THE DESIGN AND ANALYSIS OF EXPERIMENTS. By Oscar Kempthorne. New York, John Wiley and Sons, Inc., 1952. 631 pp. $8.50. This book by a teacher of statistics (as well as a consultant for \"experimenters\") is a comprehensive study of the philosophical background for the statistical design of experiment. It is necessary to have some facility with algebraic notation and manipulation to be able to use the volume intelligently. The problems are presented from the theoretical point of view, without such practical examples as would be helpful for those not acquainted with mathematics. The mathematical justification for the techniques is given. As a somewhat advanced treatment of the design and analysis of experiments, this volume will be interesting and helpful for many who approach statistics theoretically as well as practically. With emphasis on the \"why,\" and with description given broadly, the author relates the subject matter to the general theory of statistics and to the general problem of experimental inference. MARGARET J. ROBERTSON

The Design and Analysis of Experiments

Accurate and timely traffic flow information is important for the successful deployment of intelligent transportation systems. Over the last few years, traffic data have been exploding, and we have truly entered the era of big data for transportation. Existing traffic flow prediction methods mainly use shallow traffic prediction models and are still unsatisfying for many real-world applications. This situation inspires us to rethink the traffic flow prediction problem based on deep architecture models with big traffic data. In this paper, a novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently. A stacked autoencoder model is used to learn generic traffic flow features, and it is trained in a greedy layerwise fashion. To the best of our knowledge, this is the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction. Moreover, experiments demonstrate that the proposed method for traffic flow prediction has superior performance.

Traffic Flow Prediction With Big Data: A Deep Learning Approach

The development of the Internet in recent years has made it possible and useful to access many different information systems anywhere in the world to obtain information. While there is much research on the integration of heterogeneous information systems, most commercial systems stop short of the actual integration of available data. Data fusion is the process of fusing multiple records representing the same real-world object into a single, consistent, and clean representation.This article places data fusion into the greater context of data integration, precisely defines the goals of data fusion, namely, complete, concise, and consistent data, and highlights the challenges of data fusion, namely, uncertain and conflicting data values. We give an overview and classification of different ways of fusing data and present several techniques based on standard and advanced operators of the relational algebra and SQL. Finally, the article features a comprehensive survey of data integration systems from academia and industry, showing if and how data fusion is performed in each.

Data fusion

Statistical Analysis With Missing Data (2nd ed.) (Book)

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.

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

Impact of cyberattacks on safety and stability of connected and automated vehicle platoons under lane changes.

Intelligent transportation systems (ITS) include large numbers of sensors that collect enormous quantities of traffic-flow data. The data provided by ITS are necessary for advanced forms of control. However, more basic forms of control, such as time-of-day (TOD) signal-timing plans that are widely used in the United States, do not directly rely on the data. Thus, sensor data often are unused and discarded. The sensor data, however, can provide large amounts of information that can aid in the development of improved TOD signal-timing plans. Data-mining tools are necessary to extract information from the data necessary to improve timing-plan development and to allow the timing-plan development and monitoring processes to be automated. A research effort that investigates the application of data-mining tools, including statistical clustering and classification techniques, to aid in the development of traffic-signal-timing plans is described. A case study was conducted that illustrated that hierarchical cluster analysis can be used to identify temporal interval breakpoints that support the design of a TOD signal-control system. The cluster analysis approach was able to use a high-resolution system state definition that takes full advantage of the extensive set of sensors deployed in a traffic signal system. Finally, the case study also demonstrated that a classification and regression tree could be developed that can be used to monitor automatically the quality of TOD intervals as traffic conditions change. The results of this research indicate that advanced data-mining techniques have great potential to provide automated techniques that assist traffic engineers in signal-control-system design and operations.

Data-Mining Tools for the Support of Signal-Timing Plan Development:

Transportation agencies spend significant resources to collect pavement roughness data using profiler vans. A potential alternative to collect functionally equivalent data at a significantly lower cost and higher level of temporal resolution is to use existing accelerometers in smartphones as the “set” of sensors. In this research, a prototype smartphone application was developed to investigate the feasibility of such an approach. Acceleration data were collected using a prototype application running on Android tablets on two routes in Virginia. The analysis results show that the proposed smartphone application can generate consistent data sets from different data collecting runs. In addition, the average of the collected data sets is found to be highly correlated with the International Roughness Index data collected by the Virginia Department of Transportation using profiler vans. Also, a sample size analysis revealed that most pavement sections require fewer than 12 data collecting trips at a 50 Hz sampling rate while fewer than 16 trips are required for a rate of 10 Hz. Finally, a preliminary benefit assessment for Virginia showed that the proposed smartphone application approach allows for collection of comparable roughness data for more roadways, more frequently with significantly less cost.

Feasibility Assessment of a Smartphone-Based Application to Estimate Road Roughness

Large-scale data archives compiled by transportation management systems capture a wide range of experience. However, to use this experience effectively, transportation professionals must be able to search these archives efficiently to identify cases of interest. An example of this challenge is to find past events that are similar to a current event to understand traffic flow and the impact of utilized control strategies. These similar events are referred to as nearest neighbors to the current event. To identify near neighbors in a data archive, a distance metric is required to measure similarity between cases. However, common distance metrics, such as Euclidean distance, are not valid when used with categorical variables, which commonly make up traffic event data. To address this challenge, this research effort developed a distance metric that can be effectively used with categorical data. The metric is based on the influence of variable values on a measurable objective meaningful to the purpose of selecting nearest neighbors. The metric was developed in a case study to identify similar past incidents in an archive to a current incident, with the objective of forecasting incident duration. When this method was incorporated in a nonparametric regression forecasting model, it was demonstrated to outperform parametric forecasting models significantly.

Identifying nearest neighbors in a large-scale incident data archive

This paper presents an innovative traffic signal control algorithm, the IntelliGreen Algorithm (IGA), that utilizes IntelliDriveSM technologies to improve the efficacy of traffic signals. The IGA takes a novel approach to traffic signal control using k-means clustering and is fully decentralized. A VISSIM model of a real-world arterial was used to evaluate the IGA and its performance was compared to that of an actuated timing plan. The IGA consistently improved traffic mobility, and sustainability as volumes increased, even at lower IntelliDrive market penetration levels. The results demonstrate the power of IntelliDrive data and that decentralized traffic signal control can achieve system-wide benefits at lower computational costs.

Brian L. Smith

Papers

Impact of cyberattacks on safety and stability of connected and automated vehicle platoons under lane changes.

Data-Mining Tools for the Support of Signal-Timing Plan Development:

Feasibility Assessment of a Smartphone-Based Application to Estimate Road Roughness

Identifying nearest neighbors in a large-scale incident data archive

Using k-means clustering to improve traffic signal efficacy in an IntelliDrive SM environment