Filters








1,066 Hits in 3.4 sec

An Unsupervised Approach to Anomaly Detection in Music Datasets

Yen-Cheng Lu, Chih-Wei Wu, Chang-Tien Lu, Alexander Lerch
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
This paper presents an unsupervised method for systematically identifying anomalies in music datasets.  ...  When applied to a music genre recognition dataset, the new method is able to detect corrupted, distorted, or mislabeled audio samples based on commonly used features in music information retrieval.  ...  In this paper, we propose an unsupervised approach to address this problem and to detect the anomalies in music datasets.  ... 
doi:10.1145/2911451.2914700 dblp:conf/sigir/LuWLL16 fatcat:dogpxumtoraopfv32dejpvmf6u

Learning from Usage Analysis of Mobile Devices

Subhankar Mishra
2020 Procedia Computer Science  
In this paper, a novel approach of user behavior detection is proposed with Deep Learning Network (DNN).  ...  In this paper, a novel approach of user behavior detection is proposed with Deep Learning Network (DNN).  ...  This is similar to the approach followed by [15] for anomaly detection in network logs.  ... 
doi:10.1016/j.procs.2020.03.375 fatcat:u23i47bbprendpx3em5k33a52i

Hubness in Unsupervised Outlier Detection Techniques for High Dimensional Data –A Survey

R.Lakshmi Devi, R. Amalraj
2015 International Journal of Computer Applications Technology and Research  
Outlier detection in high dimensional data becomes an emerging technique in today's research in the area of data mining.  ...  This survey article, discusses some important aspects of the hubness in detail and presents a comprehensive review on the state-of-the-art specialized algorithms for unsupervised outlier detection for  ...  The paper [32] proposes a new approach for unsupervised outlier detection in high dimensional data.  ... 
doi:10.7753/ijcatr0411.1004 fatcat:l3lxmvua2je7xpvxnp7k7ni2pa

Unsupervised Detection of Anomalous Sound for Machine Condition Monitoring using Fully Connected U-Net

Hoang Van Truong, Nguyen Chi Hieu, Pham Ngoc Giao, Nguyen Xuan Phong
2021 Journal of ICT Research and Applications  
Anomaly detection in the sound from machines is an important task in machine monitoring.  ...  An autoencoder architecture based on the reconstruction error using a log-Mel spectrogram feature is a conventional approach for this domain.  ...  In order to detect anomalies in sounds through machine learning, we can use supervised methods or unsupervised methods.  ... 
doi:10.5614/itbj.ict.res.appl.2021.15.1.3 fatcat:yo7rnabjl5hsbidh5uxzulzxz4

Improving unsupervised anomaly localization by applying multi-scale memories to autoencoders [article]

Yifei Yang, Shibing Xiang, Ruixiang Zhang
2020 arXiv   pre-print
Autoencoder and its variants have been widely applicated in anomaly detection.The previous work memory-augmented deep autoencoder proposed memorizing normality to detect anomaly, however it neglects the  ...  module of the autoencoder for anomaly detection, namely MMAE.MMAE updates slots at corresponding resolution scale as prototype features during unsupervised learning.  ...  detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection.  ... 
arXiv:2012.11113v1 fatcat:zmt6qecypvbe3ltm7unyv2tucm

Outlier Detection with Explanations on Music Streaming Data: A Case Study with Danmark Music Group Ltd

Jonas Herskind Sejr, Thorbjørn Christiansen, Nicolai Dvinge, Dan Hougesen, Peter Schneider-Kamp, Arthur Zimek
2021 Applied Sciences  
In collaboration with Danmark Music Group Ltd. we developed an unsupervised system for this problem based on a predictive neural network.  ...  We discuss the challenges in unsupervised parameter tuning and show that the system could be further improved with personalization and integration of additional information, unrelated to the raw outlier  ...  Acknowledgments: The authors would like to acknowledge Henrik Vistisen, Erhvervshus Midtjylland, for initiating and facilitating the collaboration between Danmark Music Group Ltd. and Department of Mathematics  ... 
doi:10.3390/app11052270 fatcat:dvv266rg3nhuhnxr5pm2ejviui

Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples [article]

Paul Primus, Verena Haunschmid, Patrick Praher, Gerhard Widmer
2020 arXiv   pre-print
As a consequence, most anomaly detection methods use unsupervised rather than supervised machine learning methods.  ...  Unsupervised anomalous sound detection is concerned with identifying sounds that deviate from what is defined as 'normal', without explicitly specifying the types of anomalies.  ...  To show that our approach can be applied in an unsupervised AD setting (i.e., without explicitly defining anomalies), we make no assumptions on the nature of anomalies and presume only normal data and  ... 
arXiv:2011.02949v1 fatcat:c4otvq45nzentkvktqkx3flp7u

MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks [article]

Dan Li, Dacheng Chen, Lei Shi, Baihong Jin, Jonathan Goh, and See-Kiong Ng
2019 arXiv   pre-print
In this work, we propose an unsupervised multivariate anomaly detection method based on Generative Adversarial Networks (GANs).  ...  On the other hand, current unsupervised machine learning approaches have not fully exploited the spatial-temporal correlation and other dependencies amongst the multiple variables (sensors/actuators) in  ...  Due to the inherent lack of labeled data, anomaly detection is typically treated as an unsupervised machine learning task.  ... 
arXiv:1901.04997v1 fatcat:cl2oslliybeyrp4hqcvokuvxgi

Group Anomaly Detection: Past Notions, Present Insights, and Future Prospects

Aqeel Feroze, Ali Daud, Tehmina Amjad, Malik Khizar Hayat
2021 SN Computer Science  
We have also listed the datasets used in various studies to detect group anomalies along with detected anomalies and the various performance measures used to validate the results.  ...  Anomaly detection is also a crucial problem in processing large-scale datasets when our goal is to find abnormal values or unusual events.  ...  A certain activity in a particular dataset that is beyond normal is an anomaly.  ... 
doi:10.1007/s42979-021-00603-x fatcat:oyjzthza7vbhnakpm3t2ko6ctq

An Ameliorated method for Fraud Detection using Complex Generative Model: Variational Autoencoder

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
The current Supervised and Unsupervised Machine Learning Algorithm approaches to the discovery of fraud are their inability to learn and explore all possible information representation.  ...  The VAE based fraud detection model consists of three major layers, an encoder, a decoder and a fraud detector element.  ...  The unsupervised approach of machine learning is able to detect all the unseen anomalies in the data and able to tackle the dynamic nature of fraudster.  ... 
doi:10.35940/ijitee.b1005.1292s19 fatcat:seg34ssutbbqzktx6o52hcmfni

Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning [article]

Robert Müller, Fabian Ritz, Steffen Illium, Claudia Linnhoff-Popien
2020 arXiv   pre-print
We then use these features to train a variety of anomaly detection models and show that this improves results compared to convolutional autoencoders in recordings of four different factory machines in  ...  In our setting, Gaussian Mixture Models and One-Class Support Vector Machines achieve the best anomaly detection performance.  ...  The remaining paper is structured as follows: In Section 2, we survey related approaches to acoustic anomaly detection in an unsupervised learning learning setting.  ... 
arXiv:2006.03429v2 fatcat:comzhbsfbbeibirmotbenzxlzy

Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series [article]

Dan Li and Dacheng Chen and Jonathan Goh and See-kiong Ng
2019 arXiv   pre-print
possible anomalies in the complex CPS.  ...  In this work, we proposed a novel Generative Adversarial Networks-based Anomaly Detection (GAN-AD) method for such complex networked CPSs.  ...  to detect anomalies due to cyber attacks being carried out against the CPS in an unsupervised fashion.  ... 
arXiv:1809.04758v3 fatcat:lj24chtitba2lfyhxjnxbu556u

Concept Drift Challenge in Multimedia Anomaly Detection: A Case Study with Facial Datasets [article]

Pratibha Kumari, Priyankar Choudhary, Pradeep K. Atrey, Mukesh Saini
2022 arXiv   pre-print
Anomaly detection in multimedia datasets is a widely studied area. Yet, the concept drift challenge in data has been ignored or poorly handled by the majority of the anomaly detection frameworks.  ...  In this paper, we systematically investigate the effect of concept drift on various detection models and propose a modified Adaptive Gaussian Mixture Model (AGMM) based framework for anomaly detection  ...  Kumari and Saini [2] used AGMM based adaptive framework for anomaly detection in an untrimmed video dataset.  ... 
arXiv:2207.13430v1 fatcat:nreac5rmvvazlhvkstvu2ivczu

Guest Editorial

Eamonn Keogh
2005 Machine Learning  
In addition, similarity measurement is an important subroutine in all clustering algorithms and many classification, prediction, association detection, summarization, motif discovery, and anomaly detection  ...  This is very important since data mining is often touted as an interactive and iterative process. Begnum and Burgess consider the problem of anomaly detection in computer systems.  ... 
doi:10.1007/s10994-005-5822-9 fatcat:zshgwl4mwbenpfdnzpu3dzdi64

An Adaptive Framework for Anomaly Detection in Time-series Audio-visual Data

Pratibha Kumari, Mukesh Saini
2022 IEEE Access  
Anomaly detection is an integral part of a number of surveillance applications.  ...  As a result, their usefulness is limited to controlled scenarios. In this paper, we fuse information from live streams of audio and video data to detect anomalies in the captured environment.  ...  UNSUPERVISED ANOMALY DETECTION Unsupervised approaches for anomaly detection have been in research focus for the past few years [4] .  ... 
doi:10.1109/access.2022.3164439 fatcat:xmpmdssshvdg3lbjvjp6nmj5ti
« Previous Showing results 1 — 15 out of 1,066 results