A Probabilistic Tensor Factorization Approach to Detect Anomalies in Spatiotemporal Traffic Activities

Wang, Xudong; Fagette, Antoine; Sartelet, Pascal; Sun, Lijun

doi:10.1109/itsc.2019.8917169

Cited by 11 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other than mobility pattern mining, tensor factorization has a wide range of applications in more general spatiotemporal modelling tasks. Such as traffic data imputation [44,45,46,47], anomaly detection [43,48,49], and traffic prediction [50,51,52,53].…”

Section: Predictive Models To Forecast Mobility Demandmentioning

confidence: 99%

Machine learning and data mining for urban mobility intelligence

Côme¹,

Oukhellou²,

Samé³

et al. 2021

ESANN 2021 Proceedings

Self Cite

View full text Add to dashboard Cite

The last few decades have seen a faster development of digital systems for observing the mobility of people and goods. Various sensing systems -such as radio communication, Wi-Fi, Bluetooth, validation of smart cards, mobile phone, and road traffic monitoring systems -have enabled researchers and practitioners to acquire large amounts of data, which generally refer to individual and collective trajectories. The mobility data can be further enriched with side information, such as text corpora from social media, survey data, and weather information. These massive data, temporally and spatially structured, can benefit from advanced machine learning and data mining methods, providing decision aid tools, and contributing to the development of safer, cleaner, and more efficient transportation systems. They can also help to implement new mobility services for the user. This article provides an overview of methodological advances in temporal and spatial mobility data processing. Structural time series decomposition applied to mobility dataConsidering mobility data as time series, structural models [1] have been used to extract from them multiple latent components, each representing an aspect of 453

show abstract

Section: Predictive Models To Forecast Mobility Demandmentioning

confidence: 99%

Machine learning and data mining for urban mobility intelligence

Côme¹,

Oukhellou²,

Samé³

et al. 2021

ESANN 2021 Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…Anomalies can be viewed in two ways: (i) erroneous data generated due to device failure or system faults, and (ii) unusual data representing rare/exceptional activities/events which are anomalous but actually happened [23].Some of the anomalies linked to road networks include: vehicle collisions, vehicle breakdowns, debris on the road, pot holes, and vehicle(s) stopped in the middle of the road. Most of these can be attributed to driving behavior and the status of the road.…”

Section: Anomaly Detectionmentioning

confidence: 99%

Anomaly Detection on Roads Using C-ITS Messages

Moso

Boutahala

Leblanc

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Cooperative Intelligent Transport Network is one of the most challenging issue in networking and computer science. In this area, huge amount of data are exchanged. Smart analysis of this collected data could be achieved for many purposes: traffic prediction, driver profile detection, anomaly detection, etc. Anomaly detection is an important issue for road operators. An anomaly on roads could be caused by various reasons: potholes, obstacles, weather conditions, etc. An early detection of such anomalies will reduce incident risks such as traffic jams, accidents. The aim of this paper is to collect message exchanges between vehicles and analyze trajectories. This analysis becomes difficult since a privacy principle is applied in the case of C-ITS. Indeed, each message sent is generated with an identifier of the sender. This identifier is kept only over a specified time interval thus one vehicle will have multiple identifiers. We first have to solve Trajectory-User Linking problem by chaining anonymous trajectories to potential vehicles by considering similarity in movement patterns. After that we apply various methods to check variations of trajectories from normal ones. When we observe some differences, we can raise an alarm about a potential anomaly. In order to check the validity of this work, we generated a large amount of messages exchanges by many vehicles using the Omnet ++simulator together with the Artery, Sumo plug-in. We applied various variations on some obtained trajectories. Finally, we ran our detection algorithm on the obtained trajectories using different parameters (angles, speed, acceleration) and obtained very interesting results in terms of detection rate.

show abstract

“…Research works on anomaly detection have been reported and studied in various applications to find out patterns not consistent with predicted behaviors [6], [7]. In time series analysis, a lot of useful information is able to be extracted from dataset.…”

Section: Introductionmentioning

confidence: 99%

Traffic Anomaly Detection in Intelligent Transport Applications with Time Series Data using Informer

Peng

Lin

Cao

et al. 2022

2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

Multivariate time series traffic dataset is usually large with multiple feature dimensions for long time duration under certain time intervals or sampling rates. In applications such as intelligent transportation systems, some machine learning methods being applied to traffic anomaly detections are computed under certain assumptions and require further improvements. Transport traffic time series data may also suffer from unbalanced number of training data where large amount of labelled training data available for a few popular classes, but with very small amount of labelled data for corner cases. In this paper, based on the recent long sequences prediction method Informer, an anomaly detection algorithm with an anomaly score generator is proposed that does not require any assumptions of data. The encoder-decoder architecture is adopted in the anomaly score generator. The encoder consists of three stacking ProbSparse self-attention mechanisms that significantly reduce computing complexity. The decoder incorporates two multihead attention layers and a fully connected layer to obtain an output of anomaly scores. Then a One-Class Support Vector Machines (OCSVM) is applied to be the anomaly classifier. The proposed algorithm is capable of detecting anomalies for both vehicle traffic flows and pedestrian flows. It has been verified by applying to a real-world dataset consisting of traffic flows recorded in 2021, as well as to a public anomaly detection dataset.

show abstract

A Probabilistic Tensor Factorization Approach to Detect Anomalies in Spatiotemporal Traffic Activities

Cited by 11 publications

References 14 publications

Machine learning and data mining for urban mobility intelligence

Machine learning and data mining for urban mobility intelligence

Anomaly Detection on Roads Using C-ITS Messages

Traffic Anomaly Detection in Intelligent Transport Applications with Time Series Data using Informer

Contact Info

Product

Resources

About