Signal Processing

This dataset covers cellular communication signals in the SCF format. There is a total of 60000 signal instances, 36000 of them are reserved as training data and the rest is for the test. The SNR levels are between 1 dB and 15 dB.

44 views
  • Machine Learning
  • Last Updated On: 
    Mon, 01/20/2020 - 15:16

    In the fifth generation (5G) wireless communication, high-speed railway (HSR) communication is one of the most challenging scenarios. By adopting massive multi-input multi-output (mMIMO) technology in HSR communication, the design of the underlying communication system becomes more challenging. Some new channel characteristics must be studied, such as non-stationarity in space, time and frequency domains. In this paper, two models are established for the two states of HSR at rest or in motion.

    22 views
  • Communications
  • Last Updated On: 
    Thu, 01/16/2020 - 10:03

    In the fifth generation (5G) wireless communication, high-speed railway (HSR) communication is one of the most challenging scenarios. By adopting massive multi-input multi-output (mMIMO) technology in HSR communication, the design of the underlying communication system becomes more challenging. Some new channel characteristics must be studied, such as non-stationarity in space, time and frequency domains. In this paper, two models are established for the two states of HSR at rest or in motion.

    14 views
  • Communications
  • Last Updated On: 
    Thu, 01/16/2020 - 09:50

    For more information please take a look at the corresponding paper (DOI: 10.1109/JBHI.2019.2963786)

    59 views
  • Biomedical and Health Sciences
  • Last Updated On: 
    Mon, 01/13/2020 - 08:15

    This dataset contains source and processed audio files designed primarily for use with Time-Scale Modification (TSM) research.  88 source files were processed at 10 different time-scale ratios by 6 different TSM algorithms resulting in training set of 5280 files.  Each file was then subjectively evaluated by a minimum of 7 participants providing opinion scores.  Mean Opinion Scores (MeanOS) and Median Opinion Scores (MedianOS) are provided for each file.  An additional 20 files were processed at 4 time-scale ratios by an additional 3 methods were also subjectively evaluated resulting in a t

    103 views
  • Machine Learning
  • Last Updated On: 
    Thu, 02/27/2020 - 10:07

    With the development of audio synthesis techniques, the most state-of-art synthesis methods are based on  Generative Adversarial Network(GAN)。 To imporve the detection algorithm to discriminate genuine audio from spoofed audio produced using GAN based audio synthesis  shcemes, we make this public dataset.

    53 views
  • Artificial Intelligence
  • Last Updated On: 
    Wed, 02/26/2020 - 23:30

    monitoring, processing and prediction data

    51 views
  • Machine Learning
  • Last Updated On: 
    Mon, 12/23/2019 - 20:42

    The experimental measurement setup is performed in an anechoic chamber to secure the LOS transmission at the Millimeter Wave and Terahertz Technologies Research Laboratories (MILTAL), Scientific and Technological Research Council of Turkey (TUBİTAK), Kocaeli. The dimensions of anechoic chamber are 7m × 4m × 3m. The dataset includes channel impulse response in between 240GHz and 300GHz for the transmitter-receiver distance of 20cm, 30cm, 40cm, 60cm, and 80cm.

    246 views
  • Signal Processing
  • Last Updated On: 
    Tue, 01/21/2020 - 14:54

    The development of electronic nose (e-nose) for a rapid, simple, and low-cost meat assessment system becomes the concern of researchers in recent years. Hence, we provide time-series datasets that were recorded from e-nose for beef quality monitoring experiment. This dataset is originated from 12 type of beef cuts including round (shank), top sirloin, tenderloin, flap meat (flank), striploin (shortloin), brisket, clod/chuck, skirt meat (plate), inside/outside, rib eye, shin, and fat.

    80 views
  • IoT
  • Last Updated On: 
    Fri, 12/06/2019 - 05:37

    This dataset has 11 sets of feature data extracted with different signal-to-noise and a set of simulation results of modulation classification. Feature dataset consists of 2 novel features and 15 classic features, and dataset of simulation results represents the effectiveness of FS_DT-SSVM classifier.

    These data match the experimental data of the paper “Automatic Modulation Classification Based on Novel Feature Extraction Algorithms”.

    38 views
  • Communications
  • Last Updated On: 
    Tue, 12/03/2019 - 22:12

    Pages