Alexander N Pisarchik
Universidad Politécnica de Madrid, Centro de Tecnología Biomédica, Distinguished Researcher, Isaac-Peral Chair in Computational System Biology
Alexander Pisarchik is Distinguished Researcher, Isaac-Peral Chair in Computational System Biology at the Center for Biomedical Technology of the Technical University of Madrid. He obtained PhD in Physics and Mathematics in 1990 from the Institute of Physics of the Belarus Academy of Science and in 1997 he completed special courses on Nonlinear Dynamics in Physiology and Medicine at the McGill University, Montreal, Canada and Time Evolution of Complex Systems in Lisbon, Portugal. In 1992 he won a visiting grant from the University Libre of Brussels, and between 1993 and 1998 several grants from Spanish and Catalonia governments and worked at the University Autónoma of Barcelona. In 1995 he was employed as a researcher at the Iceland State University in Reykjavik, and in 1999 as a laser designer at Monocrom: Laser Applications in Vilanova i la Geltrú, Spain. He has been honored with several awards including the First Prize from the Belarus Academy of Science and the Second Prize from the Institute of Physics for his studies on nonlinear dynamics of complex systems. In 1999 he has been awarded by the Patrimonial Cathedra of Excellence from the Council for Science and Technology (CONACYT) and worked at the Center for Optical Research in Mexico. Since 2001 he is a member of the System of National Researchers (SNI). In 2006 he has received the highest level III (equivalent to full professor) in SNI. In 2010-2012 he has been elected member of the Evaluation Commission for the System of National Researchers of CONACYT. In 2013 he has been assigned as Isaac-Peral Chair (the most prestigious grant in Spain) in Computational Systems Biology at the Center for Biomedical Technology in the frame of the BBVA-UPM BioTech Program of Chairs. Dr. Pisarchik is associate editor of Applied Sciences, Frontier in Network Physiology, Biophysical Review and Letters, and Discontinuity, Nonlinearity and Complexity, academic editor of PLoS ONE and Open Life Sciences, editorial board member of several scientific journals, and reviewer of 80 journals. He was guest editor of 18 special volumes of international journals and 6 proceedings of international conferences. He organized 4 international conferences and participated in organization of 3 scientific schools. He is Board Member of International Physics and Control Society (IPACS) and member of 15 scientific societies. He is author and editor of 7 monographs, 17 book chapters, 13 patents and more than 300 papers in peer-reviewed scientific journals. He presented more than 60 invited and plenary lectures at international scientific conferences, led 30 research projects and supervised 13 PhD and 8 master students. His scientific interests cover nonlinear dynamics, chaos, synchronization, neural dynamics, laser dynamics, brain dynamics, multistability, intermittency, stochastic effects, complex networks, cognitive brain functions, EEG, MEG, artificial intelligence, brain-computer interfaces, chaotic cryptography and chaotic communication.
less
InterestsView All (16)
Uploads
Papers by Alexander N Pisarchik
Materials and Methods
The biological part of the investigation. Young healthy outbred CD1 mice were used in our study. They were divided into two groups: control (n=6) and the group with induced chronic epileptiform activity (n=6). Local field potentials (LFP) were recorded from the hippocampus and medial entorhinal cortex of the mice of both groups to register neuronal activity. The LFP recordings were used for deep ANN training. Epileptiform activity in mice was modeled by intraperitoneal injection of pilocarpine (280 mg/kg). LFP were recorded in the awake mice a month after the induction of epileptiform activity.
Mathematical part of the investigation. A deep long short-term memory (LSTM) ANN capable of predicting biological signals of neuronal activity in mice has been developed. The ANN implementation is based on memristive devices, which are described by the equations of the redox processes running in the memristive thin metal–oxide–metal films, e.g., Au/ZrO2(Y)/TiN/Ti and Au/SiO2(Y)/TiN/Ti. In order to train the developed ANN to predict epileptiform activity, a supervised learning algorithm was used, which allowed us to adjust the network parameters and train LSTM on the described recordings of neuronal activity.
Results. After training on the LFP recordings from the hippocampus and medial entorhinal cortex of the mice with chronic epileptiform activity, the proposed deep ANN has demonstrated high values of evaluation metric (root-mean-square error, RMSE) and successfully predicted epileptiform activity shortly before its occurrence (40 ms). The results of the numerical experiments have shown that the RMSE value of 0.019 was reached, which indicates the efficacy of proposed approach. The accuracy of epileptiform activity prediction 40 ms before its occurrence is a significant result and shows the potential of the developed neural network architecture.
Conclusion. The proposed deep ANN can be used to predict pathological neuronal activity including epileptic seizure (focal) activity in mice before its actual occurrence. Besides, it can be applied for building a long-term prognosis of the disease course based on the LFP data. Thus, the proposed ANN based on memristive devices represents a novel approach to the prediction and analysis of pathological neuronal activity possessing a potential for improving the diagnosis and prognostication of epileptic seizures and other diseases associated with neuronal activity.
The conference was focused on the multidisciplinary topics of Physics and Control with emphasis on both theory and applications. The event was provided insights into actual problems and scientific issues, which determine the current state and future directions in modern nonlinear dynamics and control theory.
Conference materials are intended for a wide range of scientific and engineering workers, university professors, secondary special educational institutions, graduate students and students.