Predicting proximity with ambient mobile sensors for non-invasive health diagnostics
This work addresses non-invasive health monitoring for medical practitioners, but it appears incremental as it builds on existing sensor-based detection methods.
The paper tackled the problem of non-invasive health diagnostics by predicting human body proximity to mobile devices using ambient sensor data, achieving 88.75% accuracy and 88.3% specificity.
Modern smart phones are becoming helpful in the areas of Internet-Of-Things (IoT) and ambient health intelligence. By learning data from several mobile sensors, we detect nearness of the human body to a mobile device in a three-dimensional space with no physical contact with the device for non-invasive health diagnostics. We show that the human body generates wave patterns that interact with other naturally occurring ambient signals that could be measured by mobile sensors, such as, temperature, humidity, magnetic field, acceleration, gravity, and light. This interaction consequentially alters the patterns of the naturally occurring signals, and thus, exhibits characteristics that could be learned to predict the nearness of the human body to a mobile device, hence provide diagnostic information for medical practitioners. Our prediction technique achieved 88.75% accuracy and 88.3% specificity.