Among the authors of this article, which was published in a renowned international journal in the field of multimedia tools and applications, are three members of the project team: Jože Guna, Emilija Stojmenova and Matevž Pogačnik. They presented an innovative gesture based identification system suited for applications such as user logins for various personalized services, e.g. home multimedia services. The authors used the term “implicit gesture” to refer to natural physical hand gestures which occur during the execution of other activities; e.g. simply picking a remote control device up from its neutral, motionless position is a natural implicit gesture which occurs in using the device. For reference with other related systems, explicit and well defined identification gestures were used, such as the user's signature in the form of a 3D gesture. Gestures were acquired with the Nintendo WiiMote remote controller, which has a built-in accelerometer sensor. A dynamic time warping method is at the core of this gesture based identification system. For a further increase of the computational efficiency and temporal stability of the procedure, the authors introduced the concept of the “supergesture”, where acceleration features of multiple gestures are combined in a single supergesture template for each user. Ten users participated in a system evaluation conducted over a period of 10 days. Evaluation results showed 88 per cent recognition accuracy of 5 users and 77 per cent accuracy in identifying 10 users using the implicit “pickup” gesture. When it came to explicit identification signature gestures, the algorithm ensured nearly 100 per cent recognition accuracy, which indicates that the performance of the proposed system is comparable to the results of other systems. The results support implicit gesture based identification as a viable example of a non-invasive, easy method of user identification for the home environment. As part of the project and the "DriveGreen" mobile application development, the above research findings and the gesture based identification system will be tested in vehicles.
COBISS.SI-ID: 10034516
A prolonged exposure to stress can lead to mental disorders and psychosomatic diseases, e.g declining of health. This survey reviews sensors, human-body parameters and context information correlated with the stress level, and investigates various stress analysis methods. Sensors for stress determination are classified and divided into four groups with regard to the physiological and physical parameters of the human-body, context information, expert assessment and questionnaires. The work to be done in future in the field of stress recognition is discussed. Results will be directly applicable in further development of the "DriveGreen" mobile application.
COBISS.SI-ID: 10918996
This paper present a state-of-the art overview of devices and services in the areas of well-being, sports, lifestyle and communications, and environment monitoring. The need for healthier and better quality of life makes these devices an important market from the business perspective as well. Specific trends and blending of functionality as well as the importance of communications hubs (e.g. smartphone) are especially apparent. Results of the study will be directly applicable in further development of the "DriveGreen" application and also in research, carried out in the project, e.g. measurement of drivers' mood by wearable sensors.
COBISS.SI-ID: 10784340