Andrey N. Yakovlev

Andrey N. Yakovlev is a researcher affiliated with the Federal Research Center "Computer Science and Control" at the Russian Academy of Sciences in Moscow, Russia. His work focuses on the intersection of machine learning and psychophysiological detection, contributing to computational approaches in polygraph science. While limited information is publicly available about his broader career, his 2022 publication indicates involvement in a Russian research team exploring automated approaches to deception detection.

Yakovlev co-authored research proposing a machine learning approach to automate the polygraph examiner's work using neural network architectures from the scikit-learn library based on the Voting Classification architecture and a transformer, which aimed to increase the efficiency of polygraph testing and decrease the number of erroneous conclusions on testees' answers. The methodology utilized standard polygraph channels: electrodermal resistance (galvanic skin response), blood vessel capacity (plethysmogram), and respiratory rhythms. This work represents an application of contemporary machine learning techniques to traditional psychophysiological measurement, a growing area of interest in automated scoring and test data analysis.

Yakovlev worked as part of a collaborative research team at the Federal Research Center that included Lev A. Derevyagin, Veniamin V. Makarov (corresponding author), Andrey Yuryevich Molchanov, and Vladimir I. Tsurkov. This group appears to be exploring computational methods for improving polygraph testing reliability, a topic that has seen renewed interest with advances in artificial intelligence and neural networks. Their 2022 paper was published in the Journal of Computer and Systems Sciences International, a peer-reviewed journal focused on control theory, systems science, and computational applications.