Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2211.08415v1
• Date: Sat, 12 Nov 2022 15:17:57 GMT
• Title: Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning
• Authors: Qianru Zhang, Zheng Wang, Cheng Long, Chao Huang, Siu-Ming Yiu, Yiding Liu, Gao Cong, Jieming Shi
• Abstract summary: We propose a novel reinforcement learning based solution called RL4OASD. RL4OASD involves two networks, one responsible for learning features of road networks and trajectories and the other responsible for detecting anomalous subtrajectories.
• Score: 38.71141801699763
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Detecting anomalous trajectories has become an important task in many location-based applications. While many approaches have been proposed for this task, they suffer from various issues including (1) incapability of detecting anomalous subtrajectories, which are finer-grained anomalies in trajectory data, and/or (2) non-data driven, and/or (3) requirement of sufficient supervision labels which are costly to collect. In this paper, we propose a novel reinforcement learning based solution called RL4OASD, which avoids all aforementioned issues of existing approaches. RL4OASD involves two networks, one responsible for learning features of road networks and trajectories and the other responsible for detecting anomalous subtrajectories based on the learned features, and the two networks can be trained iteratively without labeled data. Extensive experiments are conducted on two real datasets, and the results show that our solution can significantly outperform the state-of-the-art methods (with 20-30% improvement) and is efficient for online detection (it takes less than 0.1ms to process each newly generated data point).

Related papers

• A Self-Supervised Task for Fault Detection in Satellite Multivariate Time Series [45.31237646796715]
  This work proposes a novel approach leveraging Physics-Informed Real NVP neural networks, renowned for their ability to model complex and high-dimensional distributions. The experiments involve various configurations, including pre-training with self-supervision, multi-task learning, and standalone self-supervised training. Results indicate significant performance improvements across all settings.
  arXiv  Detail & Related papers  (2024-07-03T07:19:41Z)
• Simple Ingredients for Offline Reinforcement Learning [86.1988266277766]
  offline reinforcement learning algorithms have proven effective on datasets highly connected to the target downstream task. We show that existing methods struggle with diverse data: their performance considerably deteriorates as data collected for related but different tasks is simply added to the offline buffer. We show that scale, more than algorithmic considerations, is the key factor influencing performance.
  arXiv  Detail & Related papers  (2024-03-19T18:57:53Z)
• Run-time Introspection of 2D Object Detection in Automated Driving Systems Using Learning Representations [13.529124221397822]
  We introduce a novel introspection solution for 2D object detection based on Deep Neural Networks (DNNs) We implement several state-of-the-art (SOTA) introspection mechanisms for error detection in 2D object detection, using one-stage and two-stage object detectors evaluated on KITTI and BDD datasets. Our performance evaluation shows that the proposed introspection solution outperforms SOTA methods, achieving an absolute reduction in the missed error ratio of 9% to 17% in the BDD dataset.
  arXiv  Detail & Related papers  (2024-03-02T10:56:14Z)
• Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream [15.599296461516984]
  This paper presents a framework for online deep anomaly detection, ARCUS, which can be instantiated with any autoencoder-based deep anomaly detection methods. It handles the complex and evolving data streams using an adaptive model pooling approach with two novel techniques. In comprehensive experiments with ten data sets which are both high-dimensional and concept-drifted, ARCUS improved the anomaly detection accuracy of the streaming variants of state-of-the-art autoencoder-based methods by up to 22% and 37%, respectively.
  arXiv  Detail & Related papers  (2022-06-09T23:11:43Z)
• Meta-learning with GANs for anomaly detection, with deployment in high-speed rail inspection system [7.220842608593749]
  Key challenges for anomaly detection in the AI era with big data include lack of prior knowledge of potential anomaly types. Within this framework, we incorporate the idea of generative adversarial networks (GANs) with appropriate choices of loss functions. Our framework has been deployed in five high-speed railways of China since 2021: it has reduced more than 99.7% workload and saved 96.7% inspection time.
  arXiv  Detail & Related papers  (2022-02-11T17:43:49Z)
• Training a Bidirectional GAN-based One-Class Classifier for Network Intrusion Detection [8.158224495708978]
  Existing generative adversarial networks (GANs) are primarily used for creating synthetic samples from reals. In our proposed method, we construct the trained encoder-discriminator as a one-class classifier based on Bidirectional GAN (Bi-GAN) Our experimental result illustrates that our proposed method is highly effective to be used in network intrusion detection tasks.
  arXiv  Detail & Related papers  (2022-02-02T23:51:11Z)
• Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection [55.888835686183995]
  We propose a neural network-based meta-learning method for supervised anomaly detection. We experimentally demonstrate that the proposed method achieves better performance than existing anomaly detection and few-shot learning methods.
  arXiv  Detail & Related papers  (2021-03-01T01:43:04Z)
• Solving Sparse Linear Inverse Problems in Communication Systems: A Deep Learning Approach With Adaptive Depth [51.40441097625201]
  We propose an end-to-end trainable deep learning architecture for sparse signal recovery problems. The proposed method learns how many layers to execute to emit an output, and the network depth is dynamically adjusted for each task in the inference phase.
  arXiv  Detail & Related papers  (2020-10-29T06:32:53Z)
• SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks [81.64530401885476]
  We propose a self-supervised LiDAR odometry method, dubbed SelfVoxeLO, to tackle these two difficulties. Specifically, we propose a 3D convolution network to process the raw LiDAR data directly, which extracts features that better encode the 3D geometric patterns. We evaluate our method's performances on two large-scale datasets, i.e., KITTI and Apollo-SouthBay.
  arXiv  Detail & Related papers  (2020-10-19T09:23:39Z)
• SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection [63.253850875265115]
  Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples. We propose a modular acceleration system, called SUOD, to address it.
  arXiv  Detail & Related papers  (2020-03-11T00:22:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.