Research on polygraph technology based on ballistocardiogram signal

Polygraph technology has always been concerned by the society. At present, there are many technologies used in the field of lie detection research. By summarizing the characteristics of the current technology, this paper proposes a multi-channel concealed polygraph technology based on ballistocardiogram (BCG), which can make up for the shortcomings of the existing technology. In this paper, the BCG signal, image signal, speech signal and galvanic skin response (GSR) signal are used to preprocess and extract the features. Using the extracted features to train the classification model, we can get an overall accuracy of 78%, and the area under the curve (AUC) score is 0.84. This experiment proves the effectiveness and advantages of BCG signal for lie detection, and also provides an effective method for the study of concealed polygraph technology.

[1]  M. Palaniswami,et al.  Complex Correlation Measure: a novel descriptor for Poincaré plot , 2009, BioMedical Engineering OnLine.

[2]  Wei Gao,et al.  Obstructive sleep apnea syndrome detection based on ballistocardiogram via machine learning approach. , 2019, Mathematical biosciences and engineering : MBE.

[3]  R D Hare,et al.  Psychopathy and detection of deception in a prison population. , 1978, Psychophysiology.

[4]  Amir Hussain,et al.  Deep learning driven multimodal fusion for automated deception detection , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[5]  Mohamed Abouelenien,et al.  Detecting Deceptive Behavior via Integration of Discriminative Features From Multiple Modalities , 2017, IEEE Transactions on Information Forensics and Security.

[6]  S. Thomas George,et al.  A Study on Using Blink Parameters from EEG Data for Lie Detection , 2018, 2018 International Conference on Computer Communication and Informatics (ICCCI).

[7]  Sipi Dubey,et al.  Deception detection using artificial neural network and support vector machine , 2018, 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA).

[8]  Sung-Nien Yu,et al.  Emotion state identification based on heart rate variability and genetic algorithm , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[9]  Damodar Reddy Edla,et al.  Subject based Deceit Identification using Empirical Mode Decomposition , 2018 .

[10]  Wataru Zaitsu External validity of Concealed Information Test experiment: Comparison of respiration, skin conductance, and heart rate between experimental and field card tests. , 2016, Psychophysiology.

[11]  Verónica Pérez-Rosas,et al.  A Multimodal Dataset for Deception Detection , 2014, LREC.

[12]  T. Seppänen,et al.  Quantitative beat-to-beat analysis of heart rate dynamics during exercise. , 1996, The American journal of physiology.

[13]  Krishna K. Venkatasubramanian,et al.  Ballistocardiogram-based Authentication using Convolutional Neural Networks , 2018, ArXiv.

[14]  Zhu Wang,et al.  Identifying Obstructive Sleep Apnea by Exploiting Fine-Grained BCG Features Based on Event Phase Segmentation , 2016, 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering (BIBE).

[15]  Venu Govindaraju,et al.  Automatic Deceit Indication through Reliable Facial Expressions , 2007, 2007 IEEE Workshop on Automatic Identification Advanced Technologies.

[16]  Heng Wang,et al.  Ballistocardiogram Based Person Identification and Authentication Using Recurrent Neural Networks , 2018, 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[17]  Ahmad Fadzil Ismail,et al.  Lie Detection Using Acceleration Plethysmography Signal , 2018 .

[18]  Mohamed Abouelenien,et al.  Deception Detection using Real-life Trial Data , 2015, ICMI.

[19]  Sarun Sumriddetchkajorn,et al.  Simultaneous Analysis of Far Infrared Signals From Periorbital and Nostril Areas for Nonintrusive Lie Detection: Performance From Real Case Study , 2015, Journal of Lightwave Technology.