The UrbanSense project is the environmental monitoring part of the Smart City initiative at the city of Porto, Portugal. This dataset contains observational data collected at 23 locations: Rua das Flores; Damião de Góis; Reitoria; Praça do Marquês-pole1; Combatentes; Estádio do Dragão; Bolhão-pole1; Avenida de França; Casa da Música; Trindade; Castelo do Queijo; Anemona; Campo Alegre; D.Manuel II; Praça da Galiza; Hospital de S.João; Congregados; Cândido dos Reis; Praça da Liberdade (Cardosas); 24 de Agosto...
The dataset was acquired at Porto, one of the most iconic city of Portugal. It were obtained diverse trajectories in different type of scenarios - around of the costal zone of Matosinhos and in a highway - with a moving car. The dataset provides diverse sensor information mainly by high resolution cameras, LIDAR, GPS and IMU devices installed in the roof of a car from the INESC TEC and provides realistic insights of urban road...
The dataset consists on measurements of the total number of gamma rays counted by a NaI(Tl) scintillator on the roof of INESC TEC main building.
This application allows the user to measure the average width of a chosen blood vessel in a retinal image. After uploading an image, the program automatically segments the blood vessels in the image, and extracts individual vessel segments (by removing junctions). The user then clicks on the segment to be analysed, and the program processes that segment via a model fitting and random forests-based approach to retrieve the average width of that vessel segment. The...
Gamma radiation data from ENVRIplus TNA campaign RELECT at SMEAR II – HYYTIÄLÄ multi-disciplinary RI platform.Susana Barbosa
Gamma radiation measurements in counts/minute (cpm) every 5-minutes.
Electric field data from ENVRIplus TNA campaign RELECT at SMEAR II – HYYTIÄLÄ multi-disciplinary RI platform.Susana Barbosa
Vertical electric field measurements (in V/m), 1-min averages.
This dataset contains 2 subsets of anonymized video capsule endoscopy images with annotated red lesions. Folder "Set 1" has 3,295 non-sequential frames in sub-folder "A" and the corresponding annotated masks in sub-folder "B"; Similarly, folder "Set 2" has 600 sequential frames. All frames are 320x320 pixels wide. This dataset was used in the article "A Deep Learning Approach for Red Lesions Detection in Video Capsule Endoscopies" published at ICIAR 2018 to evaluate deep learning U-Net...
This dataset is taken from the portuguese music social network "Palco Principal", that gathers non-mainstream musicians with fans. The website allows free music streaming and users can organize their favorite music tracks in personal playlists. The dataset consists of three files. Two of them are music streaming logs (one line per play), and one file is a music track playlisting log (users adding music tracks to their personal playlist).
Monitoring of Albergaria Firefighters ECG during emergency events during the summer of 2010 and correspondent event labels.
The dataset consists on 1-min measurements of the atmospheric electric field by a CS110 field mill installed on the roof of INESC TEC main building.
Radon data from ENVRIplus TNA campaign RELECT at SMEAR II – HYYTIÄLÄ multi-disciplinary RI platform.Susana Barbosa
Radon concentration measurements (in Bq/m3) every 2-hours.
This dataset contains breast histology images from four classes: normal, benign, in situ carconima and invasive carcinoma. A trained Convolutional Neural Network for the classification of these images is also available. To access the dataset please request your password via the link http://bioimglab.inesctec.pt/?page_id=893 and fill the form. Users of this dataset should cite the following article: Teresa Araújo, Guilherme Aresta, Eduardo Castro, José Rouco, Paulo Aguiar, Catarina Eloy, António Polónia, and Aurélio Campilho, Classification of...
The dataset consists on measurements every 6-hours of radon concentration on the roof of INESC TEC main building.
The dataset comes originally from UCI Machine Learning. The multiclass datasets were transformed in binary classification as mentioned in the paper. Ranking methods were applied to improve class imbalance. The datasets are divided in 30 folds so that other class imbalance methods can be compared to the methods in the paper. The code used in the paper is also provided.