Xinmeng Wang1, Yuanqing Shi2, Lu Liu2, *
1Nanjing Forest Police College, Nanjing, China
2Shenzhen Cmcross Technology Co., Ltd., Shenzhen, China
*Corresponding author: firstname.lastname@example.org
The studies on polygraph technology in China started in the 1990s, after nearly 30 years of research and practice, great progress has been made in technical methods, technical equipment, and the development of effective detection indicators, especially Multi-channel polygraph technology has been widely used in the fields of public security, prosecution, and law enforcement etc., with many successful use cases. But there are still many bottlenecks that are preventing the adaption of polygraph technology in the other areas. With the recent development of new technologies such as big data, machine vision and deep learning, new opportunities have been brought to solve historical issues. This article proposes a new psychological detection solution by leveraging these new technologies, specifically, we are proposing to use non-invasive technique, i.e., video based machine vision and deep learning, to measure the physiological indicator that cannot be controlled by subjective consciousness, which, combined with other indicators such as expression recognition, and big data, provides a better and more accurate multiple dimension psychological indicator recognition solution. This paper attempt to discuss the technical principles, system design, and application of this new solution.
non-invasive physiological index recognition, psychological recognition, emotion recognition, machine vision, deep learning, big data
Xinmeng Wang, Yuanqing Shi, Lu Liu. Research on non-invasive psychological detection technology based on artificial intelligence. Academic Journal of Humanities & Social Sciences (2021) Vol. 4, Issue 3: 10-16. https://doi.org/10.25236/AJHSS.2021.040303.
 Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology, “Heart rate variability: standards of measurement, physiological interpretation, and clinical use,” European Heart Journal, vol. 17, pp. 1043-1065,
 Accuracy Demonstrations, Threat, and the Detection of Deception: Cardiovascular, Electrodermal, and Pupillary Measures, M. T. BRADLEY AND MICHEL PIERRE JANISSE, PSYCHOPHYSIOLOOY.
 PokerMetrics: Stress and Lie Detection through Non-Invasive Physiological Sensing, M Sung, A Pentland - Tech. Rep, MIT Media Lab, 2005.
 Mental stress detection using physiological signals based on soft computing techniques, 2011 18th Iranian Conference of Biomedical Engineering (ICBME).
 F.Adib, Z.Kabelac, D.Katabi, and R.C.Miller.3d tracking via body radio reflections. In 11th USENIX Symposium on Networked Systems Design and Implementation, 2014.
 C.L. Krumhansl, “An Exploratory Study of Musical Emotions and Psychophysiology,” Canadian J. Experimental Psychology, vol. 51, pp. 336-352, 1997.
 W. Wang, A. C. den Brinker, S. Stuijk, and G. de Haan, “Algorithmic principles of remote-PPG,” IEEE Transactions on Biomedical Engineering, vol. 64, no. 7, pp. 1479–1491, 2017