Experimental Source

Walking-friendly cities not only promote health and environmental benefits but also play crucial roles in urban development and local economic revitalization. Generally, pedestrian interviews and surveys used to evaluate walkability, but this is expensive and lack professional insight. To address limitations in current methods for evaluating pedestrian pathways, we propose a novel approach utilizing wearable sensors and deep learning. This new method provides benefits in terms of efficiency and cost-effectiveness while ensuring a more objective and consistent evaluation of sidewalk surfaces. In the proposed method, acceleration data is captured along the V, AP, and ML axes during 10-minute walks across five distinct sidewalk surfaces. This data is then transformed into the frequency domain using Fast Fourier Transform (FFT), Kalman filter, lowpass filter, and moving average filter. A deep learning model is subsequently utilized to classify the conditions of the sidewalk surfaces using this transformed data. Experimental results indicate that the proposed model achieves a notable accuracy rate.