Discrete-time signal processing

This dataset contains the actual sensor and calculated process variables in a winder station in a paper mill. Several Process variables change in time with the change of the rewind diameter. I provided the process data for two sets, in future I will add more data. Advanced time series forcasting techniques can be used to estimate many process variables considering the rewind diameter as the time axis.

65 views
  • Machine Learning
  • Last Updated On: 
    Tue, 10/08/2019 - 06:23

    Dataset for Flood paper.

    24 views
  • Machine Learning
  • Last Updated On: 
    Thu, 10/10/2019 - 23:45

    Typically, a paper mill comprises three main stations: Paper machine, Winder station, and Wrapping station. The Paper machine produces paper with particular grammage in gsm (gram per square meter). The typical grammage classes in our paper mill are 48 gsm, 50 gsm, 58 gsm, 60 gsm, 68 gsm, 70 gsm. The Winder station takes a paper spool that is about 6 m width as it’s input and transfers is to customized paper rolls with particular diameter and width.

    70 views
  • Artificial Intelligence
  • Last Updated On: 
    Tue, 10/08/2019 - 06:26

    This dataset shows the amount of water used by a company in southern China from 2016 to 2017.

    137 views
  • Discrete-time signal processing
  • Last Updated On: 
    Sun, 09/29/2019 - 00:13

    S&P 500 index of monthly data of bull/bear markets

    155 views
  • Nonlinear signal processing
  • Last Updated On: 
    Mon, 08/19/2019 - 04:52

    The dataset has 150 three-second sampling motor current signals from each synthetically-prepared motors. There are five motors with respective fault condition - bearing axis deviation (F1), stator coil inter-turn short circuit (F2), rotor broken strip (F3), outer bearing ring damage (F4), and healthy (H). The motors are run under five coupling loads - 0, 25, 50, 75, and 100%. The sampling signals are collected and processed into frequency occurrence plots (FOPs). Each image has a label, for example F2_L50_130, where F2 is the fault condition, L50 is the coupling load condition.

    179 views
  • Sensors
  • Last Updated On: 
    Fri, 05/24/2019 - 22:27

    A VOR receiver based on Software-Defined Radio is presented. Experiments showed that the system indicated the radials of the VOR station of São José dos Campos with an average error rate of less than 1% and a standard deviation of less than 2.14% in relation to those calculated cartographically. The results suggest that low volume and weight SDR-based VOR receivers can be developed with processing on microcontrollers or FPGAs to equip drones that need to operate in aerodrome environments.

     

    256 views
  • Signal Processing
  • Last Updated On: 
    Thu, 11/08/2018 - 10:34

    Audio dataset for Household Multimodal Environment (HoME). It is a collection of audio samples from the Freesound.org collaborative database of Creative Commons Licensed sounds.

    171 views
  • Discrete-time signal processing
  • Last Updated On: 
    Tue, 08/07/2018 - 11:57

    This dataset includes  the Channels Switch Sequences of 300 IPTV viewers in Guangzhou, P.R. China, in Augest, 2014. There are 4 columns in the file, which represent viewer ID, the current channel number, the next channel number, the date of the month, respectively. The first column, the ID code of a viewer, ranks in descent with the times the viewer watched tv channels. The more times a viewer watches tv channels, the bigger the ID is. In a day, the rows are time series and generated step by step as the real watching tv behavior. 

     

     

     

     

    275 views
  • Communications
  • Last Updated On: 
    Thu, 11/08/2018 - 10:34

    This dataset includes  the Channels Switch Sequences of 300 IPTV viewers in Guangzhou, P.R. China, in Augest, 2014.

    There are 4 columns in the file, which represent viewer ID, the current channel number, th next channel number, the date of the month, respectively.

    The first column, the ID code of a viewter, ranks with the times the viewer watched tv channels. The more times a viewer watches tv channels, the bigger

    the ID is. In a day, the rows are time series and generated step by step as the real watching tv behavior. 

     

     

     

     

    60 views
  • Communications
  • Last Updated On: 
    Thu, 11/08/2018 - 10:34