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.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-its.2016.0208

LSTM network: a deep learning approach for short-term traffic forecast

Since the early 1980s, short-term traffic forecasting has been an integral part of most Intelligent Transportation Systems (ITS) research and applications; most effort has gone into developing methodologies that can be used to model traffic characteristics and produce anticipated traffic conditions. Existing literature is voluminous, and has largely used single point data from motorways and has employed univariate mathematical models to predict traffic volumes or travel times. Recent developments in technology and the widespread use of powerful computers and mathematical models allow researchers an unprecedented opportunity to expand horizons and direct work in 10 challenging, yet relatively under researched, directions. It is these existing challenges that we review in this paper and offer suggestions for future work.

Short-term traffic forecasting: Where we are and where we’re going

Data centers are critical, energy-hungry infrastructures that run large-scale Internet-based services. Energy consumption models are pivotal in designing and optimizing energy-efficient operations to curb excessive energy consumption in data centers. In this paper, we survey the state-of-the-art techniques used for energy consumption modeling and prediction for data centers and their components. We conduct an in-depth study of the existing literature on data center power modeling, covering more than 200 models. We organize these models in a hierarchical structure with two main branches focusing on hardware-centric and software-centric power models. Under hardware-centric approaches we start from the digital circuit level and move on to describe higher-level energy consumption models at the hardware component level, server level, data center level, and finally systems of systems level. Under the software-centric approaches we investigate power models developed for operating systems, virtual machines and software applications. This systematic approach allows us to identify multiple issues prevalent in power modeling of different levels of data center systems, including: i) few modeling efforts targeted at power consumption of the entire data center ii) many state-of-the-art power models are based on a few CPU or server metrics, and iii) the effectiveness and accuracy of these power models remain open questions. Based on these observations, we conclude the survey by describing key challenges for future research on constructing effective and accurate data center power models.

Data Center Energy Consumption Modeling: A Survey

Informed driving is increasingly becoming a key feature for increasing the sustainability of taxi companies. The sensors that are installed in each vehicle are providing new opportunities for automatically discovering knowledge, which, in return, delivers information for real-time decision making. Intelligent transportation systems for taxi dispatching and for finding time-saving routes are already exploring these sensing data. This paper introduces a novel methodology for predicting the spatial distribution of taxi-passengers for a short-term time horizon using streaming data. First, the information was aggregated into a histogram time series. Then, three time-series forecasting techniques were combined to originate a prediction. Experimental tests were conducted using the online data that are transmitted by 441 vehicles of a fleet running in the city of Porto, Portugal. The results demonstrated that the proposed framework can provide effective insight into the spatiotemporal distribution of taxi-passenger demand for a 30-min horizon.

/pdf/predicting-taxi-passenger-demand-using-streaming-data-225dzhts9n.pdf

Predicting Taxi–Passenger Demand Using Streaming Data

Tree based ensemble methods have reached a celebrity status in prediction field. By combining simple regression trees with ‘poor’ performance, they usually produce high prediction accuracy. In contrast to other machine learning methods that have been treated as black-boxes, tree based ensemble methods provide interpretable results, while requiring little data preprocessing, are able to handle different types of predictor variables, and can fit complex nonlinear relationship. These properties make the tree based ensemble methods good candidates for solving travel time prediction problems. However, applications of tree-based ensemble algorithms in traffic prediction area are limited. In this paper, we employ a gradient boosting regression tree method (GBM) to analyze and model freeway travel time to improve the prediction accuracy and model interpretability. The gradient boosting tree method strategically combines additional trees by correcting mistakes made by its previous base models, therefore, potentially improves prediction accuracy. Different parameters’ effect on model performance and correlations of input–output variables are discussed in details by using travel time data provided by INRIX along two freeway sections in Maryland. The proposed method is, then, compared with another popular ensemble method and a bench mark model. Study results indicate that the GBM model has its considerable advantages in freeway travel time prediction.

A gradient boosting method to improve travel time prediction

Embodiments of the present disclosure can provide a road traffic analysis method and an apparatus. The method can comprise obtaining a traffic parameter of a road intersection by analyzing road traffic information of the road intersection, determining a reference adjustment length for each phase of a traffic signal cycle corresponding to each lane of the road intersection based on the road traffic information and the traffic parameter. The traffic signal cycle has one or more phases. The method can also comprise determining a first adjustment length when a difference between the reference adjustment length and the first adjustment length satisfies a condition associated with the lanes of the road intersection and the corresponding traffic parameter, and adjusting the phases of the traffic light cycle at the road intersection based on the first adjustment length for each phase.

Road traffic analysis methods and apparatuses

The invention discloses a traffic condition analysis system. The system includes a data access module, a data analysis module, a road condition monitoring module, and a signal optimization module. Thedata access module is used for accessing the attribute information and road traffic information of a traffic network, wherein the traffic network includes road intersections and sections; the data analysis module is used for analyzing the attribute information and the road traffic information and generating the road condition parameters of the traffic network; the road condition monitoring moduleis used for monitoring the road condition of the traffic network based on the road condition parameters and generating a road condition monitoring result of the traffic network. The signal optimization module is used for adjusting the phase signal of a road intersection signal lamp according to the attribute information and the road condition parameters to generate the phase signal adjustment scheme of the road intersection signal lamp. The system monitors the traffic condition of the road intersections and sections, and optimizes the overall traffic conditions of the road intersections, so as to make the traffic condition analysis of the traffic network more comprehensive.

Traffic condition analysis system, method and device

The invention provides a data analysis method and apparatus used for logistics monitoring. The method comprises a model building stage of extracting influence factors of each logistics line in each time segment from commodity sales records in each time segment and external factors of each area in each time segment, determining influence factors and delay reasons of each delayed logistics line in each time segment according to delivery duration information of each logistics line in each time segment, and building a delay reason identification model, and a reason identification stage of obtaining a to-be-analyzed logistics line and departure time, determining influence factors of the to-be-analyzed logistics line in a time segment t from commodity sales records in the time segment t corresponding to the departure time and external factors of an area involved by the logistics line in the time segment t, inputting the influence factors of the to-be-analyzed logistics line in the time segment t into the delay reason identification model, and obtaining delay reasons of the to-be-analyzed logistics line. According to the method and the apparatus, automatic diagnosis of the logistics delay reasons can be realized.

Data analysis method and apparatus used for logistics monitoring

The invention discloses an information pushing method, device and system The method comprises the following steps: receiving dynamic time-space behavior information of a motion individual; analyzing historical data of the dynamic time-space behavior information of the motion individual to obtain behavior characteristics relevant to time and the position of the motion individual; determining appropriate information for the motion individual according to the behavior characteristics of the motion individual in conjunction with dynamic time-space behavior information of current time to use the appropriate information as matching information; and transmitting the matching information to the motion individual According to the method, the behavior characteristics of the motion individual are analyzed to obtain habit and preference characteristics of the motion individual, and specific pushed information is transmitted, so that the problems of unicity, poor diversity, poor pertinence and poor accuracy of the pushed information are solved

Information pushing method, device and system

A method of thresholding of a database of customer purchasing history using a computer, includes providing a customer purchase history database including data regarding customer satisfaction, awareness of vendor brands, previous purchasing history, and size of customer budget, providing a predetermined threshold regarding the data, establishing, in the computer, boundaries surrounding the predetermined threshold, splitting the data, in the computer, to maximize the differences in the data across the split; generating, in the computer, a model of the data, in the computer, based upon the split, and allocating marketing resources based upon the model.

Wanli Min

Papers

Road traffic analysis methods and apparatuses

Traffic condition analysis system, method and device

Data analysis method and apparatus used for logistics monitoring

Information pushing method, device and system

Most informative thresholding of heterogeneous data