Article
Computer Science, Artificial Intelligence
Christian Cintrano, Javier Ferrer, Manuel Lopez-Ibanez, Enrique Alba
Summary: In the traffic light scheduling problem, evaluating candidate solutions through simulation under different scenarios is crucial. This study explores the combination of IRACE and evolutionary operators for optimizing traffic light programs. By reviewing previous research, new hybrid algorithms are proposed based on the best performing evolutionary operators. The experimental analysis on a realistic case study shows that the hybrid algorithm consisting of IRACE and differential evolution outperforms other algorithms when the simulation budget is low. However, IRACE performs better than the hybrids for a high simulations budget, despite an increase in optimization time.
EVOLUTIONARY COMPUTATION
(2023)
Article
Engineering, Mechanical
C. Correia Ramos, Nada El Bouziani, Mouhaydine Tlemcani, Sara Fernandes
Summary: In this study, deterministic and probabilistic cellular automata are used to study and describe patterns in material blocks, with a focus on fracture-like patterns. The distribution of the internal structure is obtained using probabilistic cellular automata, and different methods of combining these patterns into a final one are discussed. Refinement techniques are introduced to improve the probability distributions and adjust the behavior of the cellular automata rules.
NONLINEAR DYNAMICS
(2023)
Article
Multidisciplinary Sciences
Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
Summary: Industries and services are experiencing a transformation centered around the Internet of Things, resulting in a vast amount of multi-modal data being generated every second. Edge and cloud computing have been widely adopted to meet the demand for low-latency result delivery. However, efficient resource management in hybrid edge-cloud platforms remains a challenge, and data saturation limits the performance improvement of deep neural networks (DNNs) when fed with volatile data.
SCIENTIFIC REPORTS
(2022)
Article
Engineering, Multidisciplinary
Liang Chen, Jingsen Qi, Jin Shi
Summary: This paper presents an analysis and application method of ship traffic flow considering navigation rules in narrowing channel. It aims to provide a reasonable judgment for decision makers to improve navigation efficiency and ensure navigation safety. The relationship model between narrowing channel and ships is analyzed, and navigation rules are formulated for different positions of the channel. The mutual influence of ships at the narrowed position is also analyzed. A traffic flow model of narrowing channel with navigation safety distance is proposed using cellular automata algorithm, and its correctness is verified with measured data. The experimental results demonstrate that the method can effectively capture the characteristics of actual ship traffic flow in narrowing channels.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Engineering, Multidisciplinary
Jinghui Wang, Wei Lv, Yajuan Jiang, Guangchen Huang
Summary: This study proposes an improved cellular automata model for modeling mixed pedestrian-vehicle traffic scenes. The analysis of the model shows high simulation accuracy. By applying the model to simulate real-life situations, the research results reveal the impact of pedestrian intrusion behavior on traffic flow and the changes in vehicles' speed and flow rate caused by pedestrian intrusion behavior. Additionally, the study finds that lower speeds and wider sidewalks can effectively reduce the frequency of conflicts between pedestrians and vehicles.
APPLIED MATHEMATICAL MODELLING
(2023)
Article
Engineering, Civil
Wen Li, Hongying Zhang, Zhaoguo Huang, Chenhui Li
Summary: The purpose of this research is to find an optimal traffic light timing scheme. By analyzing the crossing time distribution of pedestrians and vehicles at an intersection, and using the VISSIM software for traffic simulation, the optimal scheme is obtained. The results show that the scheme can reduce vehicle queuing delays, improve pedestrian crossing speed, and be applicable to different traffic conditions and cities.
JOURNAL OF ADVANCED TRANSPORTATION
(2022)
Article
Automation & Control Systems
Lintao Ye, Zhi-Wei Liu, Ming Chi, Vijay Gupta
Summary: We discussed the problem of maximizing a monotone nondecreasing set function under multiple constraints, and proposed two greedy algorithms with provable approximation guarantees. The first algorithm has better time complexity by exploiting the structure of a special class of problem instances. The second algorithm is suitable for general problems. We characterized the approximation guarantees of the two algorithms using the concepts of submodularity ratio and curvature, and discussed applications to specific problems in the literature. The theoretical results were validated using numerical examples.
Article
Green & Sustainable Science & Technology
Tianjun Feng, Keyi Liu, Chunyan Liang
Summary: An improved cellular automata model considering driving styles was proposed to analyze traffic flow characteristics and study traffic congestion's dissipation mechanism. The improved model introduced driving styles and two operation mechanisms (over-acceleration and speed adaptation) based on analyzing existing CA models and actual road conditions. The simulation result showed that the improved CA model is effective in dissipating traffic congestion and improving traffic capacity up to around 115% compared to the NaSch model.
Article
Engineering, Civil
Jiawei Zhang, Cheng Chang, Zimin He, Wenqin Zhong, Danya Yao, Shen Li, Li Li
Summary: This paper introduces CAVSim, a novel microscopic traffic simulator for connected and automated vehicles (CAVs), which addresses the deficiencies of traditional simulators in planning and modeling vehicles and providing standardized algorithms for multi-CAV cooperative driving.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Chong Di, Fangqi Li, Pengyao Xu, Ying Guo, Chao Chen, Minglei Shu
Summary: This paper proposes a new family of greedy algorithms based on learning automata for stochastic submodular maximization problems, and compares them with conventional greedy algorithms through experiments, showing the advantages of the proposed algorithms.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Interdisciplinary Applications
Xingyu Lu, Li Fei, Huibing Zhu, Wangjun Cheng, Zijie Wang
Summary: The new traffic model proposed can effectively alleviate traffic congestion in the work zone and eliminate the inducement of traffic accidents under traffic light control, but traffic lights are not necessary in the work zone when the traffic density is low.
INTERNATIONAL JOURNAL OF MODERN PHYSICS C
(2021)
Article
Computer Science, Artificial Intelligence
Yi Wang, Yangsheng Jiang, Yunxia Wu, Zhihong Yao
Summary: This paper proposes a control strategy for connected and automated vehicles (CAVs) that considers the driving behavior of CAV platoons. Numerical simulations show that this strategy effectively reduces traffic oscillations and congestion, and performs better than the existing strategy in improving traffic efficiency.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Chemistry, Analytical
Yongfeng Suo, Zhihong Sun, Christophe Claramunt, Shenhua Yang, Zhibing Zhang
Summary: This research introduces a modelling approach using cellular automata (CA) simulation to analyze and evaluate real-time maritime traffic risks in port environments. The approach includes designing a CA model, refining the modelling method, and establishing a risk assessment model to achieve the research objective.
Article
Computer Science, Artificial Intelligence
Juan Carlos Seck-Tuoh-Mora, Norberto Hernez-Romero, Pedro Lagos-Eulogio, Joselito Medina-Marin, Nadia Samantha Zuniga-Pena
Summary: Cellular automata can generate complex behaviors based on simple local interactions, and this paper proposes the continuous-state cellular automata algorithm that utilizes different evolution rules to balance and maximize exploration and exploitation properties. The algorithm's efficiency is proven through various tests, showing competitiveness with state-of-the-art algorithms, and its source code is publicly available.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Management
Oscar F. Carrasco Heine, Antonia Demleitner, Jannik Matuschke
Summary: This paper presents an approximation algorithm for the capacitated version of the location routing problem. By introducing a bifactor approximation, the algorithm can find approximate solutions within a small fraction beyond the facility capacity while approximating the optimal cost by a constant factor. In addition, a comprehensive computational study shows that the algorithm outperforms current state-of-the-art heuristics in terms of efficiency.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Editorial Material
Engineering, Electrical & Electronic
Hilmi Berk Celikoglu, Javier Sanchez-Medina
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE
(2018)
Article
Chemistry, Analytical
Javier J. Sanchez-Medina, Juan Antonio Guerra-Montenegro, David Sanchez-Rodriguez, Itziar G. Alonso-Gonzalez, Juan L. Navarro-Mesa
Article
Computer Science, Artificial Intelligence
Dorra Mellouli, Tarek M. Hamdani, Javier J. Sanchez-Medina, Mounir Ben Ayed, Adel M. Mimi
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2019)
Editorial Material
Engineering, Civil
Javier Del Ser, Javier J. Sanchez-Medina, Eleni I. Vlahogianni
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2019)
Article
Engineering, Civil
Javier Del Ser, Eneko Osaba, Javier Sanchez-Medina, Iztok Fister, Iztok Fister
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2020)
Article
Environmental Sciences
David Sanchez-Rodriguez, Miguel A. Quintana-Suarez, Itziar Alonso-Gonzalez, Carlos Ley-Bosch, Javier J. Sanchez-Medina
Editorial Material
Engineering, Civil
Matthew Barth, Javier J. Sanchez-Medina
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2020)
Article
Engineering, Civil
Muhammad Sajjad, Muhammad Irfan, Khan Muhammad, Javier Del Ser, Javier Sanchez-Medina, Sergey Andreev, Weiping Ding, Jong Weon Lee
Summary: The paper introduces a model car using monocular vision and scalar sensor for autonomous driving, equipped with a lightweight deep learning model. The use of economical hardware, such as Raspberry Pi, is investigated for deploying deep learning models, proposing an efficient and cost-effective approach. This designed system serves as a platform for developing economical technologies for autonomous vehicles in current intelligent transportation systems.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Chemistry, Analytical
Ibai Lana, Javier J. Sanchez-Medina, Eleni I. Vlahogianni, Javier Del Ser
Summary: Advancements in Data Science are transforming the transportation sector to be more data-driven, particularly through Intelligent Transportation Systems generating and processing a vast amount of data. This data is sourced from various sensors and software systems, providing opportunities for improving model development and decision-making within the transportation industry.
Article
Engineering, Civil
Mariam Zouari, Nesrine Baklouti, Javier Sanchez-Medina, Habib M. Kammoun, Mounir Ben Ayed, Adel M. Alimi
Summary: The research proposed an advanced vehicle guidance system based on a Hierarchical Interval Type-2 Fuzzy Logic model optimized by Particle Swarm Optimization method, which can intelligently adjust road traffic network and improve road network quality, especially in congested situations.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Rahma Fourati, Boudour Ammar, Javier Sanchez-Medina, Adel M. Alimi
Summary: This article describes an optimized Echo State Network (ESN) with different neural plasticity rules for classifying emotions based on EEG time series. The results show that the ESN with intrinsic plasticity outperforms feature-based methods and has certain advantages compared to other existing methods.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2022)
Article
Computer Science, Information Systems
Zineb Bousbaa, Javier Sanchez-Medina, Omar Bencharef
Summary: Data stream mining can be used to forecast financial time series exchange rate. Traditional static machine learning models are not suitable for the cyclical patterns in financial historical data. This paper proposes a possible methodology that uses incremental and adaptive strategy to cope with instability. The proposed algorithm utilizes online learning and statistical techniques to detect and respond to pattern shifts in the data trend.
Article
Engineering, Electrical & Electronic
Andrey Alekseenko, Hien Q. Dang, Gaurav Bansal, Javier Sanchez-Medina, Takatsugu Hirayama, Chiyomi Miyajima, Ichiro Ide, Kazuya Takeda
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE
(2019)
Proceedings Paper
Automation & Control Systems
Christina Iliopoulou, Christina Milioti, Eleni Vlahogianni, Konstantinos Kepaptsoglou, Javier Sanchez-Medina
2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)
(2018)
Proceedings Paper
Automation & Control Systems
Eneko Osaba, Javier Del Ser, Antonio J. Nebro, Ibai Lana, Miren Nekane Bilbao, Javier J. Sanchez-Medina
2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)
(2018)