As an alternative to classical cryptography, Physical Layer Security (PhySec) provides primitives to achieve fundamental security goals like confidentiality, authentication or key derivation. Through its origins in the field of information theory, these primitives are rigorously analysed and their information theoretic security is proven. Nevertheless, the practical realizations of the different approaches do take certain assumptions about the physical world as granted.


The data is provided as zipped NumPy arrays with custom headers. To load an file the NumPy package is required.

The respective loadz primitive allows for a straight forward loading of the datasets.

To load a file “file.npz” the following code is sufficient:

import numpy as np

measurement = np.load(’file.npz ’, allow pickle =False)

header , data = measurement [’header ’], measurement [’data ’]

The dataset comes with a supplementary script illustrating the basic usage of the dataset.


The MIMOSigRef-SD dataset was created with the goal to support the research community in the design and development of novel multiple-input multiple-ouotput (MIMO) transceiver architectures. It was recorded using software radios as transmitters and receivers, and a wireless channel emulator to facilitate a realistic representation of a variety of different channel environments and conditions.


The MIMOSigRef-SD dataset is provided in the form of 8 individual TAR files. Each file represents one of the 8 modulation schemes utilized in our dataset. Within each file, the data is organized in a similar format: Naming of the contained folders represents the modulation scheme and order, channel environment, MIMO configuration, and type of MIMO. An example of such naming is: 16QAM – Vehicular B – (TX2 – RX1) – Spatial Diversity. This provides easy access to the information of interest.


YonseiStressImageDatabase is a database built for image-based stress recognition research. We designed an experimental scenario consisting of steps that cause or do not cause stress; Native Language Script Reading, Native Language Interview, Non-native Language Script Reading, Non-native Language Interview. And during the experiment, the subjects were photographed with Kinect v2. We cannot disclose the original image due to privacy issues, so we release feature maps obtained by passing through the network.



Database Structure

- YonseiStressImageDatabase

         - Subject Number (01~50)

                  - Data acquisition phase

                    (Native Language Script Reading, Native Language Interview, Non-native Language Script Reading, Non-native Language Interview)

                           - Data (*.npy, the filename is set to the time the data was acquired; YYYYMMDD_hhmmss_ms)


In the case 'Non-native_Language_Interview' data of subject 26, it was not acquired due to equipment problems.


Citing YonseiStressImageDatabase

If you use YonseiStressImageDatabase in a scientific publication, we would appreciate references to the following paper:

Jeon, T.; Bae, H.B.; Lee, Y.; Jang, S.; Lee, S. Deep-Learning-Based Stress Recognition with Spatial-Temporal Facial Information. Sensors 2021, 21, 7498.


Usage Policy

Copyright © 2019 AI Hub, Inc.,

AI data provided by AI Hub was built as part of a business National Information Society Agency's 'Intelligent information industry infrastructure construction project' in Korea, and the ownership of this database belongs to National Information Society Agency.

Specialized field AI data was built for artificial intelligence technology development and prototype production and can be used for research purposes in various fields such as intelligent services and chatbots.



This file is the related program and data of a deep interpolation convnet for bearing fault classification under complex conditions


Anxiety affects human capabilities and behavior as much as it affects productivity and quality of life. It can be considered as the main cause of depression and suicide. Anxious states are easily detectable by humans due to their acquired cognition, humans interpret the interlocutor’s tone of speech, gesture, facial expressions and recognize their mental state. There is a need for non-invasive reliable techniques that perform the complex task of anxiety detection.


Download Zip file and extract it.


The ADAB database (The Arabic handwriting Data Base) was developed to advance the research and development of Arabic on-line handwritten systems. This database is developed in cooperation between the Institut fuer Nachrichtentechnik (IfN) and Research Groups in Intelligent Machines, University of Sfax, Tunisia. The text written is from 937 Tunisian town/village names. A pre-label assigned to each file consists of the postcode in a sequence of Numeric Character References, which stored in the UPX file format.


Download Zip file and extract it.

A pre-label assigned to each file consists of the postcode in a sequence of Numeric Character References, which stored in the UPX file format. 

An InkML file including trajectory information and a plot image of the word trajectory are also generated. 

Additional information about the writer can also be provided.


The PD-BioStampRC21 dataset provides data from a wearable sensoraccelerometry study conducted for studying activity, gait, tremor, andother motor symptoms in individuals with Parkinson's disease (PD).  Inaddition to individuals with PD, the dataset also includes data forcontrols that also went through the same study protocol as the PDparticipants.  Data were acquired using lightweight MC 10 BioStamp RCsensors (MC 10 Inc, Lexington, MA), five of which were attached toeach participant for gathering data over a roughly two dayinterval.


Users of the dataset should cite the following paper:

Jamie L. Adams, Karthik Dinesh, Christopher W. Snyder, Mulin Xiong,Christopher G. Tarolli, Saloni Sharma, E. Ray Dorsey, Gaurav Sharma,"A real-world study of wearable sensors in Parkinson’sdisease". Accepted for publication at npj Parkinsons Disease, 2021, toappear.

An overview of the study protocol is also provided in the abovementioned paper. Additional detail specific to the dataset and filenaming conventions is provided here.

The dataset is comprised of two main components: (I) Sensor andUPDRS-assessment-task annotation data for each participant and (II)demographic and clinical assessment data for all participants. Each ofthese is described in turn below:

I) Sensor and UPDRS-assessment-task annotation data:

The sensor accelerometry and UPDRS-assessment-task annotation data forall the participants are provided as a zip file The size of the zip file is 11GB and,when unzipped, it generates a set of folders and files with a totalsize of approximately 56GB. Unzipping the file generates folders withname matching the participant ID for each of the Control and PDparticipants (17 Control + 17 PD). Each participant folder containsthe data organized as the following files.

a) Accelerometer sensor data files (CSV) corresponding to the fivedifferent sensor placement locations, which are abbreviated as:  

1) Trunk (chest)           - abbreviated as "ch"  

2) Left anterior thigh     - abbreviated as "ll"  

3) Right anterior thigh    - abbreviated as "rl"  

4) Left anterior forearm   - abbreviated as "lh"  

5) Right anterior forearm  - abbreviated as "rh"   

Example file name for accelerometer sensor data files:   "AbbreviatedSensorLocation"_ID"ParticipantID"Accel.csv   E.g. ch_ID018Accel.csv, ll_ID018Accel.csv, rl_ID018Accel.csv,   lh_ID018Accel.csv, and rh_ID018Accel.csv  

File format for the accelerometer sensor data files: Comprises of four columns that provide a timestamp for each measurement and   corresponding triaxial accelerometry relative to the sensor   coordinate system.     

Column 1: "Timestamp (ms)" - Time in milliseconds  

Column 2: "Accel X (g)"    - Acceleration in X-direction (in units of g = 9.8 m/s^2)

   Column 3: "Accel Y (g)"    - Acceleration in Y-direction (in units of g = 9.8 m/s^2)

   Column 4: "Accel Z (g)"    - Acceleration in Z-direction (in units of g = 9.8 m/s^2)

   Times and timestamps are consistently reported in units of   milliseconds starting from the instant of the earliest sensor   recording (for the first sensor applied to the participant).

b) Annotation file (CSV). This file provides tagging annotations for   the sensor data that identify, via start and end timestamps, the   durations of various clinical assessments performed in the study.   

   Example file name for annotation file: AnnotID"ParticipantID".csv   E.g. AnnotID018.csv   

   File format for the annotation file: Comprises of four columns

   Column 1: "Event Type"           - List of in-clinic MDS-UPDRS assessments. Each assessment comprises of                                       two queries -  medication status and MDS-UPDRS assessment body locations

   Column 2: "Start Timestamp (ms)" - Start timestamp for the MDS-UPDRS assessments

   Column 3: "Stop Timestamp (ms)"  - Stop timestamp for the MDS-UPDRS assessments

   Column 4: "Value"                - Responses to the queries in Column 1 - medication status (OFF/ON) and                                       MDS-UPDRS assessment body locations (E.g. RIGHT HAND, NECK, etc.)   

II) Demographic and clinical assessment data

For all participants, the demographic and clinical assessment data areprovided as a zip file "". Unzippingthe file generates a CSV file named Clinic_Data_PD-BioStampRC21.csv

File format for the demographic and clinical assessment data file: Comprises of 19 columns

Column 1: "ID"                                               - Participant ID

Column 2: "Sex"                                              - Participant sex (Male/Female)

Column 3: "Status"                                           - Participant disease status (PD/Control)

Column 4: "Age"                                              - Participant age

Column 5: "updrs_3_17a"                                      - Rest tremor amplitude (RUE - Right Upper Extremity)

Column 6: "updrs_3_17b"                                      - Rest tremor amplitude (LUE - Left Upper Extremity)

Column 7: "updrs_3_17c"                                      - Rest tremor amplitude (RLE - Right Lower Extremity)

Column 8: "updrs_3_17d"                                      - Rest tremor amplitude (LLE - Right Lower Extremity)

Column 9: "updrs_3_17e"                                      - Rest tremor amplitude (Lip/Jaw)

Column 10 - Column 14: "updrs_3_17a_off" - "updrs_3_17e_off" - Rest tremor amplitude during OFF medication assessment                                                                (ordering similar as that from Column 5 to Column 9)

Column 15 - Column 19: "updrs_3_17a_on" - "updrs_3_17e_on"   - Rest tremor amplitude during ON medication assessment

Note that columns 10-19 do not contain any data for controlparticipants and for PD participants that did not participate in theON/OFF medication component of the assessment protocol for the study.

For details about different MDS-UPDRS assessments and scoring schemes, the reader is referred to:        

Goetz, C. G. et al. Movement Disorder Society-sponsored revision ofthe Unified Parkinson's Disease Rating Scale (MDS-UPDRS): scalepresentation and clinimetric testing results. Mov Disord 23,2129-2170, doi:10.1002/mds.22340 (2008)




These .MAT files contain MATLAB Tables of raw and preprocessed data. Information detailing the bed system used to collect these signals and the steps used to create the preprocessed data are contained in a publication in Sensors – Carlson, C.; Turpin, V.-R.; Suliman, A.; Ade, C.; Warren, S.; Thompson, D.E.; Bed-Based Ballistocardiography: Dataset and Ability to Track Cardiovascular Parameters. Sensors 2021, 21, 156.

The reBAP signal is scaled at 100 mmHg/volt. The interbeat interval (IBI), stroke volume (SV), and dP/dt_max are scaled at 1000 ms/volt, 100 mL/volt, and 1 mHg/s/volt, respectively.


This data is used to test parameter estimation algorithms of complex exponiential signal with Gaussian White Noise. The data can be used to test RMSE of different SNR, N, and p value.