In contemporary urban management, the rapid advancement of technology and widespread use of location-based services provide critical insights, particularly in traffic planning. Analyzing urban spatiotemporal trajectory data reveals diverse perspectives that inform effective city management. This paper focuses on extracting insights from spatiotemporal trajectories and introduces a suite of urban data mining techniques applicable across scenarios, including points of interest diversification. The framework aids in understanding city dynamics, including the distribution and activities of individuals. The method begins by constructing spatiotemporal stay information through two processes: stay point and stay area extraction. Spatiotemporal semantic trajectory data is then integrated with Points of Interest (POI) semantic details. A novel clustering method based on network community detection is proposed. Our experiments show that the method not only achieves comparable or superior results but also ensures time efficiency, aligning with the demands of the big data era. © 2025 IEEE.

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. © Published under licence by IOP Publishing Ltd.

Differentiable architecture search (DARTS) is a promising end to end NAS method which directly optimizes the architecture parameters through general gradient descent. However, DARTS is brittle to the catastrophic failure incurred by the skip connection in the search space. Recent studies also cast doubt on the basic underlying hypotheses of DARTS which are argued to be inherently prone to the performance discrepancy between the continuous-relaxed supernet in the training phase and the discretized finalnet in the evaluation phase. We Figure out that the robustness problem and the skepticism can both be explained by the information bypass leakage during the training of the supernet. This naturally highlights the vital role of the sparsity of architecture parameters in the training phase which has not been well developed in the past. We thus propose a novel sparse-regularized approximation and an efficient mixed-sparsity training scheme to robustify DARTS by eliminating the information bypass leakage. We subsequently conduct extensive experiments on multiple search spaces to demonstrate the effectiveness of our method. © 2021 IEEE.

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.
© Published under licence by IOP Publishing Ltd.

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. © 2020 IEEE.

The fire of the XPS foams on the building facade is a big threat since their fast burning with melting, dripping and flowing. This work developed an image processing algorithm to track the flowing sub-flame and extract the dynamic flame leading curves. The flame leading edges were extracted with Moore-Neighbor tracing algorithm and the image close operation. The image morphology operation was used to locate the candidate flowing sub-flames, and the true melting sub-flames were identified by SVM and a critical distance to the flame leading edge. The moving trajectory of flowing molten sub-flame was obtained through the db-scan method. The results show a wave-like movement of the flame leading curves. The disturbance to the flame leading curve is more obvious for the bigger dripping at the lower locations. The flowing sub-flames can be well tracked by this image processing method. The results indicate that the size of the flowing sub-flames is close to the lognormal distribution. © 2020 IEEE.

COVID-19 arouses worldwide attention because huge health costs and economic losses it has caused. Different countries have adopted different control measures. This article explores the main factors affecting the spread of COVID-19 by the fault tree analysis (FTA) method. A government response score table is developed on this basis. Government responses of 14 countries are collected for assessment and are categorized into five groups according to their scores. The suitable functions are fitted to the trend curve piecewise. Correlation between typical patterns of government response and epidemic trends are analyzed. It was found that a rigorous government response will shorten the time to the peak of confirmed curves and accelerate end of the epidemic. This study will improve our understanding of government response measures to COVID-19 and enhance our emergency response capabilities in the future. © 2020 ACM.

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. © 2020 IEEE.

To solve the problem of route planning for security patrol in smart communities, a simulation framework comprising of multi-agent based model and genetic algorithm (GA) has been proposed for community patrol. The GA is used to determine and evolve the route collection and find the optimal results, while multi-agent simulation model can be used to set constraints and get the objective values of routes. First of all, in view of the traditional directed graph model is insufficient to describe the route information, GIS map is used as the environment of the community patrol inspection, which can efficiently reflect the environment features and facilitate the expansion of traffic and road information. Secondly, the task nodes are visited by the movement of the person agent. The implementation of the simulation system is based on Anylogic, which is beneficial for interacting GA program code. Simulation results show that not only the designed multi-agent system can obtain the optimal results, but also the route planning process is intuitive and visible, which meets the requirements of dynamic route planning. © 2020 IEEE.

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.
© 2020 IEEE.