The Feasibility of Information-Entropy-Based Behavioral Analysis for Detecting Environmental Barriers

Feasibility of DRNN for Identifying Built Environment Barriers to Walkability Using Wearable Sensor Data from Pedestrians’ Gait

Identifying built environment barriers to walkability is the first step toward monitoring and improving our walking environment. Although conventional approaches (i.e., surveys by experts or pedestrians, walking interviews, etc.) to identify built environment barriers have contributed to improving the walking environment, these approaches may require time and effort. To address the limitations of conventional approaches, wearable sensing technologies and data analysis techniques have recently been adopted in the investigation of the built environment. Among various wearable sensors, an inertial measurement unit (IMU) can continuously capture gait-related data, which can be used to identify built environment barriers to walkability. To propose a more efficient method, the author adopts a cascaded bidirectional and unidirectional long short-term memory (LSTM)-based deep recurrent neural network (DRNN) model for classifying human gait activities (normal and abnormal walking) according to walking environmental conditions (i.e., normal and abnormal conditions). This study uses 101,607 gait data collected from the author’s previous study for training and testing a DRNN model. In addition, 31,142 gait data (20 participants) have been newly collected to validate whether the DRNN model is feasible for newly added gait data. The gait activity classification results show that the proposed method can classify normal gaits and abnormal gaits with an accuracy of about 95%. The results also indicate that the proposed method can be used to monitor environmental barriers and improve the walking environment.

Two-Step k-means Clustering Based Information Entropy for Detecting Environmental Barriers Using Wearable Sensor

Walking is the most basic means of transportation. Therefore, continuous management of the walking environment is very important. In particular, the identification of environmental barriers that can impede walkability is the first step in improving the pedestrian experience. Current practices for identifying environmental barriers (e.g., expert investigation and survey) are time-consuming and require additional human resources. Hence, we have developed a method to identify environmental barriers based on information entropy considering that every individual behaves differently in the presence of external stimuli. The behavioral data of the gait process were recorded for 64 participants using a wearable sensor. Additionally, the data were classified into seven gait types using two-step k-means clustering. It was observed that the classified gaits create a probability distribution for each location to calculate information entropy. The values of calculated information entropy showed a high correlation in the presence or absence of environmental barriers. The results obtained facilitated the continuous monitoring of environmental barriers generated in a walking environment.