533e9ef22ef81350

AN-APPLICATION-OF-CLUSTER-ANALYSIS.PDF

NSA·UFO_FOIA·pdf·1.6 MB·20 pages

Scores

3.5
Document value
0.0
Cross-references
6.0
Provenance
3.9
Info density
4.0
Topic relevance
0.8
Anomalousness

OCR'd text preview (8 of 20 pages)

Source: embedded

page 0
_..,=· --- -- ----==-:::..:·;.:;-,..:.:·--=-=-=·  
=======:::::-::;:-:.=.:;;,;;-·;.;.;-··,;;,;··· ;::·;;;;;;.;;;· ··-:;;;;···;;;,-··==-.;;,; -·;,:;-·.;.;· ··;.;;;··-;;.;,;··;;:·-;·--·--- ... 
Dors8666 
I ( 
b) ( 3) - P . L. 8 6-3 6 I· -: . · 
NATIONAL SECURITY AGENCY 
CENTRAL SECURITY SERVICE 
FORT GEORGE G. MEADE, MARYLAND 
Pl INFORMAL No. 3 
JUNE 1978 
An Application of Cluster Analysis 
to the Question of 
"Hands" and ''Lan·guages" in the Voynich Manuscript 
S-21·5, 8·67 
By: 
M. E. D'IMPERIO 
Pl3 
Approved for Release by NSA on 08-03-2017, FOIA Case # 101982 
page 1
Doc ID: 6588666 ek ek ee ee ee ee Distribution: r | ($3) - P.L. 86-36 |
page 2
Doc ID: 6588666
•. p_.__ .-·--·-
.. --- ---- B--------·-.,.--
--- -
,__ 
----· ____ ...,_ ___ . ___ _ 
-----------------
I am reasonably certain that few readers of this paper 
will require much of an introduction to the topic of the 
Voynich Manuscript. 
Brigadier John Tiltman's informative 
and enjoyable presentation on 17 November 1975, and the 
seminar on 30 November 1976 served to familiarize many 
with this cryptanalytic challenge from the late Middle Ages. 
There have also been several articles on the subject in 
Cryptolog during the last few years. for_any reader who desires 
an overvi
page 3
Doc ID: 6588666
. ---·-. > ... . --· - ----- ----·--'"··----------· -
·--·-
---"-;-
-----------------
Here are a few highlights drawn from Currier's exposition 
of his theory at the 1976 conference: 
ttThe first twenty-five folios in the herbal section are 
obviously in one hand and one 'language', which I call 'A' • 
•••• The second twenty-five folios are in two hands, very 
obviously the work of at least two different men C{A and HJ. 
In 
addition to this fact, the text of this second portion of the 
herbal section (that is, the next twenty-five or thirty folios) is 
in two 'languages' CA an
page 4
Doc ID: 6588666
This, then, is the exciting hypothesis put forward by 
Currier. 
several of us, after attending his presentation, confirmed 
his sugqestions t o  our own satisfaction by replicating his 
original procedure of choosing some pages showing obviously 
different writing styles in the large herbal section (where the 
conttasts between scribes A- and B are especially striking) , and 
verifyinq both the consistent differences in hand and 
certain clear accompanying differences in symbol patterns. 
Nevertheless, since so many other approaches t o  the problem 
posed by the Voynich Manus
page 5
Doc ID: 6588666
--------
------· 
There are numerous ways of carrying out cluster analysis, 
and the published computer programs embody various combinations 
of these, considered by their designers to offer some special 
advantage for certain applications. 
In general, however, the 
analysis involves the following stages: 1) deciding upon a 
group of objects that constituteʋ a good sample of the groupings 
or clusters hypothesized by the analyst; 2) deciding upon the 
observations to be made across all the objects; 3) taking the 
measurements, scores, rankings, labellings, etc. of each 
objec
page 6
Doc ID: 6588666
1------ -----··· ·- --- -- -·---
! 
Un׳voidably, as is the case with many sophisticated 
statistical tools, there is a real danger of 
imposing spurious structure upon the data if the techniques 
are badly chosen or unintelligently used. 
A factor 
analysis or multiple correlation method will find "factors" 
of some sort in any data, however difficult they may be to 
interpret or put to use. 
Similarly, a cluster analysis 
will always find clusters, and it is up to us to pay 
attention to the indications of significance (the relative 
compactness of the clusters, the strength o
page 7
-----····--- ...•... --··-· · ·  .. -·· . ... ...  -·. -.... 
-. .  
· -·-.. ..-. ....... -·-·-·- -·-·---__ 
., ..  
-, .... __ 
, ...  --·- ·-·" . ů ·-··· 
-----------------
Doc ID: 6588666 
In 1aqs, a large cache of Egyptian royal mummies was 
found in tne Vdlley of the Kings; these mummies, having been 
plundered and damaged by tomb robbers, had then been 
gathered together by a later Egyptian ruler, rewrapped, and 
deposited in two new hiding places. 
ln the process of reburial, 
the identities of certain mummies were obscured Cat least for 
the. modern archaeologist). 
One in particular, 

Full text and original imagery available on Internet Archive →