L.N. Anishchenko - Ph.D. (Eng.), Senior Research Scientist, Research Section of Scientific and Educational Complex «Basic Sciences», Bauman Moscow State Technical University
E.M. Rutskova - Ph.D. (Biol.), IHNA&NPh RAS (Moscow)
At present sleep-wake cycle studies in laboratory animals are based on electroencephalogram and electrimiorgam signals analysis, which are registered by implanted electrodes. The main drawback of such method is the necessity to implant them, which is time and labor consuming task involving ethical issues. That is why development of new noncontact methods for remote monitoring of laboratory animals vital signs and corresponding algorithms for sleep-wake cycle stages classification are up-to-date tasks. Such methods would not have an impact on the animal, unlike the implanted ones, which would allow increasing the informative value of the registered data.
In this paper we propose to use the method of bioradiolocation for remote monitoring of laboratory animals sleep-wake cycle during prolonged period (e.g. for several days). The algorithm for bioradar signal pre-processing is described, and list features for each epoch classification is proposed. Analysis of feature vector with the help of sequential forward selection algorithm allows to reduce the used features number from 24 to 10 while maintaining sleep-stages classification quality at the same level with Kohen's kappa of 55 % and accuracy of 77 %. As a ground truth we used classified data of a standard biology method based on analysis of signals registered by means of implanted EEG and EMG. Classifier performance was estimated using data gathered during sleep experiments conducted in a laboratory of Neuroontogenesis of Institute of Higher Nervous Activity and Neurophysiology of RAS.
- Ethovision XT. http://www.noldus.com/animal-behavior-research/products/ethovision-xt (data obrashhenija 31.05.2017).
- PhenoMaster/LabMaster, http://www.tse-systems.com/products/metabolism/home-cage/phenomaster/index.htm (data obrashhenija 31.05.2017).
- Sistema NM-2 dlja izuchenija potreblenija edy, pit'ja i registracii aktivnosti. http://ec2-52-58-138-81.eu-central-1.compute.amazonaws.com/ products/sistema-nm-2 (data obrashhenija 31.05.2017).
- Pattent № 3633011 (USA). Apparatus for measuring the activity of laboratory animals / S. Bederman, L.G. Lankford.
- ECGenie. Awake Lab Animal ECG System. https://mou¬ses¬pecifics.com/heart-monitoring/ecgenie/ (accessed May 2017).
- Pattent № 5608209 (USА). Method and apparatus for measuring motion amount of laboratory animal / Matsuda Hideo.
- Li C., Lin J. Microwave Noncontact Motion Sensing and Analysis. John Wiley & Sons, Inc. 2014. 238 p.
- Anishchenko L., Bechtel T., Ivashov S., Alekhin M., Tataraidze A., Vasiliev I. Bioradiolocation as a Technique for Remote Monitoring of Vital Signs / In: Advanced Ultrawideband Radar: Signals, Targets and Applications. Taylor J.D. (Ed.). CRC Press. 2016. P. 297-322.
- Wu Q., Zhang Y.D., Tao W., Amin M.G. Radar-based fall detection based on Doppler time-frequency signatures for assisted living // IET Radar, Sonar & Navigation. Special issue on Application of Radar to Remote Patient Monitoring and Eldercare. 2015. V. 9. № 2. Р. 164–172.
- Huang T.Y., Lin J., Hayward L. Non-invasive measurement of laboratory rat's cardiorespiratory movement using a 60-GHz radar and nonlinear Doppler phase modulation // IEEE MTT-S 2015 International Microwave Workshop Series on RF and Wireless Technologies for Biomedical and Heal-thcare Applications (IMWS-BIO). Taipei. 2015. Р. 83-84.
- Anishchenko L.N., Rutskova E.M., Dremina M.K., Anishchenko L.N. Contactless fall detection by means of CW bioradar // Progress in Electromagnetic Research Symposium (PIERS). St. Petesburg, Moscow. 2017 (in press).
- Anishhenko L.N., Tataraidze A.B., Ruckova E.M. Verifikacija rezul'tatov beskontaktnogo monitoringa patterna dyhanija zhivotnogo pri pomoshhi bioradiolokatora // Biomedicinskaja radiojelektronika. 2016. № 7. C. 56–63.
- Anishchenko L., Gennarelli G., Tataraidze A., Gaisina E., Soldovieri F., Ivashov S. Evaluation of rodents' respiratory activity using a bioradar // IET Radar, Sonar & Navigation. 2015. V. 9. Iss. 9. Р. 1296–1302.
- Kudo M., Sklansky J. Comparison of algorithms that select features for pattern classifiers // Pattern Recognition. 2000. V. 33. № 1. Р. 25-41.