Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data

• URL: http://arxiv.org/abs/2012.03062v2
• Date: Sun, 9 May 2021 02:21:57 GMT
• Title: Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data
• Authors: Yutao Chen, Yu Zhang, Fei Yang
• Abstract summary: We showcase an application framework for predicting vertical track irregularity, based on a real-world, large-scale dataset produced by several operating railways in China. We also proposed a novel approach for handling imbalanced data in time series prediction tasks with adaptive data sampling and penalized loss.
• Score: 6.448383767373112
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Railway systems require regular manual maintenance, a large part of which is dedicated to inspecting track deformation. Such deformation might severely impact trains' runtime security, whereas such inspections remain costly for both finance and human resources. Therefore, a more precise and efficient approach to detect railway track deformation is in urgent need. In this paper, we showcase an application framework for predicting vertical track irregularity, based on a real-world, large-scale dataset produced by several operating railways in China. We have conducted extensive experiments on various machine learning & ensemble learning algorithms in an effort to maximize the model's capability in capturing any irregularity. We also proposed a novel approach for handling imbalanced data in multivariate time series prediction tasks with adaptive data sampling and penalized loss. Such an approach has proven to reduce models' sensitivity to the imbalanced target domain, thus improving its performance in predicting rare extreme values.

Related papers

• RealTraj: Towards Real-World Pedestrian Trajectory Forecasting [10.332817296500533]
  We propose a novel framework, RealTraj, that enhances the real-world applicability of trajectory forecasting. We present Det2TrajFormer, a trajectory forecasting model that remains invariant in tracking noise by using past detections as inputs. Unlike previous trajectory forecasting methods, our approach fine-tunes the model using only ground-truth detections, significantly reducing the need for costly person ID annotations.
  arXiv  Detail & Related papers  (2024-11-26T12:35:26Z)
• A Scalable Approach to Covariate and Concept Drift Management via Adaptive Data Segmentation [0.562479170374811]
  In many real-world applications, continuous machine learning (ML) systems are crucial but prone to data drift. Traditional drift adaptation methods typically update models using ensemble techniques, often discarding drifted historical data. We contend that explicitly incorporating drifted data into the model training process significantly enhances model accuracy and robustness.
  arXiv  Detail & Related papers  (2024-11-23T17:35:23Z)
• A Dataset for Evaluating Online Anomaly Detection Approaches for Discrete Multivariate Time Series [0.01874930567916036]
  Current publicly available datasets are too small, not diverse and feature trivial anomalies. We propose a solution: a diverse, extensive, and non-trivial dataset generated via state-of-the-art simulation tools. We make different versions of the dataset available, where training and test subsets are offered in contaminated and clean versions. As expected, the baseline experimentation shows that the approaches trained on the semi-supervised version of the dataset outperform their unsupervised counterparts.
  arXiv  Detail & Related papers  (2024-11-21T09:03:12Z)
• FaultFormer: Pretraining Transformers for Adaptable Bearing Fault Classification [7.136205674624813]
  We present a novel self-supervised pretraining and fine-tuning framework based on transformer models. In particular, we investigate different tokenization and data augmentation strategies to reach state-of-the-art accuracies. This introduces a new paradigm where models can be pretrained on unlabeled data from different bearings, faults, and machinery and quickly deployed to new, data-scarce applications.
  arXiv  Detail & Related papers  (2023-12-04T22:51:02Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Towards Accelerated Model Training via Bayesian Data Selection [45.62338106716745]
  We propose a more reasonable data selection principle by examining the data's impact on the model's generalization loss. Recent work has proposed a more reasonable data selection principle by examining the data's impact on the model's generalization loss. This work solves these problems by leveraging a lightweight Bayesian treatment and incorporating off-the-shelf zero-shot predictors built on large-scale pre-trained models.
  arXiv  Detail & Related papers  (2023-08-21T07:58:15Z)
• Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection [58.789823426981044]
  We propose a novel auxiliary loss formulation that aims to align the class confidence of bounding boxes with the accurateness of predictions. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios.
  arXiv  Detail & Related papers  (2023-03-25T08:56:21Z)
• Adapting to Continuous Covariate Shift via Online Density Ratio Estimation [64.8027122329609]
  Dealing with distribution shifts is one of the central challenges for modern machine learning. We propose an online method that can appropriately reuse historical information. Our density ratio estimation method is proven to perform well by enjoying a dynamic regret bound.
  arXiv  Detail & Related papers  (2023-02-06T04:03:33Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning [55.733193075728096]
  Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
  arXiv  Detail & Related papers  (2022-02-11T13:49:51Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.