Multivariate time series anomaly detection: A framework of Hidden Markov Models

Li, Jinbo; Pedrycz, Witold; Jamal, Iqbal

doi:10.1016/j.asoc.2017.06.035

Cited by 117 publications

(41 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is important to be able to identify anomalous changes as they may represent early opportunities for outreach and relapse prevention. While time-series methods for multivariate anomaly detection have been developed, such as methods which transform the multivariate time series to a univariate function or statistic [24,25], or network-based methods [26][27][28], these approaches are not equipped to handle the missing observations that frequently arise when collecting active and passive smartphone data from patient populations.…”

Section: Methodsmentioning

confidence: 99%

Relapse prediction in schizophrenia through digital phenotyping: a pilot study

Barnett

Torous

Staples

et al. 2018

Neuropsychopharmacol

323

226

View full text Add to dashboard Cite

Among individuals diagnosed, hospitalized, and treated for schizophrenia, up to 40% of those discharged may relapse within 1 year even with appropriate treatment. Passively collected smartphone behavioral data present a scalable and at present underutilized opportunity to monitor patients in order to identify possible warning signs of relapse. Seventeen patients with schizophrenia in active treatment at a state mental health clinic in Boston used the Beiwe app on their personal smartphone for up to 3 months. By testing for changes in mobility patterns and social behavior over time as measured through smartphone use, we were able to identify statistically significant anomalies in patient behavior in the days prior to relapse. We found that the rate of behavioral anomalies detected in the 2 weeks prior to relapse was 71% higher than the rate of anomalies during other time periods. Our findings show how passive smartphone data, data collected in the background during regular phone use without active input from the subjects, can provide an unprecedented and detailed view into patient behavior outside the clinic. Real-time detection of behavioral anomalies could signal the need for an intervention before an escalation of symptoms and relapse occur, therefore reducing patient suffering and reducing the cost of care.

show abstract

Section: Methodsmentioning

confidence: 99%

Relapse prediction in schizophrenia through digital phenotyping: a pilot study

Barnett

Torous

Staples

et al. 2018

Neuropsychopharmacol

323

226

View full text Add to dashboard Cite

show abstract

“…Often, these approaches require a transformation be carried out on the data in order to generate a useful feature representation [ 19 , 20 , 21 ]. However, deep learning-based methods benefit by not requiring this step.…”

Section: Introductionmentioning

confidence: 99%

A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors

Cowton

Kyriazakis

Plötz

et al. 2018

Sensors

View full text Add to dashboard Cite

We designed and evaluated an assumption-free, deep learning-based methodology for animal health monitoring, specifically for the early detection of respiratory disease in growing pigs based on environmental sensor data. Two recurrent neural networks (RNNs), each comprising gated recurrent units (GRUs), were used to create an autoencoder (GRU-AE) into which environmental data, collected from a variety of sensors, was processed to detect anomalies. An autoencoder is a type of network trained to reconstruct the patterns it is fed as input. By training the GRU-AE using environmental data that did not lead to an occurrence of respiratory disease, data that did not fit the pattern of “healthy environmental data” had a greater reconstruction error. All reconstruction errors were labelled as either normal or anomalous using threshold-based anomaly detection optimised with particle swarm optimisation (PSO), from which alerts are raised. The results from the GRU-AE method outperformed state-of-the-art techniques, raising alerts when such predictions deviated from the actual observations. The results show that a change in the environment can result in occurrences of pigs showing symptoms of respiratory disease within 1–7 days, meaning that there is a period of time during which their keepers can act to mitigate the negative effect of respiratory diseases, such as porcine reproductive and respiratory syndrome (PRRS), a common and destructive disease endemic in pigs.

show abstract

“…In these models, a time series is assumed to maintain a steady-state transition pattern that can be modeled as a stable property. This stable model is normally realized as a Markov model, a hidden Markov model (HMM) [10], or a finite-state machine (FSM) [11]. Over the years, numerous studies have been undertaken to exploit the state-transition models for sequential-data anomaly detection.…”

Section: State-transition Modelsmentioning

confidence: 99%

KPI-TSAD: A Time-Series Anomaly Detector for KPI Monitoring in Cloud Applications

Qiu

Qian

2019

Symmetry

View full text Add to dashboard Cite

Accurately detecting anomalies and timely interventions are critical for cloud application maintenance. Traditional methods for performance anomaly detection based on thresholds and rules work well for simple key performance indicator (KPI) monitoring. Unfortunately, it is difficult to find the appropriate threshold levels when there are significant differences between KPI values at different times during the day or when there are significant fluctuations stemming from different usage patterns. Therefore, anomaly detection presents a challenge for all types of temporal data, particularly when non-stationary time series have special adaptability requirements or when the nature of potential anomalies is vaguely defined or unknown. To address this limitation, we propose a novel anomaly detector (called KPI-TSAD) for time-series KPIs based on supervised deep-learning models with convolution and long short-term memory (LSTM) neural networks, and a variational auto-encoder (VAE) oversampling model was used to address the imbalanced classification problem. Compared with other related research on Yahoo’s anomaly detection benchmark datasets, KPI-TSAD exhibited better performance, with both its accuracy and F-score exceeding 0.90 on the A1benchmark and A2Benchmark datasets. Finally, KPI-TSAD continued to perform well on several KPI monitoring datasets from real production environments, with the average F-score exceeding 0.72.

show abstract

Multivariate time series anomaly detection: A framework of Hidden Markov Models

Cited by 117 publications

References 33 publications

Relapse prediction in schizophrenia through digital phenotyping: a pilot study

Relapse prediction in schizophrenia through digital phenotyping: a pilot study

A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors

KPI-TSAD: A Time-Series Anomaly Detector for KPI Monitoring in Cloud Applications

Contact Info

Product

Resources

About