Search

With the deterioration of the transportation ecosystem and traffic congestion, traffic graph representations become more complex and lack intelligibility. The deep learning method provides a new way for traffic prediction by mining the spatiotemporal relations of historical states in traffic network. Recurrent neural networks based on gate control can avoid the gradient vanishing and graph convolutional networks provide theoretical support for spatial feature extraction of traffic graph. However, in the prediction of traffic evolution behaviors, the statuses of units and groups distributed in the traffic network have strong and continuous spatiotemporal correlations. Modeling only based on the temporal or spatial perspective usually lacks comprehensiveness and semantic relevance which results in poor prediction performance. In this paper, we propose a spatiotemporal hierarchical propagation graph convolutional network(SHPGCN) to get the whole spatiotemporal evolution features of traffic graph, which can be used to predict the propagation effects and state changes of traffic flow. Considered the inadequacy of graph convolution in the learning of hierarchical features, we construct a low-dimensional propagation graph representation that projects complex node relationships into first-order neighborhoods to capture dynamic changes at different spatial and temporal scales. The SHPGCN uses graph convolution to encode the traffic propagation features and embeds them into a bidirectional recurrent sequence for traffic prediction. The experiment results show that SHPGCN can provide good prediction accuracy and robustness for the traffic evolution behaviors.

With the development of location-based services and smart terminals, skyline query technique has been used widely in intelligent transportation systems. In skyline queries, the areas and keywords queried by users have a great impact on the quality of the query results and users may only be interested in the closer results of the skyline query. However, current approaches for the continuous skyline query limit the area of the skyline query to a specific area in the road network, which leads to that many useful query results cannot be retrieved. To this end, an innovative continuous skyline query approach in city range is proposed in this paper, where a multi-scale area divisions of the urban road network are provided to find the optimize query scale and area. In our approach, first, the dominant area of each intersection node in the road network is established based on the Voronoi. Then, all Points of Interest (POIs) are divided into the dominant area of each intersection node. After that, the intersection node aggregation algorithm (INAA), link remolding algorithm (LMA) and link fitting algorithm (LFA) are proposed to reduce the number of intersection nodes in the road network, so as to increase the dominant area of the remaining intersection nodes and the number of POIs in these nodes. Finally, a better query scale by considering the efficiency and quality of the query is given through the studies.

Emergency supplies scheduling needs to consider the state of the demanders, and reasonably scheduling and resource allocation are the heart of efficient rescue. Taking rescue time, scheduling cost and demanders’ satisfaction as goals, in this paper, an emergency supplies scheduling model based on multi-objective optimization was proposed to provide a wealth of decision-making information. Then four multi-objective optimization algorithms are employed to obtain the optimal set of scheduling models. In addition, we design the minimum time cost model and the shortest route cost model by considering the change of the road network status. The extensive simulation experiments are conducted on a real urban traffic dataset. The experimental results show that the two cost models can serve different scheduling needs and provide efficient scheduling for emergency supplies.

Urban rail transit stations are the key nodes of urban rail transit network. Identifying and analyzing land use characteristics around urban rail transit stations can significantly contribute to urban rail transportation operation and management. Therefore, a visualization method of land use characteristics around urban rail transit stations based on POI is proposed in this paper. In the proposed method, first, the Voronoi diagram is used to determine coverage of urban rail transit stations and each POI is put in a coverage area based on their physical location. Then, topic-oriented hierarchical POIs of each urban rail transit station are extracted based on skyline idea. Finally, the land use characteristics around an urban rail transit station are visualized based on the extracted hierarchical POIs. We carried out two case studies and a quality evaluation. By using realistic data from Beijing rail transit in order to validate the method proposed in this paper. Results show that our method can clarify various situations of land use of urban rail transit stations and may provide support for the application of transportation model technology.

Multi-agent technologies have been widely applied to many applications, such as in e-markets, cloud computing, service-oriented environments, etc. In real applications, service-oriented environments are open and dynamic, where loosely coupled agents interact to consume and provide services. How to accurately evaluate the potential performance (i.e., QoS) of service providers on the service requested by a service consumer in such open and dynamic environments is a challenging issue in both theory and practice. In this paper, an innovative approach is proposed to evaluate the QoS of service providers in service-oriented environments. The proposed approach first borrows the reference report mechanism from the certified reputation model, so as to efficiently collect reference reports (i.e., historical performance) of service providers in open and dynamic environments. Then, a tensor-based QoS model is proposed to construct multi-dimensional relationships between QoS evaluation factors and the QoS values of service providers based on the collected reference reports. The QoS evaluation factors include the type of services, the performance of service providers, the subjectivity of service consumers, the time slot of reference reports. Finally, a CANDECOMP/PARAFAC decomposition and gradient descent-based mechanism is used to evaluate the QoS values of service providers through completing the missing entry values in the constructed tensor. The uniform random simulation experiments indicate that the proposed approach can achieve efficient and accurate QoS evaluation in service-oriented environments with only limited collected reference reports, especially when some service providers do not have reference reports.

In recent years, the amount of user check-in data has significantly increased on social network platforms. Such data is an ideal source for characterizing user behaviors and identifying similar users, contributing to many research areas (e.g. user-based collaborative filtering). However, existing trajectory-based user similarity analysis approaches do not distinguish the effects of geographical factors at a fine-grained level, and thus are not able to unleash the full power of semantic information that is hidden in the trajectory. In this paper, we have proposed an effective graph embedding approach to identify similar users based on their check-in data. Specifically, we firstly identify meaningful concepts of user check-in data, based on which we design two metagraphs for representing features of similar user behaviors. Then we characterize each user with a sequence of nodes that are derived through a metagraph-guided random walk strategy. Such sequences are embedded to generate meaningful user vectors for measuring user similarity and eventually identifying similar users. We have evaluated our proposal on three public datasets, the results of which show that our approach is 4% higher than the best existing approach in terms of F1-measure.

With the development of society and economy, the urban rail transit has become one of the important components of urban transportation system, while the construction of the urban rail greatly improves the public transportation environments. Currently, there are many research focus on the passenger flow predictions according to their corresponding historical data, however, it is hard to assist transport models vary such volumes for a new station planning or being constructed. In view of this limitation, we provide a novel method for urban rail station characteristics analysis in intelligent transportation considering city land usages. Initially, point of interest (POIs) are divided by the proposed RC-tree (Colored R-tree)-based algorithm into the bounded areas for each station. Second, the Diversity and Proportion approaches are proposed to extract the $top$ - $k$ POIs from bounded areas based on their semantic and spatial characteristics. Then, classify the stations based on the similarity of the extracted $top$ - $k$ POIs. Moreover, we made a case study on real dataset, including a large volume of Automatic Fare Collection system (AFC) records for the experimental evaluations, and the results show that the proposed method can verify the rationality of land use and provide support for the application of transportation model technology.

With the extensive development of big data and social networks, the user profile field has received much attention. User profiling is essential for understanding the characteristics of various users, contributing to better understanding of their requirements in specific scenarios. User-generated contents which directly reflect people’s thoughts and intention are a valuable source for profiling users, among which user reviews by nature are invaluable sources for acquiring user requirements and have drawn increasing attention from both academia and industry. However, review-based user profiling (RBUP), as an emerging research direction, has not been systematically reviewed, hindering researchers from further investigation. In this work, we carry out a systematic mapping study on review-based user profiling, with an emphasis on investigating the generic analysis process of RBUP and identifying potential research directions. Specifically, 51 out of 2478 papers were carefully selected for investigation under a standardized and systematic procedure. By carrying out in-depth analysis over such papers, we have identified a generic process that should be followed to perform review-based user profiling. In addition, we perform multi-dimensional analysis on each step of the process in order to review current research progress and identify challenges and potential research directions. The results show that although traditional methods have been continuously improved, they are not sufficient to unleash the full potential of large-scale user reviews, especially the use of heterogeneous data for multi-dimensional user profiling.

When an emergency occurs in the city, a large area of road congestion usually occurs. Therefore, it is particularly important to provide an effective emergency path planning strategy for vehicles. However, existing emergency path planning methods do not take into account the connectivity characteristics of the road network and commuting capacity. For this purpose, a Grid Map Emergency Path Planning (GMEPP) framework based on a novel model Grid Road Network (GRN) is designed in this paper. First, the road network data is divided into grids under equal spacing bands, and the roads data divided into different grids and use the commuting capacity of each road as the weight of each edge in the grid. Then a Grid PageRank (GPR) algorithm will be introduced, the output value of this methodology is calculated based on the capacity and number of connected edges of all vertices pointed by the external grid in each grid. The higher value of the grid will be recommended to users first when the path is planning. According to the GRN model, an improved Bidirectional Dijkstra will be applied to query the shortest path between two points, which is called Gird Bidirectional Dijkstra (GBD). At last, GMEPP uses Reverse Contraction Hierarchies (RCH) and Multiple Reverse Contraction Hierarchies (MRCH) originality methodologies based on intersection type to speed up the query algorithm GBD. To compare the efficiency of the proposed method, this paper conducted extensive experiments to verify. The results of the test showed that the Gird Bidirectional Dijkstra Multiple Reverse Contraction Hierarchies (GBD-MRCH) is better than other methods in different grid distributions.

Wireless sensor networks have played an important role in many applications, where sensors in the network can automatically collect and transmit information in an environment without much human maintenance. To enhance the adaptability of sensors, people produce mobile wireless sensors through fixing wireless sensors on mobile vehicles or robots. The same as static wireless sensors, since the energy of mobile wireless sensors is still supplied by the battery, their energy management has a great impact on their lifetime. Different with static wireless sensors, the mobility of mobile wireless sensors gives us a new perspective to achieve the efficient energy management. In this paper, a decentralized self-adaptive approach is proposed for mobile wireless sensors, which enables sensors in a mobile wireless sensor network to adapt their locations according to the information transmission regularity in the network so as to reduce their energy consumption for the information transmission. The experimental results indicate that after employed the proposed approach to adapt locations, the energy consumption for the information transmission of sensors in a mobile wireless sensor network can be greatly reduced and their lifetime is extended.

The daily trajectories of individual movements convey a concise overview of their behaviors, with different social roles having different trajectory patterns. Therefore, we can identify users or groups based on the similar of their trajectory patterns. However, most existing trajectory analysis focuses only on the spatial and temporal analyses of the raw trajectory data and misses essential semantic information concerning behaviors. In this paper, we propose a new trajectory semantics calculation method to identify groups with similar behaviors. We first propose a fast and efficient two-phase method for identifying stay regions within daily trajectories and enriching the stay regions with semantic labels based on points of interest to generate semantic trajectories. Furthermore, we design a semantic similarity measure model using geographic and semantic similarity factors to measure the similarity between semantic trajectories. We also propose a pruning strategy using time entropy to decrease the number of complex calculations and comparisons to improve performance. The results of our extensive experiments on the real trajectory dataset of the Geolife project show that our proposed method is both effective and efficient.

Emergency path planning technology is one of the research hotspots of intelligent transportation systems. Due to the complexity of urban road networks and congested road conditions, emergency path planning is very difficult. Road congestion caused by urban emergencies directly affects the original road network structure. In this way, the static weight of the original road network is no longer suitable as the basis for path recommendation. To handle the dynamic situational road network, an equidistant grid emergency path planning framework will be designed. A novel situation grid road network model, based on situation information, is proposed and applied to an equidistant grid emergency path planning framework. A situational grid heuristic search will be proposed methodology based on this model, which can be used to detect the vehicles passing around the congestion area grid and the road to the destination in the shortest time. In the path planning methodology, a grid inspired search strategy based on quaternion function is included, which can make the algorithm converge to the target grid quickly. Three graph acceleration algorithms are proposed to improve the search efficiency of path planning algorithm. Finally, this paper will set up three experiments to verify our proposed method.

With the rapid development of artificial intelligence science, more and more researchers try to use deep learning to train neural networks and have achieved great success in object detection. Vehicle detection based on UAV image is a special field of object detection. Due to the low resolution of the vehicle object, complex background, and less image information, it is challenging to extract robust visual and spatial features from the depth network and accurately locate the object in complex scenes. In this paper, combining the characteristics of vehicles in aerial images, we design a novel feature pyramid network called channel-spatial attention fused feature pyramid network (CSF-FPN) with Faster R-CNN as the basic framework. In CSF-FPN, a hybrid attention mechanism and feature cross-fusion module are introduced, so that feature maps can be generated with enhanced spatial and channel interdependence to extract richer semantic information. After our CSF-FPN is integrated into the Faster R-CNN network, the detection performance of small objects is greatly improved. The experimental results based on the VEDIA Dataset showed that the proposed framework could effectively detect the vehicle in large scene azimuth. Compared with the existing advanced methods, mAP and F1-score are improved.

In a modern Intelligent Transportation System (ITS), traffic prediction exerts an enormous function in alleviating traffic congestion and path planning. Due to the complex dynamic spatial-temporal dependence of traffic data, the traditional prediction methods have some limitations in the spatial-temporal correlation modeling, and cannot effectively predict both long-short term traffic conditions. In this paper, a novel deep learning framework Spatial-Temporal Graph Wavelet Attention Neural Network (ST-GWANN) is proposed for long-short term traffic prediction, which can comprehensively capture the spatial-temporal features. In the framework, the graph wavelet neural network and attention mechanism are integrated into the spatial gated block, which can obtain the spatial dependence of the road network. By combining the Gated Linear Units (GLU) and the temporal transformer layer, the local and global dependence of the time dimension are obtained. The proposed framework experimented on two real-world datasets, the results show that ST-GWANN outperforms state-of-art methods in traffic prediction tasks.

How to detect and predict the critical situation in large-scale activities is a very important research issue. The existing researches of emergency prediction are mainly focus on the micro events in some specific fields. Applying existing results directly to predict the critical situation in large-scale activity is a big challenge. In this paper, we show a novel method to predict emergency based on historical data analysis. We integrate relevant research results into a unified spatiotemporal model. Firstly, constructing the historical spatiotemporal context time series based on historical activity data. Then, dividing the time series into time period and time window. Finally, exploiting the time series’ spatiotemporal patterns to predict the emergency of current activity. Experimental results show that the proposed method can achieve better prediction of large-scale activity emergencies in a specific venue.

The time-varying property of traffic networks has brought a problem of modeling large-scale dynamic networks. Based on the real-time traffic sensing data of the road network, community division and prediction can effectively reduce the complexity of local management in urban regions. However, traffic-based communities have complex topology and real-time dynamic features, and traditional community division and topology prediction cannot effectively be applied to this structure. Therefore, we propose a dynamic traffic community prediction model based on hierarchical graph attention network. It uses the hierarchical features fusion with spatiotemporal convolution and the ADGCN proposed in this paper to compose a hierarchical graph attention architecture. In which, each layer component coordinates to perform different features extraction for capturing traffic community of road network in different time periods respectively. Finally, the output features of each layer are combined to represent the dynamically divided regions in the traffic network. The effectiveness of the model was verified in experiments on the Xi'an urban traffic dataset.

Differentiable architecture search (DARTS) is widely considered to be easy to overfit the validation set which leads to performance degradation. We first employ a series of exploratory experiments to verify that neither high-strength architecture parameters regularization nor warmup training scheme can effectively solve this problem. Based on the insights from the experiments, we conjecture that the performance of DARTS does not depend on the well-trained supernet weights and argue that the architecture parameters should be trained by the gradients which are obtained in the early stage rather than the final stage of training. This argument is then verified by exchanging the learning rate schemes of weights and parameters. Experimental results show that the simple swap of the learning rates can effectively solve the degradation and achieve competitive performance. Further empirical evidence suggests that the degradation is not a simple problem of the validation set overfitting but exhibit some links between the degradation and the operation selection bias within bilevel optimization dynamics. We demonstrate the generalization of this bias and propose to utilize this bias to achieve an operation-magnitude-based selective stop., Comment: Accepted as a full paper at the CIKM 2021 conference

Students have produced a large number of data in the teaching life of colleges and universities. At present, the development trend of university data is to gradually form a high-dimensional data storage system composed of student status information, educational administration information, behavior information, etc. It is of great significance to make use of the existing data of students in Colleges and universities to carry out deep-seated and personalized data mining for college education decision-making, implementation of education and teaching programs, and evaluation of education and teaching. Student portrait is the extension of user portrait in the application of education data mining. According to the data of students’ behavior in school, a labeled student model is abstracted. To address above problems, a hybrid neural network model is designed and implemented to mine the data of college students and build their portraits, so as to help students’ academic development and improve the quality of college teaching. In this paper, experiments are carried out on real datasets (the basic data of a college’s students in Beijing and the behavior data in the second half of 2018–2019 academic year). The results show that the hybrid neural network model is effective.

The reliable road network plays a vital role in many applications. Owing to the development of remote sensing technology and the success of deep learning in computer vision, automatic road extraction from remote sensing images is a research hotspot in recent years. However, due to the complicated image background and special road structure, the results of automatic road extraction are still far from perfect. In this paper, we propose a road segmentation network that is designed based on improved U-Net, which contains an encoder and a decoder. First, the recurrent criss-cross attention module (CCA) is introduced into the encoder to obtain long-range contextual dependencies with a relatively small number of computations and parameters, which results in better understanding and expression of image information. Second, we propose the attention-based multi-scale feature fusion module (AMS) to resolve the problem of different shapes and widths of the roads, which is placed between the encoder and decoder and uses attention mechanisms to guide multi-scale information fusion. Experimental on the Massachusetts Roads Dataset show that the proposed method achieves better performance in road extraction than other methods in terms of precision, recall, F1-score, and accuracy.

Due to the influence of the shooting angle of view and the flight height, the images taken by UAV often have complex backgrounds and contain a large number of small and unevenly distributed objects. In order to solve the problem that it is difficult to accurately locate and recognize small objects in UAV images under complex backgrounds, this paper proposes an multi-scale feature fusion algorithm D-A-FS SSD (Dilated-Attention-Feature Fusion SSD) based on the combination of dilated convolution and attention mechanism. In the process of feature extraction, the receptive field of the feature is expanded through the dilated convolution, which improves the network's feature expression of object distribution and scale difference information. And a attention network is used in our method to effectively suppresse the background information. In the multi-scale detection stage, our method fuses the low-level feature map responsible for detecting small objects with the high-level feature map which have much higher semantic information to improve the recognition accuracy of small objects. Experimental results show that our method effectively improves the accuracy of UAV image object detection.

Processing application user reviews has recently been recognized as an efficient approach to explore user requirements. However, most existing approaches focus on mining the reviews themselves without effectively associating the reviews with requirements concepts, limiting the effectiveness of review mining for requirements analysis tasks. In this paper, we propose to automatically identify Requirements-oriented Reviews (RoRs) from software application reviews by considering requirements specific domain knowledge and syntactic information of user reviews. Specifically, we first define a conceptual model of RoRs based on existing requirements ontology and user review categories, establishing connections between the concepts of requirements engineering and user reviews. We then systematically identify the textual features of RoRs by following a conceptual model-driven top-down strategy. Based on such features, we then train effective RoR classifiers to identify RoRs. To evaluate the performance of our approach, we have applied our approach to a real dataset of mobile application reviews, the results of which show that our approach can effectively identify RoRs with an F-measure of 0.8, outperforming than the baselines.

Accurate traffic flow forecasting plays an increasingly important role in traffic management and intelligent information service. Mining and analyzing the hidden rules and patterns in the historical data of traffic flow are helpful to understand the rules of the data and better assist the prediction. For the long-term sequence similarity measurement, this paper proposes the correlation matrix sequence description method based on wavelet decomposition, which can better express the sequence information and perform better in the long-term prediction compared with Euclidean distance. Furthermore, we propose a similar search scheme based on the nearest neighbor and seasonality. The searched candidates are input into the prediction model as the attention value, and the output of prediction results is assisted at each step. Compared with the state-of-the-art methods on the PeMS dataset, the proposed model can effectively learn the long-term dependence of time series and perform better in detail, showing advantages in multi-step prediction.

With the developing of smart sensors and mobile devices produces an increasing volume of data, and it captures the states of transportation infrastructures. Such data are collected and uploaded frequently, which forms the heavy data calculation and storage. Moreover, state of monitored object may be keeping the same or slight change according to a certain state during a period, such as moving vehicles on a certain path with a basic uniform speed. Therefore, if trajectory pattern of vehicles can be obtained through the state change mode, scale and update frequency of the data can be greatly reduced. Based on the above-mentioned ideas, we are aware that the trajectory data storage is divided into traceability storage and vector storage, where original sampled data from sensing device, and state vectors are extracted from the analysis of the original sample data. In this way, only a relatively small amount of vector data is stored. The system will not only effectively reduce the frequency of sampling data storage, but also reduce query and analysis operations involved with the amount of data. The vector function is used to represent road network with indexes, and the data query based on the road network is used to extract the semantic information. Our experimental results show that our proposed methodologies have significant improvements in intelligent transportation.

In recent years, the number of motor vehicles in the country has risen rapidly. Traffic demand has continued to grow, while land resources, capital and energy have become increasingly tense. The development trend of urban transport system is not optimistic. Especially in the face of major events, vehicle evacuation suddenly increased, which is a serious planning for the evacuation of a serious challenge. Reasonable and accurate implementation of the emergency evacuation plan is to make the evacuation time at least, to minimize the major traffic congestion protection. Among them, route selection and traffic flow distribution are the core contents of emergency evacuation plan. In this paper, traffic emergency evacuation of major activities is taken as the research object, and the state vector of each road is introduced into the navigation system according to the linking analysis algorithm thought. The network model of evacuation route selection is established by using the theory of spatial diversity and the theory of minimum cost maximum flow, and an empirical analysis is made on the road network. Based on the research, the emergency evacuation plan for large-scale activities is proposed, and the theory and method system of emergency evacuation are enriched, which can help with formulating more reasonable and effective traffic management policies according to the characteristics of emergency evacuation, meanwhile we provide decision-making basis for urban emergency evacuation transportation planning and management. An experimental evaluation is also conducted with the real data from city of Beijing, in aspects of effectiveness and efficacy.

This paper addresses the problem of multi-objective coalition formation for task allocation. In disaster rescue, due to the dynamics of environments, heterogeneity and complexity of tasks as well as limited available agents, it is hard for the single-objective and single (task)-to-single (agent) task allocation approaches to handle task allocation in such circumstances. To this end, two multi-objective coalition formation for task allocation models are proposed for disaster rescues in this paper. First, through coalition formation, the proposed models enable agents to cooperatively perform complex tasks that cannot be completed by single agent. In addition, through adjusting the weights of multiple task allocation objectives, the proposed models can employ the linear programming to generate more adaptive task allocation plans, which can satisfy different task allocation requirements in disaster rescue. Finally, through employing the multi-stage task allocation mechanism of the dynamic programming, the proposed models can handle the dynamics of tasks and agents in disaster environments. Experimental results indicate that the proposed models have good performance on coalition formation for task allocation in disaster environments, which can generate suitable task allocation plans according to various objectives of task allocation.

The urban rail transit stations are an important part of an urban transit system. Scientific and reasonable location of rail transit station can greatly alleviate traffic pressure. The number of people in the surrounding area of a rail transit station is an important factor for site selection. However, it is difficult to obtain the spatial distribution of population, which brings great difficulties in terms of site selection. Due to the large-scale popularization of AP (Access Point) in China, the spatial distribution of AP is used instead of population distribution to assist site selection. Therefore, a density visualization method based on a dynamic grid is proposed, which can help decision-makers intuitively see the AP density of the uncovered grid of rail transit stations, and then cluster the AP density of the uncovered area to predict the location of new rail transit stations. The validity of the proposed method is demonstrated by using the AP dataset and rail transit data of Beijing in 2013. The results show that our method has high accuracy in predicting the location of rail transit stations. It can provide data support for urban traffic development and management.

Map matching is the process of matching GPS points to roads. Local methods and incremental methods usually have faster-running speed, however, the performance of these methods may be insufficient for complex road networks and data with significant error. Global methods can get better results in complex situations, while most of them handle high-frequency GPS data slowly. In order to solve these problems, a weight-based algorithm(FWMM) is developed in this paper. We introduce a new method of weight fusion to avoid the influence of dimension and adopt Particle Swarm Optimization(PSO) for parameter estimation. In order to accelerate the matching process of data with a high sampling rate, we designed a mechanism which can adaptively accelerate high-frequency data piece. Thus this method can be more accurate than existing methods mentioned above.

Eliciting precise user preferences and establishing a comprehensive user profile significantly contribute to personalized recommendations from numerous applications. However, existing methods do not adequately establish critical relationships at the knowledge level. In this paper, we argue that precisely processing applications' user feedback is essential for understanding user requirements and making application recommendations. Therefore, we first establish an ontological model of user feedback, guiding the generation of a knowledge graph regarding user reviews and user ratings. In particular, we augment the graph with topics of each review and application in order to deal with the sparsity of user feedback. Moreover, we explore in-depth knowledge from the graph by identifying three meaningful meta-paths, which are essential for calculating user similarity and thus making recommendations. Specifically, we propose a feedback-based similarity calculation model FSCM, with the purpose of predicting applications that are of interests of certain users. We have evaluated our model over 1386 reviews from a mobile application store, the results of which show that our approach can improve the prediction accuracy, as well as to enhance the interpretability of analysis results.

With increasing demand for trip on urban transportation networks, optimal traveler routing has become a hot spot of public concern in recent years. In parallel, traffic congestion has an effect on travel routing strategy. The fundamental observation is about the prediction of real-time traffic flow, which is focus on the results based on short-term traffic volume. This paper presents a new approach which provides a dynamic route planning model based on the spatio-temporal interactions in a road network. In addition, it is necessary to consider the factors of security threats (weather, construction, etc.) and the road conditions of real-time while maintaining the accuracy of the model. Firstly, it predicts the traffic congestion status upon the existing historical trajectory data, which defines congestion coefficient for dynamic planning. Secondly, the simulation results show that the improved A* algorithm and introducing the congestion coefficient and safety factor parameters greatly improves the real-time dynamic route planning.

User profiling is essential for understanding the characteristics of various users, contributing to understanding their requirements better. User reviews by nature are invaluable sources for acquiring user requirements and have drawn increasing attention from both academia and industry, which have not been well explored by traditional user profiling techniques. This paper carries out a systematic mapping study on review-based user profiling. Specifically, 21 out of 1372 papers were carefully selected for investigation under a standardized and systematic procedure. By carrying out in-depth analysis over such papers, we have identified a general process that should be followed to perform review-based user profiling. In addition, we perform multidimensional analysis on each step of the process to review current research progress, identify challenges, and propose potential research directions. The results show that although traditional methods have been continuously improved, they are not effective enough to unleash the full potential of large-scale user reviews, especially the use of heterogeneous data for multi-dimensional user profiling.

Emergency path planning technology is one of the hot research points in intelligent transportation systems. There are many methodologies and applications in emergency path planning. However, due to the complexity of the urban network and crowded road conditions, the difficulty of emergency path planning. The objective of emergency path planning is to get the vehicle out of the emergency areas and to its destination in the shortest time. Road congestion caused by emergency situations in cities directly affects the original road network structure. Then the weight of the original road network is no longer suitable as a basis for path recommendation and the value of edges of weight will change over time. To handle the dynamic road network, a novel situational time-stamp heuristic search algorithm (STH) is introduced for the situation space. This algorithm can effectively solve the problem of diversity of situational networks. STH can build a heuristic that adapts to time changes based on the map refresh time, and ensures that the path given in the time window T is optimal. Moreover, STH can give a pruning strategy according to the search time window T, which significantly improves the efficiency of the algorithm. Finally, the path planned by STH is better than the baseline algorithm.

In the context of business process management, the resources required by business processes, such as workshop staff, manufacturing machines, etc., tend to follow certain availability patterns, due to maintenance cycles, work shifts and other factors. Such availability patterns heavily influence the efficiency and effectiveness of enterprise resource management. Most existing process scheduling and resource management approaches tend to tune the process structure to seek better resource utilisation, yet neglect the constraints on resource availability. In this article, we investigate the scheduling of business process instances in accordance with resource availability patterns, to find out how enterprise resources can be rationally and sufficiently used. Three heuristic-based planning strategies are proposed to maximise the process instance throughput together with another strategy based on a genetic algorithm. The performance of these strategies has been evaluated by conducting experiments of different settings and analysing the strategy characteristics.

To support a large amount of GPS data generated from various moving objects, the back-end servers usually store low-sampling-rate trajectories. Therefore, no precise position information can be obtained directly from the back-end servers and uncertainty is an inherent characteristic of the spatio-temporal data. How to deal with the uncertainty thus becomes a basic and challenging problem. A lot of researches have been rigidly conducted on the uncertainty of a moving object itself and isolated from the context where it is derived. However, we discover that the uncertainty of moving objects can be efficiently reduced and effectively ranked using the context-aware information. In this paper, we focus on contextaware information and propose an integrated framework, Context-Based Uncertainty Reduction and Ranking (CURR), to reduce and rank the uncertainty of trajectories. Specifically, given two consecutive samplings, we aim to infer and rank the possible trajectories in accordance with the information extracted from context. Since some context-aware information can be used to reduce the uncertainty while some context-aware information can be used to rank the uncertainty, to leverage them accordingly, CURR naturally consists of two stages: reduction stage and ranking stage which complement each other. We also implement a prototype system to validate the effectiveness of our solution. Extensive experiments are conducted and the evaluation results demonstrate the efficiency and high accuracy of CURR.

The false advertising of food and drag on the Internet is mainly based on the content of the product website promotion pages. When people browse a website, they get the most parts of the information from texts on the web. In order to help people to distinguish whether it is false propaganda on this website, we propose a solution for identifying false advertising of text content on food and drug websites by designing the sensitive word recognition model. This paper introduces in detail the specific design and implementation of the food webpage text sensitive text recognition model, including the system improvement of text acquisition and word segmentation algorithm, feature extraction algorithm and text classification in the sensitive word list extraction. The detailed design and execution flow of the voting decision determination result algorithm of the five text classification algorithms are combined for filtering. Finally, we conducted a series of experiments, and the experimental results demonstrated that the proposed filtering solution is effective.

In recent years, frequent public emergencies have resulted in heavy casualties and economic losses. In the early stage of emergency rescue, the demand for emergency resources is strictly greater than the supply. As an important part of emergency management, emergency resource scheduling is an important manifestation of its rescue value. At present, Many studies take emergency resource scheduling as a multi-objective optimization problem. They focus on the total emergency cost and does not evaluate the emergency resource allocation according to the actual disaster severity of each emergency demand point. What's more, they do not consider road information. However, in actual, the condition of roads directly affects the emergency cost. To address this problem, we proposed an effective emergency logistics scheduling model based on multi-objective optimization algorithms. We get road information from spatial-temporal trajectory data. The research on emergency resource scheduling in this paper is helpful to achieve greater utility under the condition of limited emergency resources and reduce the loss of public emergencies.

Group identification refers to discovering groups with similar behaviors or preferences. The daily trajectories record the activities of moving objects, which reflect their behaviors. These mobile data provide us with a new data analysis approach for groups identification. Therefore, we can identify users or groups based on similar trajectory patterns by mining implicit behaviors patterns. In this paper, we propose a novel trajectory semantics calculation method to identify groups that have similar behaviors. In our model, we first propose a fast and efficient two-phase discovering stay regions method (TPD) from daily trajectories, then generate semantic trajectories by enriching the stay regions with semantic labels based on POI information and LDA topic model. To measure the similarity between semantic trajectories, we design a semantic similarity measure model based on geographic and semantic similarity factor. We have conducted extensive experiments on real trajectory dataset of Geolife project, and the experimental results show our proposed method is both effective and efficient.

With the development of big data, the heuristic query based on the semantic relationship network has become a hot topic, which attracts much attention. Due to the complex relationship between data records, the traditional query technologies cannot satisfy the requirements of users. To this end, this paper proposes a heuristic query method based on the semantic relationship network, which first constructs the semantic relationship model, and then expands the query based on the constructed semantic relationship network. The experiments demonstrate the reasonableness, high precision of our method.

Online trip planning is a popular service that has facilitated a lot of people greatly. However, little attention has been paid to personalized trip planning which is even more useful. In this paper, we define a highly expressive personalized route planning query-the Personalized and Sequenced Route (PSR) Query which considers both personalization and sequenced constraint, and propose a novel framework to deal with the query. The framework consists of three phases: guessing, crossover and refinement. The guessing phase strives to obtain one high quality route as the baseline to bound the search space into a circular region. The crossover phase heuristically improve the quality of multiple guessed routes via a modified genetic algorithm, which further narrows the radius of the search space. The refinement phase backwardly examines each candidate point and partial route to rule out impossible ones. The combination of these phases can efficiently and effectively narrow our search space via a few iterations. In the experiment part, we firstly show our evaluation results of each phase separately, proving the effectiveness of each phase. Then, we present the evaluation results of the combination of them, which offers insight into the merits of the proposed framework.

One promising solution to improve the efficiency of wireless networks is to control the number of nodes involved in multi-hop routing by employing virtual backbone. On the one hand, a virtual backbone becomes more efficient as its size is getting smaller. However, as the size of a virtual backbone is getting smaller, the throughput of the virtual backbone is degraded since the length of a routing path between a pair of nodes through the virtual backbone can be much longer than their hop distance in the original network. Due to the reason, several efforts are recently made to identify a virtual backbone including a shortest path between every pair of nodes in the original graph. In this paper, we investigate a new strategy to compute higher throughput virtual backbone in wireless networks. We employ a new information theoretic metric called spectral-efficiency by Chen et al. and propose a new virtual backbone computation algorithm in homogeneous wireless networks with some interesting theoretical analysis. Our simulation results indicate our algorithm produces a virtual backbone with higher spectral-efficiency than the existing alternatives. We also conduct another simulation using OMNet++ and show the virtual backbone produced by our algorithm has the highest throughput.

In this paper, we propose a novel approach for instance retrieval. Compared with traditional retrieval pipeline, we first locate several candidate regions of target object with a region proposal network (RPN), instead of exhausting sliding window method. The candidate regions are detected through the trained RPN. Then we obtain the region-wise convolutional feature maps (CFMs) by forwarding them through a ROI pooling layer. Our feature encoding representation builds on the common sense that similar patterns have similar activations on feature maps. The target object is regarded as a combination of several meaningful patterns. In this way, we represent an image with the combination of encoded descriptors corresponding to the subsets of the proposed region. We also implement reranking algorithm to refine the proposed region in local retrieval. Through extensive experiments, we demonstrate the suitability of our feature encoding representation for instance retrieval, achieving comparable performance on both Oxford and Paris buildings benchmarks.

Multi-objective spatial keyword query finds broad applications in map services nowadays. It aims to find a set of objects that can cover all query objectives and are reasonably distributed in spatial. However, existing approaches mainly take the coverage of query keywords into account, while leaving the semantics behind the textual data to be largely ignored. This limits us to return those rational results that are synonyms but morphologically different. To address this problem, this paper studies the problem of multi-objective spatial keyword query with semantics. It targets to return the object set that is optimum regarding to both spatial proximity and semantic relevance. We propose an indexing structure called LIR-tree, as well as two advanced query processing approaches to achieve efficient query processing. Empirical study based on real dataset demonstrates the good effectiveness and efficiency of our proposed algorithms.

Streams of short text, such as news titles, enable us to effectively and efficiently learn the real world events that occur anywhere and anytime. Short text messages that are companied by timestamps and generally brief events using only a few words differ from other longer text documents, such as web pages, news stories, blogs, technical papers and books. For example, few words repeat in the same news titles, thus frequency of the term (i.e., TF) is not as important in short text corpus as in longer text corpus. Therefore, analysis of short text faces new challenges. Also, detecting and tracking events through short text analysis need to reliably identify events from constant topic clusters; however, existing methods, such as Latent Dirichlet Allocation (LDA), generates different topic results for a corpus at different executions. In this paper, we provide a Finding Topic Clusters using Co-occurring Terms (FTCCT) algorithm to automatically generate topics from a short text corpus, and develop an Event Evolution Mining (EEM) algorithm to discover hot events and their evolutions (i.e., the popularity degrees of events changing over time). In FTCCT, a term (i.e., a single word or a multiple-words phrase) belongs to only one topic in a corpus. Experiments on news titles of 157 countries within 4 months (from July to October, 2013) demonstrate that our FTCCT-based method (combining FTCCT and EEM) achieves far higher quality of the event's content and description words than LDA-based method (combining LDA and EEM) for analysis of streams of short text. Our method also visualizes the evolutions of the hot events. The discovered world-wide event evolutions have explored some interesting correlations of the world-wide events; for example, successive extreme weather phenomenon occur in different locations - typhoon in Hong Kong and Philippines followed hurricane and storm flood in Mexico in September 2013.

Mobile phones with embedded sensors have been applied in various collaborative sensing applications. To encourage mobile phone users to perform collaborative sensing, the data demanders usually pay mobile phone users for required data. In this paper, we study the Minimum Payment of Attaining the Required Data with mobile phones (MPARD) problem in collaborative sensing network: given sensing regions $$R = \{R_1, R_2, \ldots , R_m\}$$ R = { R 1 , R 2 , ? , R m } , the set of requisite data $$D_i$$ D i for each sensing region $$R_i$$ R i and a set of mobile phones $$M$$ M , the $$MPARD$$ M P A R D problem studies how to select mobile phones to obtain all the required data such that the data demanders' total payment to mobile phone users is minimized. In reality, some systems need the fresh sensing data from mobile phones at each pre-determined time slot, and others don't require the real-time data and the sensing data from previous time slots is also deemed useful. Based on the above two different requirements of data timeliness, we first define two subproblems derived from $$MPARD$$ M P A R D problem: $$MPARD_t$$ M P A R D t and $$MPARD_p$$ M P A R D p . After that, for each subproblem, we propose an approximation algorithm for the situation where the trajectories of mobile phones are determinate and a heuristic for the situation where trajectories are unknown. Simulation results demonstrate that our algorithms are efficient.

The widespread use of GPS navigations and trip planning on web has aroused considerable interests in fast and scalable path query processing. Existing research has mostly focused on static route optimization where the traffic network is assumed to be stable. Nevertheless, in most cases, route planning is in the presence of frequent updates to the traffic graph due to the dynamic nature of traffic network, and such updates always greatly affect the performance of route planning. Most existing methods, however, cannot efficiently support traffic aware route planning. In this paper, two efficient strategies are proposed to handle this problem. We analyze the traffic condition on the road network and explore spatio-temporal knowledge to guide effective route planning. In particular, several effective techniques are employed to avoid both unnecessary calculations on huge graph and excessive re-calculations caused by traffic condition updates. A comprehensive experiment is also conducted to evaluate the performance of our proposed strategies.

In recent years, large-scale events have been held frequently, and more and more people are participating in these activities. When encountering an emergency, it is necessary to quickly evacuate the participating people. A reasonable traffic evacuation plan is an important part of the efficient evacuation. However, the uneven geographical distribution of a large number of vehicles and participants poses a challenge for efficient evacuation planning. An efficient emergency evacuation plan needs to minimise evacuation time and traffic congestion. Reasonable route selection and traffic flow assessment are key to the evacuation plan. In this paper, we propose an efficient multi-vehicle navigation method based on trajectory vector features considering non-uniform destination distribution for emergency evacuation. First, we employ the CrossRank algorithm to extract the real-time state vector of roads and then navigate the vehicle based on these state vectors. In addition, spatial diversity theory is introduced into our model for the non-uniform distribution of multiple vehicle evacuation. We conduct a series of multi-vehicle navigation simulation experiment on a real taxi trajectory data set. The experimental results demonstrate that our approach is effective and efficient.

With proliferation of lightweight mobile devices such as mobile phones and explosion of location-based social networking services, there is a growing demand for matching between geographic locations and road networks on mobile devices. Nonetheless, existing methods for map matching only focus on accuracy and/or efficiency improvement, whereas they seldom take into account the capacity for storing map data and energy consumption during the matching process. This paper presents a method that is specifically designed for lightweight mobile devices with limited storage and computing resources, thereby providing an effective solution for map matching on mobile and embedded environments. Extensive experiments were carried out to compare proposed method against traditional approaches. The results indicate that our method can cut down the storage cost for road networks by 75 % compared to traditional methods, with only 3---5 % extra running time, which demonstrates the practical usefulness and superiority of our proposal in real-world mobile applications.

The tracking of moving objects consists of two critical operations: location reporting, in which moving objects (or clients) send their locations to centralized servers, and index maintenance, through which centralized servers update the locations of moving objects. In existing location reporting techniques, each moving object reports its locations to servers by utilizing long-distance links such as 3G/4G. Corresponding to this location reporting strategy, servers need to respond to all the location updating requests from individual moving objects. Such techniques suffer from very high communication cost (due to the individual reporting using long-distance links) and high index update I/Os (due to the massive amount of location updating requests). In this paper, we present a novel Group-movement based location Reporting and Indexing (GRI) framework for location reporting (at moving object side) and index maintenance (at server side). In the GRI framework, we introduce a novel location reporting strategy which allows moving objects to report their locations to servers in a group (instead of individually) by aggregating the moving objects that share similar movement patterns through wireless local links (such as WiFi). At the server side, we present a dual-index, Hash-GTPR-tree (H-GTPR), to index objects sharing similar movement patterns. Our experimental results on synthetic and real data sets demonstrate the effectiveness and efficiency of our new GRI framework, as well as the location reporting strategy and the H-GTPR tree index technique.