Search results

Beijing rail transit can actively control the density of rail transit passenger flow, ensure travel facilities and provide a safe and comfortable riding atmosphere for rail transit passengers during the epidemic. The purpose of this paper is to efficiently monitor the flow of rail passengers, the first method is to regulate the flow of passengers by means of a coordinated connection between the stations of the railway line; the second method is to objectively distribute the inbound traffic quotas between stations to achieve the aim of accurate and reasonable control according to the actual number of people entering the station.

This paper analyzes the rules of rail transit passenger flow and updates the passenger flow prediction model in time according to the characteristics of passenger flow during the epidemic to solve the above-mentioned problems. Big data system analysis restores and refines the time and space distribution of the finely expected passenger flow and the train service plan of each route. Get information on the passenger travel chain from arriving, boarding, transferring, getting off and leaving, as well as the full load rate of each train.

A series of digital flow control models, based on the time and space composition of passengers on trains with congested sections, has been designed and developed to scientifically calculate the number of passengers entering the station and provide an operational basis for operating companies to accurately control flow.

This study can analyze the section where the highest full load occurs, the composition of passengers in this section and when and where passengers board the train, based on the measured train full load rate data. Then, this paper combines the full load rate control index to perform reverse deduction to calculate the inbound volume time-sharing indicators of each station and redistribute the time-sharing indicators for each station according to the actual situation of the inbound volume of each line during the epidemic. Finally, form the specified full load rate index digital time-sharing passenger flow control scheme.

To predict the passenger volume reasonably and accurately, this paper fills the gap in the research of quarterly data forecast of railway passenger volume. The research results can also provide references for railway departments to plan railway operation lines reasonably and efficiently.

This paper intends to establish a seasonal cycle first order univariate grey model (GM(1,1) model) combing with a seasonal index. GM (1,1) is termed as the trend equation to fit the railway passenger volume in China from 2014 to 2018. The railway passenger volume in 2019 is used as the experimental data to verify the forecasting effect of the proposed model. The forecasting results of the seasonal cycle GM (1,1) model are compared with the traditional GM (1,1) model, seasonal grey model (SGM(1,1)), Seasonal Autoregressive Integrated Moving Average (SARIMA) model, moving average method and exponential smoothing method. Finally, the authors forecast the railway passenger volume from 2020 to 2022.

The quarterly data of national railway passenger volume have a clear tendency of cyclical fluctuations and show an annual growth trend. According to the comparison of the modeling results, the authors know that the seasonal cycle GM (1,1) model has the best prediction effect with the mean absolute percentage error of 1.32%. It is much better than the other models, reflecting the feasibility of the proposed model.

As the previous grey prediction model could not solve the series prediction problem with seasonal fluctuation, and there are few research studies on quarterly railway passenger volume forecasting, GM (1,1) model is taken as the trend equation and combined with the seasonal index to construct a combination forecasting model for accurate forecasting results in this study. Besides, considering the impact of the epidemic on passenger volume, the authors introduce a disturbance factor to deal with the forecasting results in 2020, making the modeling results more scientific, practical and referential.

This paper aims to propose a medium-term forecast model for the daily passenger volume of High Speed Railway (HSR) systems to predict the daily the Origin-Destination (OD) daily volume for multiple consecutive days (e.g. 120 days).

By analyzing the characteristics of the historical data on daily passenger volume of HSR systems, the date and holiday labels were designed with determined value ranges. In accordance to the autoregressive characteristics of the daily passenger volume of HSR, the Double Layer Parallel Wavelet Neural Network (DLP-WNN) model suitable for the medium-term (about 120 d) forecast of the daily passenger volume of HSR was established. The DLP-WNN model obtains the daily forecast result by weighed summation of the daily output values of the two subnets. Subnet 1 reflects the overall trend of daily passenger volumes in the recent period, and subnet 2 the daily fluctuation of the daily passenger volume to ensure the accuracy of medium-term forecast.

According to the example application, in which the DLP-WNN model was used for the medium-term forecast of the daily passenger volumes for 120 days for typical O-D pairs at 4 different distances, the average absolute percentage error is 7%-12%, obviously lower than the results measured by the Back Propagation (BP) neural network, the ELM (extreme learning machine), the ELMAN neural network, the GRNN (generalized regression neural network) and the VMD-GA-BP. The DLP-WNN model was verified to be suitable for the medium-term forecast of the daily passenger volume of HSR.

This study proposed a Double Layer Parallel structure forecast model for medium-term daily passenger volume (about 120 days) of HSR systems by using the date and holiday labels and Wavelet Neural Network. The predict results are important input data for supporting the line planning, scheduling and other decisions in operation and management in HSR systems.

Efficient traffic incident management is needed to alleviate the negative impact of traffic incidents. Accurate and reliable estimation of traffic incident duration is of great importance for traffic incident management. Previous studies have proposed models for traffic incident duration prediction; however, most of these studies focus on the total duration and could not update prediction results in real-time. From a traveler’s perspective, the relevant factor is the residual duration of the impact of the traffic incident. Besides, few (if any) studies have used dynamic traffic flow parameters in the prediction models. This paper aims to propose a framework to fill these gaps.

This paper proposes a framework based on the multi-layer perception (MLP) and long short-term memory (LSTM) model. The proposed methodology integrates traffic incident-related factors and real-time traffic flow parameters to predict the residual traffic incident duration. To validate the effectiveness of the framework, traffic incident data and traffic flow data from Shanghai Zhonghuan Expressway are used for modeling training and testing.

Results show that the model with 30-min time window and taking both traffic volume and speed as inputs performed best. The area under the curve values exceed 0.85 and the prediction accuracies exceed 0.75. These indicators demonstrated that the model is appropriate for this study context. The model provides new insights into traffic incident duration prediction.

The incident samples applied by this study might not be enough and the variables are not abundant. The number of injuries and casualties, more detailed description of the incident location and other variables are expected to be used to characterize the traffic incident comprehensively. The framework needs to be further validated through a sufficiently large number of variables and locations.

The framework can help reduce the impacts of incidents on the safety of efficiency of road traffic once implemented in intelligent transport system and traffic management systems in future practical applications.

This study uses two artificial neural network methods, MLP and LSTM, to establish a framework aiming at providing accurate and time-efficient information on traffic incident duration in the future for transportation operators and travelers. This study will contribute to the deployment of emergency management and urban traffic navigation planning.

The purpose of this paper is to develop a dynamic control method to improve bus schedule adherence under connected bus system.

The authors developed a dynamic programming model that optimally schedules the bus operating speed at road sections and multiple signal timing plans at intersections to improve bus schedule adherence. First, the bus route was partitioned into three types of sections: stop, road and intersection. Then, transit agencies can control buses in real time based on all collected information; i.e. control bus operating speed on road sections and adjust the signal timing plans through signal controllers to improve the schedule adherence in connected bus environment. Finally, bus punctuality at the downstream stop and the saturation degree deviations of intersections were selected as the evaluation criteria in optimizing signal control plans and bus speeds jointly.

An illustrative case study by using a bus rapid transit line in Jinan city was performed to verify the proposed model. It revealed that based on the proposed strategy, the objective value could be reduced by 73.7%, which indicated that the punctuality was highly improved but not to incur excessive congestion for other vehicular traffic.

In this paper, the authors applied speed guidance and the adjustment of the signal control plans for multiple cycles in advance to improve the scheduled stability; furthermore, the proposed control strategy can reduce the effect on private traffics to the utmost extend.

Traditional multivariable grey prediction models define the background-value coefficients of the dependent and independent variables uniformly, ignoring the differences between their physical properties, which in turn affects the stability and reliability of the model performance.

A novel multivariable grey prediction model is constructed with different background-value coefficients of the dependent and independent variables, and a one-to-one correspondence between the variables and the background-value coefficients to improve the smoothing effect of the background-value coefficients on the sequences. Furthermore, the fractional order accumulating operator is introduced to the new model weaken the randomness of the raw sequence. The particle swarm optimization (PSO) algorithm is used to optimize the background-value coefficients and the order of the model to improve model performance.

The new model structure has good variability and compatibility, which can achieve compatibility with current mainstream grey prediction models. The performance of the new model is compared and analyzed with three typical cases, and the results show that the new model outperforms the other two similar grey prediction models.

This study has positive implications for enriching the method system of multivariable grey prediction model.

Perception has been identified as the main cause underlying most autonomous vehicle related accidents. As the key technology in perception, deep learning (DL) based computer vision models are generally considered to be black boxes due to poor interpretability. These have exacerbated user distrust and further forestalled their widespread deployment in practical usage. This paper aims to develop explainable DL models for autonomous driving by jointly predicting potential driving actions with corresponding explanations. The explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify any model deficiencies or limitations during the system development phase.

This paper proposes an explainable end-to-end autonomous driving system based on “Transformer,” a state-of-the-art self-attention (SA) based model. The model maps visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations, and aims to achieve soft attention over the image’s global features.

The results demonstrate the efficacy of the proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with much lower computational cost on a public data set (BDD-OIA). From the ablation studies, the proposed SA module also outperforms other attention mechanisms in feature fusion and can generate meaningful representations for downstream prediction.

In the contexts of situational awareness and driver assistance, the proposed model can perform as a driving alarm system for both human-driven vehicles and autonomous vehicles because it is capable of quickly understanding/characterizing the environment and identifying any infeasible driving actions. In addition, the extra explanation head of the proposed model provides an extra channel for sanity checks to guarantee that the model learns the ideal causal relationships. This provision is critical in the development of autonomous systems.

The purpose of this paper is to solve the problems existing in topic popularity prediction in online social networks and advance a fine-grained and long-term prediction model for lack of sufficient data.

Based on GM(1,1) and neural networks, a co-training model for topic tendency prediction is proposed in this paper. The interpolation based on GM(1,1) is employed to generate fine-grained prediction values of topic popularity time series and two neural network models are considered to achieve convergence by transmitting training parameters via their loss functions.

The experiment results indicate that the integrated model can effectively predict dense sequence with higher performance than other algorithms, such as NN and RBF_LSSVM. Furthermore, the Markov chain state transition probability matrix model is used to improve the prediction results.

Fine-grained and long-term topic popularity prediction, further improvement could be made by predicting any interpolation in the time interval of popularity data points.

The paper succeeds in constructing a co-training model with GM(1,1) and neural networks. Markov chain state transition probability matrix is deployed for further improvement of popularity tendency prediction.

This study aims to provide a comprehensive review of hotel demand forecasting to identify its key fundamentals and evolution and future research directions and trends to advance the field.

Articles on hotel demand modeling and forecasting were identified and rigorously selected using transparent inclusion and exclusion criteria. A final sample of 85 empirical studies was obtained for comprehensive analysis through content analysis.

Synthesis of the literature highlights that hotel forecasting based on historical demand data dominates the research, and reservation/cancellation data and combined data gradually attracted research attention in recent years. In terms of model evolution, time series and AI-based models are the most popular models for hotel demand forecasting. Review results show that numerous studies focused on hybrid models and AI-based models.

To the best of the authors’ knowledge, this study is the first systematic review of the literature on hotel demand forecasting from the perspective of data source and methodological development and indicates future research directions.

本研究旨在对酒店需求预测进行全面回顾, 以确定其关键基础和演变以及未来的研究方向和趋势, 以推动该领域的发展。

使用严格和透明的纳入和排除的标准对酒店需求建模和预测的文章进行识别和选择。通过内容分析, 最终有 85个实证研究作为综合分析的样本。

综合文献发现, 基于历史需求数据的酒店预测在研究中占主导地位, 近年来预订/取消数据和组合数据逐渐引起研究关注。在模型演化方面, 时间序列和基于人工智能的模型是最受欢迎的酒店需求预测模型。审查结果表明, 许多研究都集中在混合模型和基于 AI 的模型上。

本研究是第一次从数据源和方法发展的角度对酒店需求预测文献进行系统回顾, 并指出未来的研究方向。

Este estudio tiene como objetivo proporcionar una revisión amplia de la previsión sobre la demanda hotelera a la hora de identificar sus fundamentos clave, la evolución y las direcciones y tendencias de investigación futuras para avanzar en el campo de estudio.

Se identificaron y seleccionaron de forma rigurosa artículos sobre modelado y previsión de la demanda hotelera utilizando criterios transparentes de inclusión y exclusión. Se obtuvo una muestra final de 85 estudios empíricos para su análisis integral a través del análisis de contenido.

La síntesis de la literatura destaca que la previsión hotelera basada en datos históricos de demanda ha dominado la investigación, y los datos de reserva/cancelación, así como los datos combinados han atraído gradualmente en los últimos años la atención de la investigación. En términos de evolución del modelo, las series temporales y los modelos basados en IA son los modelos más populares para la previsión de la demanda hotelera. Los resultados de la revisión muestran que numerosos estudios se han centrado en modelos híbridos y basados en IA.

Este estudio es la primera revisión sistemática de la literatura sobre la previsión de la demanda hotelera desde la perspectiva de la fuente de datos y el desarrollo metodológico e indica futuras líneas de investigación.

This paper aims to overcome the problem that the single structure of the driving term of the grey prediction model is not adapted to the complexity and diversity of the actual modeling objects, which leads to poor modeling results.

Firstly, the nonlinear law between the raw data and time point is fully mined by expanding the nonlinear term and the range of order. Secondly, through the synchronous optimization of model structure and parameter, the dynamic adjustment of the model with the change of the modeled object is realized. Finally, the objective optimization of nonlinear driving term and cumulative order of the model is realized by particle swarm optimization PSO algorithm.

The model can achieve strong compatibility with multiple existing models through parameter transformation. The synchronous optimization of model structure and parameter has a significant improvement over the single optimization method. The new model has a wide range of applications and strong modeling capabilities.

A novel grey prediction model with structure variability and optimizing parameter synchronization is proposed.

The highlights of the paper are as follows:

1. A new grey prediction model with a unified nonlinear structure is proposed.

2. The new model can be fully compatible with multiple traditional grey models.

3. The new model solves the defect of poor adaptability of the traditional grey models.

4. The parameters of the new model are optimized by PSO algorithm.

5. Cases verify that the new model outperforms other models significantly.

A new grey prediction model with a unified nonlinear structure is proposed.

The new model can be fully compatible with multiple traditional grey models.

The new model solves the defect of poor adaptability of the traditional grey models.

The parameters of the new model are optimized by PSO algorithm.

Cases verify that the new model outperforms other models significantly.