Course/Project description Head landmarks are the key points that describe the shape of the head attributes, e.g. eyes, nose, and chin etc. Most available landmark detection algorithms focus on the facial landmarks detection, which do not cover ears. However, ears are very important reference positi...
Course/Project description Fitting eyeglasses to head via trial and error is inefficient. The proposed student project aims at automating the eyeglasses fitting process by using head image information with the target to generate eyeglasses frames (key points) using only facial landmarks (key points ...
The aim of the seminar is to design knowledge extraction algorithms based on deep learning techniques for activity recognition in free-living using wearable sensing systems. Challenges will be related to imbalance of target classes, scarcity of computational resources and design of parallel computin...
The aim of the project is to design an energy-efficient context-aware strategy for activity recognition using sparse sampling and sensor data compression. Prototyping will be done in Python. Evaluation will be performed on free-living dataset and benchmarked in terms of energy/memory savings, time c...
Course/Project description Chewing and biting are two interesting targets of dietary monitoring. The proposed student project aims at offering a wearable solution of chewing and biting monitoring in free-living by integrating sensors in smart eyeglasses. In the first stage, chewing and biting sensor...
Course/Project description Chewing is an essential component of eating. Chewing cycles can be recorded using various sensors and detected applying appropriate algorithms. However, evaluating a chewing detection algorithm is usually difficult due to the lack of accurate ground truth. It is even more ...
Course description Wearable sensor technology, particularly inertial measurement sensors are used in various motion analysis including applications in sport, medicine, and rehabilitation of patients after stroke. However, how would a hemiparetic stroke patient attach a sensor to the wrist? The quest...
Course description Nordic Walking is a complex sport including interactions between upper and lower-body and body-sides. Nordic Walking provides many health benefits, i.e. cardio-vascular fitness when performed correctly . In this work, we aim to extend our analysis for the performance-oriented Nord...
Course/Project description Chewing produces sound and this vibration also travels in the head, that’s why we can hear and estimate what we are eating. In this project, we will establish a procedure of food texture classification using eyeglasses integrated sensors (vibration sensor and microphone), ...
Course description To monitor eating, we attach dry electrodes on eyeglasses to measure EMG signals from Temporalis muscles. Due to head shape variation, dry electrodes usually face bad skin contact issue, which impairs EMG signal quality. The project aims at solving this problem by designing a mech...
