Quality of Life Prediction in Driving Scenes on Thailand Roads Using Information Extraction from Deep Convolutional Neural Networks

Abstract

In the modern era, urban design and sustainable development are vital topics for megacities, as they are important for the wellbeing of its residents. One of the effective key performance indices (KPIs) measuring the city plan’s efficiency in quantity and quality factors is Quality of Life (QOL), an index that policymakers can use as a critical KPI to measure the quality of urbanscape design. In the traditional approach, the researchers conduct the questionnaire survey and then analyze the gathered data to acquire the QOL index. The conventional process is costly and time-consuming, but the result of the evaluation area is limited. Moreover, it is difficult to embed in an application or system; we proposed artificial intelligence (AI) approaches to solve the limitation of the traditional method in Bangkok as a case study. There are two steps for our proposed method. First, in the knowledge extraction step, we apply deep convolutional neural networks (DCNNs), including semantic segmentation and object detection, to extract helpful information images. Second, we use a linear regression model for inferring the QOL score. We conducted various state-of-the-art (SOTA) models and public datasets to evaluate the performance of our method. The experiment results show that our novel approach is practical and can be considered for use as an alternative QOL acquisition method. We also gain some understanding of drivers’ insights from the experiment result.

Quality of Life Prediction on Walking Scenes Using Deep Neural Networks and Performance Improvement Using Knowledge Distillation

“…Some studies conduct deep learning neural networks (DNNs) to improve the limitation of traditional QoL evaluation methods. Thitisiriwech et al [23] suggested that the traditional QoL evaluation is costly and time-consuming. Hence, researchers proposed an AI approach using deep convolutional neural networks (DCNNs) and linear regression to predict QoL scores from driving-scene images, using DeepLab-v3+ and YOLO-v3 for knowledge extraction.…”

“…Thitisiriwech et al [22] proposed the Bangkok Urbanscapes dataset, the first labeled urban scene dataset in Bangkok, and models that have an excellent performance on semantic segmentation processing. Thitisiriwech et al [23] proposed an AI approach using DCNNs and a linear regression model to extract information from images and infer the QoL score. Iamtrakul et al [24] investigated how the built environment affects the QoL related to transportation using a combination of GIS and DL in the Sukhumvit district, Bangkok.…”

Diversified Impacts of Enabling a Technology-Intensified Agricultural Supply Chain on the Quality of Life in Hinterland Communities

“…There is also a study on healthy farmers that found three factors predicting QoL: education, living standards, and the number of working members [7]. Referring to the transportation aspect, there exists research regarding the prediction of a QoL score from an evaluation model based on the satisfaction level derived from scenery experienced while driving [8]. On the consumer side, by developing healthy fruit and vegetable juice products, not only can the QoL of people with illnesses in need of nutritious products be improved, but also the income and QoL of the producers [9].…”