Unsupervised Anomaly Detection Using Variational Auto-Encoder based Feature Extraction

Ye, Rong; Liu, Chongdang; Zhang, Linxuan; Peng, Peng

doi:10.1109/icphm.2019.8819434

Cited by 55 publications

(35 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To answer this challenge, an unsupervised anomaly detection model should be implemented [ 31 ]. Utilizing the variational autoencoder (VAE) as a generative model can identify abnormalities by mapping the time-series data into a latent variable and reconstructing them through the latent variable [ 32 ]. In a VAE model, the encoder and decoder are defined by the probabilistic function of q ( z | x , Ɵ ) and p ( z , Ɵ ), respectively.…”

Section: Methodsmentioning

confidence: 99%

“…The variable z is assigned to a Gaussian distribution with defined parameters of mean and variance N ( µ x ,σ 2 x ). After the encoding process, the underlying characteristic of the input is generated by sampling from the Gaussian distribution (z*) that is reconstructed during the decoding process as described in Figure 1 [ 32 ].…”

Section: Methodsmentioning

confidence: 99%

“…In supervised anomaly detection, the label approach is used to identify the anomalous and normal samples using the labels 1 and 0, respectively. In contrast, for unsupervised anomaly detection, the score approach is used to identify the confidence value between 0 and 1, which reflects the likelihood of an instance being anomalous [ 32 ].…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Understanding User Behavior Through the Use of Unsupervised Anomaly Detection: Proof of Concept Using Internet of Things Smart Home Thermostat Data for Improving Public Health Surveillance

Jalali¹,

Sahu²,

Oetomo³

et al. 2020

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

Background One of the main concerns of public health surveillance is to preserve the physical and mental health of older adults while supporting their independence and privacy. On the other hand, to better assist those individuals with essential health care services in the event of an emergency, their regular activities should be monitored. Internet of Things (IoT) sensors may be employed to track the sequence of activities of individuals via ambient sensors, providing real-time insights on daily activity patterns and easy access to the data through the connected ecosystem. Previous surveys to identify the regular activity patterns of older adults were deficient in the limited number of participants, short period of activity tracking, and high reliance on predefined normal activity. Objective The objective of this study was to overcome the aforementioned challenges by performing a pilot study to evaluate the utilization of large-scale data from smart home thermostats that collect the motion status of individuals for every 5-minute interval over a long period of time. Methods From a large-scale dataset, we selected a group of 30 households who met the inclusion criteria (having at least 8 sensors, being connected to the system for at least 355 days in 2018, and having up to 4 occupants). The indoor activity patterns were captured through motion sensors. We used the unsupervised, time-based, deep neural-network architecture long short-term memory-variational autoencoder to identify the regular activity pattern for each household on 2 time scales: annual and weekday. The results were validated using 2019 records. The area under the curve as well as loss in 2018 were compatible with the 2019 schedule. Daily abnormal behaviors were identified based on deviation from the regular activity model. Results The utilization of this approach not only enabled us to identify the regular activity pattern for each household but also provided other insights by assessing sleep behavior using the sleep time and wake-up time. We could also compare the average time individuals spent at home for the different days of the week. From our study sample, there was a significant difference in the time individuals spent indoors during the weekend versus on weekdays. Conclusions This approach could enhance individual health monitoring as well as public health surveillance. It provides a potentially nonobtrusive tool to assist public health officials and governments in policy development and emergency personnel in the event of an emergency by measuring indoor behavior while preserving privacy and using existing commercially available thermostat equipment.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Understanding User Behavior Through the Use of Unsupervised Anomaly Detection: Proof of Concept Using Internet of Things Smart Home Thermostat Data for Improving Public Health Surveillance

Jalali¹,

Sahu²,

Oetomo³

et al. 2020

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

show abstract

“…VAE system does not only pursue an accurate reconstruction of original signals but also require the distribution of latent space that obeys a specific probability distribution (usually normal distribution). Existing works show that VAE may outperform the more traditional AE based system for anomaly detection [14]. However, as VAEs are used as generative models in most cases, this paper proposes to use β-VAE [15] that enables controls on the balance between the reconstruction loss and the distribution in latent space.…”

Section: Literature Reviewmentioning

confidence: 99%

Unsupervised Heart Abnormality Detection Based on Phonocardiogram Analysis with Beta Variational Auto-Encoders

Tian

Wang

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Heart Sound (also known as phonocardiogram (PCG)) analysis, is a popular way that detects cardiovascular diseases (CVDs). Most PCG analysis uses supervised way, which demands both normal and abnormal samples. This paper proposes a method of unsupervised PCG analysis that uses beta variational auto-encoder (β − VAE) to model the normal PCG signals. The best performed model reaches an AUC (Area Under Curve) value of 0.91 in ROC (Receiver Operating Characteristic) test for PCG signals collected from the same source. Unlike majority of β − VAEs that are used as generative models, the best-performed β − VAE has a β value smaller than 1. This fact demonstrates that the resampling process helps the improvements on anomaly PCG detection through reconstruction loss worth a heavier weight. Further investigations suggest that anomaly score based on reconstruction loss may be better than anomaly scores based on latent vectors of samples in PCG analysis based on VAE systems.

show abstract

“…Two relatively recent approaches for detecting anomalies are employing variational autoencoders (VAEs) and generative adversarial networks (GANs). A variational autoencoder represents the input data by extracting new features that can remove noise and redundant information [ 138 ], which can also be used for dimensionality reduction. It has been used in a variety of applications.…”

Section: Solutions For Minimising Impact Of Covid‐19mentioning

confidence: 99%

Data‐driven operation of the resilient electric grid: A case of COVID‐19

Noorazar

Srivastava

Pannala

et al. 2021

The Journal of Engineering

View full text Add to dashboard Cite

Electrical energy is a vital part of modern life, and expectations for grid resilience to allow a continuous and reliable energy supply has tremendously increased even during adverse events (e.g. Ukraine cyberattack, Hurricane Maria). The global pandemic COVID‐19 has raised the electric energy reliability risk due to potential workforce disruptions, supply chain interruptions, and increased possible cybersecurity threats. Additionally, the pandemic introduces a significant degree of uncertainty to the grid operation in the presence of other challenges including aging power grids, high proliferation of distributed generation, market mechanism, and active distribution network. This situation increases the need for measures for the resiliency of power grids to mitigate the impact of the pandemic as well as simultaneous extreme events including cyberattacks and adverse weather events. Solutions to manage such an adverse scenario will be multi‐fold: (a) emergency planning and organisational support, (b) following safety protocol, (c) utilising enhanced automation and sensing for situational awareness, and (d) integration of advanced technologies and data points for ML‐driven enhanced decision support. Enhanced digitalisation and automation resulted in better network visibility at various levels, including generation, transmission, and distribution. These data or information can be employed to take advantage of advanced machine learning techniques for automation and increased power grid resilience. In this paper, the resilience of power grids in the face of pandemics is explored and various machine learning tools that can be helpful to augment human operators are discused by: (a) reviewing the impact of COVID‐19 on power grid operations and actions taken by operators/organisations to minimise the impact of COVID‐19, and (b) presenting recently developed tools and concepts of machine learning and artificial intelligence that can be applied to increase the resiliency of power systems in normal and extreme scenarios such as the COVID‐19 pandemic.

show abstract

Unsupervised Anomaly Detection Using Variational Auto-Encoder based Feature Extraction

Cited by 55 publications

References 20 publications

Understanding User Behavior Through the Use of Unsupervised Anomaly Detection: Proof of Concept Using Internet of Things Smart Home Thermostat Data for Improving Public Health Surveillance

Understanding User Behavior Through the Use of Unsupervised Anomaly Detection: Proof of Concept Using Internet of Things Smart Home Thermostat Data for Improving Public Health Surveillance

Unsupervised Heart Abnormality Detection Based on Phonocardiogram Analysis with Beta Variational Auto-Encoders

Data‐driven operation of the resilient electric grid: A case of COVID‐19

Contact Info

Product

Resources

About