Machine Learning

With the rapid deployment of indoor Wi-Fi networks, Channel State Information (CSI) has been used for device-free occupant activity recognition. However, various environmental factors interfere with the stable propagation of Wi-Fi signals indoors, which causes temporal variation of CSI data. In this study, we investigated temporal CSI variation in a real-world housing environment and its impact on learning-based occupant activity recognition.

Four independently built Twitter JSON files containing between 40,000 - 50,000 tweets with a common Hashtag to be used with network discovery algorithms.

eLearning, or online learning, has reached every corner of the globe in this era of digitization. As a result of the COVID-19 pandemic, the value of eLearning has increased substantially. In eLearning recommendation systems, information overload, personalised suggestion, sparsity, and accuracy are all major problems. The correct eLearning Recommendation System is necessary to tailor the course recommendation according to the user's needs. To create this model, dataset of the User Profile and User Rating is needed.

Switching vectors of an inverter with model predictive control were collected for different conditions of an induction machine. The induction machine had a rated speed of w=3000 rpm and a rated torque of T=1.20 N·m. The switching vectors were recorded as data series for the induction machine operating at different combinations of speed and torque at healthy and faulty states. Each data series consisted of 22000 switching vectors. Inter-turn short circuit fault was introduced over 2 turns (out of 104 turns) in one phase of the machine.