Who we are

BDALab is a research group from Brno University of Technology that is focused on development of objective and non-invasive brain diseases analysis methods.

What we do

Using the state-of-the-art techniques of biomedical signal processing, machine learning and statistical analysis we provide neurologists, psychologists and clinical speech therapists with tools for diagnosis and monitoring of different brain diseases. We are working in Health 4.0 concept.

What we offer

We offer a design and implementation of software that can objectively analyse different modalities such as speech, handwriting, postural stability, and brain activity. All solutions provided by BDALab are individualized depending on customer’s requirements.

Our Skills

We mainly deal with speech signal and handwriting processing, but beside this we process MR images, facial expression from videosequences, postural data from pressure pads, etc.

Signal processing

Machine learning

Software development

Health 4.0

Our Team

Meet our team
Publications
Projects we have done
International partners
Awards

Our Partners

Applied Neuroscience research group, CEITEC
FNUSA
FN Brno
MUNI
Ciberehd
Hospital de Mataró
Tecnocampus
University of Haifa
IIASS
EHU
UPM
CTB
ULPGC
IDETIC
UVIC
Gjovik
Inria
Stirling
IBA
SPLab
TUKE
University of Antioquia
MUNI FF
University of Arizona
University of Szeged

We were the first who quantified in-air movement in parkinsonic dysgraphia analysis.

Our Projects

Selected projects we participated on.

  • 18-16835S - Research of advanced developmental dysgraphia diagnosis and rating methods based on quantitative analysis of online handwriting and drawing (2018-2020, Czech Science Foundation)
  • CoBeN - Novel Network-Based Approaches for Studying Cognitive Dysfunction in Behavioral Neurology (2017-2021, Marie Skłodowska-Curie Research and Innovation Staff Exchange)
  • 16-30805A - Effects of non-invasive brain stimulation on hypokinetic dysarthria, micrographia, and brain plasticity in patients with Parkinson's disease (2016-2019, Ministry of Health)
  • NT13499 - Speech, its impairment and cognitive performance in Parkinson's disease (2012-2015, Ministry of Health)
  • GAP102/12/1104 - Study of metabolism and localization of high grade glioma using MR imaging techniques (2012-2014, Czech Science Foundation)
  • COST IC1206 - De-Identification for Privacy Protection in Multimedia Content (2013-2016, European Union)
  • OC08057 - Analysis and Enhancement of Speech and Image Signals form Noise for Cross-Modal Analysis of Verbal and Non-verbal Communication (2008-2010, Ministry of Education, Youth and Sports)
  • EE.2.3.20.0094 - Support for incorporating R&D teams in international cooperation in the area of image and audio signal processing (2011-2014, Ministry of Education, Youth and Sports)

Downloads

Use our databases and software for your research.

Parkinson's Disease Handwriting Database (PaHaW)

Description

The Parkinson's Disease Handwriting Database (PaHaW) consists of multiple handwriting samples from 37 parkinsonian patients (19 men/18 women) and 38 gender and age matched controls (20 men/18 women). The database was acquired in cooperation with the Movement Disorders Center at the First Department of Neurology, Masaryk University and St. Anne's University Hospital in Brno, Czech Republic.


handwriting template

Each subject was asked to complete a handwriting task according to the prepared filled template at a comfortable speed. The completed task sheet is depicted on the right. The completed template was shown to the subjects; no restrictions about the number of repetitions of syllables/words in tasks or their height were given.


A tablet was overlaid with a empty paper template (containing only printed lines and square box specifying area for Archimedean spiral), and a conventional ink pen was held in a normal fashion, allowing for immediate full visual feedback. The signals were recorded using the Intuos 4M (Wacom technology) digitizing tablet with 200 Hz sampling frequency.


Digitized signals were acquired during the movements executed while exerting pressure on the writing surface and during the movement above the writing surface. We denote these signals as on-surface movement and in-air movement, respectively. The perpendicular pressure exerted on the tablet surface was also recorded. The recordings started when the pen touched the surface of the digitizer and finished when the task was completed. the tablet captured the following dynamic features (time-sequences): x-coordinate; y-coordinate; time stamp; button status; pressure; tilt; and elevation. Button status is a binary variable, being 0 for pen-up state (in-air movement) and 1 for pen-down state (on-surface movement).

Access to the database

Please fill in a license agreement that can be downloaded in DOCX or PDF and send it to mekyska@feec.vutbr.cz with CC to peter.drotar@tuke.sk and irena.rektorova@fnusa.cz. You will consequently get an access to the database.


Tweets

Check what's going on at our laboratory.