Machine Learning with partially labeled Data for Indoor Outdoor Detection

Abstract

This paper demonstrates the feasibility of an hybrid/semi-supervised classification method for detecting the environment of an active mobile phone, based on both labeled and unlabeled cellular radio data. Precisely, we provide answers to the following question: what is the environment of the mobile user when it is/was experiencing a mobile service/application: indoor or outdoor? Implementing this method within the mobile network is interesting for mobile operators since it has low complexity, is less human intrusive (minimal intervention of mobile users) and more accurate. The semi-supervised classification algorithm learns to identify the environment using large and real collected 3GPP signals measurements. As compared to existing work, in addition to existing parameters used for classification, we propose to also use a radio metric called Timing Advance. It is computed within the mobile network. We empirically validate the innovative semi-supervised algorithm using new real-time radio measurements, with partial ground truth information, gathered daily, weekly, monthly, from indoor and outdoor locations and from multiple typical and diversified environments crossed by mobile users. The study confirms the effectiveness of the proposed scheme compared to the existing supervised classification methods including SVM and Deep Learning.

Mobile User Environment Detection using Deep Learning based Multi-Output Classification

“…As a consequence, some classes (the most popular) have much more measurement points than others. This unbalancing between the categories of various environments, observed in case of two classes in [3], is also augmented when classifying with more than two classes. Therefore, achieving a multi-output classification will first require to tackle this phenomenon.…”

“…In literature, the environment detection issue has been studied mainly considering an Indoor Outdoor Detection (IOD) binary classification to detect the environment [3], [4]. However, identifying the user's environment is a more complicated task than just IOD.…”

“…The evaluation of the proposed solution will be done using real and large 4G LTE radio data collected through a crowdsourcing approach, i.e. collected by the phone device and sent to the mobile network via 3GPP procedures [3]. Thus, Machine Learning algorithms trained on datasets collected in crowdsourcing mode allow to learn very diverse real-world environments.…”

Multi-task Deep Learning based Environment and Mobility Detection for User Behavior Modeling

“…The compared system which implements independent tasks is explained as follows. IOD task is done using the input features and a supervised Deep Learning algorithm described in [4]. MSE task uses a part of features described above and use a similar Deep Learning algorithm.…”

“…Thus, to achieve it, we investigate the association of both Indoor/Outdoor Detection (IOD) and Mobility State Estimation (MSE). IOD refers to the detection of the mobile users' environments, that is to infer whether the user is Indoor or Outdoor [4]. MSE refers to the estimation whether a given user moves with low, medium or high speed.…”