Background and activities
My Research Hypothesis
The energy resource is limited on most sensor nodes. Therefore, they need to use it wisely in order to prolong their lifetime and, as a result, to be able to provide the data as long as possible. It is beneficial that the sensor node can adapt itself software-wise according to the available energy resource and required data depending on specific use cases. The adaptation can be based on the prediction of the near future energy resource, e.g. the battery level and harvested energy of tomorrow. Such a prediction needs to be learned from parameters provided by the sensor node, and can be performed on a remote server with virtually unlimited energy resource. Many sensor nodes are not designed with the energy resource prediction in mind. Hence they may not provide accesses to parameters required by the prediction.
Thus we aim at designing a sensor node specification with parameters necessary for energy prediction and sensor node adaptation. Moreover, it is opened for feasible energy-aware algorithms that can be selected by an external entity to improve energy efficiency to a certain level.
Scientific, academic and artistic work
A selection of recent journal publications, artistic productions, books, including book and report excerpts. See all publications in the database
- (2017) Fog Computing in Healthcare – A Review and Discussion. IEEE Access. vol. 5.
- (2017) Machine Learning in IoT for Autonomous, Adaptive Sensing. ERCIM News. vol. 2017 (110).
Part of book/report
- (2017) Energy Consumption Estimation for Energy-Aware, Adaptive Sensing Applications. Mobile Secure and Programmable Networking.