TXT

This dataset is derived from a research paper proposing a wireless localization correction methodology based on Convolutional Neural Networks (CNN). The approach involves feature extraction from maps that depict both line of sight (LOS) and non-line of sight (NLOS) effects. The research includes four prediction tasks, categorizing CNN models based on building distribution and propagation mode, resulting in models with low prediction loss. Additionally, an error compensation scheme is designed using CNN-predicted localization errors.

This dataset presents a comprehensive collection of measurements obtained from a self-made test bed called the NET Playground, focusing on the performance evaluation of an IPFS (InterPlanetary File System) consumer and multiple providers. The dataset comprises 45 sets of data, each representing a scenario involving the consumer requesting a 10MB file from a varying number of available providers ranging from 1 to 15. The network configuration involves all nodes (consumer and providers) being connected in a peer-to-peer network and utilizing IPFS as the communication protocol.

Data based on capacitive and pressure measurement on physical vascular model developed at out university. We used capacitve sensing for dielectric volume change of artificial arterial segment on two measurement sites. For verification we used pressure sensors commonly used in medical applications to measure blood pressure or fluid pressure within the human body. Overall, your approach combining capacitive sensing and pressure measurements provides a comprehensive analysis of the dielectric volume changes in the artificial arterial segment.

For the UNB-GCN  classification model, UNB as the input feature vector to the graph structure node, phenotypic information, such as gender, age and APOE genetic information, as the weight of the edges between nodes.