Title :
A single vs. multi-sensor approach to enhanced detection of smartphone placement
Author :
Guiry, John J. ; Karr, Chris J. ; Van de Ven, Pepijn ; Nelson, John ; Begale, Mark
Author_Institution :
Dept. of Electron. & Comput. Eng., Univ. of Limerick, Limerick, Ireland
Abstract :
In this paper, the authors evaluate the ability to detect on-body device placement of smartphones. A feasibility study is undertaken with N=5 participants to identify nine key locations, including in the hand, thigh and backpack, using a multitude of commonly available smartphone sensors. Sensors examined include the accelerometer, magnetometer, gyroscope, pressure and light sensors. Each sensor is examined independently, to identify the potential contributions it can offer, before a fused approach, using all sensors is adopted. A total of 139 features are generated from these sensors, and used to train five machine learning algorithms, i.e. C4.5, CART, Naïve Bayes, Multilayer Perceptrons, and Support Vector Machines. Ten-fold cross validation is used to validate these models, achieving classification results as high as 99%.
Keywords :
accelerometers; belief networks; gyroscopes; magnetometers; mobile computing; multilayer perceptrons; pressure sensors; sensor fusion; sensor placement; smart phones; support vector machines; C4.5; CART; Naïve Bayes; accelerometer; gyroscope; light sensors; machine learning algorithms; magnetometer; multilayer perceptrons; on-body device placement; pressure sensors; smartphone placement; smartphone sensors; support vector machines; Accelerometers; Breast; Gyroscopes; Hip; Magnetic sensors; Magnetometers; Enhanced Contextual Awareness; Machine Learning; Multi-Sensor Fusion; Smartphone Placement;
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE
Conference_Location :
Chicago, IL
DOI :
10.1109/EMBC.2014.6944424