Yang Xing

Bio: Yang Xing is an academic researcher from Nanyang Technological University. The author has contributed to research in topics: Computer science & Advanced driver assistance systems. The author has an hindex of 18, co-authored 67 publications receiving 988 citations. Previous affiliations of Yang Xing include University of Oxford & Cranfield University.

Levenberg–Marquardt Backpropagation Training of Multilayer Neural Networks for State Estimation of a Safety-Critical Cyber-Physical System

Abstract: As an important safety-critical cyber-physical system (CPS), the braking system is essential to the safe operation of the electric vehicle. Accurate estimation of the brake pressure is of great importance for automotive CPS design and control. In this paper, a novel probabilistic estimation method of brake pressure is developed for electrified vehicles based on multilayer artificial neural networks (ANNs) with Levenberg–Marquardt backpropagation (LMBP) training algorithm. First, the high-level architecture of the proposed multilayer ANN for brake pressure estimation is illustrated. Then, the standard backpropagation (BP) algorithm used for training of the feed-forward neural network (FFNN) is introduced. Based on the basic concept of BP, a more efficient training algorithm of LMBP method is proposed. Next, real vehicle testing is carried out on a chassis dynamometer under standard driving cycles. Experimental data of the vehicle and the powertrain systems are collected, and feature vectors for FFNN training collection are selected. Finally, the developed multilayer ANN is trained using the measured vehicle data, and the performance of the brake pressure estimation is evaluated and compared with other available learning methods. Experimental results validate the feasibility and accuracy of the proposed ANN-based method for braking pressure estimation under real deceleration scenarios.

Driver Activity Recognition for Intelligent Vehicles: A Deep Learning Approach

Abstract: Driver decisions and behaviors are essential factors that can affect the driving safety. To understand the driver behaviors, a driver activities recognition system is designed based on the deep convolutional neural networks (CNN) in this paper. Specifically, seven common driving activities are identified, which are the normal driving, right mirror checking, rear mirror checking, left mirror checking, using in-vehicle radio device, texting, and answering the mobile phone, respectively. Among these activities, the first four are regarded as normal driving tasks, while the rest three are classified into the distraction group. The experimental images are collected using a low-cost camera, and ten drivers are involved in the naturalistic data collection. The raw images are segmented using the Gaussian mixture model to extract the driver body from the background before training the behavior recognition CNN model. To reduce the training cost, transfer learning method is applied to fine tune the pre-trained CNN models. Three different pre-trained CNN models, namely, AlexNet, GoogLeNet, and ResNet50 are adopted and evaluated. The detection results for the seven tasks achieved an average of 81.6% accuracy using the AlexNet, 78.6% and 74.9% accuracy using the GoogLeNet and ResNet50, respectively. Then, the CNN models are trained for the binary classification task and identify whether the driver is being distracted or not. The binary detection rate achieved 91.4% accuracy, which shows the advantages of using the proposed deep learning approach. Finally, the real-world application are analyzed and discussed.

Driver Lane Change Intention Inference for Intelligent Vehicles: Framework, Survey, and Challenges

Abstract: Intelligent vehicles and advanced driver assistance systems (ADAS) need to have proper awareness of the traffic context, as well as the driver status since ADAS share the vehicle control authorities with the human driver. This paper provides an overview of the ego-vehicle driver intention inference (DII), which mainly focuses on the lane change intention on highways. First, a human intention mechanism is discussed in the beginning to gain an overall understanding of the driver intention. Next, the ego-vehicle driver intention is classified into different categories based on various criteria. A complete DII system can be separated into different modules, which consist of traffic context awareness, driver states monitoring, and the vehicle dynamic measurement module. The relationship between these modules and the corresponding impacts on the DII are analyzed. Then, the lane change intention inference system is reviewed from the perspective of input signals, algorithms, and evaluation. Finally, future concerns and emerging trends in this area are highlighted.

Advances in Vision-Based Lane Detection: Algorithms, Integration, Assessment, and Perspectives on ACP-Based Parallel Vision

Abstract: Lane detection is a fundamental aspect of most current advanced driver assistance systems U+0028 ADASs U+0029. A large number of existing results focus on the study of vision-based lane detection methods due to the extensive knowledge background and the low-cost of camera devices. In this paper, previous vision-based lane detection studies are reviewed in terms of three aspects, which are lane detection algorithms, integration, and evaluation methods. Next, considering the inevitable limitations that exist in the camera-based lane detection system, the system integration methodologies for constructing more robust detection systems are reviewed and analyzed. The integration methods are further divided into three levels, namely, algorithm, system, and sensor. Algorithm level combines different lane detection algorithms while system level integrates other object detection systems to comprehensively detect lane positions. Sensor level uses multi-modal sensors to build a robust lane recognition system. In view of the complexity of evaluating the detection system, and the lack of common evaluation procedure and uniform metrics in past studies, the existing evaluation methods and metrics are analyzed and classified to propose a better evaluation of the lane detection system. Next, a comparison of representative studies is performed. Finally, a discussion on the limitations of current lane detection systems and the future developing trends toward an Artificial Society, Computational experiment-based parallel lane detection framework is proposed.

Personalized Vehicle Trajectory Prediction Based on Joint Time-Series Modeling for Connected Vehicles

Abstract: Motion prediction for the leading vehicle is a critical task for connected autonomous vehicles. It provides a method to model the leading-following vehicle behavior and analysis their interactions. In this study, a joint time-series modeling approach for leading vehicle trajectory prediction considering different driving styles is proposed. The proposed method enables a precise and personalized trajectory prediction for the leading vehicle based on limited inter-vehicle communication signals, such as the vehicle speed and acceleration of the front vehicles. Three different driving styles are first recognized based on an unsupervised clustering algorithm, namely, Gaussian Mixture Model (GMM). The GMM generates a specific driving style for each vehicle based on the speed, acceleration, jerk, time, and space headway features of the leading vehicle. The feature importance of driving style recognition is also evaluated based on the Maximal Information Coefficient (MIC) algorithm. Then, a personalized joint time series modeling (JTSM) method based on the Long Short-Term Memory (LSTM) Recurrent Neural Network model (RNN) is proposed to predict the front vehicle trajectories. The JTSM contains a common LSTM layer and different fully connected regression layers for different driving styles. The proposed method is tested with the Next Generation Simulation (NGSIM) data on the US101, and I-80 highway dataset. The JTSM is tested for making predictions one to five seconds ahead. Results indicate that the proposed personalized JTSM approach shows a significant advantage over the baseline algorithms.

A Comprehensive Survey on Transfer Learning

Abstract: Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target-domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. Due to the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning research studies, as well as to summarize and interpret the mechanisms and the strategies of transfer learning in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Unlike previous surveys, this survey article reviews more than 40 representative transfer learning approaches, especially homogeneous transfer learning approaches, from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, over 20 representative transfer learning models are used for experiments. The models are performed on three different data sets, that is, Amazon Reviews, Reuters-21578, and Office-31, and the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.

Assessing Public Opinions of and Interest in New Vehicle Technologies: An Austin Perspective

Abstract: Technological advances are bringing connected and autonomous vehicles (CAVs) to the ever- evolving transportation system. Anticipating the public acceptance and adoption of these technologies is important. A recent internet-based survey was conducted polling 347 Austinites to understand their opinions on smart-car technologies and strategies. Ordered-probit and other model results indicate that respondents perceive fewer crashes to be the primary benefit of autonomous vehicles (AVs), with equipment failure being their top concern. Their average willingness to pay (WTP) for adding full (Level 4) automation ($7,253) appears to be much higher than that for adding partial (Level 3) automation ($3,300) to their current vehicles. This study estimates the impact of demographics, built-environment variables, and travel characteristics on Austinites’ WTP for adding such automations and connectivity to their current and coming vehicles. It also estimates adoption rates of shared autonomous vehicles (SAVs) under different pricing scenarios ($1, $2, and $3 per mile), choice dependence on friends’ and neighbors’ adoption rates, and home-location decisions after AVs and SAVs become a common mode of transport. Higher-income, technology-savvy males, living in urban areas, and those who have experienced more crashes have a greater interest in and higher WTP for the new technologies, with less dependence on others’ adoption rates. Such behavioral models are useful to simulate long-term adoption of CAV technologies under different vehicle pricing and demographic scenarios. These results can be used to develop smarter transportation systems for more efficient and sustainable travel.

Blockchain for AI: Review and Open Research Challenges

Abstract: Recently, artificial intelligence (AI) and blockchain have become two of the most trending and disruptive technologies. Blockchain technology has the ability to automate payment in cryptocurrency and to provide access to a shared ledger of data, transactions, and logs in a decentralized, secure, and trusted manner. Also with smart contracts, blockchain has the ability to govern interactions among participants with no intermediary or a trusted third party. AI, on the other hand, offers intelligence and decision-making capabilities for machines similar to humans. In this paper, we present a detailed survey on blockchain applications for AI. We review the literature, tabulate, and summarize the emerging blockchain applications, platforms, and protocols specifically targeting AI area. We also identify and discuss open research challenges of utilizing blockchain technologies for AI.