TY - JOUR T1 - Cross-source sensing data fusion for building occupancy prediction with adaptive lasso feature filtering JF - Building and Environment Y1 - 2019 A1 - Wang, Wei A1 - Tianzhen Hong A1 - Xu, Ning A1 - Xu, Xiaodong A1 - Chen, Jiayu A1 - Shan, Xiaofang KW - data fusion KW - Feature selection KW - Machine learning KW - occupancy prediction KW - Physics-based model AB -

Fusing various sensing data sources can significantly improve the accuracy and reliability of building occupancy detection. Fusing environmental sensors and wireless network signals are seldom studied for its computational and technical complexity. This study aims to propose an integrated adaptive lasso model that is able to extract critical data features for environmental and Wi-Fi probe dual sensing sources. Through rapid feature extraction and process simplification, the proposed method aims to improve the computational efficiency of occupancy detecting models. To validate the proposed model, an onsite experiment was conducted to examine two occupancy data resolutions, (real-time and four-level occupancy resolutions). The results suggested that, among all twelve features, eight features are most relevant. The mean absolute error of the real-time occupancy can be reduced to 2.18 and F1_accuracy is about 84.36% for the four-level occupancy.

VL - 162 JO - Building and Environment ER - TY - JOUR T1 - Revealing Urban Morphology and Outdoor Comfort through Genetic Algorithm-Driven Urban Block Design in Dry and Hot Regions of China JF - Sustainability Y1 - 2019 A1 - Xu, Xiaodong A1 - Yin, Chenhuan A1 - Wang, Wei A1 - Xu, Ning A1 - Hong, Tianzhen A1 - Li, Qi KW - dry and hot areas; outdoor thermal comfort; urban morphology; urban performance simulation; genetic algorithm-driven AB -

In areas with a dry and hot climate, factors such as strong solar radiation, high temperature, low humidity, dazzling light, and dust storms can tremendously reduce people’s thermal comfort. Therefore, researchers are paying more attention to outdoor thermal comfort in urban environments as part of urban design. This study proposed an automatic workflow to optimize urban spatial forms with the aim of improvement of outdoor thermal comfort conditions, characterized by the universal thermal climate index (UTCI). A city with a dry and hot climate—Kashgar, China—is further selected as an actual case study of an urban block and Rhino & Grasshopper is the platform used to conduct simulation and optimization process with the genetic algorithm. Results showed that in summer, the proposed method can reduce the averaged UTCI from 31.17 to 27.43 °C, a decrease of about 3.74 °C, and reduce mean radiation temperature (MRT) from 43.94 to 41.29 °C, a decrease of about 2.65 °C.

VL - 11 UR - https://www.mdpi.com/2071-1050/11/13/3683https://www.mdpi.com/2071-1050/11/13/3683/pdf IS - 13 JO - Sustainability ER -