In order to explore the effect of curb parking on dynamic traffic and formulate some reasonable and effective traffic management measures, the effects on capacity and traffic safety are studied. Four road segments with curb parking were selected as the investigation location. Several traffic characteristics and parameters were then investigated and counted, including traffic flow volume, speed, headway and traffic conflict. Based on a reduction of lane effective width and the Gap Acceptance Theory, two effect models describing curb parking and road capacity were constructed. Considering the factors involved in motor vehicle conflicts (such as non-motor vehicle lane distribution and stopping sight distance), the effects of curb parking on both motor vehicle and non-motor vehicle traffic safety was analyzed, as well as pedestrian crossing safety. This case study analyzes both the capacity and traffic safety of all four investigation segments. Results show that the lane effective width of road segment with curb parking significantly influences the road capacity and impacts the traffic flow volumes of the parking lane and its adjacent lane. Curb parking significantly effects traffic operation safety; however, it can be improved by implementing traffic safety management measures.

This paper proposes an approach combining historical data and real-time situation information to forecast the bus arrival time. The approach includes two phases. Firstly, Radial Basis Function Neural Networks (RBFNN) model is used to learn and approximate the nonlinear relationship in historical data in the first phase. Then, in the second phase, an online oriented method is introduced to adjust to the actual situation, which means to use the practical information to modify the predicted result of RBFNN in the first phase. Afterwards, the system designing outline is given to summarize the structure and components of the system. We did an experimental study on bus route No.21 in Dalian by deploying this system to demonstrate the validity and effectiveness of this approach. In addition, Multiple Linear Regression model, BP Neural Networks and RBFNN without online adjustment are used in contrast. Results show that the approach with RBFNN and online adjustment has a better predicting performance.

This research aims at establishing an integrated urban public transport system with a subway route supplemented by conventional bus lines, in order to enable residents’ “door-to-door” travel. This paper first analyzed the attraction area of the subway, and then used the GIS tools to calculate and analyze residents’ accessibility to adjacent bus stops. Moreover, it created a preliminary layout of bus stops for residential areas with extremely low accessibility using an improved potential model. From the perspective of minimizing residents’ travel costs and bus stop infrastructure deployment costs, a bus stop site selection optimization model was developed. According to the characteristics of the model, the non-dominated sorting genetic algorithm II (NSGA-II) was employed to solve the optimal bus stop locations. In addition, the entropy weight technique for order of preference by similarity to ideal solution (TOPSIS) evaluation model was used to evaluate and sort candidate schemes, accordingly, and thus the optimal site selection scheme was identified. Finally, a before-after comparative analysis on residents’ travel accessibility was conducted. Results show that the proposed method can effectively improve residents’ accessibility to bus stops, which facilitates residents to transfer from conventional bus to subway. Furthermore, it provides a basis for the follow-up optimization of the connection between subway and conventional bus lines.

To improve bus passengers’ degree of comfort, it is necessary to determine the real-time crowd coefficient in the bus. With this concern, this paper employed the RBF Neural Networks approach to predict the number of passengers in the bus based on historical data. To minimize the impact of the randomness of passenger flow on the determination of bus crowd coefficient, a cloud model-based bus crowd coefficient identification method was proposed. This paper first selected the performance measurements for determining bus crowd coefficient and calculated the digital characteristics of the cloud model based on the boundary values of the selected performance measures under six Levels-of-Service (LOSs). Then the subclouds obtained under the six LOSs were synthesized into a standard cloud. According to the predicted number of passengers in the bus, the passenger density and loading frequency were calculated, which were imported into the cloud generator to set up the bus crowd coefficient identification model. By calculating the crowd degrees of identification cloud and template cloud at each site, this paper determined the crowed coefficient of each bus station. Finally, this paper took the bus line No. 10 in Dalian city as case study to verify the proposed model. It was found that the crowd coefficients of the selected route ranged from 60.265 to 109.825, and the corresponding LOSs ranged between C and F. The method of discriminating bus crowding coefficient can not only effectively determine the congestion coefficient, but also effectively avoid the fuzziness and randomness of the crowding coefficient judgment in the bus, which has strong theoretical and practical significance.

Remaining life prediction (RUL) is a critical link of maintenance decision-making, the accurate RUL prediction is an important means to monitor the operating status and achieve the safe operation of equipment. However, existing studies rarely considered the multi-stage characteristics of indicator fusion in the degradation process, and directly used the Wiener process to establish degradation model, which results in significant errors in RUL prediction results. Therefore, to solve above issues, a two-stage RUL prediction method of bearing based on the Wiener process model with data fusion and stage division is proposed in the paper. Firstly, the concept of multi-feature fusion is introduced to construct a comprehensive health indicator (CHI) that considers indicator performance. After that, a two-stage RUL prediction model based on the CHI is developed, and a method for detecting change points and dividing stages is proposed. Finally, the effectiveness and predictability of the proposed method and CHI are demonstrated based on the bearing test datasets.

This paper focuses on travel mode recognition based on Radial Basis Function (RBF) Neural Networks using the characters extracted from travel trace information collected by smartphone. First, we analyzed the characters of travel mode to find out what the key parameters are to divide the two kinds of travel mode by using the F-score method in order to make up the character vectors to recognize different travel modes. Eventually, a classifier of the RBF-based Neural Network can be established. This Neural Network is trained by travel mode samples extracted from travel trace data in Dalian. For comparison, BP Neural Networks are used. The result shows that the recognition accuracy rate of RBF Neural Network is better than BP Neural Network, and suggests that the RBF Neural Network has a better recognition performance.