Freeway Travel Time Prediction Using Takagi–Sugeno–Kang Fuzzy Neural Network

This article presents a Takagi–Sugeno–Kang Fuzzy Neural Network (TSKFNN) approach to predict freeway corridor travel time with an online computing algorithm. TSKFNN, a combination of a Takagi–Sugeno–Kang (TSK) type fuzzy logic system and a neural network, produces strong prediction performance because of its high accuracy and quick convergence. Real world data collected from US‐290 in Houston, Texas are used to train and validate the network. The prediction performance of the TSKFNN is investigated with different combinations of traffic count, occupancy, and speed as input options. The comparison between online TSKFNN, offline TSKFNN, the back propagation neural network (BPNN) and the time series model (ARIMA) is made to evaluate the performance of TSKFNN. The results show that using count, speed, and occupancy together as input produces the best TSKFNN predictions. The online TSKFNN outperforms other commonly used models and is a promising tool for reliable travel time prediction on a freeway corridor.     

Fuzzy‐Entropy Neural Network Freeway Incident Duration Modeling with Single and Competing Uncertainties

An approach for predicting incident durations that are susceptible to severe congestion, the occurrence of secondary incidents, and their joint effect is proposed. First, a fuzzy entropy feature selection methodology is applied to determine redundant factors and rank factor importance with respect to their contribution on the predictability of incident duration. Second, neural network models for incident duration prediction with single and competing uncertainties are developed. The results indicate that alignment, collision type, and downstream geometry may be considered as redundant when modeling incident duration. Rainfall intensity is a highly contributing feature, while lane volume, number of blocked lanes, as well as number of vehicles involved in the incident are among the top ranking factors for determining the extent of duration. Finally, the joint consideration of severe congestion and secondary incident occurrence may improve the generalization power of the prediction models.     

Development of a Data‐Driven Framework for Real‐Time Travel Time Prediction

Travel time prediction is one of the most important components in Intelligent Transportation Systems implementation. Various related techniques have been developed, but the efforts for improving the applicability of long‐term prediction in a real‐time manner have been lacking. Existing methods do not fully utilize the advantages of the state‐of‐the‐art cloud system and large amount of data due to computation issues. We propose a new prediction framework for real‐time travel time services in the cloud system. A distinctive feature is that the prediction is done with the entire data of a road section to stably and accurately produce the long‐term (at least 6‐hour prediction horizon) predicted value. Another distinctive feature is that the framework uses a hierarchical pattern matching called Multilevel k‐nearest neighbor (Mk‐NN) method which is compared with the conventional k‐NN method and Nearest Historical average method. The results show that the method can more accurately and robustly predict the long‐term travel time with shorter computation time.     

Recurrent Neural Network for Approximate Earthquake Time and Location Prediction Using Multiple Seismicity Indicators

Abstract:  A computational approach is presented for predicting the location and time of occurrence of future moderate-to-large earthquakes in an approximate sense based on neural network modeling and using a vector of eight seismicity indicators as input. Two different methods are explored. In the first method, a large seismic region is subdivided into several small subregions and the temporal historical earthquake record is divided into a number of small equal time periods. Seismicity indicators are computed for each subregion for each time period and their relationship to the magnitude of the largest earthquake occurring in that subregion during the following time-period is studied using a recurrent neural network. In the second more direct approach, the temporal historical earthquake record is divided into a number of unequal time periods where each period is defined as the time between large earthquakes. Seismicity indicators are computed for each time-period and their relationship to the latitude and longitude of the epicentral location, and time of occurrence of the following major earthquake is studied using a recurrent neural network.     

Recurrent Neural Networks for Uncertain Time‐Dependent Structural Behavior

Abstract: In this article, an approach is introduced which permits the numerical prediction of future structural responses in dependency of uncertain load processes and environmental influences. The approach is based on recurrent neural networks trained by time‐dependent measurement results. Thereby, the uncertainty of the measurement results is modeled as fuzzy processes which are considered within the recurrent neural network approach. An efficient solution for network training and prediction is developed utilizing α‐cuts and interval arithmetic. The capability of the approach is demonstrated by means of the prediction of the long‐term structural behavior of a reinforced concrete plate strengthened by a textile reinforced concrete layer.     

Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces with a Recurrent Neural Network

A recurrent neural network (RNN) called CrackNet‐R is proposed in the article for fully automated pixel‐level crack detection on three‐dimensional (3D) asphalt pavement surfaces. In the article, a new recurrent unit, gated recurrent multilayer perceptron (GRMLP), is proposed to recursively update the internal memory of CrackNet‐R. Unlike the widely used long short‐term memory (LSTM) and gated recurrent unit (GRU), GRMLP is intended for deeper abstractions on the inputs and hidden states by conducting multilayer nonlinear transforms at gating units. CrackNet‐R implements a two‐phase sequence processing: sequence generation and sequence modeling. Sequence generation is specifically developed in the study to find the best local paths that are most likely to form crack patterns. Sequence modeling predicts timely probabilities of the input sequence being a crack pattern. In terms of sequence modeling, GRMLP slightly outperforms LSTM and GRU by using only one more nonlinear layer at each gate. In addition to sequence processing, an output layer is proposed to produce pixel probabilities based on timely probabilities predicted for sequences. The proposed output layer is critical for pixel‐perfect accuracy, as it accomplishes the transition from sequence‐level learning to pixel‐level learning. Using 3,000 diverse 3D images, the training of CrackNet‐R is completed through optimizing sequence modeling, sequence generation, and the output layer serially. The experiment using 500 testing pavement images shows that CrackNet‐R can achieve high Precision (88.89%), Recall (95.00%), and F‐measure (91.84%) simultaneously. Compared with the original CrackNet, CrackNet‐R is about four times faster and introduces tangible improvements in detection accuracy.     

End‐to‐End Deep Learning Methodology for Real‐Time Traffic Network Management

This article presents a novel real‐time traffic network management system using an end‐to‐end deep learning (E2EDL) methodology. A computational learning model is trained, which allows the system to identify the time‐varying traffic congestion pattern in the network, and recommend integrated traffic management schemes to reduce this congestion. The proposed model structure captures the temporal and spatial congestion pattern correlations exhibited in the network, and associates these patterns with efficient traffic management schemes. The E2EDL traffic management system is trained using a laboratory‐generated data set consisting of pairings of prevailing traffic network conditions and efficient traffic management schemes designed to cope with these conditions. The system is applied for the US‐75 corridor in Dallas, Texas. Several experiments are conducted to examine the system performance under different traffic operational conditions. The results show that the E2EDL system achieves travel time savings comparable to those recorded for an optimization‐based traffic management system.     

Determining Inputs for Neural Network Models of Multivariate Time Series

In recent years, artificial neural networks have been used successfully to model multivariate water resources time series. By using analytical approaches to determine appropriate model inputs, network size and training time can be reduced. In this paper, it is proposed that the method of Haugh and Box and a new neural network–based approach can be used to identify the inputs for multivariate artificial neural network models. Both methods were used to obtain the inputs for a multivariate artificial neural network model used for forecasting salinity in the River Murray at Murray Bridge, South Australia. The methods were compared with a third method that uses knowledge of travel times in the river to identify a reasonable set of inputs. The results obtained indicate that all three methods are suitable for determining the inputs for multivariate time series models. However, the neural network–based method is preferable because it is quicker and simpler to use. Any prior knowledge of the underlying processes should be used in conjunction with the neural network method.     

Wavelet‐Based Denoising for Traffic Volume Time Series Forecasting with Self‐Organizing Neural Networks

Abstract: In their goal to effectively manage the use of existing infrastructures, intelligent transportation systems require precise forecasting of near‐term traffic volumes to feed real‐time analytical models and traffic surveillance tools that alert of network links reaching their capacity. This article proposes a new methodological approach for short‐term predictions of time series of volume data at isolated cross sections. The originality in the computational modeling stems from the fit of threshold values used in the stationary wavelet‐based denoising process applied on the time series, and from the determination of patterns that characterize the evolution of its samples over a fixed prediction horizon. A self‐organizing fuzzy neural network is optimized in its configuration parameters for learning and recognition of these patterns. Four real‐world data sets from three interstate roads are considered for evaluating the performance of the proposed model. A quantitative comparison made with the results obtained by four other relevant prediction models shows a favorable outcome.     

A Generic Approach to Estimate Freeway Traffic Time Using Vehicle ID‐Matching Technologies

New technologies have emerged to estimate the travel time on freeways by matching certain unique identifications of passing vehicles at different locations. These types of technologies share many similarities despite having different mechanisms. In this article, a generic method is presented to estimate freeway travel times using vehicle ID‐matching technologies. In particular, the new method addresses two long‐standing challenges: outlier screening and travel time estimation. Innovations include (1) using both statistical methods and traffic flow theory to screen outliers; and (2) accounting for mechanisms of various equipment measurement errors. The effectiveness of the proposed method is demonstrated using simulation and shown to be more accurate and responsive to travel time changes than methods based on the use of traditional inductive loops.     

Modeling of Shotcrete Application for Use in a Real‐Time Training Simulator

Simulators provide significant advantages in training operators of concrete spraying machinery, such as economic savings, the practical absence of safety risks, and environmental and educational benefits. The main challenge in developing a real‐time training simulator for concrete spraying machinery lies in the modeling of shotcrete application. This article presents a novel method that models and simulates in real time the three main factors influencing shotcrete sprayability: adhesion, cohesion, and rebound. Furthermore, thanks to the addition of an obstacle model, the method makes it possible to spray onto additional supporting elements, which is a typical shotcrete application. The proposed method considers a wet‐mix thick flow spraying process and is based on experiments that were run with a real concrete spraying machine and complemented by expert advice. The method was developed and evaluated using a user‐centered methodology, resulting in realistic shotcrete application modeling that meets the needs for training concrete spraying machinery operators.     

A Two‐Dimension Dynamic Bayesian Network for Large‐Scale Degradation Modeling with an Application to a Bridges Network

Modeling the stochastic evolution of a large‐scale fleet or network generally proves to be challenging. This difficulty may be compounded through complex relationships between various assets in the network. Although a great number of probabilistic graph‐based models (e.g., Bayesian networks) have been developed recently to describe the behavior of single assets, one can find significantly fewer approaches addressing a fully integrated network. It is proposed an extension to the standard dynamic Bayesian network (DBN) by introducing an additional dimension for multiple elements. These elements are then linked through a set of covariates that translate the probabilistic dependencies. A Markov chain is utilized to model the elements and develop a distribution‐free mathematical framework to parameterize the transition probabilities without previous data. This is achieved by borrowing from Cooke's method for structured expert judgment and also applied to the quantification of the covariate relationships. Some metrics are also presented for evaluating the sensitivity of information inserted into the covariate DBN where the focus is given on two specific types of configurations. The model is applied to a real‐world example of steel bridge network in the Netherlands. Numerical examples highlight the inference mechanism and show the sensitivity of information inserted in various ways. It is shown that information is most valuable very early and decreases substantially over time. Resulting observations entail the reduction of inference combinations and by extension a computational gain to select the most sensitive pieces of information.     

Selection of Methodology for Neural Network Modeling of Constitutive Hystereses Behavior of Soils

Classic constitutive modeling of geomaterials based on the elasticity and plasticity theories suffers from limitations pertaining to formulation complexity, idealization of behavior, and excessive empirical parameters. This article capitalizes on the modeling capabilities of neural networks as substitutes for the classic approaches. The neural network–based modeling overcomes the difficulties encountered in understanding the underlying microscopic processes governing the material's behavior by redirecting the efforts into learning the cause-effect relations from behavioral examples. Several methodologies are presented and cross-compared for effectiveness in approximating a theoretical hysteresis model resembling stress-strain behavior. The most effective methodology was used in modeling the constitutive behavior of an experimentally tested soil and produced models that simulated the real behavior of the soil with high accuracy. Although these models are empirical, they are retrainable and thus, unlike classic constitutive modeling techniques, can be revised and generalized easily when new data become available.     

A Spatial Network Model for Civil Infrastructure System Development

Infrastructure networks play an important role in improving economic prosperity, enabling movement of resources, and protecting communities from hazards. As these networks serve population, they evolve in response to social, economic, environmental, and technological changes. Consideration of these interactions has thus far been limited by use of simplified data sets and idealized network structures, and is unable to explain the complexity and suboptimal structures displayed by real infrastructure networks. This article presents a new computational model that simulates the growth and evolution of infrastructure systems. Empirical evidence obtained from analysis of nontrivial real‐world data sets is used to identify the mechanisms that guide and govern system‐scale evolution of infrastructure networks. The model investigates the interplay of three key drivers, namely network demand, network efficiency, and network cost in shaping infrastructure network architectures. The validity of the model is verified by comparing key topological and spatial properties of simulated networks with real‐world networks from six infrastructure sectors. The model is used to develop and explore different scenarios of infrastructure network futures, and their resilience is shown to change as a result of different infrastructure management policies. The model can therefore be used to identify system‐wide infrastructure engineering strategies to reduce network costs, increase network efficiency, and improve the resilience of infrastructure networks to disruptive events.     

A Wavelet Support Vector Machine‐Based Neural Network Metamodel for Structural Reliability Assessment

Wavelet neural network (WNN) has been widely used in the field of civil engineering. However, WNN can only effectively handle problems of small dimensions as the computational cost for constructing wavelets of large dimensions is prohibitive. To expand the application of WNN to higher dimensions, this article develops a new wavelet support vector machine (SVM)‐based neural network metamodel for reliability analysis. The method first develops an autocorrelation wavelet kernel SVM and then uses a set of wavelet SVMs with different resolution as the activation function of WNN. The output of network is obtained through aggregating outputs of different wavelet SVMs. The method takes advantage of the excellent capacities of SVM to handle high‐dimensional problems and of the attractive properties of wavelet to represent complex functions. Four examples are given to demonstrate the application and effectiveness of the proposed method.     

Hybrid CPN–Neural Dynamics Model for Discrete Optimization of Steel Structures

Abstract: In practical design of steel structures, the designer usually must choose from a limited number of commercially available shapes such as the widely used wide flange shapes. In this article, we present a hybrid counterpropagation-neural dynamics model and a new neural network topology for discrete optimization of large structures subjected to the AISC ASD specifications. The constrained structural optimization problem is formulated in terms of a neural dynamics model with constraint and variable layers. The counterpropagation part of the model consists of the competition and interpolation layers. The CPN network is trained to learn the relationship between the cross-sectional area and the radius of gyration of the available sections. The robustness of the hybrid computational model is demonstrated by application to three examples representing the exterior envelope of high-rise and super-high-rise steel building structures, including a 147-story structure with 8904 members.     

Modeling of two‐cell cores for three‐dimensional analysis of multi‐story buildings

The reliability of simplified models for single‐cell cores, and particularly for open and semi‐open U‐cross‐section cores, has been the subject of many research papers in the recent past. In contrast, on an international level, only little mention has been made of the efficiency of such models for multi‐cell cores of multi‐story R/C buildings. This paper evaluates and comments on the reliability of several simplified models for open two‐cell cores that are often used in practice. The models examined are: (a) models composed of equivalent columns in alternative configurations; (b) models composed of panel elements; and (c) finite shell element models with one element for each flange in each story. These models are compared with one another and with the solution considered accurate, which is the one obtained by using a finite element method consisting of an adequately dense mesh of finite shell elements. The conclusions obtained refer to both the simplified modal response analysis and the multi‐modal response spectrum analysis, while the specific assumptions for the numerical investigations are compatible with the provisions of modern seismic design codes. Copyright © 2000 John Wiley & Sons, Ltd.     

基于Civil 3D的排水管网辅助建模二次开发

针对Civil 3D软件管网模块中缺失或者不完善的功能,进行二次开发,增加若干参数化建模功能,使其能够高效地进行市政道路排水管网BIM设计。基于Civil 3D.NET API,采用C#编程语言,开发了排水管网模型的参数化创建、批量修改、快速查找以及数据转换等功能; 并在此基础上,探讨了Civil 3D管网模块二次开发的主要流程和若干技术细节。最后,通过实际工程案例,验证了二次开发功能对软件管网建模效率有显著提升。     

岩土工程位移预测神经网络建模的几个问题

本文从神经网络理论及实践方面研究了目前岩土工程位移预测神经网络模型存在的几个问题,最后提出了几个可供借鉴的其它预测模型.