Search results

Traffic flow prediction has always been a top priority of intelligent transportation systems. There are many mature methods for short-term traffic flow prediction. However, the existing methods are often insufficient in capturing long-term spatial-temporal dependencies. To predict long-term dependencies more accurately, in this paper, a new and more effective traffic flow prediction model is proposed.

This paper proposes a new and more effective traffic flow prediction model, named channel attention-based spatial-temporal graph neural networks. A graph convolutional network is used to extract local spatial-temporal correlations, a channel attention mechanism is used to enhance the influence of nearby spatial-temporal dependencies on decision-making and a transformer mechanism is used to capture long-term dependencies.

The proposed model is applied to two common highway datasets: METR-LA collected in Los Angeles and PEMS-BAY collected in the California Bay Area. This model outperforms the other five in terms of performance on three performance metrics a popular model.

(1) Based on the spatial-temporal synchronization graph convolution module, a spatial-temporal channel attention module is designed to increase the influence of proximity dependence on decision-making by enhancing or suppressing different channels. (2) To better capture long-term dependencies, the transformer module is introduced.

The authors provide a way to represent spatial and temporal equilibria in terms of error correction models in a panel setting. This requires potentially two different processes for spatial or network dynamics, both of which can be expressed in terms of spatial weights matrices. The first captures strong cross-sectional dependence, so that a spatial difference, suitably defined, is weakly cross-section dependent (granular) but can be non-stationary. The second is a conventional weights matrix that captures short-run spatio-temporal dynamics as stationary and granular processes. In large samples, cross-section averages serve the first purpose and the authors propose the mean group, common correlated effects estimator together with multiple testing of cross-correlations to provide the short-run spatial weights. The authors apply this model to the 324 local authorities of England, and show that our approach is useful for modeling weak and strong cross-section dependence, together with partial adjustments to two long-run equilibrium relationships and short-run spatio-temporal dynamics. This exercise provides new insights on the (spatial) long-run relationship between house prices and income in the UK.

This paper examines the price setting behaviour over time and space in the Athens residential market. In periods of house price inflation asking prices are often based upon the last observed highest selling price achieved for a similar property in the same micro-location. However, in a falling market, prices may be rigid downwards and less sensitive to the most recent transaction prices, weakening spatial effects. Furthermore, the paper considers whether future price expectations affect price setting behaviour.

The paper employs a dataset of approximately 24,500 property values from 2007 until 2014 in Athens incorporating characteristics and locational variables. The authors begin by estimating a baseline hedonic price model using property characteristics, neighbourhood amenities and location effects. Following this, a spatio-temporal autoregressive (STAR) model is estimated. Running separate models, the authors account for spatial dependence from historic valuations, contemporaneous peer effects and expectations effects.

The initial STAR model shows significant spatial and temporal effects, the former remaining important in a falling market contrasting with previous literature findings. In the second STAR model, whilst past sales effects remain significant although smaller, contemporaneous and price expectations effects are also found to be significant, the latter capturing anchoring and slow adjustment heuristics in price setting behaviour.

As valuations used in the database are based upon comparable sales, then in the recessionary periods covered in the dataset, finding comparables may have become more difficult, and hence this, in turn, may have impacted on valuation accuracy.

In addition to past effects, contemporaneous transactions and expected future values need to be taken in consideration in analysing spatial interactions in housing markets. These factors will influence housing markets in different cities and countries.

The information content of property valuations should more carefully consider the relative importance of different components of asking prices.

This is the first paper to use transactions data over a period of falling house prices in Athens and to consider current and future values in addition to past values in a spatio-temporal context.

This study aims to examine the evolution of spatial–temporal patterns in China’s hotel industry from 1978 to 2018.

A database comprising over 140,000 hotels with more than 30 rooms was created. The exploratory spatial–temporal data analysis (ESTDA) method, based on space–time cube model, was used to explore and visualize the spatial–temporal pattern of hotels.

The Chinese hotel industry can be divided into two development stages, namely, a large hotel-dominant stage before 2000 and a small–medium-sized hotel-dominant stage after 2000. China’s prefecture-level cities were clustered into four tiers. The higher the tier, the earlier the city will initiate hotel development. The Chinese hotel industry has four continuous hotspots (the Yangtze River Delta, Pearl River Delta, Bohai Rim and Sichuan and Chongqing) and some temporary hotspots.

This study lacks quantitative investigation, which could show the underlying mechanism of the evolution of the Chinese hotel industry.

This study is the first to investigate China’s hotel evolution over 40 years by applying big data and the ESTDA method. The systematic and evolutionary exploration will enable hotel researchers to understand the spatial–temporal nature of hotel distribution better. Introducing the ESTDA method into tourism and hotel research also provides an additional tool to researchers. Hotel investors and operators, city and tourism planners and market regulators can learn from the evolution of location patterns to make better where and when decisions.

Service encounters are becoming increasingly virtual through the infusion of computer-mediated technologies. Virtual services separate consumers and service providers both spatially and temporally. With the advent of virtual services is the need to theoretically explain how service separability is psychologically perceived by consumers across the spectrum of computer-mediated technologies. Drawing on construal-level theory, the purpose of this paper is to conceptualize a theoretical framework depicting consumer’s construal of spatial and temporal separation across a continuum of technology-mediated service virtuality.

The authors conducted two studies: first, to investigate consumers’ levels of mental construal associated with varying degrees of service separation across a spectrum of technology-mediated services; second, to empirically examine consumer evaluations of service quality in response to varying degrees of spatial and temporal service separation. These relationships were tested across two service industries: education and tourism.

Consumers mentally construe psychological distance in response to service separation and these observations vary across the spectrum of service offerings ranging from face-to-face (no psychological distance) through to virtual (spatially and temporally separated – high psychological distance) services. Further, spatial separation negatively affects consumers’ service evaluations; such that as service separation increases, consumers’ service evaluations decrease. No such significant findings support the similar effect of temporal separation on customer service evaluations. Moreover, specific service industry-based distances exist such that consumers responded differentially for a credence (education) vs an experiential (tourism) service.

Recent studies in services marketing have challenged the inseparability assumption inherent for services. This paper builds on this knowledge and is the first to integrate literature on construal-level theory, service separability, and virtual services into a holistic conceptual framework which explains variance in consumer evaluations of separated service encounters. This is important due to the increasingly virtual nature of service provider-customer interactions across a diverse range of service industries (i.e. banking and finance, tourism, education, and health care). Service providers must be cognisant of the psychological barriers which are imposed by increased technology infusion in virtual services.

Incorporating dynamic spatial effects exhibits considerable potential in improving the accuracy of forecasting tourism demands. This study aims to propose an innovative deep learning model for capturing dynamic spatial effects.

A novel deep learning model founded on the transformer architecture, called the spatiotemporal transformer network, is presented. This model has three components: the temporal transformer, spatial transformer and spatiotemporal fusion modules. The dynamic temporal dependencies of each attraction are extracted efficiently by the temporal transformer module. The dynamic spatial correlations between attractions are extracted efficiently by the spatial transformer module. The extracted dynamic temporal and spatial features are fused in a learnable manner in the spatiotemporal fusion module. Convolutional operations are implemented to generate the final forecasts.

The results indicate that the proposed model performs better in forecasting accuracy than some popular benchmark models, demonstrating its significant forecasting performance. Incorporating dynamic spatiotemporal features is an effective strategy for improving forecasting. It can provide an important reference to related studies.

The proposed model leverages high-frequency data to achieve accurate predictions at the micro level by incorporating dynamic spatial effects. Destination managers should fully consider the dynamic spatial effects of attractions when planning and marketing to promote tourism resources.

This study incorporates dynamic spatial effects into tourism demand forecasting models by using a transformer neural network. It advances the development of methodologies in related fields.

纳入动态空间效应在提高旅游需求预测的准确性方面具有相当大的潜力。本研究提出了一种捕捉动态空间效应的创新型深度学习模型。

本研究提出了一种基于变压器架构的新型深度学习模型, 称为时空变压器网络。该模型由三个部分组成：时空转换器、空间转换器和时空融合模块。时空转换器模块可有效提取每个景点的动态时间依赖关系。空间转换器模块可有效提取景点之间的动态空间相关性。提取的动态时间和空间特征在时空融合模块中以可学习的方式进行融合。通过卷积运算生成最终预测结果。

结果表明, 与一些流行的基准模型相比, 所提出的模型在预测准确性方面表现更好, 证明了其显著的预测性能。纳入动态时空特征是改进预测的有效策略。它可为相关研究提供重要参考。

所提出的模型利用高频数据, 通过纳入动态空间效应, 在微观层面上实现了准确预测。旅游目的地管理者在规划和营销推广旅游资源时, 应充分考虑景点的动态空间效应。

本研究通过使用变压器神经网络, 将动态空间效应纳入旅游需求预测模型。它推动了相关领域方法论的发展。

La incorporación de efectos espaciales dinámicos ofrece un considerable potencial para mejorar la precisión de la previsión de la demanda turística. Este estudio propone un modelo innovador de aprendizaje profundo para capturar los efectos espaciales dinámicos.

Se presenta un novedoso modelo de aprendizaje profundo basado en la arquitectura transformadora, denominado red de transformador espaciotemporal. Este modelo tiene tres componentes: el transformador temporal, el transformador espacial y los módulos de fusión espaciotemporal. El módulo transformador temporal extrae de manera eficiente las dependencias temporales dinámicas de cada atracción. El módulo transformador espacial extrae eficientemente las correlaciones espaciales dinámicas entre las atracciones. Las características dinámicas temporales y espaciales extraídas se fusionan de manera que se puede aprender en el módulo de fusión espaciotemporal. Se aplican operaciones convolucionales para generar las previsiones finales.

Los resultados indican que el modelo propuesto obtiene mejores resultados en la precisión de las previsiones que algunos modelos de referencia conocidos, lo que demuestra su importante capacidad de previsión. La incorporación de características espaciotemporales dinámicas supone una estrategia eficaz para mejorar las previsiones. Esto puede proporcionar una referencia importante para estudios afines.

El modelo propuesto aprovecha los datos de alta frecuencia para lograr predicciones precisas a nivel micro incorporando efectos espaciales dinámicos. Los gestores de destinos deberían tener plenamente en cuenta los efectos espaciales dinámicos de las atracciones en la planificación y marketing para la promoción de los recursos turísticos.

Este estudio incorpora efectos espaciales dinámicos a los modelos de previsión de la demanda turística mediante el empleo de una red neuronal transformadora. Supone un avance en el desarrollo de metodologías en campos afines.

The purpose of this paper is to examine the effects of temporal myopia (focussing on the short-term) and spatial myopia (focussing on the current market) on firm strategy. Specifically the paper investigates the effects of temporal and spatial myopia on the persistence and conformity of firm strategy. Additionally, the paper tests how environmental munificence moderates these effects. A secondary purpose of this paper is to develop a replicable method of measurement of temporal and spatial myopia.

The authors conducted a manual content analysis of letters to shareholders for 100 firms over three years to measure spatial and temporal myopia. After collecting strategy variables and control variables from Compustat, the authors utilize a random-effects panel methodology.

The results indicate that strategy is influenced by both temporal and spatial myopia. Specifically, temporal myopia creates a focus on the firm's current strategy, leading to a persistent strategy over time and spatial myopia focusses firm decision makers on better known technologies and competitors, leading to conformity to industry strategic profiles. Additionally, the paper tests how environmental munificence influences these relationships. In total, the paper finds that the differing types of managerial myopia have distinct influences on firm outcomes.

This paper makes two important contributions to the literature on managerial myopia. First, the paper investigates the differential effects of both spatial and temporal myopia on firm strategy, topics that have been relatively overlooked in empirical investigations of decision making. Second, the paper develops replicable measures for both temporal and spatial myopia, which have been previously suggested to limit the ability to empirically test the implications of managerial myopia (Laverty, 1996).

Accurate segmentation of artificial assembly action is the basis of autonomous industrial assembly robots. This paper aims to study the precise segmentation method of manual assembly action.

In this paper, a temporal-spatial-contact features segmentation system (TSCFSS) for manual assembly actions recognition and segmentation is proposed. The system consists of three stages: spatial features extraction, contact force features extraction and action segmentation in the temporal dimension. In the spatial features extraction stage, a vectors assembly graph (VAG) is proposed to precisely describe the motion state of the objects and relative position between objects in an RGB-D video frame. Then graph networks are used to extract the spatial features from the VAG. In the contact features extraction stage, a sliding window is used to cut contact force features between hands and tools/parts corresponding to the video frame. Finally, in the action segmentation stage, the spatial and contact features are concatenated as the input of temporal convolution networks for action recognition and segmentation. The experiments have been conducted on a new manual assembly data set containing RGB-D video and contact force.

In the experiments, the TSCFSS is used to recognize 11 kinds of assembly actions in demonstrations and outperforms the other comparative action identification methods.

A novel manual assembly actions precisely segmentation system, which fuses temporal features, spatial features and contact force features, has been proposed. The VAG, a symbolic knowledge representation for describing assembly scene state, is proposed, making action segmentation more convenient. A data set with RGB-D video and contact force is specifically tailored for researching manual assembly actions.

The purpose of this paper is to detect spatial-temporal clusters of violence in Gwanak-gu, Seoul with space-time permutation scan statistics (STPSS) and identifies the temporal threshold for such detection to alert law enforcement officers quickly.

The case study was the Gwanak Police Station Call Database 2017 where civilian calls reporting violence were georeferenced with coordinated points. In analyzing the database, this study used the STPSS requiring only individual case data, such as time and location, to detect clusters of investigated phenomena. This study executed a series of experiments using different minimum and maximum temporal thresholds in detecting clusters of violence.

Results of the STPSS analyses with different temporal thresholds detected spatial-temporal clusters in Gwanak-gu. Number, location and duration of clusters depended on the temporal settings of the scanning window. Among four models, a model allowing the possible clusters to be detected within a 7-day minimum and 30-day maximum temporal threshold was more representative of reality than other models.

This study illustrates the clustering of violence with the STPSS by detecting spatial-temporal clusters of violence and identifying the appropriate temporal threshold in detecting such clusters. Identification of such a threshold is useful to alert law enforcement officers quickly and enables them to allocate their resources optimally.

This paper aims to describe two Web-based technologies of geographic information systems (GIS) to be used in monitoring and analysis of environmental processes, proposed by the authors. The technologies analyze the temporal aspect of the process together with the spatial aspect, which defers them from most other works on environmental processes, as these are usually limited either to spatial statistics or to temporal statistics. The approach is instrumental in dynamically finding the relationships between the processes and predicting critical incidents.

Often, the study of natural processes is limited to the analysis of their spatial properties presented by individual time series. The principal idea of this approach consists in supplementing this traditional analysis with the analysis of time fields. In this way, the authors are able to analyze temporal and spatial properties of environmental processes together.

The paper presents two technologies which provide the analysis of spatial and temporal data obtained in natural environment monitoring. The discussed spatio-temporal data mining methods are shown to enable the research into environmental processes, and the solution of practical issues of critical situation forecasts.

The paper discussed Web-based GIS technologies for the analysis of the temporal aspect of the environmental process together with the spatial aspect. Application examples demonstrate the ability of this approach to find the relationships in dynamics of the processes and to predict critical incidents.