20883 research outputs found
Sort by
Enhanced precision in axle configuration inference for bridge weigh-in-motion systems using computer vision and deep learning
No full textHeavy goods vehicles (HGVs) have a significant impact on road and bridge infrastructure, with overloaded vehicles accelerating structural deterioration and increasing safety risks. Bridge weigh-in-motion (B-WIM) systems estimate gross vehicle weight (GVW) using strain measurements, but inaccuracies in axle configuration recognition can reduce reliability. This study presents a low-cost computer vision (CV) extension for existing B-WIM installations that verifies strain-inferred axle configurations using traffic camera images and flags GVW estimates as reliable or unreliable. Experiments on a data set of over 30,000 HGV records show that by combining convolutional neural networks with strain-based heuristics, GVW reliability can improve from 96.7% to 99.89%, effectively excluding nearly all erroneous measurements. The approach operates without interrupting ongoing B-WIM operations and can be applied retrospectively to historical data. Limitations include the inability to detect raised axles (RAs), which the method excludes as unreliable. This method provides a practical, high-precision enhancement for structural health monitoring of bridges
Dual-task gait analysis
No full textCognitive tasks significantly influence automated acts, such as walking. This study included 41 healthy individuals, who were over 65 years of age. We examined dual-task effects on the spatiotemporal and kinematic parameters of gait in older adults during four tasks carried out in single-task, cognitive, motor, and combined cognitive–motor conditions. An analysis of walking according to spatiotemporal and kinematic parameters was performed using an inertial movement analysis system. The combined task showed the most significant impairments, with substantially reduced gait speed (p < 0.001, r = −0.80), shorter stride length (p < 0.001, r = −0.82), and decreased hip flexion (p < 0.001, r = −0.80) compared to single-task walking. Cognitive tasks alone significantly affected gait speed (p = 0.001) and stride length (p = 0.001), while motor tasks showed minimal effects. The combined task also significantly increased double-support time (p < 0.001) and reduced single-support time (p = 0.001), indicating compensatory walking strategies. These findings demonstrate that concurrent cognitive–motor demands disproportionately impair gait, suggesting that clinical assessments should prioritize combined-task evaluation. The observed kinematic and spatiotemporal changes highlight the profound interdependence between cognitive function and automatic locomotor control during walking. It is likely that dual-task gait analysis may offer clinical utility for the early detection of cognitive–motor deficits
