Machine Learning

This data set contains information on cardiopulmonary signals that were recorded simultaneously. The signals are separated into two folders, one titled heart sounds and the other lung sounds. In addition, two matlab programs are included, one with which the signals can be recorded and another to make graphs in time and frequency. It also has a pdf file that details the nomenclature of the signals.

This data set can be useful for various signal processing algorithms: filtering, PCA, LDA, ICA, CNN, etc.

The dataset contains the data collected using an Arduino Nano 33 BLE Sense for several classification tasks: color detection, keyword spotting, sound frequency recognition, vibration pattern detection, hand-gesture recognition, and vibration intensity detection. 

The dataset contains physiological data collected using a wearable device from 5 children with autism (all males) during interaction sessions with different stimuli. The dataset (QU_Autism_dataset.csv) is related to our investigations of using wearable devices to detect the occurrence of challenging behaviors among children with autism. The study used a wearable device that acquired the acceleration (ACC) (i.e., in X, Y, Z), electrodermal activity (EDA), temperature (TEMP), heart rate (HR), and blood volume pulse (BVP).

This dataset contains pathloss and ToA radio maps generated by the ray-tracing software WinProp from Altair. The dataset allows to develop and test the accuracies of pathloss radio map estimation methods and localization algorithms based on RSS or ToA in realistic urban scenarios. More details on the datasets can be found in the dataset paper: https://arxiv.org/abs/2212.11777.