Trajectory data is becoming more and more popular nowadays and extensive studies have been conducted on trajectory data. One important research direction about trajectory data is the anomaly detection which is to find all anomalies based on trajectory patterns in a road network. In this paper, we introduce a road segment-based anomaly detection problem, which is to detect the abnormal road segments each of which has its "real" traffic deviating from its "expected" traffic and to infer the major causes of anomalies on the road network. First, a deviation-based method is proposed to quantify the anomaly of reach road segment. Second, based on the observation that one anomaly from a road segment can trigger other anomalies from the road segments nearby, a diffusionbased method based on a heat diffusion model is proposed to infer the major causes of anomalies on the whole road network. To validate our methods, we conduct intensive experiments on a large real-world GPS dataset of about 23,000 taxis in Shenzhen, China to demonstrate the performance of our algorithms.
With rapid economic growth, city sizes are expanding, and city traffic flow is surging. Thus traffic congestion, traffic accidents, and serious air pollution are becoming more common. Priority has been given to the development of urban public transportation policy by using GPS, GIS, the internet, and communication technology to realize the collection, transmission, storage, and processing of the massive historical and real-time data gathered from bus IC cards, in order to build an intelligent, modern city public transport dispatching platform that will solve social problems such as urban traffic congestion, energy shortages, and air pollution. In addition, when passengers choose a reasonable travel plan, they can lessen not only their travel costs but can also increase the efficiency of public transport vehicles. Therefore, the choice of a reasonable bus route is of great importance to the daily operation and management of urban traffic.In recent years both in China and abroad, urban public transport has been the subject of extensive research and discussion. However, there are still many complaints about crowded buses, the length of waiting time, and the unpunctuality of the buses. How to effectively and efficiently recommend comfortable bus routes to bus passengers is a challenging and complex task. To address this critical challenge, we must consider factors reflecting the passengers' demands such as waiting time, crowded time, and driving time. To recommend comfortable bus routes for bus passengers, we suggest using multi-objective programming with various constraints and have developed a genetic algorithm to search for solutions. As a result, a bus route according to the differing requirements of passengers can be recommended.The rest of the paper is organized as follows. In Section 2, we review related work on the data processing of bus IC cards and personalized information recommendation services. In Section 3, we present a multiobjective program with various constraints to recommend comfortable bus routes for bus passengers and use a genetic algorithm to search for solutions. In Section 4, we discuss our implementation and empirical analysis of the proposed method. Finally, we conclude the paper and point out future research directions. With the generation of massive data from bus IC cards, how to effectively and efficiently recommend comfortable bus routes to bus passengers is a challenging and complex task. In this paper, waiting time, crowded time, and driving time between different bus stations on different bus routes at different times of the day are calculated from bus IC cards data history. Then, a multiobjective program with various constraints is suggested to recommend comfortable bus routes for bus passengers, and a genetic algorithm is developed to search for expected solutions. The proposed method is implemented using bus IC cards data from Chongqing, China and will be a promising tool for bus passengers when choosing comfortable bus routes. PROCEEDINGS PAPER
Determining whether a site has a search interface is a crucial priority for further research of deep web databases. This study first reviews the current approaches employed in search interface identification for deep web databases. Then, a novel identification scheme using hybrid features and a feature-weighted instance-based learner is put forward. Experiment results show that the proposed scheme is satisfactory in terms of classification accuracy and our feature-weighted instance-based learner gives better results than classical algorithms such as C4.5, random forest and KNN.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.