Cerebral Blood Flow Classification Dataset Using Ultra-Wideband RF Sensors with Statistical and Autoencoder-Based Features

This dataset provides measurements of cerebral blood flow using Radio Frequency (RF) sensors operating in the Ultra-Wideband (UWB) frequency range, enabling non-invasive monitoring of cerebral hemodynamics. It includes blood flow feature data from two arterial networks, Arterial Network A and Arterial Network B. Statistical features were manually extracted from the RF sensor data, while autonomous feature extraction was performed using a Stacked Autoencoder (SAE) with architectures such as 32-16-32, 64-32-16-32-64, and 128-64-32-16-32-64-128. To expand the feature dataset, Gaussian noise-based feature augmentation with a mean of 0.2 and variance of 0 was applied to both statistical and autonomously extracted features. The dataset supports binary and multi-class classification. In the binary scheme, 10ml and 90ml blood flow values are labeled as abnormal, while 50ml is normal. For multi-class classification, measurements are categorized separately for each arterial network, where 10ml-A, 90ml-A, and 50ml-A represent Arterial Network A, and 10ml-B, 90ml-B, and 50ml-B correspond to Arterial Network B.