METHODS AND ASSETS OF BIOSIGNAL MEASURING AND COMPUTER PROCESSING

1
Lviv Polytechnic National University
2
Lviv Polytechnic National University
3
Lviv Polytechnic National University, Ukraine
4
SoftServe Inc.

Information  about  the psychophysiological  state of humans  is  important not only  in medical practice  for  the diagnosis  of  possible  diseases  but  is  also  for  affective  informatics,  biometrics,  rehabilitation  engineering,  human-machine interaction, etc. Currently biosignals measurement  instrumentations  are highly  specialized  and designed  to process  the  separate types of biosignals  (ECG, EEG), or  to perform  the  specific  tasks,  for  example, medical diagnosis or biometry. Methods  aimed obtaining final top-level information are still "manual" since they rely heavily on the expert’s experience.

Purpose of current work is to consider the ways of provision the flexibility and functionality of bioinformatic means on the basis of computing platforms, digital signal processing methods and machine-learning algorithms.

Genesis of biosignals is analyzed. Classification of biosignals generation methods is proposed:

– biosignals, the primary nature of which is electric (sensing using of electrodes, e.g. EEG);

– biosignals that reflect non-electrical processes in the body (formed by sensors, e.g MCG);

– biosignals, which are a response to external stimuli (e.g. BIA).

Factors  that complicate the processing of biosignals are described. Different generation ways and parameter variabilities become  the appreciable barrier  for  the structure unification of  the computer-measuring systems. Another barrier  is related to  the dissimilarity of  the  algorithms of determining biomedical data. There exist  the drivers  that offer opportunities  in providing  the flexibility and functionality of the bioinformatics system. Such an approach makes possible to distribute the structural elements of a computer-measuring system into three groups:

– individual items (electrodes, sensors, actuators, measuring cascade, stimulus formatter);

– specific group (signal conditioning, ADC and DAC);

– universal group (digital processing unit; computer with software, including library of machine learning algorithms).

At the final stage an interpretation of the results is carried out.

[1] R. Rangayyan. Biomedical Signal Analysis. A CaseStudy Approach. John Willey and Sons Inc. 2002.

[2] R. Singh, S. Conjeti, R. Banerjee, “Comparative evaluation of neural network classifiers for stress level analysis of automotive drivers using physiological signals”, Biomed. Signal Processing and Control, vol.8, p.740-744, 2013.

[3] D. Jenkins, S. Gerred, ECGs by Example, 2011. [Online]. Available: https://www.elsevier.com/books/ecgs-byexample/jenkins/978-0-7020-4228-7

[4] K. Najarian, R. Splinter, Biomedical Signal and Image Processing. CRC Press Taylor & Francis Group, 2012.

[5] Advanced Biosignal Processing. Ed. A. Nait-Ali, 2009. [Online]. Available: https://www.springer.com/la/book/9783540895053.

[6] S. Ogloblin, A. Molchanov, Instrumental Detection of Lying. Yaroslavl, RF: Nuances, 2004.

[7] Ya. Zhevandrova, A. Syropyatov, V. Buryak, “Comprehensive Biometric Authentication of Personality”, Information Processing Systems, iss.4(141), p.104-107, 2016.

[8] J. Cunha, B. Cunha, W. Xavier, N. Ferreira, A.Pereira, “Vital-Jacket: a wearable wireless vital signs monitor for patients’ mobility”, in Proc. the Avantex Symposium, 2010, s.1-2. [Online]. Available: https://www.researchgate.net/profile/Nuno_Ferreira11/publication/2241444... vital_signs_monitor_for_patients'_mobility_in_cardiology_and_sports/links/0deec5268d9e86b08e000000/Vital-JacketR-A-wearable-wireless-vital-signs-monitor-for-patientsmobility-in-cardiology-and-sports.pdf

[9] S. Meshchaninov, V. Spivak, A. Orlov, Electronic methods and means of biomedical measurements. Kyiv, Ukraine: KPI, 2015.

[10] V. Khoma, Yu.Khoma, V.Gerasimenko, D. Sabodashko, “ECG-identification using deep neural networks”, Bull. Lviv Polytechn. Nat. Univ. "Automation, Measurement and Control", no.880, p.67-72, 2017.

[11] J. Allen, “Photoplethysmography and its application in clinical physiological measurement”, Physiological Measurement, vol.28, p.1-39, 2007.

[12] D. Nikolaev, Bioimpedance analysis of human body. Moscow, RF: Science, 2009.

[13] M. Dorozhovets, Processing the measurement results. Lviv, Ukraine: Publ. House Lviv Pol. Nat. Univ., 2007.

[14] A. Fedotov, S. Akulov, Measuring transducers of biomedical signals of systems of clinical monitoring. Moscow, RF: Radio and communication, 2013.

[15] V. Khoma, M. Pelc, Y. Khoma, D. Sabodashko, “Outlier Correction in ECG-Based Human Identification”, in Biomedical Engineering and Neuroscience. BCI 2018. Advances in Intelligent Systems and Computing, Springer: vol.720. p.11-22, 2018.

[16] W. Lukasz, Yu. Khoma, P. Falat, D. Sabodashko, V. Herasymenko, “Biometric Identification From Raw ECG Signal Using Deep Learning Techniques”, in Proc. 9th IEEE Internat. Conf. on Intel. Data Acquis. and Adv. Comp. Systems: Technology and Applications, Bucharest, Romania, Sept. 21-23, 2017,pp.129-133.

[17] B. Stadnyk, T. Fröhlich, Yu. Khoma, V. Herasymenko, O. Chaban, “Impedance analyser error correction using artificial neural networks”, in Proc. 59th Ilm. Sc. Col., TU-Ilmenau, Germany, Sept. 11-15, 2017, p.18.

[18] V. Khoma, V. Ivanyuk, “High Sensitive Wiretap Detector: Design and Modeling”, Przegląd Elektrotechniczny, vol.93, no.2, p.250-254, 2017.

[19] M. Dorozhovets, "Conditioning the sensor signals", in “Sensors”. Lviv, Ukraine: Beskyd Bit, 2014, pp.124-152.

[20] Scikit-Learn Machine Learning in Python. [Online]. Available: http://scikit-learn.org/stable/modules/model_evaluation.html#accuracy-score. Acc. Apr. 21, 2017.