Technology Category
Intelligent Robots: State EstimationData Mining & Knowledge Management: Anomaly/Outlier DetectionMachine Learning: Calibration & Uncertainty Quantification
Outlier Detection of Poisson-Distributed Targets Using a Seabed Sensor Network
🤖 AI Summary
This paper addresses spatial anomaly detection for Poisson-distributed targets in underwater acoustic sensor networks. We propose a hybrid modeling framework based on the Log-Gaussian Cox Process (LGCP) that jointly characterizes the spatial generative mechanisms of both normal and anomalous events, enabling probabilistic anomaly estimation. A key contribution is the introduction of a mean–variance second-order approximation for the log-intensity field, rigorously justified via Jensen’s inequality to demonstrate its superiority over first-order approximations—thereby significantly improving estimation accuracy. Furthermore, we design a real-time, near-optimal dynamic sensor deployment strategy to enhance monitoring efficacy. Experiments conducted on real-world vessel trajectory data from the Norfolk海域 confirm substantial improvements: our method achieves higher anomaly detection accuracy and greater sensor deployment efficiency compared to state-of-the-art baselines.
Technology Category
Application Category
📝 Abstract
This paper presents a framework for classifying and detecting spatial commission outliers in maritime environments using seabed acoustic sensor networks and log Gaussian Cox processes (LGCPs). By modeling target arrivals as a mixture of normal and outlier processes, we estimate the probability that a newly observed event is an outlier. We propose a second-order approximation of this probability that incorporates both the mean and variance of the normal intensity function, providing improved classification accuracy compared to mean-only approaches. We analytically show that our method yields a tighter bound to the true probability using Jensen's inequality. To enhance detection, we integrate a real-time, near-optimal sensor placement strategy that dynamically adjusts sensor locations based on the evolving outlier intensity. The proposed framework is validated using real ship traffic data near Norfolk, Virginia, where numerical results demonstrate the effectiveness of our approach in improving both classification performance and outlier detection through sensor deployment.
Problem
Research questions and friction points this paper is trying to address.
Detecting spatial outliers in maritime sensor networks
Classifying normal vs outlier events using probability estimation
Optimizing sensor placement for improved outlier detection
Innovation
Methods, ideas, or system contributions that make the work stand out.
Log Gaussian Cox processes model target arrivals
Second-order approximation improves classification accuracy
Dynamic sensor placement enhances outlier detection
🔎 Similar Papers
No similar papers found.
