A Self-Supervised Transformer for Unusable Shared Bike Detection

TL;DR

This paper introduces a self-supervised Transformer model that effectively detects unusable shared bikes by leveraging spatiotemporal GPS data, significantly improving accuracy over traditional methods and addressing label scarcity issues.

Contribution

The paper presents a novel self-supervised Transformer framework that enhances bike fault detection using spatiotemporal features, outperforming existing supervised and static threshold approaches.

Findings

Achieved 97.81% accuracy in detecting unusable bikes.

Outperformed traditional machine learning and deep learning baselines.

Demonstrated robustness on real-world dataset with 10,730 bikes.

Abstract

The rapid expansion of bike-sharing systems (BSS) has greatly improved urban "last-mile" connectivity, yet large-scale deployments face escalating operational challenges, particularly in detecting faulty bikes. Existing detection approaches either rely on static model-based thresholds that overlook dynamic spatiotemporal (ST) usage patterns or employ supervised learning methods that struggle with label scarcity and class imbalance. To address these limitations, this paper proposes a novel Self-Supervised Transformer (SSTransformer) framework for automatically detecting unusable shared bikes, leveraging ST features extracted from GPS trajectories and trip records. The model incorporates a self-supervised pre-training strategy to enhance its feature extraction capabilities, followed by fine-tuning for efficient status recognition. In the pre-training phase, the Transformer encoder learns generalized representations of bike movement via a self-supervised objective; in the fine-tuning phase, the encoder is adapted to a downstream binary classification task. Comprehensive experiments on a real-world dataset of 10,730 bikes (1,870 unusable, 8,860 normal) from Chengdu, China, demonstrate that SSTransformer significantly outperforms traditional machine learning, ensemble learning, and deep learning baselines, achieving the best accuracy (97.81%), precision (0.8889), and F1-score (0.9358). This work highlights the effectiveness of self-supervised Transformer on ST data for capturing complex anomalies in BSS, paving the way toward more reliable and scalable maintenance solutions for shared mobility.