Special Issues

Machine Learning and Deep Learning for Transportation

Submission Deadline: 30 March 2021 (closed) View: 533

Guest Editors

Prof. Chi-Hua Chen, Fuzhou University, China
Dr. Feng-Jang Hwang, University of Technology Sydney, Australia
Dr. Chunjia Han, University of Greenwich, United Kingdom
Prof. Xiao-Guang Yue, European University Cyprus, Cyprus
Dr. K. Shankar, Alagappa University, India
Prof. Fangying Song, Fuzhou University, China

Summary

In recent years, machine learning techniques (e.g. support vector machine (SVM), decision tree, random forest, etc.) and deep learning techniques (e.g. convolutional neural network (CNN), recurrent neural network (RNN), long-short term memory (LSTM), etc.) have been popularly applied into image recognition and time-series inferences for intelligent transportation systems (ITS). For instance, advanced driver assistance systems and autonomous cars have been developed based on machine learning and deep learning techniques to perform forward collision warning, blind spot monitoring, lane departure warning systems, traffic sign recognition, traffic safety, infrastructure management and congestion, and so on. Autonomous vehicles can share their detected information (e.g., traffic signs, collision events, etc.) with other vehicles via vehicular communication systems (e.g., dedicated short range communication (DSRC), vehicular ad hoc networks (VANETs), long term evolution (LTE), and the 5th generation mobile networks) for cooperation. However, the performance and efficiency of these techniques are big challenges for performing real-time applications.

 

Therefore, several optimization techniques (e.g. gradient descent algorithm, Adam optimization algorithm, particle swarm optimization algorithm, etc.) have been proposed to support deep learning algorithms in finding faster solutions. For example, the gradient descent method is one of the most popular optimization techniques to quickly seek the optimized weight sets and filters of CNN for image recognition. The ITS applications based on these image recognition techniques (e.g., autonomous cars, augmented reality navigation systems, etc.) have gained increasing attention, and the hybrid approaches typical of mathematics for engineering and computer science (e.g. machine learning, deep learning, and optimization techniques) can be investigated and developed to support a variety of ITS applications.

 

The aim of this Special Issue is to focus on both original research and review articles on various disciplines of ITS applications, including particularly machine learning, deep learning and optimization techniques for ITS time-series data analyses, ITS spatio-temporal data analyses, advanced traffic management systems, advanced traveler information systems, commercial vehicle operation systems, advanced vehicle control and safety systems, advanced public transportation services, emergency management services, electronic payment services, advanced information management services, information management services, vulnerable individual protection services, etc.

 

Potential topics include, but are not limited to, the following:

• Machine learning, deep learning, and optimization techniques for ITS time-series and spatio-temporal data analyses

• Machine learning, deep learning, and optimization techniques for advanced traffic management and safety, traveler information, commercial vehicle operation, advanced vehicle control and safety, and advanced public transportation systems

• Machine learning, deep learning, and optimization techniques for emergency management, electronic payment, advanced information management, and vulnerable individual protection services

• Machine learning, deep learning, and optimization techniques for image recognition

• Applications and techniques for image recognition based on machine learning and deep learning for ITS

• Applications and techniques for autonomous cars and ships based on machine learning and deep learning

• Machine learning, deep learning, and optimization techniques for quality of service in VANET

• Machine learning, deep learning, and optimization techniques for infrastructure management and congestion

 

Warm reminder: Please select Special Issue: Machine Learning and Deep Learning for Transportation when you submit your article in IASC submission system


Keywords

• Machine learning
• Deep learning
• Convolutional neural network
• Recurrent neural network
• Intelligent Transportation

Published Papers


  • Open Access

    ARTICLE

    CVAE-GAN Emotional AI Music System for Car Driving Safety

    Chih-Fang Huang, Cheng-Yuan Huang
    Intelligent Automation & Soft Computing, Vol.32, No.3, pp. 1939-1953, 2022, DOI:10.32604/iasc.2022.017559
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract Musical emotion is important for the listener’s cognition. A smooth emotional expression generated through listening to music makes driving a car safer. Music has become more diverse and prolific with rapid technological developments. However, the cost of music production remains very high. At present, because the cost of music creation and the playing copyright are still very expensive, the music that needs to be listened to while driving can be executed by the way of automated composition of AI to achieve the purpose of driving safety and convenience. To address this problem, automated AI music… More >

  • Open Access

    ARTICLE

    Predicting the Breed of Dogs and Cats with Fine-Tuned Keras Applications

    I.-Hung Wang, Mahardi, Kuang-Chyi Lee, Shinn-Liang Chang
    Intelligent Automation & Soft Computing, Vol.30, No.3, pp. 995-1005, 2021, DOI:10.32604/iasc.2021.019020
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract The images classification is one of the most common applications of deep learning. Images of dogs and cats are mostly used as examples for image classification models, as they are relatively easy for the human eyes to recognize. However, classifying the breed of a dog or a cat has its own complexity. In this paper, a fine-tuned pre-trained model of a Keras’ application was built with a new dataset of dogs and cats to predict the breed of identified dogs or cats. Keras applications are deep learning models, which have been previously trained with general More >

  • Open Access

    ARTICLE

    A Novel Automatic Meal Delivery System

    Jhe-Wei Lin, Cheng-Yan Siao, Ting-Hsuan Chien, Rong-Guey Chang
    Intelligent Automation & Soft Computing, Vol.29, No.3, pp. 685-695, 2021, DOI:10.32604/iasc.2021.018254
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract Since the rapid growth of the Fourth Industrial Revolution (or Industry 4.0), robots have been widely used in many applications. In the catering industry, robots are used to replace people to do routine jobs. Because meal is an important part of the catering industry, we aim to design and develop a robot to deliver meals for saving cost and improving a restaurant’s performance in this paper. However, for the existing meal delivery system, the guests must make their meals by themselves. To let the food delivery system become more user-friendly, we integrate an automatic guided… More >

  • Open Access

    ARTICLE

    A General Technique for Real-Time Robotic Simulation in Manufacturing System

    Ting-Hsuan Chien, Cheng-Yan Siao, Rong-Guey Chang
    Intelligent Automation & Soft Computing, Vol.29, No.3, pp. 827-838, 2021, DOI:10.32604/iasc.2021.018256
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract This paper describes a real-time simulator that allows the user in the factories to simulate arbitrary interaction between machinery and equipment. We discussed in details not only the general technique for developing such a real-time simulator but also the implementation of the simulator in its actual use. As such, people on the production line could benefit from observing and controlling robots in factories for preventing or reducing the severity of a collision, using the proposed simulator and its related technique. For that purpose, we divided the simulator into two main models: the real-time communication model More >

  • Open Access

    ARTICLE

    Paralleling Collision Detection on Five-Axis Machining

    Cheng-Yan Siao, Jhe-Wei Lin, Ting-Hsuan Chien, Rong-Guey Chang
    Intelligent Automation & Soft Computing, Vol.29, No.2, pp. 559-569, 2021, DOI:10.32604/iasc.2021.018252
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract With the rapid growth of the Fourth Industrial Revolution (or Industry 4.0), five-axis machining has played an important role nowadays. Due to the expensive cost of five-axis machining, how to solve the collision detection for five-axis machining in real-time is very critical. In this paper, we present a parallel method to detect collision for five-axis machining. Moreover, we apply the bounding volume hierarchy technique with two-level bounding volume represent the surface or solid of the object to reduce triangle meshes inside each axis of the five-axis machine tool, and then matching the operating range limit… More >

  • Open Access

    ARTICLE

    A Deep Learning Approach for the Mobile-Robot Motion Control System

    Rihem Farkh, Khaled Al jaloud, Saad Alhuwaimel, Mohammad Tabrez Quasim, Moufida Ksouri
    Intelligent Automation & Soft Computing, Vol.29, No.2, pp. 423-435, 2021, DOI:10.32604/iasc.2021.016219
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract A line follower robot is an autonomous intelligent system that can detect and follow a line drawn on floor. Line follower robots need to adapt accurately, quickly, efficiently, and inexpensively to changing operating conditions. This study proposes a deep learning controller for line follower mobile robots using complex decision-making strategies. An Arduino embedded platform is used to implement the controller. A multilayered feedforward network with a backpropagation training algorithm is employed. The network is trained offline using Keras and implemented on a ATmega32 microcontroller. The experimental results show that it has a good control effect More >

  • Open Access

    ARTICLE

    Implementation of Multi-Object Recognition System for the Blind

    Huijin Park, Soobin Ou, Jongwoo Lee
    Intelligent Automation & Soft Computing, Vol.29, No.1, pp. 247-258, 2021, DOI:10.32604/iasc.2021.015274
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract Blind people are highly exposed to numerous dangers when they walk alone outside as they cannot obtain sufficient information about their surroundings. While proceeding along a crosswalk, acoustic signals are played, though such signals are often faulty or difficult to hear. The bollards can also be dangerous if they are not made with flexible materials or are located improperly. Therefore, since the blind cannot detect proper information about these obstacles while walking, their environment can prove to be dangerous. In this paper, we propose an object recognition system that allows the blind to walk safely… More >

  • Open Access

    ARTICLE

    Analysis of Roadside Accident Severity on Rural and Urban Roadways

    Fulu Wei, Zhenggan Cai, Yongqing Guo, Pan Liu, Zhenyu Wang, Zhibin Li
    Intelligent Automation & Soft Computing, Vol.28, No.3, pp. 753-767, 2021, DOI:10.32604/iasc.2021.014661
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract The differences in traffic accident severity between urban and rural areas have been widely studied, but conclusions are still limited. To explore the factors influencing the occurrence of roadside accidents in urban and rural areas, 3735 roadside traffic accidents from 2017 to 2019 were analyzed. Fourteen variables from the aspects of driver, vehicle, driving environment, and other influencing factors were selected to establish a Bayesian binary logit model of roadside crashes. The deviance information criterion and receiver operating characteristic curve were used to test the goodness of fit for the traffic crash model. The results… More >

  • Open Access

    ARTICLE

    Driving Pattern Profiling and Classification Using Deep Learning

    Meenakshi Malik, Rainu Nandal, Surjeet Dalal, Vivek Jalglan, Dac-Nhuong Le
    Intelligent Automation & Soft Computing, Vol.28, No.3, pp. 887-906, 2021, DOI:10.32604/iasc.2021.016272
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract The last several decades have witnessed an exponential growth in the means of transport globally, shrinking geographical distances and connecting the world. The automotive industry has grown by leaps and bounds, with millions of new vehicles being sold annually, be it for personal commuting or for public or commodity transport. However, millions of motor vehicles on the roads also mean an equal number of drivers with varying levels of skill and adherence to safety regulations. Very little has been done in the way of exploring and profiling driving patterns and vehicular usage using real world… More >

  • Open Access

    ARTICLE

    Constructional Cyber Physical System: An Integrated Model

    Tzer-Long Chen, Chien-Yun Chang, Yung-Cheng Yao, Kuo-Chang Chung
    Intelligent Automation & Soft Computing, Vol.28, No.1, pp. 73-82, 2021, DOI:10.32604/iasc.2021.015980
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract Artificial intelligence, machine learning, and deep learning have achieved great success in the fields of computer vision and natural language processing, and then extended to various fields, such as biology, chemistry, and civil engineering, including big data in the field of logistics. Therefore, many logistics companies move towards the integration of intelligent transportation systems. Only virtual and physical development can support the sustainable development of the logistics industry. This study aims to: 1.) collect timely information from the block chain, 2.) use deep learning to build a customer database so that sales staff in physical… More >

  • Open Access

    ARTICLE

    Design and Validation of a Route Planner for Logistic UAV Swarm

    Meng-Tse Lee, Ying-Chih Lai, Ming-Lung Chuang, Bo-Yu Chen
    Intelligent Automation & Soft Computing, Vol.28, No.1, pp. 227-240, 2021, DOI:10.32604/iasc.2021.015339
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract Unmanned Aerial Vehicles (UAV) are widely used in different fields of aviation today. The efficient delivery of packages by drone may be one of the most promising applications of this technology. In logistic UAV missions, due to the limited capacities of power supplies, such as fuel or batteries, it is almost impossible for one unmanned vehicle to visit multiple wide areas. Thus, multiple unmanned vehicles with well-planned routes become necessary to minimize the unnecessary consumption of time, distance, and energy while carrying out the delivery missions. The aim of the present study was to develop… More >

  • Open Access

    ARTICLE

    Parallel Equilibrium Optimizer Algorithm and Its Application in Capacitated Vehicle Routing Problem

    Zonglin Fu, Pei Hu, Wei Li, Jeng-Shyang Pan, Shuchuan Chu
    Intelligent Automation & Soft Computing, Vol.27, No.1, pp. 233-247, 2021, DOI:10.32604/iasc.2021.014192
    (This article belongs to the Special Issue: Machine Learning and Deep Learning for Transportation)
    Abstract The Equilibrium Optimizer (EO) algorithm is a novel meta-heuristic algorithm based on the strength of physics. To achieve better global search capability, a Parallel Equilibrium Optimizer algorithm, named PEO, is proposed in this paper. PEO is inspired by the idea of parallelism and adopts two different communication strategies between groups to improve EO. The first strategy is used to speed up the convergence rate and the second strategy promotes the algorithm to search for a better solution. These two kinds of communication strategies are used in the early and later iterations of PEO respectively. To More >

Share Link