In order to meet the real-time public travel demands, the bus operators need to adjust the timetables in time. Therefore, it is necessary to predict the variations of the short-term passenger flow. Under the help of the advanced public transportation systems, a large amount of real-time data about passenger flow is collected from the automatic passenger counters, automatic fare collection systems, etc. Using these data, different kinds of methods are proposed to predict future variations of the short-term bus passenger flow. Based on the properties and background knowledge, these methods are classified into three categories: linear, nonlinear and combined methods. Their performances are evaluated in detail in the major aspects of the prediction accuracy, the complexity of training data structure and modeling process. For comparison, some long-term prediction methods are also analyzed simply. At last, it points that, with the help of automatic technology, a large amount of data about passenger flow will be collected, and using the big data technology to speed up the data preprocessing and modeling process may be one of the directions worthy of study in the future.

For the increasing travel demands and public transport problems, dynamically adjusting timetable or bus scheduling is necessary based on accurate real-time passenger flow forecasting. In order to get more accurate passenger flow in future, this paper proposes a novel hierarchical hybrid model based on time series model, deep belief networks (DBNs), and improved incremental extreme learning machine (Im-ELM) to forecast short-term passenger flow. The proposed model is named HTSDBNE with two modelling steps. First, referring the idea of parallelization, the hybrid model, constructed by time series model, DBN, and Im-ELM, is used to forecast short-term passenger flow in different time scales hierarchically and parallel. Second, Im-ELM is utilized to analyse the relationship of forecasting results from the first step, and the weighted outputs of Im-ELM are as the final forecasting results. Comparing with single forecasting models and typical hybrid forecasting models, the testing results indicate that HTSDBNE has better performances. The mean absolute percent error of prediction results is around 10% and fully meets the application requirements of bus operation enterprise.

As there are more and more available Web services with the same or similar functionalities but different Quality of Service (QoS), the challenge of QoS-aware service composition is to efficiently select appropriate component services to achieve maximum utility and meet the global QoS constraints with low time cost. In this paper, we propose a dynamic service selection approach based on adaptive global QoS constraints decomposition. Fuzzy logic technology and Cultural Genetic Algorithm are used to adaptively decompose global QoS constraints into near-optimal local constraints. According to the near-optimal local constraints, the optimal service is selected for each service class during the running time efficiently. Experimental results show that the proposed approach not only achieves the near-optimal solution, but also significantly reduces the computation time, and has good adaptability and scalability.

For resolving or alleviating the transportation problems, it is necessary to efficiently manage the public transportation and provide public transport services with high quality and advocate green travel, which rely on accurate traffic data. In order to obtain more accurate bus speed in the future, this paper proposed a novel dynamic hierarchical spatial-temporal network model based on Grey Relation Analysis (EGRA), the convolutional neural network (CNN), and the gated recurrent unit (GRU). The proposed model is named the DHSTN; it exploited EGRA to analyze and choose the suitable candidate line sections with high impacts on the target section and, then, construct a multilayer structure based on the CNN, GRU, and attention mechanism to analyze and capture the spatial and temporal dependency, and finally, the extreme learning machine (ELM) is exploited for the fusion of the long-term and short-term dependency to predict the bus speed variation in the next time interval. Comparative experiments indicate that the DHSTN has better performances, the mean absolute error is around 2.6, and it meets the real requirements.

An extreme learning machine (ELM) is an innovative algorithm for the single hidden layer feed-forward neural networks and, essentially, only exists to find the optimal output weight so as to minimize output error based on the least squares regression from the hidden layer to the output layer. With a focus on the output weight, we introduce the orthogonal constraint into the output weight matrix, and propose a novel orthogonal extreme learning machine (NOELM) based on the idea of optimization column by column whose main characteristic is that the optimization of complex output weight matrix is decomposed into optimizing the single column vector of the matrix. The complex orthogonal procrustes problem is transformed into simple least squares regression with an orthogonal constraint, which can preserve more information from ELM feature space to output subspace, these make NOELM more regression analysis and discrimination ability. Experiments show that NOELM has better performance in training time, testing time and accuracy than ELM and OELM.

In recent years, the volume of spatial data has rapidly grown, so it is crucial to process them in an efficient manner. The level of parallel processing in big data platforms such as Hadoop and Spark is determined by partitioning the dataset. A common approach is to split the data into chunks based on the number of bytes. While this approach works well for text-based batch processing, in many cases, it is preferable to take advantage of the structured information contained in the dataset (e.g., spatial coordinates) to plan data partitioning. In view of the huge amount of data and the impossibility of quickly establishing partitions, this paper designs a method for approximate partition boundary solving, which divides the data space into multiple non-overlapping symmetric bins and samples each bin, making the probability density of the sampling set bounded by the deviation of the probability density of the original data. The sampling set is read into the memory at one time for calculation, and the established partition boundary satisfies the partition threshold-setting. Only a few boundary adjustment operations are required, which greatly shortens the partition time. In this paper, the method proposed in the paper is tested on the synthetic dataset, the bus trajectory dataset, and six common spatial partitioning methods (Grid, Z-curve, H-curve, STR, Kd-tree, and R*-Grove) are selected for comparison. The results show that the symmetric bin sampling method can describe the spatial data distribution well and can be directly used for partition boundary division.