Purnell’s Lie Detector – Indecent Disclosures

In defiance of Denis Healey’s First Law of Holes, Nemesysco have stuck out a lengthy press release in an effort to defend their technology, one which, rather hilariously puts forward this specific criticism of the work of Professors Eriksson and Lacerda:

The article’s claims that our technology does not work and cannot work are based on assumptions made by Eriksson and Lacerda, selectively (as explained below) citing from only three published US research studies, while completely ignoring all the other studies that have been published in diverse scientific publications, or presented at conferences, many of which are available for review on our web site.

Quite how many of these studies the two Professors have reviewed I’m not certain, but I’ve certainly been through all the studies on Nemesysco’s website and I’m now about to do something that the company hasn’t done – make a full disclosure of interest relating to these studies.

So, taking the studies in date order…

1. The Truster Pro Technology Reliability Test – Research by Shlomo Bruck, chairman of the Israeli polygraph association and owner of URAN Polygraph Ltd.

That would be the same Shlomo Bruck who was described in a 1998 article by Ilene R Prusher as follows:

“Shlomo Bruck, the head of Uran Polygraph, a private polygraph firm in Tel Aviv, and an outside consultant to Mach-Shevet, believes that despite drawbacks, polygraphs remain more accurate than the Truster system but that the new technology is important because of the different ways it can be used.”

Mach Shevet is, of course, the Israeli software company that developed and released the Truster software, the first program derived from Amir Liberman’s 1997 patent.

2. “Forensic Criminology and Psychophysiology: Truth Verification tools, with a special study of Truster Pro” , Drs. Guy van Damme , Crime Research in South Africa (CRISA), Volume 2, Number 2 (April 2001)

Drs. Guy I L M Van Damme is listed, on his LinkedIn profile, as the owner of Nemesysco’s South African Service Centre.

3. Preliminary Results from a Comparative Analysis Conducted in a Criminal Justice Field Setting By John Joseph Palmatier – Ph.D.

Palmatier’s finished paper does not appear on Nemesysco’s website, but can be found on the website of Nemesysco’s UK distributors, DigiLog UK, under the title ‘A Study Testing the Validity of Truster Voice Analysis Technology in a Criminal Field Context.”

And what the full paper discloses is…

A trained voice analyst in Israel, Dr. Albert de Vries analyzed the voice recordings using the Trustech software and rendered decisions regarding each subject’s status.

De Vries is Nemesysco’s Vice President of Training & Research.

4. USA Department Of Justice – Rome Labs research on LVA technology by US Air Force Research Laboratory (AFRL)

The link on Nemesysco’s site leads to a copy of press release issued in 2000, but the full paper (by Haddad et al) was not published until 2002. The link to the full report leads to a zip archive containing a PDF version of the full report, and putting the report in a zip archive knocks a mere 400Kb off a 6Mb download making this barely worth the effort, but for the fact that it makes getting to the report that little bit more awkward.

This may well be intentional as the full report has this to say about the Truster software:

Some of the claims made by these manufacturers have no basis, or are so extreme that they go against basic speech science. The Truster web-page states that their system will be able to determine deception even if the speaker is under different levels and types of emotion. Such a claim has no scientific merit, since it is not possible to cleanly separate the excitation signal into component dues to emotion and those due to deception.

5. “The sexual arousal factor in pedophiles” Prof Herman Conradie, Department of Criminology, University of South Africa, Codicillus, Volume 48, Issue 1, 2007

Not only does Conradie’s paper indicate that part of research for the study was carried out by Drs. Guy Van Damme, but further investigations led to the website of a South African organisation calling itself ‘Truthfinders’, which describes its purpose in the following terms:

“Truth Finders is a Non Profit Organization (NPO) that uses the highly specialized knowledge and experience of its members to create the funds necessary to obtain its goals. These goals are to use 100 percent of the NPO’s profit to establish and maintain Christian church based centers of counseling and education throughout Africa.

The members are all academics in the field of Criminology. Because Criminology is an interdisciplinary science, they are also skilled in social work, law and religious sciences. Some have even followed extensive training in the field of Psycho Physiology, the underlying science of what is commonly known as truth verification.”

Yes, that is what it sounds – “Polygraph Examiners for Jesus”.

Conradie is the site’s ‘project leader’ and its main administrative contact, and its ‘Truth Verification’ page includes the following statement:

We have the unique ability to offer you truth verification services in the broadest spectrum: Multi Layer Voice Analysis technology (the latest and most advanced systems, LVA 6.50, presently unique to us in South Africa), polygraph services, Scientific Content Analysis, View questionnaires, post victimization and trauma counseling.

Working in sinc [sic] with Van Damme and Associates (www.vandamme.co.za), Truth Finders guarantees the latest technology and knowledge available worldwide. Prof. Drs. Guy Van Damme was the world Chairman of the International Institute of Veracity Assessors (2000 and 2001) and a psycho physiologist and polygraphist since 1983. Now residing in RSA we have obtained access to the largest pool of equipment and experience on this continent. Our qualifications and experience guarantee the highest degree of validity and reliability.

Conradie appears to be a sales rep for Nemesysco’s South African Service Centre, which is owned by Van Damme.

6. Internal study – LVA Computerized Global Stress Readings as a Function of Task Induced Stress by Igor Salganik, MD. Psychiatry & Albert De Vries, Psychologist, PhD.

De Vries we’ve already ‘met’ but its also worth noting, at this point, that he obtained his doctorate from Newport University, an unaccredited private university based in California which specialises in ‘distance learning’. In other words, he has a mail order ‘Gillian McKeith’ doctorate.

7. “Reliability and Validity of Layered Voice Analysis technology in the detection of mental stress”, Nemoto K, Tachikawa H, Takao T, Sato H, Ashizawa Y, Endo G, Tanaka K, Ishii R, Ishii N, Hashimo-to K, Iguchi T, Hada S, Hori M and Asada T

What Nemesysco provides is a partial translation of a conference paper in which much of the information one would expect to find in the methodology section is simply missing.

One of the listed co-authors, S Hada, works for Alegria Corporation:

Alegria Corporation is Nemesysco’s exclusive representative in Japan and partner Asia. Throughout the long and intimate partnership with Nemesysco, Alegria has established its own research center, having many medical authorities as its members, and now Alegria plays an active role in research and development of medical software solutions, based on LVA technology.

8. “The Power of Voice: Managerial Affective States and Future Firm Performance”, William J. Mayew and Mohan Venkatachalam , Fuqua School of Business, Duke University, July 21, 2008

The study makes this acknowledgement:

We appreciate the assistance of Amir Liberman and Albert De Vries of Nemesysco for helpful discussions and for customizing the LVA software for our academic use.

The study refers, throughout, to non standard output parameters which are unique to this particular study and customised version of Nemesysco’s software, and its apparent that the researchers were wholly reliant on Liberman and De Vries for their understanding of the system and how to interpret its outputs.

As you’ll see in my next post, these outputs are as arbitrary and meaningless as the method that the software uses to generate them, which means, of course, that the system’s output could only mean whatever it was the the researchers were told that it meant by Liberman and De Vries.

9. “Robotic KANSEI Communication System Based on Emotional Synchronization” Hashimoto, Minoru (Shinshu University), Yamano, Misaki (Shinshu University), Usui, Tatsuya (Shinshu University), 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sept, 22-26, 2008, Acropolis Convention Center, Nice, France

Another conference paper and another study in which non-standard output parameters are cited, giving the clar impression that yet another customised version of Nemesysco’s software was used, only this time the research was entirely unrelated to any other previous study and offered no supporting evidence for any the claims made by Nemesysco for the capabilities of its system.

So, in total, Nemesysco provide access to nine published studies, eight of which include either significant (and usually undisclosed) interests or were conducted under conditions in which the researchers were entirely reliant on Nemesysco for their interpretation of the system’s outputs.

If I had to provide a simple description of Nemesysco’s core research methodology, I can think of none better than this passage, by Lewis Carroll’ from ‘Through the Looking Glass’:

‘When I use a word,’ Humpty Dumpty said, in a rather scornful tone,’ it means just what I choose it to mean, neither more nor less.’

‘The question is,’ said Alice, ‘whether you can make words mean so many different things.’

‘The question is,’ said Humpty Dumpty, ‘which is to be master – that’s all.’

UPDATE

To add to what I’ve already published above, Nemesysco’s press release also makes the following assertion:

Perhaps the most outrageous fact is that Eriksson and Lacerda decided to ignore one specific piece of research of which Eriksson at least is certainly well aware. In Swe-den itself, as yet unpublished research conducted in the psychology department of Umea University (2004-2005) on the then-latest version of the technology (on which those conducting the research had received proper training), yielded excellent results, and as repeatedly reported in the Swedish press, Eriksson is well aware of this research and its findings. To the best of our knowledge, this research has not been published to date mainly due to Eriksson’s highly aggressive attack on the Umea research team, e.g. his calling the lead research professor “an unscrupulous joker” or “an unscrupulous rascal”

The name of the lead researcher in this case appears to have been Mikael Henningsson of Umea University, about whom I managed to dig up this interesting piece of information, which Nemesysco have chosen not to disclose:

The Swedish importer, located in Holmsund, units Projections AB and is a spin-off from Umeå University. Projections have the exclusive right to Nemesyscos products in the Nordic market. According to Mikael Henningsson, doctor at Umeå University Department of Psychology and founder of Projections

So there’s yet another undisclosed pecuniary interest.

4 thoughts on “Purnell’s Lie Detector – Indecent Disclosures

  1. Yes I `m sure you are right but if you wil insist on removing money from people who work for it and handing out to people who do not what exactly can we do to stop thenm lying .
    How about less tax and less hand outs in the first place , now there`s a thought.
    BTW Sunny Hundal aka Onan the Barbarian has banned me from Illiberal Conspiracy so I will simply have to come and annoy you and others instead

    *beam*

  2. I thought there was a distinct lack of people copy-and-pasting entire amounts of text from the Bruges Group and passing it off as their own work on LC. Now I find out why.

    How about rather than less tax and less hand outs, we stop making benefits conditional on fulfilling certain circumstances and being able to fill out the relevant forms, we adopt the Basic Income concept which fulfils all the criteria which you might want out of a Welfare State. Payment would be conditional upon British citizenship (and perhaps income level) eliminating the need for Mr.Purnell’s burning desire to work out whether you fulfil the criteria laid out for claiming a particular benefit.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.