In the paper a human activity recognition system has been presented based on the data gathered with the smartphone sensors. The acceleration, magnetic field and sound have been registered and four different activities of daily living has been recognized i.e. riding a bike, driving in a car, walking and sitting. Two version of Support Vector Machine (SVM) classifier have been employed and the obtained results are promising.
Keywords Human activity recognition · Smartphones · Support vector machineThe Human Activity Recognition (HAR) systems aim to automatically determine what people do on the basis of signals recorded from different sensors. These systems can be divided into two main types: external and wearable [11].In the first approach the sensors are placed in a fixed position so the people have to interact with the system and they are confined to a certain area. The most popular are video cameras [20]. Typically they can register a 2D images but it can also record a 3D sequences when two or more devices are employed [1,17]. In order to track the human activity also the depths sensors (especially Time-of-Flight cameras) are introduced. The solutions are based on tracking both the whole body [7,14] as well as only it certain parts, in particular joints [19]. Although this approach allows obtaining a full information about the human activity and his/her environment. The image processing methods are very time consuming and not resource-efficient. Moreover, many people are not willing to be monitored permanently, except for the