Understanding maritime traffic patterns is key to Maritime Situational Awareness applications, in particular, to classify and predict activities. Facilitated by the recent build-up of terrestrial networks and satellite constellations of Automatic Identification System (AIS) receivers, ship movement information is becoming increasingly available, both in coastal areas and open waters. The resulting amount of information is increasingly overwhelming to human operators, requiring the aid of automatic processing to synthesize the behaviors of interest in a clear and effective way. Although AIS data are only legally required for larger vessels, their use is growing, and they can be effectively used to infer different levels of contextual information, from the characterization of ports and off-shore platforms to spatial and temporal distributions of routes. An unsupervised and incremental learning approach to the extraction of maritime movement patterns is presented here to convert from raw data to information supporting decisions. This is a basis for automatically detecting anomalies and projecting current trajectories and patterns into the future. The proposed methodology, called TREAD (Traffic Route Extraction and Anomaly Detection) was developed for different levels of intermittency (i.e., sensor coverage and performance), persistence (i.e., time lag between subsequent observations) and data sources (i.e., ground-based and space-based receivers).

/pdf/vessel-pattern-knowledge-discovery-from-ais-data-a-framework-4gewii0fzv.pdf

Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction

To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e.g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation. However, anomaly detection for these seasonal KPIs with various patterns and data quality has been a great challenge, especially without labels. In this paper, we proposed Donut, an unsupervised anomaly detection algorithm based on VAE. Thanks to a few of our key techniques, Donut greatly outperforms a state-of-arts supervised ensemble approach and a baseline VAE approach, and its best F-scores range from 0.75 to 0.9 for the studied KPIs from a top global Internet company. We come up with a novel KDE interpretation of reconstruction for Donut, making it the first VAE-based anomaly detection algorithm with solid theoretical explanation.

Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications

A method for fabricating a liquid crystal display (LCD) device comprises forming an active pattern and a data line on a substrate, the active pattern including a source, a drain, and a channel regions; a first insulation film on a portion of the substrate; forming a gate electrode in a portion of the active pattern where the first insulation film is formed; a second insulation film on the substrate; forming a plurality of first contact holes exposing a portion of the source and drain regions and a second contact hole exposing a portion of the data line; forming a source electrode from a transparent conductive material connected to a source region within the respective first contact hole and a data line within the second contact hole; and forming a pixel and a drain electrodes from the transparent conductive material connected to a drain region within the respective first contact hole.

Liquid crystal display device and fabricating method thereof

The automatic identification system (AIS) tracks vessel movement by means of electronic exchange of navigation data between vessels, with onboard transceiver, terrestrial, and/or satellite base stations. The gathered data contain a wealth of information useful for maritime safety, security, and efficiency. Because of the close relationship between data and methodology in marine data mining and the importance of both of them in marine intelligence research, this paper surveys AIS data sources and relevant aspects of navigation in which such data are or could be exploited for safety of seafaring, namely traffic anomaly detection, route estimation, collision prediction, and path planning.

Exploiting AIS Data for Intelligent Maritime Navigation: A Comprehensive Survey From Data to Methodology

Detection of anomalous trajectories is an important problem in the surveillance domain. Various algorithms based on learning of normal trajectory patterns have been proposed for this problem. Yet, these algorithms typically suffer from one or more limitations: They are not designed for sequential analysis of incomplete trajectories or online learning based on an incrementally updated training set. Moreover, they typically involve tuning of many parameters, including ad-hoc anomaly thresholds, and may therefore suffer from overfitting and poorly-calibrated alarm rates. In this article, we propose and investigate the Sequential Hausdorff Nearest-Neighbor Conformal Anomaly Detector (SHNN-CAD) for online learning and sequential anomaly detection in trajectories. This is a parameter-light algorithm that offers a well-founded approach to the calibration of the anomaly threshold. The discords algorithm, originally proposed by Keogh et al. , is another parameter-light anomaly detection algorithm that has previously been shown to have good classification performance on a wide range of time-series datasets, including trajectory data. We implement and investigate the performance of SHNN-CAD and the discords algorithm on four different labeled trajectory datasets. The results show that SHNN-CAD achieves competitive classification performance with minimum parameter tuning during unsupervised online learning and sequential anomaly detection in trajectories.

Online Learning and Sequential Anomaly Detection in Trajectories

This paper presents a first attempt to evaluate two previously proposed methods for statistical anomaly detection in sea traffic, namely the Gaussian Mixture Model (GMM) and the adaptive Kernel Density Estimator (KDE). A novel performance measure related to anomaly detection, together with an intermediate performance measure related to normalcy modeling, are proposed and evaluated using recorded AIS data of vessel traffic and simulated anomalous trajectories. The normalcy modeling evaluation indicates that KDE more accurately captures finer details of normal data. Yet, results from anomaly detection show no significant difference between the two techniques and the performance of both is considered suboptimal. Part of the explanation is that the methods are based on a rather artificial division of data into geographical cells. The paper therefore discusses other clustering approaches based on more informed features of data and more background knowledge regarding the structure and natural classes of the data.

/pdf/anomaly-detection-in-sea-traffic-a-comparison-of-the-59sh2smtj2.pdf

Anomaly detection in sea traffic - A comparison of the Gaussian Mixture Model and the Kernel Density Estimator

The so-called mixed labelling problem inherent to a joint state multitarget particle filter implementation is treated. The mixed labelling problem would be prohibitive for track extraction from a joint state multitarget particle filter. It is shown, using the theory of Markov chains, that the mixed labelling problem in a particle filter is inherently self-resolving. It is also shown that the factors influencing this capability are the number of particles and the number of resampling steps. Extensive quantitative analyses of these influencing factors are provided.

Mixed Labelling in Multitarget Particle Filtering

In order to achieve greater situation awareness it is necessary to identify relations between individual entities and their immediate surroundings, neighboring entities and important landmarks. The idea is that long-term intentions and situations can be identified by patterns of more rudimentary behavior, in essence situations formed by combinations of different basic relationships. In this paper we present a rule based situation assessment system that utilizes both COTS and in-house software. It is built upon an agent framework that speeds up development times, since it takes care of many of the infrastructural issues of such a communication intense application as this is, and a rule based reasoner that can reason about situations that develop over time. The situation assessment system is developed to be simple, but structurally close to an operational system, with connections to outside data sources and graphical editors and data displays. It is developed with a specific simple Sea-surveillance scenario in mind, which we also present, but the ideas behind the system are general and are valid for other areas as well.

Rule-based situation assessment for sea surveillance

The present invention is in general related to automatic alignment in multi-sensor target tracking. The process of the invention repeatedly generates estimates for sensor bias errors (b) by minimising a function, given on one hand by the magnitude of the discrepancy between measurements (M) and a measuring model, where the measuring model is a function of the unknown target location and unknown bias parameters, and on the other by the bias parameters and their predetermined statistical distributions (15). In a preferred embodiment of the present invention, the minimising step is performed by linearising components of the function around an approximate target position (normally obtained from the tracker (10)) and around nominal (typically zero) bias errors, and the function is subsequently minimised with respect to target positions as well as to the bias parameters (b). In addition, possible time dependence of the bias parameters are modelled by the incorporation of process noise.

Bias estimating method for a target tracking system

In this paper we will consider several algorithms for tracking closely spaced objects. In particular we will concentrate on various particle filter implementations. One particular problem when using a joint multi target particle filter is the so-called mixed labelling problem. This problem amounts to the fact that different particles will have a different labelling w.r.t. target identity. The combination of the mixed labelling problem and naive or straightforward track extraction leads to performance degradation. This will be illustrated and alternative methods to alleviate this effect will be presented.

Egils Sviestins

Papers

Anomaly detection in sea traffic - A comparison of the Gaussian Mixture Model and the Kernel Density Estimator

Mixed Labelling in Multitarget Particle Filtering

Rule-based situation assessment for sea surveillance

Bias estimating method for a target tracking system

Particle filters for tracking closely spaced targets