Chameleon: Online Clustering of MPI Program Traces

2018 ◽  
Author(s):  
Amir Bahmani ◽  
Frank Mueller
Keyword(s):  
Online Clustering ◽  
Program Traces

On the use of online clustering for anomaly detection in trace streams

2021 ◽  
Author(s):  
Renato Vertuam Neto ◽  
Gabriel Tavares ◽  
Paolo Ceravolo ◽  
Sylvio Barbon
Keyword(s):  
Anomaly Detection ◽  
Online Clustering

scholarly journals Data Stream Online Clustering Based on Fuzzy Expectation-Maximization Approach

2018 ◽  
Author(s):  
Anastasiia O. Deineko ◽  
Polina Ye. Zhernova ◽  
Boris Gordon ◽  
Oleksandr O. Zayika ◽  
Iryna Pliss ◽  
...  
Keyword(s):  
Expectation Maximization ◽  
Data Stream ◽  
Online Clustering

Online Clustering for Novelty Detection and Concept Drift in Data Streams

2019 ◽  
pp. 448-459
Author(s):  
Kemilly Dearo Garcia ◽  
Mannes Poel ◽  
Joost N. Kok ◽  
André C. P. L. F. de Carvalho
Keyword(s):  
Data Streams ◽  
Concept Drift ◽  
Novelty Detection ◽  
Online Clustering

Anomaly Detection in Video Surveillance via Gaussian Process

2015 ◽  
Vol 29 (06) ◽  
pp. 1555011 ◽  
Author(s):  
Nannan Li ◽  
Xinyu Wu ◽  
Huiwen Guo ◽  
Dan Xu ◽  
Yongsheng Ou ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Regression Model ◽  
Gaussian Process ◽  
Video Surveillance ◽  
Gaussian Process Regression ◽  
Bayesian Regression ◽  
Current Frame ◽  
Motion Patterns ◽  
Online Clustering ◽  
Efficient Calculation

In this paper, we propose a new approach for anomaly detection in video surveillance. This approach is based on a nonparametric Bayesian regression model built upon Gaussian process priors. It establishes a set of basic vectors describing motion patterns from low-level features via online clustering, and then constructs a Gaussian process regression model to approximate the distribution of motion patterns in kernel space. We analyze different anomaly measure criterions derived from Gaussian process regression model and compare their performances. To reduce false detections caused by crowd occlusion, we utilize supplement information from previous frames to assist in anomaly detection for current frame. In addition, we address the problem of hyperparameter tuning and discuss the method of efficient calculation to reduce computation overhead. The approach is verified on published anomaly detection datasets and compared with other existing methods. The experiment results demonstrate that it can detect various anomalies efficiently and accurately.

Sign in / Sign up

Export Citation Format

Share Document