VASP: An autoencoder-based approach for multivariate anomaly detection and robust time series prediction with application in motorsport

Schleinitz, Julian von; Graf, Michael; Trutschnig, Wolfgang; Schröder, Jörg

doi:10.1016/j.engappai.2021.104354

Cited by 19 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is especially clear when inspecting Tables 8 and 9, which are composed of mostly missing scores. Some publications investigate proprietary datasets exclusively (Que et al, 2019;Hsieh et al, 2019;Bayram et al, 2021;Lindemann et al, 2020;Park et al, 2018;Chen et al, 2020;von Schleinitz et al, 2021;Choi et al, 2020;Sun et al, 2019) and hence provide only a limited contribution to the state of the art, because the reader cannot properly assess relative anomaly detection performance. Another problem is that anomaly detection performance can be measured in different ways.…”

Section: Discussionmentioning

confidence: 99%

Online Time-series Anomaly Detection: A Survey of Modern Model-based Approaches

Correia

Goos

Kononova

et al. 2022

Preprint

View full text Add to dashboard Cite

This survey provides an extensive overview of the state-of-the-art model-based online semi-supervised and unsupervised anomaly detection algorithms used on multivariate time series. It also outlines the most popular benchmark datasets used in literature, as well as a novel taxonomy where a distinction between online and offline, and training and inference is made. To achieve this, almost 50 peer-reviewed publications are surveyed and categorised into different model families to paint a clear picture of the anomaly detection landscape for the reader. Then, where possible, a comparison of the anomaly detection performance of the surveyed approaches is provided and the key research gaps are highlighted. It is concluded that few approaches propose any enhancements that involve the user feedback. In addition to that, transformer-based models seem to have found little application in anomaly detection so far, though this is most likely due to the novelty of the model type, not necessarily due to the lack of potential. Moreover, there is no standard benchmark procedure to assess anomaly detection performance. A variety of different datasets and evaluation metrics used for evaluation are used hence it is difficult to draw conclusions from comparisons between papers. Lastly, the rarity of approaches trained and inferred in an online manner is also pointed out, possibly explained by the lower performance compared to offline trained approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

Online Time-series Anomaly Detection: A Survey of Modern Model-based Approaches

Correia

Goos

Kononova

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The environment where IoT devices are developed makes them vulnerable to failure and malfunction, leading to the generation of unusual and erroneous data [ 22 , 23 , 24 , 25 , 26 ]. On univariate or multivariate time series, anomaly detection is mainly performed through clustering or distance-based techniques [ 27 , 28 ], prediction [ 29 , 30 , 31 ], statistical approaches [ 32 , 33 ], deep learning methodologies using autoencoders [ 18 , 34 , 35 ], and neural networks [ 36 , 37 , 38 ]. In environmental datasets, the occurrence of high concentrations of an unusual pollutant may indicate air quality problems.…”

Section: Related Workmentioning

confidence: 99%

Anomaly Detection and Repairing for Improving Air Quality Monitoring

Rollo

Bachechi

2023

Sensors

View full text Add to dashboard Cite

Clean air in cities improves our health and overall quality of life and helps fight climate change and preserve our environment. High-resolution measures of pollutants’ concentrations can support the identification of urban areas with poor air quality and raise citizens’ awareness while encouraging more sustainable behaviors. Recent advances in Internet of Things (IoT) technology have led to extensive use of low-cost air quality sensors for hyper-local air quality monitoring. As a result, public administrations and citizens increasingly rely on information obtained from sensors to make decisions in their daily lives and mitigate pollution effects. Unfortunately, in most sensing applications, sensors are known to be error-prone. Thanks to Artificial Intelligence (AI) technologies, it is possible to devise computationally efficient methods that can automatically pinpoint anomalies in those data streams in real time. In order to enhance the reliability of air quality sensing applications, we believe that it is highly important to set up a data-cleaning process. In this work, we propose AIrSense, a novel AI-based framework for obtaining reliable pollutant concentrations from raw data collected by a network of low-cost sensors. It enacts an anomaly detection and repairing procedure on raw measurements before applying the calibration model, which converts raw measurements to concentration measurements of gasses. There are very few studies of anomaly detection in raw air quality sensor data (millivolts). Our approach is the first that proposes to detect and repair anomalies in raw data before they are calibrated by considering the temporal sequence of the measurements and the correlations between different sensor features. If at least some previous measurements are available and not anomalous, it trains a model and uses the prediction to repair the observations; otherwise, it exploits the previous observation. Firstly, a majority voting system based on three different algorithms detects anomalies in raw data. Then, anomalies are repaired to avoid missing values in the measurement time series. In the end, the calibration model provides the pollutant concentrations. Experiments conducted on a real dataset of 12,000 observations produced by 12 low-cost sensors demonstrated the importance of the data-cleaning process in improving calibration algorithms’ performances.

show abstract

“…The model is based on a LSTM neural network architecture, which has been used for time series prediction on a motorsport data set before [24]. The hyperparameters are listed in Table 2 and the architecture in Figure 5.…”

Section: Artificial Neural Network Architecturementioning

confidence: 99%

“…The cell state makes it easier for information to flow unchanged through multiple time steps. This results in the ability of the LSTM cells to learn long-term dependencies while avoiding the vanishing /exploding gradient problem [29,24].…”

Section: Artificial Neural Network Architecturementioning

confidence: 99%

Race Driver Evaluation at a Driving Simulator using a physical Model and a Machine Learning Approach

Schleinitz¹,

Schwarzhuber²,

Wörle³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Professional race drivers are still superior to automated systems at controlling a vehicle at its dynamic limit. Gaining insight into race drivers' vehicle handling process might lead to further development in the areas of automated driving systems. We present a method to study and evaluate race drivers on a driver-in-the-loop simulator by analysing tire grip potential exploitation. Given initial data from a simulator run, two optimiser based on physical models maximise the horizontal vehicle acceleration or the tire forces, respectively. An overall performance score, a vehicle-trajectory score and a handling score are introduced to evaluate drivers. Our method is thereby completely track independent and can be used from one single corner up to a large data set. We apply the proposed method to a motorsport data set containing over 1200 laps from seven professional race drivers and two amateur drivers whose lap times are 10 − 20% slower. The difference to the professional drivers comes mainly from their inferior handling skills and not their choice of driving line. A downside of the presented method for certain applications is an extensive computation time. Therefore, we propose a Long-short-term memory (LSTM) neural network to estimate the driver evaluation scores. We show that the neural network is accurate and robust with a root-mean-square error between 2 − 5% and can replace the optimisation based method. The time for processing the data set considered in this work is reduced from 68 hours to 12 seconds, making the neural network suitable for real-time application.

show abstract

VASP: An autoencoder-based approach for multivariate anomaly detection and robust time series prediction with application in motorsport

Cited by 19 publications

References 19 publications

Online Time-series Anomaly Detection: A Survey of Modern Model-based Approaches

Online Time-series Anomaly Detection: A Survey of Modern Model-based Approaches

Anomaly Detection and Repairing for Improving Air Quality Monitoring

Race Driver Evaluation at a Driving Simulator using a physical Model and a Machine Learning Approach

Contact Info

Product

Resources

About