasets is limited, reducing the intelligent decision's accuracy. Furthermore, the lack of quality control modules to validate the decision increases erroneous decisions in chaotic scenarios. Along with these, improvements in noise reduction and normalization of input data and innovative sensor fusion technologies are needed to enhance the performance of AI in intelligent control. Addressing these issues in AI algorithms guarantees the generation of the best suitable decision in all possible real-time scenarios.

Recent advances in artificial neural networks with unstructured data analytics have increased the performance of forecasting and decision making by artificial intelligence. Combining many IoT-based sensor devices with a general-purpose learning framework (named DeepSense) increases the training efficiency, even in unstructured data, by analysing the spatio-temporal features of input data. Moreover, general adversarial networks are specialized in analysing unlabelled data by extracting information by overlaying it with labelled data. Moreover, a multisensory fusion algorithm named RDeepSense compares and correlates multisensory data and predicts the accuracy index, which determines the reliability of decisions. An FCAN based traffic pattern intelligent control algorithm learns from the pattern of incoming vehicles and makes an intelligent decision in regulating traffic, thereby reducing the waiting time in signals. A multimodal control algorithm, stimulating intelligent human control, works based on human cognitive intelligence proficiently positions and navigates Multiple Autonomous Vehicles and guarantees complete automation. Adaptation of deep neural networks (such as MobileNet Single-Shot Detectors) detects and recognizes people and enables "Smart surveillance". Moreover, bio-inspired algorithms (such as evolutionary control and probabilistic models) are used in the complete automation of various health care sectors. Artificial intelligence harbours enormous potential in context awareness and making intelligent decisions. Empowering autonomous systems with artificial intelligence would enhance their performance to several feats, thus better serving mankind.

Therefore, this blog forms an ideal platform for researchers, entrepreneurs, engineers and programmers to present their unpublished works, reviews, and perspectives on recent innovations in the involvement of various deep learning modules in the intelligent control of autonomous systems.

Proposed List of Topics for the Special Issue: 

  • Impact of Brain-inspired algorithms for robotic process automation;
  • Innovations in deep learning and reinforcement learning in delicate motion of robotic arms;
  • Advances in the meta-analysis of semi-supervised mobility of multiple vehicles;
  • Trends in Fuzzy control systems for surveillance and public monitoringVisual SLAM in Smart Pattern Recognition using Deep Learning;
  • Impact of neural network and evolutionary models for complete automation of industrial vehicles;
  • Trends in Intelligent multi-agent control systems for "Smart Logistics.";
  • Innovations in information-based models for autonomous energy conservation in smart cities;
  • Emerging trends in soft computing for complete automation in agricultural harvesting;
  • Innovations in parsimonious and versatile machine learning approaches for food processing and packaging
  • Trends in the composite learning-based algorithm for image processing and pattern recognition;
  • Self-organizing intelligent control for positioning and navigation of unmanned aerial vehicles;
  • Trends in optimization and modelling of observer-based intelligent control;
  • Impact of bee colony optimization in self-tuning and adaptive management of robotic machinery.

Dr. Syed Hassan Ahmed
Dr. Murad Khan
Dr. Wael Guibene
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. Systems 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 (6 papers)

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

Research

19 pages, 2927 KiB  
Article
Exploring the Computational Effects of Advanced Deep Neural Networks on Logical and Activity Learning for Enhanced Thinking Skills
by Deming Li, Kellyt D. Ortegas and Marvin White
Systems 2023, 11(7), 319; https://doi.org/10.3390/systems11070319 - 22 Jun 2023
Cited by 19 | Viewed by 1116
Abstract
The Logical and Activity Learning for Enhanced Thinking Skills (LAL) method is an educational approach that fosters the development of critical thinking, problem-solving, and decision-making abilities in students using practical, experiential learning activities. Although LAL has demonstrated favorable effects on children’s cognitive growth, [...] Read more.
The Logical and Activity Learning for Enhanced Thinking Skills (LAL) method is an educational approach that fosters the development of critical thinking, problem-solving, and decision-making abilities in students using practical, experiential learning activities. Although LAL has demonstrated favorable effects on children’s cognitive growth, it presents various obstacles, including the requirement for tailored instruction and the complexity of tracking advancement. The present study presents a model known as the Deep Neural Networks-based Logical and Activity Learning Model (DNN-LALM) as a potential solution to tackle the challenges above. The DNN-LALM employs sophisticated machine learning methodologies to offer tailored instruction and assessment tracking, and enhanced proficiency in cognitive and task-oriented activities. The model under consideration has been assessed using a dataset comprising cognitive assessments of children. The findings indicate noteworthy enhancements in accuracy, precision, and recall. The model above attained a 93% accuracy rate in detecting logical patterns and an 87% precision rate in forecasting activity outcomes. The findings of this study indicate that the implementation of DNN-LALM can augment the efficacy of LAL in fostering cognitive growth, thereby facilitating improved monitoring of children’s advancement by educators and parents. The model under consideration can transform the approach toward LAL in educational environments, facilitating more individualized and efficacious learning opportunities for children. Full article
Show Figures

Figure 1

16 pages, 7771 KiB  
Article
AI-Based Environmental Color System in Achieving Sustainable Urban Development
by Pohsun Wang, Wu Song, Junling Zhou, Yongsheng Tan and Hongkong Wang
Systems 2023, 11(3), 135; https://doi.org/10.3390/systems11030135 - 02 Mar 2023
Cited by 4 | Viewed by 1908
Abstract
Confronting the age of artificial intelligence, exploring art through technology has become one of the directions of interdisciplinary development. Not only does artificial intelligence technology explore sustainability on a technical level; it can also take advantage of itself to focus on the visual [...] Read more.
Confronting the age of artificial intelligence, exploring art through technology has become one of the directions of interdisciplinary development. Not only does artificial intelligence technology explore sustainability on a technical level; it can also take advantage of itself to focus on the visual perception of the living environment. People frequently interpret environmental features through their eyes, and the use of intuitive eye-tracking can provide effective data that can contribute to environmental sustainability in managing the environment and color planning to enhance the image of cities. This research investigates the visual responses of people viewing the historic city of Macau through an eye movement experiment to understand how the color characteristics of the physical environment are perceived. The research reveals that the buildings and plantings in the historic district of Macau are the most visible objects in the environment, while the smaller scale of St. Dominic’s Square, the Company of Jesus Square, and St. Augustine’s Square, which have a sense of spatial extension, have also become iconic environmental landscapes. This also draws visual attention and guides the direction of travel. The overall impressions of the Historic Centre of Macau, as expressed by the participants after the eye movement experiment, were mainly described as “multiculturalism”, “architectural style”, “traditional architecture”, “color scheme”, and “garden planting”. The 60 colors representing the urban color of Macau are then organized around these deep feelings about the environment. Therefore, for future inspiration, the 60 colors can be applied through design practice to create color expressions that fit the local characteristics, and thereby enhance the overall visual image of the city. Full article
Show Figures

Figure 1

20 pages, 911 KiB  
Article
Applicability of the Future State Maximization Paradigm to Agent-Based Modeling: A Case Study on the Emergence of Socially Sub-Optimal Mobility Behavior
by Simon Plakolb and Nikita Strelkovskii
Systems 2023, 11(2), 105; https://doi.org/10.3390/systems11020105 - 14 Feb 2023
Cited by 1 | Viewed by 1094
Abstract
Novel developments in artificial intelligence excel in regard to the abilities of rule-based agent-based models (ABMs), but are still limited in their representation of bounded rationality. The future state maximization (FSX) paradigm presents a promising methodology for describing the intelligent behavior of agents. [...] Read more.
Novel developments in artificial intelligence excel in regard to the abilities of rule-based agent-based models (ABMs), but are still limited in their representation of bounded rationality. The future state maximization (FSX) paradigm presents a promising methodology for describing the intelligent behavior of agents. FSX agents explore their future state space using “walkers” as virtual entities probing for a maximization of possible states. Recent studies have demonstrated the applicability of FSX to modeling the cooperative behavior of individuals. Applied to ABMs, the FSX principle should also represent non-cooperative behavior: for example, in microscopic traffic modeling, there is a need to model agents that do not fully adhere to the traffic rules. To examine non-cooperative behavior arising from FSX, we developed a road section model populated by agent-cars endowed with an augmented FSX decision making algorithm. Simulation experiments were conducted in four scenarios modeling various traffic settings. A sensitivity analysis showed that cooperation among the agents was the result of a balance between exploration and exploitation. We showed that our model reproduced several patterns observed in rule-based traffic models. We also demonstrated that agents acting according to FSX can stop cooperating. We concluded that FSX can be useful for studying irrational behavior in certain traffic settings, and that it is suitable for ABMs in general. Full article
Show Figures

Figure 1

16 pages, 3895 KiB  
Article
Hybrid Particle Swarm Optimization Algorithm Based on the Theory of Reinforcement Learning in Psychology
by Wenya Huang, Youjin Liu and Xizheng Zhang
Systems 2023, 11(2), 83; https://doi.org/10.3390/systems11020083 - 06 Feb 2023
Cited by 3 | Viewed by 1642
Abstract
To more effectively solve the complex optimization problems that exist in nonlinear, high-dimensional, large-sample and complex systems, many intelligent optimization methods have been proposed. Among these algorithms, the particle swarm optimization (PSO) algorithm has attracted scholars’ attention. However, the traditional PSO can easily [...] Read more.
To more effectively solve the complex optimization problems that exist in nonlinear, high-dimensional, large-sample and complex systems, many intelligent optimization methods have been proposed. Among these algorithms, the particle swarm optimization (PSO) algorithm has attracted scholars’ attention. However, the traditional PSO can easily become an individual optimal solution, leading to the transition of the optimization process from global exploration to local development. To solve this problem, in this paper, we propose a Hybrid Reinforcement Learning Particle Swarm Algorithm (HRLPSO) based on the theory of reinforcement learning in psychology. First, we used the reinforcement learning strategy to optimize the initial population in the population initialization stage; then, chaotic adaptive weights and adaptive learning factors were used to balance the global exploration and local development process, and the individual optimal solution and the global optimal solution were obtained using dimension learning. Finally, the improved reinforcement learning strategy and mutation strategy were applied to the traditional PSO to improve the quality of the individual optimal solution and the global optimal solution. The HRLPSO algorithm was tested by optimizing the solution of 12 benchmarks as well as the CEC2013 test suite, and the results show it can balance the individual learning ability and social learning ability, verifying its effectiveness. Full article
Show Figures

Figure 1

18 pages, 5311 KiB  
Article
A New Decision Method of Flexible Job Shop Rescheduling Based on WOA-SVM
by Lijun Song, Zhipeng Xu, Chengfu Wang and Jiafu Su
Systems 2023, 11(2), 59; https://doi.org/10.3390/systems11020059 - 21 Jan 2023
Cited by 1 | Viewed by 1873
Abstract
Enterprise production is often interfered with by internal and external factors, resulting in the infeasible original production scheduling scheme. In terms of this issue, it is necessary to quickly decide the optimal production scheduling scheme after these disturbances so that the enterprise is [...] Read more.
Enterprise production is often interfered with by internal and external factors, resulting in the infeasible original production scheduling scheme. In terms of this issue, it is necessary to quickly decide the optimal production scheduling scheme after these disturbances so that the enterprise is produced efficiently. Therefore, this paper proposes a new rescheduling decision model based on the whale optimization algorithm and support vector machine (WOA-SVM). Firstly, the disturbance in the production process is simulated, and the dimensionality of the data from the simulation is reduced to train the machine learning model. Then, this trained model is combined with the rescheduling schedule to deal with the disturbance in the actual production. The experimental results show that the support vector machine (SVM) performs well in solving classification and decision problems. Moreover, the WOA-SVM can solve problems more quickly and accurately compared to the traditional SVM. The WOA-SVM can predict the flexible job shop rescheduling mode with an accuracy of 89.79%. It has higher stability compared to other machine learning methods. This method can respond to the disturbance in production in time and satisfy the needs of modern enterprises for intelligent production. Full article
Show Figures

Figure 1

15 pages, 1320 KiB  
Article
Reducing Children’s Obesity in the Age of Telehealth and AI/IoT Technologies in Gulf Countries
by Mohammed Faisal, Hebah ElGibreen, Nora Alafif and Chibli Joumaa
Systems 2022, 10(6), 241; https://doi.org/10.3390/systems10060241 - 02 Dec 2022
Cited by 1 | Viewed by 2055
Abstract
Childhood obesity has become one of the major health issues in the global population. The increasing prevalence of childhood obesity is associated with serious health issues and comorbidities related to obesity. Several studies mentioned that childhood obesity became even worse recently due to [...] Read more.
Childhood obesity has become one of the major health issues in the global population. The increasing prevalence of childhood obesity is associated with serious health issues and comorbidities related to obesity. Several studies mentioned that childhood obesity became even worse recently due to the effect of COVID-19 and the consequent policies and regulations. For that reason, Internet of Things (IoT) technologies should be utilized to overcome the challenges related to obesity management and provide care from a distance to improve the health care services for obesity. However, IoT by itself is a limited resource and it is important to consider other artificial intelligent (AI) components. Thus, this paper contributes into the literature of child obesity management by introducing a comprehensive survey for obesity management covering clinical work measuring the association between sleep disturbances and childhood obesity alongside physical activity and diet and comparatively analyzing the emerging technologies used to prevent childhood obesity. It further contributes to the literature by proposing an interactive smart framework that combines clinical and emerging AI/telehealth technologies to manage child obesity. The proposed framework can be used to reduce children obesity and improve their quality of life using Machine Learning (ML). It utilizes IoT devices to integrate information from different sources and complement it with a mobile application and web-based platform to connect parents and physicians with their child. Full article
Show Figures

Figure 1

Back to TopTop