Rule-Based Error Detection and Correction to Operationalize Movement Trajectory Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xi, Bowen, Scaria, Kevin, Bavikadi, Divyagna, Shakarian, Paulo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915501083459584
author Xi, Bowen
Scaria, Kevin
Bavikadi, Divyagna
Shakarian, Paulo
author_facet Xi, Bowen
Scaria, Kevin
Bavikadi, Divyagna
Shakarian, Paulo
contents Classification of movement trajectories has many applications in transportation and is a key component for large-scale movement trajectory generation and anomaly detection which has key safety applications in the aftermath of a disaster or other external shock. However, the current state-of-the-art (SOTA) are based on supervised deep learning - which leads to challenges when the distribution of trajectories changes due to such a shock. We provide a neuro-symbolic rule-based framework to conduct error correction and detection of these models to integrate into our movement trajectory platform. We provide a suite of experiments on several recent SOTA models where we show highly accurate error detection, the ability to improve accuracy with a changing test distribution, and accuracy improvement for the base use case in addition to a suite of theoretical properties that informed algorithm development. Specifically, we show an F1 scores for predicting errors of up to 0.984, significant performance increase for out-of distribution accuracy (8.51% improvement over SOTA for zero-shot accuracy), and accuracy improvement over the SOTA model.
format Preprint
id arxiv_https___arxiv_org_abs_2308_14250
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Rule-Based Error Detection and Correction to Operationalize Movement Trajectory Classification
Xi, Bowen
Scaria, Kevin
Bavikadi, Divyagna
Shakarian, Paulo
Machine Learning
Artificial Intelligence
Logic in Computer Science
Classification of movement trajectories has many applications in transportation and is a key component for large-scale movement trajectory generation and anomaly detection which has key safety applications in the aftermath of a disaster or other external shock. However, the current state-of-the-art (SOTA) are based on supervised deep learning - which leads to challenges when the distribution of trajectories changes due to such a shock. We provide a neuro-symbolic rule-based framework to conduct error correction and detection of these models to integrate into our movement trajectory platform. We provide a suite of experiments on several recent SOTA models where we show highly accurate error detection, the ability to improve accuracy with a changing test distribution, and accuracy improvement for the base use case in addition to a suite of theoretical properties that informed algorithm development. Specifically, we show an F1 scores for predicting errors of up to 0.984, significant performance increase for out-of distribution accuracy (8.51% improvement over SOTA for zero-shot accuracy), and accuracy improvement over the SOTA model.
title Rule-Based Error Detection and Correction to Operationalize Movement Trajectory Classification
topic Machine Learning
Artificial Intelligence
Logic in Computer Science
url https://arxiv.org/abs/2308.14250