To enhance the reliability and long-term stability of track structures, it is essential to intelligently upgrade maintenance methods. Track geometry irregularity (TGI) plays a critical role in line maintenance, as its acquisition and control efficiency directly impact maintenance effectiveness. The Chord-reference system (CR-system) is widely used for measuring TGI data, but these measurements often exhibit amplification or reduction at different wavelengths, making them unsuitable for precise track fine-tuning maintenance. In addition, traditional maintenance scheme design algorithm suffers from low solution efficiency when faced with large-scale decision variables. Therefore, we propose a two-stage physical-informed neural network (TS-PINN) approach for high-speed railway TGI Maintenance. In the first stage, we systematically introduce a PINN for TGI measurement (PINN-M) based on the classic CR-system principle, which can effectively rectify the measured TGI data into the real TGI data within a specific wavelength range. In the second stage, we propose a PINN for track fine-tuning (PINN-F) maintenance scheme design, which rectifies the real TGI data into maintenance scheme that meets specific track parameter constraints. By incorporating early stopping (ES) mechanism and shared network, we realize the automated design of maintenance schemes with specified Track Quality Index (TQI) targets using rapid measured TGI data. Case results show that the proposed approach has good robustness, can significantly reduce maintenance costs, and improve the efficiency of TGI maintenance.

Rail corrugation is a type of track geometry irregularity that induces sharp noise and reduces the service life of track components. The traditional manual inspection method of corrugation detection requires high labor costs. In general, the rail corrugation status of subway lines can be divided into three types according to wavelength: short wave, medium wave and healthy. Corrugation with different degrees of deterioration has different values of wave depth. To achieve more efficient and intelligent inspection, this study proposes a multitask learning method to detect metro rail corrugation by using in-vehicle responses and noise data. To this end, we develop a portable vehicle-mounted device to collect car body acceleration and vehicle interior noise. Second, we propose a data fusion method based on a 1/3 octave general vibration level of acceleration and noise data. Third, we develop a multitask learning model based on convolution and attention techniques that have two task towers: corrugation wavelength classification and wave depth regression. Finally, we apply the real-world data to the proposed framework. The results show that compared with single-task learning, the proposed multitask learning has a better performance in corrugation detection tasks. The$F_{1}$score of wavelength classification increased from 0.762 to 0.971, an increase of 27%; the Mean Absolute Percentage Error of wave depth regression decreased from 12% to 4.96%, a decrease of 59%. In addition, the training time consumption can be reduced by up to 66%.

Railway projects frequently pass through ecologically fragile regions and result in various ecological damages. The railway alignment determining the layout of structures plays an important role in ecological protection. This paper presents a railway alignment optimization model based on multiobjective bi-level programming (MBRAO). The upper level of MBRAO is a horizontal alignment optimization for the minimization of investment and ecological impacts from tunnel drainage and train noise. A multiobjective evolutionary algorithm based on decomposition (MOEA/D) solves the horizontal alignment optimization and naturally maintains population diversity. The lower level of MBRAO is a vertical alignment optimization for investment minimization. A self-adaptive differential evolution (DE) algorithm adjusting essential parameters based on optimization status solves the vertical alignment optimization efficiently. MBRAO is applied in multistage at both levels to find the suitable numbers of horizontal and vertical points of intersection. This paper introduces three kinds of vertical feature data generated corresponding to horizontal feature data to define different site modification costs on the bridge, subgrade, and tunnel structures. A real-world case study at Wolong Reserve is studied to verify the effectiveness of MBRAO based on a customized geographic information system (GIS).

In people’s daily lives, travel takes up an important part, and many trips are generated everyday, such as going to school or shopping. With the widely adoption of GPS-integrated devices, a large amount of trips can be recorded with GPS trajectories. These trajectories are represented by sequences of geo-coordinates and can help us answer simple questions such as “where did you go”. However, there is another important question awaiting to be answered, that is “what did/will you do”, i.e., the trip purpose inference. In practice, people’s trip purposes are very important in understanding travel behaviors and estimating travel demands. Obviously, it is very challenging to infer trip purposes solely based on the trajectories, because the GPS devices are not accurate enough to pinpoint the venues visited. In this paper, we infer individual’s trip purposes by combining the knowledge from heterogeneous data sources including trajectories, POIs and social media data. The proposed Dynamic Bayesian Network model (DBN) captures three important factors: the sequential properties of trip activities, the functionality and POI popularity of trip end areas. In addition, we propose an efficient method with local candidate pools to identify POIs from geo-tagged social media messages, and learn the POI popularities from nearby social media data. Moreover, trip data is usually imbalanced across different activities. This data imbalance problem can cause serious challenges because theDBNmodel could be biased by those “popular” class labels. Considering this challenge, we propose an ensemble DBN method with sampling technique (eDBN) which results in more accurate inference. Furthermore, real-world trip data are continuously collected on a daily basis. The batch model would result in unnecessary computation because historical data need to be revisited. We handle this problem by proposing an incremental DBN method (iDBN) which is both effective and efficient. Extensive experiments are conducted on real-world data sets with trajectories of 8,361 residents and the 6.9 million geo-tagged tweets in the Bay area. Experimental results demonstrate the advantages of the proposed method on correctly inferring the trip purposes.

This paper proposes a multi-source data fusion algorithm for rail surface defect detection in both camera-based rail inspection images and ultrasound B-scan images. First, we design a rail surface segmentation algorithm based on image bilateral filtering, Sobel edge detection, and rail surface edge detection to extract the rail surface area. Second, we build a camera and ultrasound data fusion (CUFuse) model for rail surface defect detection, including two main networks: multi-source data feature extraction and multi-scale feature fusion networks. The multi-source data feature extraction network consists of two BoTNet 50 networks as feature extraction networks to extract five stages of features in camera-based images and ultrasound B-scan images. The multi-scale feature fusion network consists of five feature fusion modules to fuse the feature information output by the multi-source data feature extraction network. Finally, we use the CUFuse model to detect the rail surface defect dataset, and output five rail surface state types, including Light, Moderate, Severe, Normal, and Joint. The results show that the accuracy of the CUFuse model is 96.97%, which can accomplish the task of rail surface defect detection on railway sites.

This paper explicitly addresses the multi-modal traffic signal control problem in the shared space street (SSS), where there are multiple travel modes (e.g. passenger cars, buses, and light rails) competing for their spaces in the same lane. SSS widely exists in central business districts where the road space is limited and the multi-modal travel demand is high. An optimization framework with a multi-modal cell transmission model (M-CTM) is developed to model the multi-modal traffic in the network. Also, this study models the passenger’s choice of choosing among different travel modes based on travel costs. Regarding multi-modal signal coordination, a cycle-based traffic signal plan selection model is developed to choose the best offline optimized signal plan to minimize the total travel cost of all three modes. Therefore, the computation burden is significantly reduced in the optimization model. Moreover, a particle swarm optimization (PSO) method is implemented to solve the proposed optimization model. A case study in downtown Buffalo validates the proposed model with microscopic traffic simulation VISSIM.

Recent advances in connected vehicle technologies enable vehicles and signal controllers to cooperate and improve the traffic management at intersections. This paper explores the opportunity for cooperative and integrated vehicle and intersection control for energy efficiency (CIVIC-E2) to contribute to a more sustainable transportation system. We propose a two-level approach that jointly optimizes the traffic signal timing and vehicles' approach speed, with the objective being to minimize total energy consumption for all vehicles passing through an isolated intersection. More specifically, at the intersection level, a dynamic programming algorithm is designed to find the optimal signal timing by explicitly considering the arrival time and energy profile of each vehicle. At the vehicle level, a model predictive control strategy is adopted to ensure that vehicles pass through the intersection in a timely fashion. Our simulation study has shown that the proposed CIVIC-E2system can significantly improve intersection performance under various traffic conditions. Compared with conventional fixed-time and actuated signal control strategies, the proposed algorithm can reduce energy consumption and queue length by up to 31% and 95%, respectively.

In our daily lives, travel takes up an important part, and many trips are generated everyday, such as going to school or shopping. With the widely adoption of GPS-integrated devices, a large amount of trips can be recorded with GPS trajectories. These trajectories are represented by sequences of geo-coordinates and can help us answer simple questions such as “where did you go”. However, there is another important question awaiting to be answered, that is “what did/will you do”, i.e., the trip purpose inference. In practice, people's trip purposes are very important in understanding travel behaviors and estimating travel demands. Obviously, it is very challenging to infer trip purposes solely based on the trajectories, because the GPS devices are not accurate enough to pinpoint the venues visited. In this paper, we infer individual's trip purposes by combining the knowledge from heterogeneous data sources including trajectories, POIs and social media data. The proposed dynamic Bayesian network model captures three important factors: the sequential properties of trip activities, the functionality and POI popularity of trip end areas. Extensive experiments are conducted on real-world data sets with trajectories of 8,361 residents and the 6.9 million geo-tagged tweets in the Bay area. Experimental results demonstrate the advantages of the proposed method on correctly inferring the trip purposes.

Detecting the travel modes such as walking and driving a car is an important task for user behavior understanding as well as transportation planning and management. Existing solutions for this task mainly train a generic classifier for all users although the walking or driving behaviors may differ greatly from one user to another. In this paper, we propose to build a personalized travel mode detection method. In particular, the proposed method can be divided into two stages. First, for a given target user, it applies user similarity computation to borrow data from a set of pre-collected data for transfer learning. Second, it estimates the data distribution in feature space, and uses it to reweight the borrowed data so as to minimize the model loss with respect to the target user. Experimental evaluations on real travel data show that the proposed method outperforms the generic method and the transfer learning method with kernel mean matching in terms of prediction accuracy.

Subway passenger flow prediction is strategically important in metro transit system management. The prediction under event occurrences turns into a very challenging task. In this paper, we adopt a new kind of data source-social media-to tackle this challenge. We develop a systematic approach to examine social media activities and sense event occurrences. Our initial analysis demonstrates that there exists a moderate positive correlation between passenger flow and the rates of social media posts. This finding motivates us to develop a novel approach for improved flow forecast. We first develop a hashtag-based event detection algorithm. Furthermore, we propose a parametric and convex optimization-based approach, called optimization and prediction with hybrid loss function (OPL), to fuse the linear regression and the results of seasonal autoregressive integrated moving average (SARIMA) model jointly. The OPL hybrid model takes advantage of the unique strengths of linear correlation in social media features and SARIMA model in time series prediction. Experiments on events nearby a subway station show that OPL reports the best forecasting performance compared with other state-of-the-art techniques. In addition, an ensemble model is developed to leverage the weighted results from OPL and support vector machine regression together. As a result, the prediction accuracy and the robustness further increase.

The increasingly connected world has catalyzed the fusion of networks from different domains, which facilitates the emergence of a new network model-multi-layered networks. Examples of such kind of network systems include critical infrastructure networks, biological systems, organization-level collaborations, cross-platform e-commerce, and so forth. One crucial structure that distances multi-layered network from other network models is its cross-layer dependency, which describes the associations between the nodes from different layers. Needless to say, the cross-layer dependency in the network plays an essential role in many data mining applications like system robustness analysis and complex network control. However, it remains a daunting task to know the exact dependency relationships due to noise, limited accessibility, and so forth. In this article, we tackle the cross-layer dependency inference problem by modeling it as a collective collaborative filtering problem. Based on this idea, we propose an effective algorithm Fascinate that can reveal unobserved dependencies with linear complexity. Moreover, we derive Fascinate-ZERO, an online variant of Fascinate that can respond to a newly added node timely by checking its neighborhood dependencies. We perform extensive evaluations on real datasets to substantiate the superiority of our proposed approaches.

Multi-layered networks have recently emerged as a new network model, which naturally finds itself in many high-impact application domains, ranging from critical inter-dependent infrastructure networks, biological systems, organization-level collaborations, to cross-platform e-commerce, etc. Cross-layer dependency, which describes the dependencies or the associations between nodes across different layers/networks, often plays a central role in many data mining tasks on such multi-layered networks. Yet, it remains a daunting task to accurately know the cross-layer dependency a prior. In this paper, we address the problem of inferring the missing cross-layer dependencies on multi-layered networks. The key idea behind our method is to view it as a collective collaborative filtering problem. By formulating the problem into a regularized optimization model, we propose an effective algorithm to find the local optima with linear complexity. Furthermore, we derive an online algorithm to accommodate newly arrived nodes, whose complexity is just linear wrt the size of the neighborhood of the new node. We perform extensive empirical evaluations to demonstrate the effectiveness and the efficiency of the proposed methods.

Personal trips in modern urban society usually involve multiple travel modes. Recognizing a traveler's transportation mode is not only critical to personal context awareness in related applications but also essential to urban traffic operations, transportation planning, and facility design. While most current practice often leverages infrastructure-based fixed sensors or a Global Positioning System (GPS) for traffic mode recognition, the emergence of the smartphone provides an alternative promising way with its ever-growing computing, networking, and sensing power. In this paper, we propose a GPS-and-network-free method to detect a traveler's travel mode using mobile phone sensors. Our application is built on the latest Android platform with multimodality sensors. By developing a hierarchical classification method with an online learning model, we achieve almost 100% accuracy in a binary classification of wheeled/unwheeled travel modes and an average of 97.1% accuracy with all six travel modes (buses, subways, cars, bicycling, walking, and jogging). Our system (a) could adapt to each traveler's pattern by using the online learning model, and it performs significantly faster in computation than the offline model, and (b) works with a low sampling frequency for sensing so that it saves the smartphone battery.

Mining time series data has been a very active research area in the past decade, exactly because of its prevalence in many high-impact applications, ranging from environmental monitoring, intelligent transportation systems, computer network forensics, to smart buildings and many more. It has posed many fascinating research questions. Among others, three prominent challenges shared by a variety of real applications are (a) high-order; (b) contextual constraints and (c) temporal smoothness. The state-of-the-art mining algorithms are rich in addressing each of these challenges, but relatively short of comprehensiveness in attacking the coexistence of multiple or even all of these three challenges.

Traffic control agencies (TCAs), including police officers, firefighters, or other traffic law enforcement officers, can override automatic traffic signal control and manually control the traffic at an intersection. TCA-based traffic signal control is crucial to mitigate nonrecurrent traffic congestion caused by planned and unplanned events. Understanding and predicting TCA behaviors is significant to optimize event traffic management and operations. In this paper, we propose a pressure-based human behavior model to mimic TCA's decision-making behavior. The model calculates TCA's pressure based on two attributes: vehicle and pedestrian queue dynamics and the red time duration for each phase. When TCA's pressure on each phase meet certain criteria and the minimal green is satisfied, TCA will terminate the current phase and switch to another phase. In order to study TCA behavior systematically, we first build a manual signal control simulator based on a microscopic traffic simulation tool. Supported by the manual control simulator, a series of human subject experiments have been conducted with real-world TCAs. Experiment data are divided into training data and test data. The proposed behavior model is then calibrated by training data, and the model is validated by both offline segment-based phase and duration prediction and online VISSIM-based simulation. Further, we test the model with videotaped TCA behavior data at a real-world intersection. Both validation results support the effectiveness of proposed behavior model.

Nowadays, railway networks are instrumented with various wayside detectors. Such detectors, automatically identifying potential railcar component failures, are able to reduce rolling stock inspection and maintenance costs and improve railway safety. In this paper, we present a methodology to predict remaining useful life (RUL) of both wheels and trucks (bogies), by fusing data from three types of detectors, including wheel impact load detector, machine vision systems, and optical geometry detectors. A variety of new features is created from feature normalization, signal characteristics, and historical summary statistics. Missing data are handled by missForest, a Random Forests-based nonparametric missing value imputation algorithm. Several data mining techniques are implemented and compared to predict the RUL of wheels and trucks in a U.S. Class I railroad railway network. Numerical tests show that the proposed methodology can accurately predict RUL of the components of a railcar, particularly in a middle-term range.