On 29 August 2017, ICT4Life technical partners organised in Lecce (Italy) the SIEARW – Smart Indoor Event and Activity Recognition Workshop, in conjunction with IEEE AVSS 2017.
ICT4Life partners organized and participated to the Smart Indoor Event and Activity Recognition Workshop (SIEARW 2017). The workshop has been organized in conjunction with the IEEE AVSS 2017 on 29 August 2017, from 14:00 to 16:00, in Lecce, Italy.
The scope of the Workshop was to bring together researchers and developers working in the area of human activity analysis and event prediction in indoor environments, also leveraging on the results of the ICT4Life project.
In the paper on “Multimodal monitoring of Parkinson’s and Alzheimer’s patients using the ICT4Life platform”, the overview of the project scope was included. The study presents ICT4Life platform, starting from low-level data capturing and performing multimodal fusion to extract relevant features. Additionally, high-level reasoning is performed to provide relevant data regarding the monitoring and evolution of the patients, and triggering proper actions for improving the quality of life of the patient.
Then, the study on “ICT4Life Open Source Libraries supporting Multimodal Analysis of different diseases” introduces a set of libraries for acquiring and processing data from different sensors, machine learning algorithms for activity recognition, as well as fusion methods of multiple modalities either at an early or at a late stage. The main purpose of the introduced system is to enable an easy customization of patients’ monitoring using different types of sensors. Furthermore, by allowing an easy integration of new sensors or types of activities, the proposed subsystem supports the development of new solutions for different diseases, than the ones considered in the ICT4Life project.
A novel multi-modal method for person identification in indoor environments is introduced in the paper “Person Tracking Association Using Multi-modal Systems”. The proposed approach relies on skeleton data from a Kinect device which is matched with wearable devices equipped with inertial sensors. Movement features such as yaw and pitch changes are employed to associate a particular Kinect skeleton to a person using the wearable, and the experimental results showed a high accuracy in the association process.
Finally, the contribution “Prediction of learning space occupation through WLAN access point data using Kalman filter and Gradient Boosting Regression” employs Machine Learning techniques on WLAN access point data for predicting learning space usage and enabling students to make proper choices. The promising results obtained on real application environments proved the suitability of the presented approach.