*.mat

Device fingerprinting is a technique for remote indirect identification or classification of a device of interest. This database is designated for device fingerprinting by current consumption; it includes current recordings for 22" computer displays from 40 devices - 20 Dell P2217H and 20 Dell E2214H. Two signals for each device were sampled independently and sequentially to provide independent train and test parts. Each sampled signal includes a 250-second recording at a 50kHz sampling frequency.

This dataset is created for neural network-based surrogate modeling of the power conversion losses. The dataset includes two sets of training and test data (for AC/DC and DC/DC converters respectively) for the neural network. The raw data is generated using PLECS Blockset Packages in MATLAB-Simulink environment. 

Conventionally, the texture of the object is used for material imaging. However, this method can mistake an image of an object, for the object itself. This dataset furthers a new and more relevant method to classify the material of an object. This data is richer, compared to RGB images, because the time of flight responses correlate with the material property of an object. This makes the features, thus extracted, more suitable to infer the material information.

Mindlin Plate data used for training DNN surrogate model for Uncertainty Quantification.

Minimally-Invasive Surgeries can benefit from having miniaturized sensors on surgical graspers to provide additional information to the surgeons. One such potential sensor is an ultrasound transducer. At long travel distances, the ultrasound transducer can accurately measure its ultrasound wave's time of flight, and from it, classify the grasped tissue. However, the ultrasound transducer has a ringing artifact arising from the decaying oscillation of its piezo element, and at short travel distances, the artifact blends with the acoustic echo.

This dataset contains the following simulated information of the IEEE 14 bus system: The 24-hour load profile of all the nodes of the IEE 14 bus circuit, voltages and currents measured by the PMUs placed at optimal locations which minimizes the variance on the estimated voltage states, voltages and currents measured by the PMUs placed at sub-optimal locations.

This publication contains three new datasets for scene-level sketch semantic segmentation task, namely SKY-Scene, TUB-Scene, and Freehand-Scene. SKY-Scene and TUB-Scene are synthetic datasets, where the scene layout templates were extracted from dataset SketchyScene, and the object components were adopted from dataset Sketchy. They are composed to include more sketch-specific characteristics, e.g., sparsity, abstractness, and diversity, to truly evaluate segmentation performance.

Fifty human-drawn scene sketches with semantic annotation.

A synthetic scene-level sketch dataset for sketch semantic segmentation task. The scene layout templates were extracted from dataset SketchyScene, and the object components were adopted from dataset TU-Berlin.

A synthetic scene-level sketch dataset for sketch semantic segmentation task. The scene layout templates were extracted from dataset SketchyScene, and the object components were adopted from dataset Sketchy.