Power grid middle platform data anomaly detection based on two-stream convolutional neural network

2021 ◽  
pp. 185-190
Author(s):  
H.Z. Cui ◽  
C. Wang ◽  
M.S. Xu ◽  
M.H. Xu
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Convolutional Neural Network ◽  
Power Grid

scholarly journals Combining Background Subtraction and Convolutional Neural Network for Anomaly Detection in Pumping-Unit Surveillance

Algorithms ◽  
2019 ◽  
Vol 12 (6) ◽  
pp. 115 ◽  
Author(s):  
Tianming Yu ◽  
Jianhua Yang ◽  
Wei Lu
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Convolutional Neural Network ◽  
Background Subtraction ◽  
Moving Objects ◽  
High Accuracy ◽  
Clustering Method ◽  
Subtraction Method ◽  
Video Scene ◽  
Pumping Unit

Background subtraction plays a fundamental role for anomaly detection in video surveillance, which is able to tell where moving objects are in the video scene. Regrettably, the regular rotating pumping unit is treated as an abnormal object by the background-subtraction method in pumping-unit surveillance. As an excellent classifier, a deep convolutional neural network is able to tell what those objects are. Therefore, we combined background subtraction and a convolutional neural network to perform anomaly detection for pumping-unit surveillance. In the proposed method, background subtraction was applied to first extract moving objects. Then, a clustering method was adopted for extracting different object types that had more movement-foreground objects but fewer typical targets. Finally, nonpumping unit objects were identified as abnormal objects by the trained classification network. The experimental results demonstrate that the proposed method can detect abnormal objects in a pumping-unit scene with high accuracy.

scholarly journals Convolutional neural network target detection in hyperspectral imaging for maritime surveillance

2019 ◽  
Vol 16 (3) ◽  
pp. 172988141984299
Author(s):  
Sara Freitas ◽  
Hugo Silva ◽  
José Miguel Almeida ◽  
Eduardo Silva
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Convolutional Neural Network ◽  
Unmanned Aerial Vehicles ◽  
Hyperspectral Imaging ◽  
Imaging System ◽  
Spectral Angle Mapper ◽  
Maritime Surveillance ◽  
Aerial Vehicles ◽  
Spectral Angle

This work addresses a hyperspectral imaging system for maritime surveillance using unmanned aerial vehicles. The objective was to detect the presence of vessels using purely spatial and spectral hyperspectral information. To accomplish this objective, we implemented a novel 3-D convolutional neural network approach and compared against two implementations of other state-of-the-art methods: spectral angle mapper and hyperspectral derivative anomaly detection. The hyperspectral imaging system was developed during the SUNNY project, and the methods were tested using data collected during the project final demonstration, in São Jacinto Air Force Base, Aveiro (Portugal). The obtained results show that a 3-D CNN is able to improve the recall value, depending on the class, by an interval between 27% minimum, to a maximum of over 40%, when compared to spectral angle mapper and hyperspectral derivative anomaly detection approaches. Proving that 3-D CNN deep learning techniques that combine spectral and spatial information can be used to improve the detection of targets classification accuracy in hyperspectral imaging unmanned aerial vehicles maritime surveillance applications.

scholarly journals Semi-Supervised Machine Condition Monitoring by Learning Deep Discriminative Audio Features

Electronics ◽  
2021 ◽  
Vol 10 (20) ◽  
pp. 2471
Author(s):  
Iordanis Thoidis ◽  
Marios Giouvanakis ◽  
George Papanikolaou
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Convolutional Neural Network ◽  
Condition Monitoring ◽  
Feature Learning ◽  
Detection Methods ◽  
Mechanical Equipment ◽  
Learning Approach ◽  
Audio Features ◽  
Front End

In this study, we aim to learn highly descriptive representations for a wide set of machinery sounds and exploit this knowledge to perform condition monitoring of mechanical equipment. We propose a comprehensive feature learning approach that operates on raw audio, by supervising the formation of salient audio embeddings in latent states of a deep temporal convolutional neural network. By fusing the supervised feature learning approach with an unsupervised deep one-class neural network, we are able to model the characteristics of each source and implicitly detect anomalies in different operational states of industrial machines. Moreover, we enable the exploitation of spatial audio information in the learning process, by formulating a novel front-end processing strategy for circular microphone arrays. Experimental results on the MIMII dataset demonstrate the effectiveness of the proposed method, reaching a state-of-the-art mean AUC score of 91.0%. Anomaly detection performance is significantly improved by incorporating multi-channel audio data in the feature extraction process, as well as training the convolutional neural network on the spatially invariant front-end. Finally, the proposed semi-supervised approach allows the concise modeling of normal machine conditions and accurately detects system anomalies, compared to existing anomaly detection methods.

scholarly journals Improving Water Quality Assessment through Anomaly Detection Using Hybrid Convolutional Neural Network Approach

2021 ◽  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Water Quality ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Convolutional Neural Network ◽  
Quality Assessment ◽  
Water Quality Assessment ◽  
Machine Learning Algorithms ◽  
Quality Analysis

<p>Water being a precious commodity for every person around the world needs to be quality monitored continuously for ensuring safety whilst usage. The water data collected from sensors in water plants are used for water quality assessment. The anomaly present in the water data seriously affects the performance of water quality assessment. Hence it needs to be addressed. In this regard, water data collected from sensors have been subjected to various anomaly detection approaches guided by Machine Learning (ML) and Deep Learning framework. Standard machine learning algorithms have been used extensively in water quality analysis and these algorithms in general converge quickly. Considering the fact that manual feature selection has to be done for ML algorithms, Deep Learning (DL) algorithm is proposed which involve implicit feature learning. A hybrid model is formulated that takes advantage of both and presented it is data invariant too. This novel Hybrid Convolutional Neural Network (CNN) and Extreme Learning Machine (ELM) approach is used to detect presence of anomalies in sensor collected water data. The experiment of the proposed CNN-ELM model is carried out using the publicly available dataset GECCO 2019. The findings proved that the model has improved the water quality assessment of the sensor water data collected by detecting the anomalies efficiently and achieves F1 score of 0.92. This model can be implemented in water quality assessment.</p>

Sign in / Sign up

Export Citation Format

Share Document