An adaptive spatial outlier detection algorithm with no parameter for WSN

Author(s):  
Wenping Xu ◽  
Hongju Gao ◽  
Yanzhe Liu ◽  
Li Li
2021 ◽  
Vol 13 (5) ◽  
pp. 2780
Author(s):  
Rayane El Sibai ◽  
Khalil Challita ◽  
Jacques Bou Abdo ◽  
Jacques Demerjian

The benefits of having a Bike Sharing System (BSS) in a city are numerous. Among other advantages, it promotes a cleaner environment with less traffic and pollution. One major problem the users of such services encounter is that of full or empty stations, causing user dissatisfaction. The objective of this work is to propose a new user-based incentive method to enhance BSS performance. The proposed method relies on a spatial outlier detection algorithm. It consists of adapting the departure and arrival stations of the users to the BSS state by stimulating the users to change their journeys in view of minimizing the number of full and empty stations. Experiments are carried out to compare our proposed method to some existing methods for enhancing the resource availability of BSSs, and they are performed on a real dataset issued from a well-known BSS called Velib. The results show that the proposed strategy improves the availability of BSS resources, even when the collaboration of users is partial.


IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 43271-43284
Author(s):  
Xite Wang ◽  
Jiafan Li ◽  
Mei Bai ◽  
Qian Ma

2021 ◽  
pp. 1-10
Author(s):  
Xuying Sun ◽  
Yu Zhang

The importance of the management of ideological and political theory courses in colleges and universities is objective to the importance of ideological and political theory courses. At present, the management of ideological and political theory courses in colleges and universities has big problems in both macro and micro aspects. This paper combines artificial intelligence technology to build an intelligent management system for ideological and political education in colleges and universities based on artificial intelligence, and conducts classroom supervision through intelligent recognition of student status. The KNN outlier detection algorithm based on KD-Tree is proposed to extract the state information of class students. Through data simulation, it can be known that the KD-KNN outlier detection algorithm proposed in this paper significantly improves the efficiency of the algorithm while ensuring the accuracy of the KNN algorithm classification. Through experimental research, it can be seen that the construction of this system not only clarifies the direction of management from a macro perspective, but also reveals specific methods of management from a micro perspective, and to a certain extent effectively solves the problems in the management of ideological and political theory courses in colleges and universities.


2009 ◽  
Vol 13 (1) ◽  
pp. 85-107 ◽  
Author(s):  
Vandana P. Janeja ◽  
Vijayalakshmi Atluri

Sign in / Sign up

Export Citation Format

Share Document