Predicting indoor crowd density using column-structured deep neural network

• Main Authors: SUDO, Akihito, TENG, Teck Hou (DENG Dehao), LAU, Hoong Chuin, SEKIMOTO, Yoshihide
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Deep Neural Network; Feature Extraction; Indoor Crowd Prediction; Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/4382; https://ink.library.smu.edu.sg/context/sis_research/article/5385/viewcontent/Predicting_indoor_crowd_density_afv.pdf
• Institution: Singapore Management University

This work proposes a deep neural network approach known as the column-structured deep neural network (COL-DNN-R) for predicting crowd density in an indoor environment using historical Wi-Fi traces of individual visitors. With a structure designed to minimize feature engineering, COL-DNN accepts raw...