Yu Haitao

Bio: Yu Haitao is an academic researcher. The author has contributed to research in topics: Taximeter & Recurrent neural network. The author has an hindex of 2, co-authored 5 publications receiving 31 citations.

Learning to Predict Bus Arrival Time From Heterogeneous Measurements via Recurrent Neural Network

Abstract: Bus arrival time prediction intends to improve the level of the services provided by transportation agencies. Intuitively, many stochastic factors affect the predictability of the arrival time, e.g. , weather and local events. Moreover, the arrival time prediction for a current station is closely correlated with that of multiple passed stations. Motivated by the observations above, this paper proposes to exploit the long-range dependencies among the multiple time steps for bus arrival prediction via recurrent neural network (RNN). Concretely, RNN with long short-term memory block is used to “correct” the prediction for a station by the correlated multiple passed stations. During the correlation among multiple stations, one-hot coding is introduced to fuse heterogeneous information into a unified vector space. Therefore, the proposed framework leverages the dynamic measurements ( i.e. , historical trajectory data) and the static observations ( i.e. , statistics of the infrastructure) for bus arrival time prediction. In order to fairly compare with the state-of-the-art methods, to the best of our knowledge, we have released the largest data set for this task. The experimental results demonstrate the superior performances of our approach on this data set.

Discovering Fine-Grained Spatial Pattern From Taxi Trips: Where Point Process Meets Matrix Decomposition and Factorization

Abstract: As increasing volumes of urban data are being available, new opportunities arise for data-driven analysis that can lead to improvements in the lives of citizens through evidence-based policies. In particular, taxi trip is an important urban sensor that provides unprecedented insights into many aspects of a city, from economic activity, human mobility to land development. However, analyzing these data presents many challenges, e.g. , sparse data for fine-grained patterns, and the regularity submerged by seemingly random data. Inspired by above challenges, we focus on Pick-Up (PU)/Drop-Off (DO) points from taxi trips, and propose a fine-grained approach to unveil a set of low spatio-temporal patterns from the regularity-discovered intensity. The proposed method is conceptually simple yet efficient, by leveraging point process to handle sparsity of points, and by decomposing point intensities into the low-rank regularity and the factorized basis patterns, our approach enables domain experts to discover patterns that are previously unattainable for them, from a case study motivated by traffic engineers.

Cloned taxi detection method and detection system

Abstract: The invention relates to a cloned taxi detection method and detection system. The method includes the following steps that: a taxi license plate is captured through a road surveillance camera, the obtained taxi license plate number, and the position and capture time of the road surveillance camera are transmitted to a data center; the GPS data of a vehicle with the license plate number and corresponding time data are retrieved in a data center database with the obtained license plate number adopted as an index; a shortest path between a position where the license plate number is captured, thatis, the location of the road surveillance camera, and the specific GPS data of the vehicle license plate number recorded by the data center is calculated, and a shortest path between GPS data of a certain time interval when the data center records the vehicle license plate number is also calculated; and the comparison result of the two shortest paths is obtained through judgment, and whether a taxi is cloned is judged. The system includes a license plate information transmission system, a license plate information retrieval system, a license plate information matching system and a matching result transmission system. The cloned taxi detection method and detection system of the embodiments of the invention have the advantages of high reliability, convenience, high efficiency, real-time performance, low cost, portability and the like.

Method and system for distinguishing handing over of taxi to another person to be driven

Abstract: The invention relates to a method and system for distinguishing handing over of a taxi to another person to be driven. The system comprises a data obtaining module, a feature constructing module and aclassifier feature classification module. The methods comprises the steps: obtained taxi GPS data and taximeter data are cleaned to obtain modeling data; individual features of a taxi driver are modelled according to the obtained modeling data; taxi individual behavior features are mapped to a uniform feature space through a self-similar calculation method and valued to obtain a feature vector; according to a judgment model, the self-similar feature vector is judged to obtain a judgment value; and according to the comparison result of a preset threshold value and the judgment value, the conclusion of whether the taxi is handed over to another person to be driven or not is obtained. According to the method and model for distinguishing whether the taxi is handed over to another person to bedriven or not, by combining big data mining and computer technologies, the taxi handed over to another person to be driven is automatically and accurately identified, thus the work burden of law enforcement officers is relieved, and the work efficiency is improved.

Method and system for distinguishing whether taxi is cloned taxi or not

Abstract: The invention discloses a method and a system for distinguishing whether a taxi is a cloned taxi or not. The invention provides a method for identifying whether a vehicle is a cloned vehicle, which comprises the following steps: identifying vehicle information by using a plurality of cameras; calculating the shortest distance between a vehicle and the cameras and comparing the shortest distance with a threshold; processing a comparison result by using a crowd-sourcing method to obtain the probability that the vehicle is a cloned vehicle; and finding out a license plate of which the probabilityis greater than 0.5, drawing a GPS track of the license plate, comparing the track with the installation positions of the cameras, and verifying whether the vehicle is a cloned vehicle or not. Compared with the prior art, because GPS data and camera data of vehicles are utilized, the identification inaccuracy of the cameras due to the influence of external factors is reduced, the correct rate oflicense plate information identification is increased, misjudgment is reduced, the accuracy and stability of cloned vehicle identification are improved, and great convenience is provided for a supervision department.

Digital Design And Computer Architecture

Abstract: Thank you for downloading digital design and computer architecture. As you may know, people have search numerous times for their chosen novels like this digital design and computer architecture, but end up in malicious downloads. Rather than enjoying a good book with a cup of coffee in the afternoon, instead they juggled with some infectious virus inside their laptop. digital design and computer architecture is available in our digital library an online access to it is set as public so you can download it instantly. Our digital library hosts in multiple countries, allowing you to get the most less latency time to download any of our books like this one. Merely said, the digital design and computer architecture is universally compatible with any devices to read.

Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions

Abstract: Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion. This problem is challenging due to the complicated and dynamic spatio-temporal dependencies between different regions in the road network. Recently, a significant amount of research efforts have been devoted to this area, especially deep learning method, greatly advancing traffic prediction abilities. The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives. Specifically, we first summarize the existing traffic prediction methods, and give a taxonomy. Second, we list the state-of-the-art approaches in different traffic prediction applications. Third, we comprehensively collect and organize widely used public datasets in the existing literature to facilitate other researchers. Furthermore, we give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset. Finally, we discuss open challenges in this field.

Deep Learning for Spatio-Temporal Data Mining: A Survey

Abstract: With the fast development of various positioning techniques such as Global Position System (GPS), mobile devices and remote sensing, spatio-temporal data has become increasingly available nowadays. Mining valuable knowledge from spatio-temporal data is critically important to many real-world applications including human mobility understanding, smart transportation, urban planning, public safety, health care and environmental management. As the number, volume and resolution of spatio-temporal data increase rapidly, traditional data mining methods, especially statistics-based methods for dealing with such data are becoming overwhelmed. Recently deep learning models such as recurrent neural network (RNN) and convolutional neural network (CNN) have achieved remarkable success in many domains due to the powerful ability in automatic feature representation learning, and are also widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, anomaly detection and classification. In this paper, we provide a comprehensive review of recent progress in applying deep learning techniques for STDM. We first categorize the spatio-temporal data into five different types, and then briefly introduce the deep learning models that are widely used in STDM. Next, we classify existing literature based on the types of spatio-temporal data, the data mining tasks, and the deep learning models, followed by the applications of deep learning for STDM in different domains including transportation, on-demand service, climate & weather analysis, human mobility, location-based social network, crime analysis, and neuroscience. Finally, we conclude the limitations of current research and point out future research directions.

Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions

Abstract: Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion. This problem is challenging due to the complicated and dynamic spatio-temporal dependencies between different regions in the road network. Recently, a significant amount of research efforts have been devoted to this area, especially deep learning method, greatly advancing traffic prediction abilities. The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives. Specifically, we first summarize the existing traffic prediction methods, and give a taxonomy. Second, we list the state-of-the-art approaches in different traffic prediction applications. Third, we comprehensively collect and organize widely used public datasets in the existing literature to facilitate other researchers. Furthermore, we give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset. Finally, we discuss open challenges in this field.