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

The purpose of this research effort was to identify benefits provided by a concept of operations in the life-cycle of a transportation management system (TMS) and to identify best practices in the development and use of the concept of operations for TMSs. Experience has shown that the systems engineering process is well suited for the complex nature of the contemporary TMS. The foundation of the systems engineering process is the concept of operations, a high-level, nontechnical document focusing vision and goals for all aspects of a system that are necessary for operation in such a way that a diverse audience will fully understand what the system will do. The research surveyed current practice in TMS applications and compared this with concept-of-operations standards from the industry. Key findings of the research include the following recommendations and best practices for development and use of the concept of operations for TMSs: (a) stakeholder communication and involvement in system development is th...

Part 3: Regional Transportation Systems Management: Investigation of the Development and Use of a Concept of Operations in Traffic Management Systems

The focus of the surface transportation community has been steadily shifting over the past decade, from one of capital construction and maintenance toward system operations. To support this new focus, new monitoring tools are necessary. The Virginia Department of Transportation’s (VDOT’s) System Operations Directorate needs to gauge system performance for planning and developing effective future operational systems and strategies. The purpose of this research was to develop system operations performance measures for VDOT. To do so, the University of Virginia Center for Transportation Studies first identified four categories of measures: traffic, incidents, traveler information, and intelligent transportation system (ITS) device reliability. Then, specific measures were identified and developed for these categories. This research report presents these measures along with examples of their use within VDOT. All these measures were compiled into a prototype monthly statewide performance report. VDOT can use this performance report to guide its system operations program, allowing it to focus resources better on activities that best address VDOT’s stated goals. The researchers recommend that the product of this research, the Virginia System Operations Performance Report (Appendix A), be used within VDOT’s System Operations Directorate to guide future activities. The performance measures provided by the performance report will enable continuous monitoring of VDOT’s progress toward stated goals. To ensure that the report is stable and consistent, the report further recommends that VDOT’s Information Technology Division maintain the production system developed to automate creation of the monthly reports and that its Operations and Security Division establish a position that is responsible for monitoring and expanding data sources used for performance measurement. This position (the so-called “data watchdog”) will serve as the business user expert that interfaces with VDOT’s Information Technology Division and all divisions within the directorate. The benefits expected from this research are significant. Measuring performance is essential to monitoring the activities within the system operations program and determining where resources should be distributed to achieve the goals of the program. A monthly report, developed as a result of this research, will provide access to key performance measures. Such continuous reporting of these measures will help ensure that performance trends will be continuously scrutinized, resulting in improved mobility for all travelers on Virginia’s roadways.

Investigation of System Operations Performance Measures for the Virginia Department of Transportation

Analysis of the capabilities and operations of the Northern Virginia Traffic Management System.

Dynamic Message Signs (DMS) have been widely used to disseminate public traffic information for decades. Despite their effectiveness, they can be costly, can only present a limited amount of information, and typically only display information in one language. The wide availability of smart devices and the development of connected vehicles offer the possibility to create “virtual” DMSs (VDMS) with geofencing and audible messages. This research aimed to address the question whether this new way of information delivery conveys information as least as well as existing DMSs. A mixed repeated measure experiment was designed that examined the impacts of driver age, information transmission mode, amount of information, and driving complexity on message comprehension. Forty-two Participants were recruited and each of them was tested under different combinations of the three within-subject factors. Participant performance was measured in terms of message comprehension, distraction, and self-reported difficulty level. Results revealed that VDMS generally performs better than DMS across different amounts of information and under different driving conditions, regardless of driver age. VDMS increased message comprehension by 16% under relatively complex conditions, reduced driver distraction (as measured with a reduced time-to-brake of 0.39 seconds), and made the same messages easier to process and retain for drivers than DMS. Based on these results, it is recommended that transportation agencies give careful consideration to future strategies for delivering public traffic information.

Examining the Effectiveness of In-Vehicle Auditory Public Traffic Information Compared with Roadside Dynamic Message Signs

As system operations plays an increasingly important role in transportation agencies, there is a need to develop solid performance measurement programs to support and guide these activities. The purpose of this research was to develop a system operations performance measurement program for the Virginia Department of Transportation (VDOT). To do so, the research team first identified four categories of measures: traffic, incidents, traveler information, and ITS device reliability. Then, specific measures were identified and developed for these categories. The paper presents these measures along with examples of their use within VDOT. Finally, it should be noted that the results presented in this paper are not intended to serve as a “turn-key” set of measures for use by other DOT’s. Rather, the paper offers benefit by (a) providing a comprehensive description of the Virginia development process that may be used/tailored by other DOT’s, and (b) introducing new measures developed to meet VDOT needs that may be of use to other DOTs.

Brian L. Smith

Papers

Part 3: Regional Transportation Systems Management: Investigation of the Development and Use of a Concept of Operations in Traffic Management Systems

Investigation of System Operations Performance Measures for the Virginia Department of Transportation

Analysis of the capabilities and operations of the Northern Virginia Traffic Management System.

Examining the Effectiveness of In-Vehicle Auditory Public Traffic Information Compared with Roadside Dynamic Message Signs

Development of Statewide System Operations Performance Measures: Virginia Case Study