Large-Scale Wi-Fi Hotspot Classification via Deep Learning

Chang Xu, Kuiyu Chang, Khee-Chin Chua, Meishan Hu, Zhenxiang Gao

Abstract: We describe the problem of classifying hundreds of millions of Wi-Fi hotspots using only connection and user count characteristics. We use a combination of deep learning and frequency analysis. Specifically, Convolution Neural Networks (CNN) capture the spatio-temporal relationship between adjacent connection/user counts across a 24 hour×7 day matrix, while FFT (Fast Fourier Transforms) extract user and connection frequencies. Our production system has been deployed to classify 239 million hotspots in 12 hours on a SPARK 2.0 cluster, achieving close to 80% F1-score for binary classification.