Filters








876 Hits in 6.7 sec

Using UMAP to Inspect Audio Data for Unsupervised Anomaly Detection under Domain-Shift Conditions [article]

Andres Fernandez, Mark D. Plumbley
2021 arXiv   pre-print
Manifold Approximations and Projections (UMAPs) for log-STFT, log-mel and pretrained Look, Listen and Learn (L3) representations of the DCASE UAD-S dataset.  ...  The goal of Unsupervised Anomaly Detection (UAD) is to detect anomalous signals under the condition that only non-anomalous (normal) data is available beforehand.  ...  We also computed 512-dimensional Look, Listen and Learn (L3) embeddings with a hop size of 0.1 seconds using openl3 [27] .  ... 
arXiv:2107.10880v2 fatcat:ru6op4432fgobnj7qlho7euge4

A design-driven sonification process for supporting expert users in real-time anomaly detection: Towards applied guidelines

S. Lenzi, G. Terenghi, A. Moreno-Fernandez-de-Leceta
2018 EAI Endorsed Transactions on Creative Technologies  
INTRODUCTION: We present early results of an ongoing investigation into the use of sound for real-time monitoring of anomalous behaviour in digital and digital/physical systems.  ...  CONCLUSION: We sketch a tentative design-driven process for sonifications for the real-time monitoring of anomalous behaviour in digital and digital/physical systems.  ...  Damiano Meacci (Conservatorio di Bologna) for their help in the development of the second Design Action prototype in Max/MSP.  ... 
doi:10.4108/eai.13-7-2018.163994 fatcat:p7vmgg77pnhzzavk3765iqusju

Sonification in security operations centres: what do security practitioners think? [article]

Louise M. Axon and Bushra Alahmadi and Jason R. C. Nurse and Michael Goldsmith and Sadie Creese
2018 arXiv   pre-print
In Security Operations Centres (SOCs) security practitioners work using a range of tools to detect and mitigate malicious computer-network activity.  ...  For example, sonification has been shown to enable peripheral monitoring of processes, which could aid practitioners multitasking in busy SOCs.  ...  that on for five minutes, and it sounds anomalous, then I know there's five minutes' worth of packets worth looking at.  ... 
arXiv:1807.06706v1 fatcat:aaf6xvdjgjh73apvmductvs5te

Data presentation in security operations centres: exploring the potential for sonification to enhance existing practice

Louise Axon, Bushra A AlAhmadi, Jason R C Nurse, Michael Goldsmith, Sadie Creese
2020 Journal of Cybersecurity  
Security practitioners working in Security Operations Centres (SOCs) are responsible for detecting and mitigating malicious computer network activity.  ...  Participants saw potential value in using sonification systems to aid in anomaly detection tasks in SOCs (such as retrospective hunting), as well as in situations in which peripheral monitoring is desirable  ...  an IDS [6] and than three leading anomaly detection systems that use machine learning [7] .  ... 
doi:10.1093/cybsec/tyaa004 dblp:journals/cybersecurity/AxonANGC20 fatcat:4hkaq6o6pzefzliu3pizbfi7b4

Smart Grid Cyber Security Challenges: Overview and Classification

Jacob Mendel
2017 e-mentor  
Analysis and simulation results demonstrate that the proposed IDS provides good detection performance against known attacks, and since this is an IDS based on anomalous event detection, we expect the same  ...  In this paper we present a model-based intrusion detection system (IDS) for home area networks (HANs) within the smart grid.  ...  Following the discussion in Section 3.3, we avoid using machine learning approaches such as SVM.  ... 
doi:10.15219/em68.1282 fatcat:meuln77yn5fphmcza6xrw5f6wa

Empathic Computing [chapter]

Yang Cai
2006 Lecture Notes in Computer Science  
As a case study, we focus on the wearable sensor network for anomalous event detection at home.  ...  Healthcare systems are looking for an easy and costeffective way to collect and transmit data from a patient's home.  ...  Franco, Xavier Boutonnier and Yongxiang Hu.  ... 
doi:10.1007/11825890_3 fatcat:s3e5kti6rffx5kxtm6a4wtbngm

Fully Learnable Deep Wavelet Transform for Unsupervised Monitoring of High-Frequency Time Series [article]

Gabriel Michau and Gaetan Frusque and Olga Fink
2021 arXiv   pre-print
High-Frequency (HF) signals are ubiquitous in the industrial world and are of great use for monitoring of industrial assets.  ...  We demonstrate the benefits of embedding all these properties on three machine-learning tasks performed on open source sound datasets.  ...  PP00P2-176878 and by the Innosuisse grant no. 27662.1 PFES-ES. The authors would like to thank Christoph Preisinger for his preliminary explorations of the proposed methodology.  ... 
arXiv:2105.00899v2 fatcat:srd3fvtrhzh3relhcriigdeh4a

Open Set Audio Classification Using Autoencoders Trained on Few Data

Javier Naranjo-Alcazar, Sergi Perez-Castanos, Pedro Zuccarello, Fabio Antonacci, Maximo Cobos
2020 Sensors  
This paper proposes an audio OSR/FSL system divided into three steps: a high-level audio representation, feature embedding using two different autoencoder architectures and a multi-layer perceptron (MLP  ...  Another problem arising in practical scenarios is few-shot learning (FSL), which appears when there is no availability of a large number of positive samples for training a recognition system.  ...  The objective can be to detect machine faults only by monitoring the sound produced by these machines.  ... 
doi:10.3390/s20133741 pmid:32635378 pmcid:PMC7374438 fatcat:nl3iuuijpjhnxic6nyvkgm57ba

Lexical viability constraints on speech segmentation by infants

E Johnson
2003 Cognitive Psychology  
In Experiments 1 and 2, infants were familiarized with target words (e.g., rush), then tested on lists of non-  ...  Five experiments using the head-turn preference procedure investigated whether, like adults, 12-month-olds observe this constraint in word recognition.  ...  The authors wish to thank Ann Marie Jusczyk and two anonymous review-  ... 
doi:10.1016/s0010-0285(02)00507-8 pmid:12646156 fatcat:f6abspmnzzd2hnaypus2qgeaa4

Grafting acoustic instruments and signal processing: Creative control and augmented expressivity

Dan Overholt
2013 Journal of the Acoustical Society of America  
In addition, various measurement techniques for this type of space are explored and reported. 9:15 1aAA2. The effect of two different rooms on acoustical and perceptual measures of mixed choir sound.  ...  In the spirit of the text Concert Halls and Opera Houses by L.  ...  Higher self noise, however, reduces detection range under quiet conditions and diminishes utility for noise monitoring.  ... 
doi:10.1121/1.4830794 fatcat:2sexsmbypjcozjctnorzoiy7te

Diagnostics for Monitoring Maintenance and Quality Manufacturing [chapter]

Rinaldo Michelini, Francesco Crenna, G Rossi
2000 Computer-Aided Design, Engineering, and Manufacturing  
thank all people who have contributed to this chapter through ideas, suggestions and technical information, in particuar:  ...  ACKNOWLEDGEMENTS We acknowledge the support of CNR (Italian National Research Council), project PFT2 (Progetto Finalizzato Trasporti 2), for the studies on innovative vibration signatures; we also would  ...  in use for product inspections.  ... 
doi:10.1201/9781420049893-c5 fatcat:xwu3j54s25hitp2wcueiooti2u

Driver Inattention Monitoring System for Intelligent Vehicles: A Review

Yanchao Dong, Zhencheng Hu, Keiichi Uchimura, Nobuki Murayama
2011 IEEE transactions on intelligent transportation systems (Print)  
In this paper, we review the state-of-the-art technologies for driver inattention monitoring, which can be classified into the following two main categories: 1) distraction and 2) fatigue.  ...  We also discuss some nonlinear modeling techniques commonly used in the literature.  ...  The eye and head parameters were obtained using faceLAB, whereas the RRI data came from ECG. In [18] , two machine-learning techniques, SVM and Adaboost, were implemented under the same conditions.  ... 
doi:10.1109/tits.2010.2092770 fatcat:bgnlewweorguzhswkz4spwaeli

Driver inattention monitoring system for intelligent vehicles: A review

Yanchao Dong, Zhencheng Hu, Keiichi Uchimura, Nobuki Murayama
2009 2009 IEEE Intelligent Vehicles Symposium  
In this paper, we review the state-of-the-art technologies for driver inattention monitoring, which can be classified into the following two main categories: 1) distraction and 2) fatigue.  ...  We also discuss some nonlinear modeling techniques commonly used in the literature.  ...  The eye and head parameters were obtained using faceLAB, whereas the RRI data came from ECG. In [18] , two machine-learning techniques, SVM and Adaboost, were implemented under the same conditions.  ... 
doi:10.1109/ivs.2009.5164395 fatcat:3qxrxi3bqreqjisnjzces3btda

Neural Substrates of Language Acquisition

Patricia Kuhl, Maritza Rivera-Gaxiola
2008 Annual Review of Neuroscience  
For personal use only.  ...  Noninvasive, safe brain technologies have now been proven feasible for use with children starting at birth.  ...  ACKNOWLEDGMENTS The authors are supported by a grant from the National Science Foundation Science of Learning Center Program to the University of Washington LIFE Center, by grants to P.K. from the National  ... 
doi:10.1146/annurev.neuro.30.051606.094321 pmid:18558865 fatcat:usr63g2lmnfczo5pl3a5rgddqe

Nericell

Prashanth Mohan, Venkata N. Padmanabhan, Ramachandran Ramjee
2008 Proceedings of the 6th ACM conference on Embedded network sensor systems - SenSys '08  
We consider the problem of monitoring road and traffic conditions in a city.  ...  In this paper, we focus specifically on the sensing component, which uses the accelerometer, microphone, GSM radio, and/or GPS sensors in these phones to detect potholes, bumps, braking, and honking.  ...  Acknowledgements Several people wrote useful pieces of code that we have borrowed in our prototype of TrafficSense: Ramya Bharathi Nimmagadda (detecting user interaction with a phone), Nilesh Mishra (extracting  ... 
doi:10.1145/1460412.1460444 dblp:conf/sensys/MohanPR08 fatcat:y4chu5invfhcthzmrjt2pom5ma
« Previous Showing results 1 — 15 out of 876 results