User:Jamesdoshea/Sandbox

The Silent Talker Lie Detector
Silent Talker is a Lie Detector which observes and analyses non-verbal behaviour in the form of micro-gestures while a subject is being interviewed. It is grounded in the psychological theory that non-verbal behaviour is modified by a number of influences when a person is being deceptive. These include arousal ( in particular stress), cognitive load, duping delight and behaviour control).

History
Silent Talker was invented between 2000 and 2002 by a team at Manchester Metropolitan University, Zuhair Bandar, David McLean, James O’Shea and Janet Rothwell. Following its invention, the Silent Talker Adaptive Psychological Profiling architecture and its specific instantiation as a lie detector, were patented internationally. In the interim, the inventors have been involved in raising investment funding and the code has been ported to various programming languages and speeded up from near real-time to real-time response. A study is currently underway to adapt the technology to the measurement of comprehension amongst participants giving informed consent to take part in clinical trials.

Testing procedure
The subject of the interview is observed by one or more cameras (e.g. head-and-shoulders, full body view, thermal imaging camera), which input the video stream to a conventional computer. As the interview takes place, Silent talker’s model of truthful vs. deceptive behaviour is used to classify the answers to the questions as truthful or deceptive in real-time. This can be as a classification at the end of the answer to a question or as a continuous monitoring stream during the interview. No calibration is required to tune the system to individuals and no training of the interviewer is required to interpret the Silent Talker classifications.

Validity
The fundamental phenomenon behind Silent Talker is non-verbal behaviour. Non-verbal behaviour is a well-established field of academic study with its origins in the work of Charles Darwin. Modern analysis of non-verbal behaviour at a fine-grained temporal level has its origins in the work of Efron. Investigations of training humans to detect truth and deceit conducted by Vrij et al. provide evidence to support the effectiveness of non-verbal behaviour as a predictive feature.

Artificial Neural Networks have been described as having a " remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. ", they have been established as a subfield of Artificial Intelligence for over 60 years and are the subject of dedicated, high impact journals such as Neural Networks. Consequently they provide a scientifically credible basis for Silent Talker's classifiers.

The distinctive features of Silent Talker are:
 * It uses banks of Artificial Neural Network classifiers to identify features
 * It uses further banks of Artificial Neural Network classifiers to detect microgestures
 * The microgestures are coded into channels over a time period.
 * The relationships between events in the channels over the time period are analysed by Artificial Neural Networks to make the classification.
 * The Artificial Neural Networks were trained using video data collected from experiments
 * Thus the classifier Artificial Neural Networks discovered which features were important and the relationships between them that discriminate between deceptive and truthful non-verbal behaviour.

Silent Talker has been published in peer-reviewed journals for both the Psychology and Artificial Intelligence communities. ``

Countermeasures
As other lie detectors detect changes in stress, the most common approach is to disrupt this either by practicing calming techniques during lying or artificially raising stress during truth-telling. Because Silent Talker is based on a multi-factor model including cognitive load, duping delight and behaviour control, its inventors claim that it is robust to countermeasures. In fact it is believed that because a large number of channels are used, attempts at behaviour control will generate more incongruities between channels which can be detected. Further experimental trials are required to investigate this hypothesis.

Some reactions to Silent Talker
The Independent newspaper http://www.independent.co.uk/news/science/truth-machine-means-liars-must-keep-a-straight-face-604482.html

The Guardian newspaper http://www.guardian.co.uk/politics/2003/jun/19/labour.comment

The Times newspaper http://www.timesonline.co.uk/tol/life_and_style/education/article438756.ece

BBC Radio 4 The material World http://www.bbc.co.uk/radio4/science/thematerialworld_20030130.shtml

BBC Television News http://news.bbc.co.uk/1/hi/england/2944563.stm

CBS Television News http://www.cbsnews.com/stories/2003/01/28/tech/main538242.shtml

ABC Radio news http://www.abc.net.au/rn/scienceshow/stories/2009/2674304.htm

The Engineer http://www.theengineer.co.uk/in-depth/the-truth-will-out/278743.article

The Scottish Herald http://www.heraldscotland.com/truth-behind-an-industry-full-of-fibs-1.840722

The Futurist http://pqasb.pqarchiver.com/futurist/results.html?QryTxt=New+System+Reads+Body+Language.+The+FuturistLie detector