Spatio-temporal outlier detection algorithms based on computing behavioral outlierness factor

Duggimpudi, Maria Bala; Abbady, Shaaban; Chen, Jian; Raghavan, Vijay V.

doi:10.1016/j.datak.2017.12.001

Cited by 17 publications

(20 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Density-based spatial clustering of applications with noise (DBSCAN) is a classic method of clustering of applications with noise (DBSCAN) is a classic method of clustering. Duggimpudi et al [20] analyzed the limitation of DBSCAN and proposed ST-DBSCAN and spatio-temporal behavioural outlier factor (ST-BOF) as the spatio-temporal extension of local outlier factor (LOF) to reduce the loss of detection accuracy during processing. General Potential Data Field (GPDf)-based trajectory clustering scheme has been adopted for detecting abnormal events such as illegal U-turn, wrong side and unusual driving behaviours, and it uses spatial and temporal attributes explicitly.…”

Section: B Abnormal Trajectory Detectionmentioning

confidence: 99%

A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Nowadays, massive data has been brought by the rapid development of technology. When finding whether trajectory to be detected is abnormal under the premise of given normal trajectories, we innovatively propose 1) Seq2Seq model based on LSTM prediction network for trajectory modelling (SL-Modelling), and 2) abnormal trajectory detection method with spatio-temporal and semantic information. Firstly, SL-Modelling is used to obtain sequence-type trajectory models of normal trajectory groups directly for subsequent detection with no need to extract a large number of features manually and adapting to different sequence length. Then we introduce the concept of distance and semantic interest sequence that makes full use of spatio-temporal and semantic information of trajectories. Finally, the similarity between models and trajectory to be detected is calculated to detect abnormal trajectory. The experimental results of publicly available flight data set show that trajectory models obtained are descriptive enough to represent normal trajectory groups well, and the accuracy of modelling is higher than the existing advanced methods. Besides, the detection with spatio-temporal and semantic information has been verified that it has stronger detection ability with higher accuracy and takes less time.

show abstract

Section: B Abnormal Trajectory Detectionmentioning

confidence: 99%

A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the past few years, some density-and clustering-based unsupervised spatio-temporal anomaly detection algorithms have been developed. The most prominent ones are ST-Outlier detection algorithm [5] and ST-BDBCAN [6] methods which are basically an extension of DBSCAN [7], a density-based spatial clustering algorithm. LDBSCAN [8], a locality-based outlier detection algorithm, is the merge of both DBSCAN and Local Outlier Factor (LOF) [9].…”

Section: Introductionmentioning

confidence: 99%

“…We compared the proposed model with the state-of-the-art spatial and spatio-temporal anomaly detection algorithms: ST-Outlier detection algorithm [5], ST-BDBCAN [6], LDBSCAN [8], LOF [9], and to a powerful model-based anomaly detection method, IsolationForest [10]. We conducted extensive experiments using the year 2005 Gulf of Mexico (West) buoy dataset from National Data Buoy Center (https://www.ndbc.noaa.gov/) and Hurricane Katrina best track path data [13] as ground truth for the experiments.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Deep Learning Framework for Unsupervised Anomaly Detection in Multivariate Spatio-Temporal Data

2020

View full text Add to dashboard Cite

Multivariate time-series data with a contextual spatial attribute have extensive use for finding anomalous patterns in a wide variety of application domains such as earth science, hurricane tracking, fraud, and disease outbreak detection. In most settings, spatial context is often expressed in terms of ZIP code or region coordinates such as latitude and longitude. However, traditional anomaly detection techniques cannot handle more than one contextual attribute in a unified way. In this paper, a new hybrid approach based on deep learning is proposed to solve the anomaly detection problem in multivariate spatio-temporal dataset. It works under the assumption that no prior knowledge about the dataset and anomalies are available. The architecture of the proposed hybrid framework is based on an autoencoder scheme, and it is more efficient in extracting features from the spatio-temporal multivariate datasets compared to the traditional spatio-temporal anomaly detection techniques. We conducted extensive experiments using buoy data of 2005 from National Data Buoy Center and Hurricane Katrina as ground truth. Experiments demonstrate that the proposed model achieves more than 10% improvement in accuracy over the methods used in the comparison where our model jointly processes the spatial and temporal dimensions of the contextual data to extract features for anomaly detection.

show abstract

“…Boxplots of the scale (a), position (b) and shape (c) parameters of the GEV distribution, with their outlier because the analyses of the boxplots enabled the detection of possible outliers, it was determined that the presence of outliers was detrimental to semivariogram modeling, as observed inFeld et al (2016),Duggimpudi et al (2017),St. Luce et al (2014),Mingoti & Rosa (2008),Tobin et al (2011) andTeixeira & Scalon (2014).…”

mentioning

confidence: 99%

Spatialization of the Annual Maximum Daily Rainfall in Southeastern Brazil

et al. 2019

View full text Add to dashboard Cite

Extreme rainfall can lead to heavy damage and losses, such as landslides, floods and agricultural productivity as well as the loss of human and animal lives. To mitigate these losses, water resources management policies are needed, among other goals, to study and predict the frequency of such events in a given region to minimize their harmful effects. The present study investigated the Generalized Extreme Value (GEV) probability distribution applied to the annual maximum daily precipitation data from rainfall stations in the southeastern Brazil. A total of 1,921 rainfall stations were considered, among which the stations with at least 15 years of uninterrupted observations were selected. Subsequently, the stationarity and adherence were tested. GEV probability distribution parameters were then estimated. The results enabled satisfactory spatial interpolation by ordinary kriging and the generation of maps of the distribution parameters. The semivariogram model with the best fit to the three GEV distribution parameters was the exponential model.

show abstract

Spatio-temporal outlier detection algorithms based on computing behavioral outlierness factor

Cited by 17 publications

References 27 publications

A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection

A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection

A Hybrid Deep Learning Framework for Unsupervised Anomaly Detection in Multivariate Spatio-Temporal Data

Spatialization of the Annual Maximum Daily Rainfall in Southeastern Brazil

Contact Info

Product

Resources

About