scispace - formally typeset
Search or ask a question
Author

Xiaolei Ma

Bio: Xiaolei Ma is an academic researcher from Beihang University. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 29, co-authored 83 publications receiving 5977 citations. Previous affiliations of Xiaolei Ma include Chinese Ministry of Public Security & University of Washington.

Papers published on a yearly basis

Papers
More filters
Journal ArticleDOI
TL;DR: In this paper, the authors have selected 15 articles for review in this special issue, and a summary of these articles can be found in Section 5.1.1, Section 2.
Abstract: The advent of Connected and Autonomous Vehicles (CAVs) and Mobile Internet technologies is reshaping the public transport sector. Autonomous buses are equipped with varying advanced sensors, and hold great promises to enhancing the responsiveness and flexibility of public transit system. In the context of CAVs, transit operators can not only optimize service headway but also adjust bus capacity to meet the time-varying passenger demand. Anticipated benefits of introducing autonomous buses to the existing transit systems include safety improvement, driver cost reduction, and optimal routing. Bus electrification is another global trend to replace traditional diesel buses for energy savings. Electric buses are advantageous to both operators and passengers due to low greenhouse gas emission, maintenance cost, as well as noise pollution. In recent years, demand responsive public transport (DRPT) services (e.g. customized bus, microtransit) receive huge success thanks to the development of Mobile Internet. Unlike traditional bus services or the fixed-route transit service that relies on passive recipients, fixed stops, and schedules, DRPT can provide personalized service for specific clients through interactive information platform (Internet or smartphone). The aforementioned new types of public transit services significantly improve service quality, reduce energy consumption, and ultimately attract more ridership. To fully explore the benefits of personalized, electric and autonomous transit systems, new analytical models and data-driven methods for transit planning and operation are needed. The authors have selected 15 articles for review in this special issue. A summary of these articles is outlined below.

3 citations

01 Jan 2011
TL;DR: A two-step empirical approach to effectively estimating link journey speeds using merely advance single-loop detector outputs is developed and an α–β filter is adopted to dynamically predict and smooth real-time spot speeds resulted from loop measurements.
Abstract: Travel time is one of the most desired operational variables serving as a key measure of effectiveness for evaluating the system performance of freeways and urban arterials. With accurate travel time information, decision makers, road users, and traffic engineers can make informed decisions. However, retrieving network-level travel time information has several challenges, such as traffic data collection and travel time estimation and prediction. This research addresses these challenges by developing innovative methodologies and computer applications. First, the authors developed a two-step empirical approach to effectively estimating link journey speeds using merely advance single-loop detector outputs. Second, an α–β filter is adopted to dynamically predict and smooth real-time spot speeds resulted from loop measurements. In addition to travel time estimation and prediction, a dynamic shortest path algorithm is also developed to determine the shortest travel time route based on real-time traffic condition. Furthermore, the developed algorithms are implemented in a web-based system called Real-time Analysis and Decision-making for ARterial Networks (RADAR Net). For real-time operations of RADAR Net, sensor and signal control databases are carefully designed to ensure fast query performance in a growing network-wide traffic dataset. Also, the data visualization and statistical analysis modules are added to RADAR Net to facilitate user applications. Currently, the RADAR Net system is part of the Digital Roadway Interactive Visualization and Evaluation Network (DRIVE Net) (www.uwdrive.net) developed by the STAR Lab of the University of Washington. RADAR Net is currently being operated in real-time for arterial traveler information, performance evaluation, and analysis.

2 citations

Patent
01 May 2018
TL;DR: In this article, a multi-mode traffic demand influence analysis method, for different areas of public traffic demands and private cars, based on a spatial vector autoregression model, is provided.
Abstract: The invention provides a multi-mode traffic demand influence analysis method, for different areas of public traffic demands and private cars, based on a spatial vector autoregression model. The methodmainly comprises that (1) a multi-mode traffic demand cooperation model among the areas is established, a traditional spVAR model is improved, a regional POI index is introduced to define the spatialweight for the areas of different traffic modes, and a multi-mode traffic demand spatial VAR model including the regional space structural relation is constructed; and (2) a multi-mode traffic demandcooperation strategy of different areas is provided. Pulse response and variance decomposition results of different traffic modes are solved on the basis of the constructed regional multi-mode traffic spatial VAR model, further, a spatial overflow effect of the traffic demands is obtained by analysis, and the cooperative strategy model for different spatial states and traffic states is provided and constructed. It is proved that the model can improve the availability and scientific performance of traffic efficiency.

2 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: A comparison with different topologies of dynamic neural networks as well as other prevailing parametric and nonparametric algorithms suggests that LSTM NN can achieve the best prediction performance in terms of both accuracy and stability.
Abstract: Neural networks have been extensively applied to short-term traffic prediction in the past years. This study proposes a novel architecture of neural networks, Long Short-Term Neural Network (LSTM NN), to capture nonlinear traffic dynamic in an effective manner. The LSTM NN can overcome the issue of back-propagated error decay through memory blocks, and thus exhibits the superior capability for time series prediction with long temporal dependency. In addition, the LSTM NN can automatically determine the optimal time lags. To validate the effectiveness of LSTM NN, travel speed data from traffic microwave detectors in Beijing are used for model training and testing. A comparison with different topologies of dynamic neural networks as well as other prevailing parametric and nonparametric algorithms suggests that LSTM NN can achieve the best prediction performance in terms of both accuracy and stability.

1,521 citations

Journal ArticleDOI
Zheng Zhao1, Weihai Chen1, Xingming Wu1, Peter C. Y. Chen, Jingmeng Liu1 
TL;DR: A novel traffic forecast model based on long short-term memory (LSTM) network is proposed, which considers temporal-spatial correlation in traffic system via a two-dimensional network which is composed of many memory units.
Abstract: Short-term traffic forecast is one of the essential issues in intelligent transportation system. Accurate forecast result enables commuters make appropriate travel modes, travel routes, and departure time, which is meaningful in traffic management. To promote the forecast accuracy, a feasible way is to develop a more effective approach for traffic data analysis. The availability of abundant traffic data and computation power emerge in recent years, which motivates us to improve the accuracy of short-term traffic forecast via deep learning approaches. A novel traffic forecast model based on long short-term memory (LSTM) network is proposed. Different from conventional forecast models, the proposed LSTM network considers temporal-spatial correlation in traffic system via a two-dimensional network which is composed of many memory units. A comparison with other representative forecast models validates that the proposed LSTM network can achieve a better performance.

1,204 citations

Journal ArticleDOI
TL;DR: In this article, a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is combined with the graph convolutionsal network and the gated recurrent unit (GRU), is proposed.
Abstract: Accurate and real-time traffic forecasting plays an important role in the intelligent traffic system and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an “open” scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time. To capture the spatial and temporal dependences simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is combined with the graph convolutional network (GCN) and the gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures for capturing spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data for capturing temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at https://www.github.com/lehaifeng/T-GCN .

1,188 citations

Journal ArticleDOI
TL;DR: In this article, the authors provide a thorough overview on using a class of advanced machine learning techniques, namely deep learning (DL), to facilitate the analytics and learning in the IoT domain.
Abstract: In the era of the Internet of Things (IoT), an enormous amount of sensing devices collect and/or generate various sensory data over time for a wide range of fields and applications. Based on the nature of the application, these devices will result in big or fast/real-time data streams. Applying analytics over such data streams to discover new information, predict future insights, and make control decisions is a crucial process that makes IoT a worthy paradigm for businesses and a quality-of-life improving technology. In this paper, we provide a thorough overview on using a class of advanced machine learning techniques, namely deep learning (DL), to facilitate the analytics and learning in the IoT domain. We start by articulating IoT data characteristics and identifying two major treatments for IoT data from a machine learning perspective, namely IoT big data analytics and IoT streaming data analytics. We also discuss why DL is a promising approach to achieve the desired analytics in these types of data and applications. The potential of using emerging DL techniques for IoT data analytics are then discussed, and its promises and challenges are introduced. We present a comprehensive background on different DL architectures and algorithms. We also analyze and summarize major reported research attempts that leveraged DL in the IoT domain. The smart IoT devices that have incorporated DL in their intelligence background are also discussed. DL implementation approaches on the fog and cloud centers in support of IoT applications are also surveyed. Finally, we shed light on some challenges and potential directions for future research. At the end of each section, we highlight the lessons learned based on our experiments and review of the recent literature.

903 citations