English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

To solve the problem of mechanisms’ delay in early warning for unexpected public security incidents, this paper proposed a highly effective time series sparse representation for determining early warning for public incidents on the basis of position and reinforcement learning. Fractal and sparse were introduced to denote multi-dimensional time series, which effectively reduced the dimensions of time series while avoiding their distortion. Reinforcement learning was used to build the model of early warning for public incidents. Paths to anomaly series or early warning for public incidents were obtained by the agent through iteration training. Then weight parameters of neural networks were analyzed for the determination of early warning for incidents. Simulation showed that under this algorithm, convergence happened when the number of steps was in the range from 500 to 800, 37.5% smaller than that when using the original data. This result of the experiment demonstrated that this method greatly improved the efficiency of early warning for public incidents. Introduction In recent years, mass emergencies in taxi industry become increasingly severe such as taxi drivers’ strikes, appealing to higher authorities for help, and conflicts. The urgency of such emergencies is that it may trigger larger-scale conflict nationwide. Reality shows that complete traditional way of experience-based management, simple punishments like fines and confiscation of property, and postevent responses now cannot cope with relevant mass emergencies in an effective and timely manner. Therefore, it is undoubtedly highly valuable both theoretically and practically to construct an early warning model to prevent such conflicts with information about conflict triggering by finding the correlation between key factors and emergencies and digging up possible potential emergencies from considerable time series generated by travelling cars. Threats to Public security are not presented instantly but evolve with time. If signals of faults could be captured before the occurrence of events, the early warning system for threats can detect anomaly as soon as possible and take early warning measures after comparing abnormal data with normal ones[1]. Hence, how to make use of considerable historical data to obtain dynamic parameter weight in public events and to predict the occurrence probability of public events is the technical issue of this paper. The advantages of the proposed method in this paper for determining dynamic parameters of the early warning model are as follows: First, public events were denoted by time series, which were then dimensionally reduced. After the dimension reduction, the time series met the principle of no false negative[2], which meant that the treated data still satisfied the lower bound lemma: ) , ( ) , ( s q D s q DF  (1) The Euclidean distance between time series after the treatment of dimension reduction should not be longer than their original distance. In the above lemma, q denoted query sequence; s, random series in the time series cluster; DF, the distance between two spatial time series after dimension reduction; and D, the real distance between the two time series.

Sparse Time Series Representation in Public Events Early Warning Model