AMIE: Automatic Monitoring of Indoor Exercises

Decroos, Tom; Schütte, Kurt; Beéck, Tim Op De; Vanwanseele, Benedicte; Davis, Jesse

doi:10.1007/978-3-030-10997-4_26

Cited by 12 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Continuous variables are discretised using equalwidth binning. 5 Pav has no parameters. MatrixProfile has a single parameter, the window size.…”

Section: Methodsmentioning

confidence: 99%

“…Then, the goal is to accurately detect the minority exercise. Before applying the algorithms, we use the methodology outlined in [5] to preprocess the raw data and further reduce the number of dimensions of S to 3. Note that the baseline algorithms are not naturally equipped to deal with multivariate time series.…”

Section: Anomaly Detection In Multivariate Time Seriesmentioning

confidence: 99%

See 1 more Smart Citation

Pattern-Based Anomaly Detection in Mixed-Type Time Series

Feremans

Vercruyssen

Čule

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The present-day accessibility of technology enables easy logging of both sensor values and event logs over extended periods. In this context, detecting abnormal segments in time series data has become an important data mining task. Existing work on anomaly detection focuses either on continuous time series or discrete event logs and not on the combination. However, in many practical applications, the patterns extracted from the event log can reveal contextual and operational conditions of a device that must be taken into account when predicting anomalies in the continuous time series. This paper proposes an anomaly detection method that can handle mixed-type time series. The method leverages frequent pattern mining techniques to construct an embedding of mixedtype time series on which an isolation forest is trained. Experiments on several real-world univariate and multivariate time series, as well as a synthetic mixed-type time series, show that our anomaly detection algorithm outperforms state-of-the-art anomaly detection techniques such as MatrixProfile, Pav, Mifpod and Fpof.

show abstract

“…Continuous variables are discretised using equalwidth binning. 5 Pav has no parameters. MatrixProfile has a single parameter, the window size.…”

Section: Methodsmentioning

confidence: 99%

Section: Anomaly Detection In Multivariate Time Seriesmentioning

confidence: 99%

Pattern-Based Anomaly Detection in Mixed-Type Time Series

Feremans

Vercruyssen

Čule

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In this section, we will illustrate our framework, implemented in Tipm, to mine a multivariate dataset. The time series dataset that was obtained by using a Kinect sensor to track the body movements during indoor physical exercises [1]. The goal is to assist people in performing exercises correctly.…”

Section: Methodsmentioning

confidence: 99%

A Framework for Pattern Mining and Anomaly Detection in Multi-dimensional Time Series and Event Logs

Vercruyssen

Meert

Čule

et al. 2020

New Frontiers in Mining Complex Patterns

View full text Add to dashboard Cite

In the present-day, sensor data and textual logs are generated by many devices. Analyzing these time series data leads to the discovery of interesting patterns and anomalies. In recent years, numerous algorithms have been developed to discover interesting patterns in time series data as well as detect periods of anomalous behaviour. However, these algorithms are challenging to apply in real-world settings. We propose a framework, consisting of generic transformations, that allows to combine state-ofthe-art time series representation, pattern mining, and pattern-based anomaly detection algorithms. Using an early-or late integration, our framework handles a mix of multi-dimensional continuous series and event logs. Finally we present an open-source, lightweight, interactive tool that assists both pattern mining and domain experts to select algorithms, specify parameters, and visually inspect the results, while shielding them from the underlying technical complexity of implementing our framework.

show abstract

“…Overall, preprocessing can improve assessment accuracy by making the input data comparable and easier to analyze. Nonetheless, it is time-consuming [34] and therefore, each application should examine which of these steps to apply.…”

Section: A Data Collection and Preprocessingmentioning

confidence: 99%

“…Of those that used an automated approach, 16/34 performed segmentation using peak detection of specific sensor values (e.g., the velocity of a specific angle or values from one axis of the accelerometer) [21], [30], [31], [32], [33], [58], [63], [66], [76], [79], [88], [91], [105], [115], [116], [119]. Other approaches included using the Euclidean distance between a body segment and a predefined reference position [34], [102], or through pattern-matching algorithms such as HMM [89], [90], and DTW [100].…”

Section: ) Preprocessingmentioning

confidence: 99%

Assessing Human Motion During Exercise Using Machine Learning: A Literature Review

et al. 2022

View full text Add to dashboard Cite

The World Health Organization promotes healthy living through regular physical activities, such as exercise and sports, as well as access to healthcare and rehabilitation services for people with motor dysfunctions. However, there is a lack of specialized personnel and increased costs associated with such activities. These have led to the increased use of machine learning for the analysis and evaluation of human motion during exercise. To study the latest advancements in this area, a systematic literature review focusing on publications from 2017 to 2021 was performed. As a result, 88 relevant publications were identified, which developed both shallow machine learning and deep learning algorithms. The results indicated that algorithms for human motion assessment should provide personalized and informative assessments, with explainable and interpretable outcomes, that can be computed in real-time or concurrently with the execution of an exercise. Furthermore, they should be easy to adapt based on the needs of applications and should be able to perform with different motion capture systems. This has been challenging because of the usually small amount of collected data, the lack of large open datasets, and the unique characteristics of exercise motions. Based on the above findings, guidelines for the development of such algorithms are proposed and discussed. They relate to the selection of the type of assessment, handling data imbalances, selecting of motion capture technologies, balancing between accuracy and speed, selecting the right algorithm, performing concurrent assessment during an exercise, personalization and scalability, and evaluation.

show abstract

AMIE: Automatic Monitoring of Indoor Exercises

Cited by 12 publications

References 27 publications

Pattern-Based Anomaly Detection in Mixed-Type Time Series

Pattern-Based Anomaly Detection in Mixed-Type Time Series

A Framework for Pattern Mining and Anomaly Detection in Multi-dimensional Time Series and Event Logs

Assessing Human Motion During Exercise Using Machine Learning: A Literature Review

Contact Info

Product

Resources

About