We provide a public available database for arcing event detection. We design a platform for arcing fault simulation. The arc simulation is carried out in our local lab under room temperature. A general procedure to collect the arcing and normal current and voltage wave, is designed, which consists of turning on the load, generating arc, stoping arc, turning off the load. The data is collected by a 16bit, 10KHz high resolution recorder and a 12bit, 64000Hz low resolution sensor.


This file is collected from a tool holder with four stain gauges for detecting machining variation in a machine tool. The associated collected signal data and description will be provided soon. 


The dataset is composed of digital signals obtained from a capacitive sensor electrodes that are immersed in water or in oil. Each signal, stored in one row, is composed of 10 consecutive intensity values and a label in the last column. The label is +1 for a water-immersed sensor electrode and -1 for an oil-immersed sensor electrode. This dataset should be used to train a classifier to infer the type of material in which an electrode is immersed in (water or oil), given a sample signal composed of 10 consecutive values.


The dataset is acquired from a capacitive sensor array composed of a set of sensor electrodes immersed in three different phases: air, oil, and water. It is composed of digital signals obtained from one electrode while it was immersed in the oil and water phases at different times. 

## Experimental setup

The experimental setup is composed of a capacitive sensor array that holds a set of sensing cells (electrodes) distributed vertically along the sensor body (PCB). The electrodes are excited sequentially and the voltage (digital) of each electrode is measured and recorded. The voltages of each electrode are converted to intensity values by the following equation:

intensity = ( |Measured Voltage - Base Voltage| / Base Voltage ) x 100

Where the Base Voltage is the voltage of the electrode recorded while the electrode is immersed in air. The intensity values are stored in the dataset instead of the raw voltage values.

## Experimental procedure 

The aim of the experiments is to get fixed-size intensity signals from one electrode (target electrode) when being immersed in water and oil; labeled as +1 (water) or -1 (oil). For this purpose, the following procedure was applied:

- The linear actuator was programmed to move the sensor up and down at a constant speed (20 mm / second).

- The actuator stops when reaching the upper and bottom positions for a fixed duration of time (60 seconds).

- At the upper position, the target electrode is immersed in oil; intensity signals are labeled -1 and sent to the PC.

- At the bottom position, the target electrode is immersed in water; intensity signals are labeled +1 and sent to the PC.

- The sampling rate is 100 msec; since each intensity signal contains 10 values, it takes 1 second to record one intensity signal 

## Environmental conditions

The experiments were perfomed under indoors laboratory conditions with room temperature of around 23 degree Celsius. 

## Dataset structure 

The signals included in the dataset are composed of intensity signals each with 10 consecutive values and a label in the last column. The label is +1 for a water-immersed electrode and -1 for an oil-immersed electrode.

## Application

The dataset should be used to train a classifier to differentiate between electrodes immersed in water and oil phases given a sample signal.

  • Graph x and Y in ABS experiment


The data set contains electrical and mechanical signals from experiments on three-phase induction motors. The experimental tests were carried out for different mechanical loads on the induction motor axis and different severities of broken bar defects in the motor rotor, including data regarding the rotor without defects. Ten repetitions were performed for each experimental condition.


Experimental Setup:

The experimental workbench consists of a three-phase induction motor coupled with a direct-current machine, which works as a generator simulating the load torque, connected by a shaft containing a rotary torque wrench.

- Induction motor: 1hp, 220V/380V, 3.02A/1.75A, 4 poles, 60 Hz, with a nominal torque of 4.1 Nm and a rated speed of 1715 rpm. The rotor is of the squirrel cage type composed of 34 bars.

- Load torque: is adjusted by varying the field winding voltage of direct current generator. A single-phase voltage variator with a filtered full-bridge rectifier is used for the purpose. An induction motor was tested under 12.5, 25, 37.5, 50, 62.5, 75, 87.5 and 100% of full load.

- Broken rotor bar: to simulate the failure on the three-phase induction motor's rotor, it was necessary to drill the rotor. The rupture rotor bars are generally adjacent to the first rotor bar, 4 rotors have been tested, the first with a break bar, the second with two adjacent broken bars, and so on rotor containing four bars adjacent broken.

Monitoring condition:

All signals were sampled at the same time for 18 seconds for each loading condition and ten repetitions were performed from transient to steady state of the induction motor.

- mechanical signals: five axial accelerometers were used simultaneously, with a sensitivity of 10 mV/mm/s, frequency range from 5 to 2000Hz and stainless steel housing, allowing vibration measurements in both drive end (DE) and non-drive end (NDE) sides of the motor, axially or radially, in the horizontal or vertical directions.

- electrical signals: the currents were measured by alternating current probes, which correspond to precision meters, with a capacity of up to 50ARMS, with an output voltage of 10 mV/A, corresponding to the Yokogawa 96033 model. The voltages were measured directly at the induction terminals using voltage points of the oscilloscope and the manufacturer Yokogawa.

Data Set Overview:

-          Three-phase Voltage

-          Three-phase Current

-          Five Vibration Signals



            The database was acquired in the Laboratory of Intelligent Automation of Processes and Systems and Laboratory of Intelligent Control of Electrical Machines, School of Engineering of São Carlos of the University of São Paulo (USP), Brazil.


We introduce a new database of voice recordings with the goal of supporting research on vulnerabilities and protection of voice-controlled systems (VCSs). In contrast to prior efforts, the proposed database contains both genuine voice commands and replayed recordings of such commands, collected in realistic VCSs usage scenarios and using modern voice assistant development kits.


The corpus consists of three sets: the core, evaluation, and complete set. The complete set contains all the data (i.e., complete set = core set + evaluation set) and allows the user to freely split the training/test set. Core/evaluation sets suggest a default training/test split. For each set, all *.wav files are in the /data directory and the meta information is in meta.csv file. The protocol is described in the readme.txt. A PyTorch data loader script is provided as an example of how to use the data. A python resample script is provided for resampling the dataset into the desired sample rate.


Dataset asscociated with a paper in IEEE Transactions on Pattern Analysis and Machine Intelligence

"The perils and pitfalls of block design for EEG classification experiments"

DOI: 10.1109/TPAMI.2020.2973153

 If you use this code or data, please cite the above paper.


See the paper "The perils and pitfalls of block design for EEG classification experiments" on IEEE Xplore.

DOI: 10.1109/TPAMI.2020.2973153

Code for analyzing the dataset is included in the online supplementary materials for the paper.

The code and the appendix from the online supplementary materials are also included here.

If you use this code or data, please cite the above paper.


This dataset is composed of 4-Dimensional time series files, representing the movements of all 38 participants during a novel control task. In the ‘5D_Data_Extractor.py’ file this can be set up to 6-Dimension, by the ‘fields_included’ variable. Two folders are included, one ready for preprocessing (‘subjects raw’) and the other already preprocessed ‘subjects preprocessed’.


These uploaded video files show the results of distributed multi-vehicle SLAM in three cases:1, simulated scenario;2, UTIAS dataset;3, Victoria park dataset.


Time Scale Modification (TSM) is a well-researched field; however, no effective objective measure of quality exists.  This paper details the creation, subjective evaluation, and analysis of a dataset for use in the development of an objective measure of quality for TSM. Comprised of two parts, the training component contains 88 source files processed using six TSM methods at 10 time scales, while the testing component contains 20 source files processed using three additional methods at four time scales.


When using this dataset, please use the following citation:

author = {Roberts,Timothy and Paliwal,Kuldip K. },
title = {A time-scale modification dataset with subjective quality labels},
journal = {The Journal of the Acoustical Society of America},
volume = {148},
number = {1},
pages = {201-210},
year = {2020},
doi = {10.1121/10.0001567},
URL = {https://doi.org/10.1121/10.0001567},
eprint = {https://doi.org/10.1121/10.0001567}


Audio files are named using the following structure: SourceName_TSMmethod_TSMratio_per.wav and split into multiple zip files.For 'TSMmethod', PV is the Phase Vocoder algorithm, PV_IPL is the Identity Phase Locking Phase Vocoder algorithm, WSOLA is the Waveform Similarity Overlap-Add algorithm, FESOLA is the Fuzzy Epoch Synchronous Overlap-Add algorithm, HPTSM is the Harmonic-Percussive Separation Time-Scale Modification algorithm and uTVS is the Mel-Scale Sub-Band Modelling Filterbank algorithm. Elastique is the z-Plane Elastique algorithm, NMF is the Non-Negative Matrix Factorization algorithm and FuzzyPV is the Phase Vocoder algorithm using Fuzzy Classification of Spectral Bins.TSM ratios range from 33% to 192% for training files, 20% to 200% for testing files and 22% to 220% for evaluation files.

  • Train: Contains 5280 processed files for training neural networks
  • Test: Contains 240 processed files for testing neural networks
  • Ref_Train: Contains the 88 reference files for the processed training files
  • Ref_Test: Contains the 20 reference files for the processed testing files
  • Eval: Contains 6000 processed files for evaluating TSM methods.  The 20 reference test files were processed at 20 time-scales using the following methods:
    • Phase Vocoder (PV)
    • Identity Phase-Locking Phase Vocoder (IPL)
    • Scaled Phase-Locking Phase Vocoder (SPL)
    • Phavorit IPL and SPL
    • Phase Vocoder with Fuzzy Classification of Spectral Bins (FuzzyPV)
    • Waveform Similarity Overlap-Add (WSOLA)
    • Epoch Synchronous Overlap-Add (ESOLA)
    • Fuzzy Epoch Synchronous Overlap-Add (FESOLA)
    • Driedger's Identity Phase-Locking Phase Vocoder (DrIPL)
    • Harmonic Percussive Separation Time-Scale Modification (HPTSM)
    • uTVS used in Subjective testing (uTVS_Subj)
    • updated uTVS (uTVS)
    • Non-Negative Matrix Factorization Time-Scale Modification (NMFTSM)
    • Elastique.


TSM_MOS_Scores.mat is a version 7 MATLAB save file and contains a struct called data that has the following fields:

  • test_loc: Legacy folder location of the test file.
  • test_name: Name of the test file.
  • ref_loc: Legacy folder location of reference file.
  • ref_name: Name of the reference file.
  • method: The method used for processing the file.
  • TSM: The time-scale ratio (in percent) used for processing the file. 100(%) is unity processing. 50(%) is half speed, 200(%) is double speed.
  • MeanOS: Normalized Mean Opinion Score.
  • MedianOS: Normalized Median Opinion Score.
  • std: Standard Deviation of MeanOS.
  • MeanOS_RAW: Mean Opinion Score before normalization.
  • MedianOS_RAW: Median Opinion Scores before normalization.
  • std_RAW: Standard Deviation of MeanOS before normalization.


TSM_MOS_Scores.csv is a csv containing the same fields as columns.

Source Code and method implementations are available at www.github.com/zygurt/TSM

Please Note: Labels for the files will be uploaded after paper publication.