TRACE: Transformer-based continuous tracking framework using IoT and MCS

Shahmir Khan Mohammed

doi:10.1016/j.jnca.2023.103793

Return

TRACE: Transformer-based continuous tracking framework using IoT and MCS

2024-02-01

PRE

Shahmir Khan Mohammed *

Shakti Singh

Rabeb Mizouni

Hadi Otrok

DOI：10.1016/j.jnca.2023.103793

Original

Original request for help

Save

Abstract

En 中文

Target tracking, a critical application in the Internet of Things (IoT) and Mobile Crowd Sensing (MCS) domains, is a complex task that involves the continuous estimation of the positions of an object by using efficient and accurate algorithms. Some potential applications of target tracking include surveillance systems, asset tracking, wildlife monitoring, and cross-border security. The existing target tracking solutions are either energy-inefficient or are only effective for fixed-length trajectories, making them impractical for real-world applications. For robust predictive tracking, with irregular trajectory lengths, energy efficiency and accuracy are vital to ensure system's longevity and reliability. In this work, using a combination of trajectory prediction and path correction techniques, a novel approach, TRACE , is proposed for continuously tracking a target in an environment. TRACE uses locations offered by IoT/MCS localization systems to make predictions about the target's future movement. A transformer neural network is implemented to learn mobility patterns to predict the target's future trajectory. To ensure accurate predictions, a path correction mechanism is devised, by updating the predicted trajectory using polynomial regression. Experiments are conducted using a real-world GeoLife dataset to evaluate the performance of the proposed approach. The results demonstrate that TRACE performs better than existing tracking techniques with an improvement in accuracy of about 50% while using 85% less energy, supporting the potential of the proposed approach for enhancing target tracking in IoT/MCS applications.

Keywords:

IoT

Continuous tracking

Machine learning

Deep learning

Transformers

Trajectory prediction