Scientific Collection «InterConf», (39): with the Proceedings of the 8th International Scientific and Practical Conference «Science and Practice: Implementation to Modern Society» (December 26-28, 2020) at Manchester, Great Britain



Download 20,59 Mb.
Pdf ko'rish
bet325/399
Sana22.02.2022
Hajmi20,59 Mb.
#114666
1   ...   321   322   323   324   325   326   327   328   ...   399
Bog'liq
Materials of GREAT BRITAIN Conference

4. Mathematical model of the 
-hypothesis. Let 𝛾 be some positive number. 
Definition 3. Texts 
𝑇
1
, 𝑇
2
 are called 
𝛾-homogeneous (written in one language) if 
𝜌 (𝑇
1
, 𝑇
2
) ≤ 𝛾
 
 
 
 
(5) 
and 
𝛾- inhomogeneous (written in different languages) if 
𝜌 (𝑇
1
, 𝑇
2
) > 𝛾
 
 
 
 
(6) 
Inequalities (5) and (6) are a mathematical interpretation (model) of hypothesis 
ℍ. This means that in the future we proceed to recognizing the languages of products 
using the mathematical apparatus called the 
𝛾-classifier [2, 3]. 
Definition 4. 
𝛾-classifier is an algorithm for making a decision on assigning a pair 


 SCIENCE AND PRACTICE: IMPLEMENTATION TO MODERN SOCIETY
837 
of texts 
𝑇
1
 and 
𝑇
2
 to one or two different languages depending on one real parameter 
𝛾. 
Obviously, the homogeneity or heterogeneity of any pair of texts depends on the 
value of 
𝛾, and hence the degree of feasibility of the hypothesis. The fact that two texts 
belong to one language within the framework of the mathematical model means the 
validity of inequality (5), and two different languages means the validity of inequality (6). 
Hypothesis 
ℍ may be violated for some pairs of texts of the same language in the case 
when inequality (6) takes place instead of inequality (5), and also in the case when some 
two texts in different languages satisfy inequality (5) instead of fulfilling inequality (6). 
Let 
𝜏 = 𝜏(𝛾) be the total number of violations of hypothesis ℍ simultaneously in 
two cases: non-fulfillment of the “homogeneity” inequality in the case of two texts 
belonging to the same language, and non-fulfillment of the “heterogeneity” inequality 
in the case of two texts belonging to different languages. Then, for a fixed 
𝛾, the 
hypothesis fulfillment index will be determined by the value 
𝜋, given by the formula 
𝜋 = 1 − 𝜏(𝛾) 𝐿 ,

where 
𝐿 is the number of mutual distances between all pairs of texts from the 
collection 
𝑪 (in our case, 𝐿 = 𝐶
10 
2
= 45). It follows from this formula that π can 
take values from the segment [0, 1], moreover, 
𝜋 = 0, if 𝜏 = 𝐿 (= 45), and 𝜋 =
1, if 𝜏 = 0. In the first case, hypothesis  should be recognized as unsuitable, and 
in the second as fully consistent with the training sample. 
Due to the fact that the efficiency of the 
𝛾-classifier depends on the value of the 
parameter 
𝛾, it is of interest to find such a value at which 𝜋 takes the maximum value. 
This is the essence of tuning the 
𝛾-classifier on the data of the training sample. If this 
setting is acceptable, then we can talk about solving the problem of training the 
𝛾-
classifier and its predisposition to recognizing the languages of the works of the most 
diverse collections. 

Download 20,59 Mb.

Do'stlaringiz bilan baham:
1   ...   321   322   323   324   325   326   327   328   ...   399




Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©hozir.org 2024
ma'muriyatiga murojaat qiling

kiriting | ro'yxatdan o'tish
    Bosh sahifa
юртда тантана
Боғда битган
Бугун юртда
Эшитганлар жилманглар
Эшитмадим деманглар
битган бодомлар
Yangiariq tumani
qitish marakazi
Raqamli texnologiyalar
ilishida muhokamadan
tasdiqqa tavsiya
tavsiya etilgan
iqtisodiyot kafedrasi
steiermarkischen landesregierung
asarlaringizni yuboring
o'zingizning asarlaringizni
Iltimos faqat
faqat o'zingizning
steierm rkischen
landesregierung fachabteilung
rkischen landesregierung
hamshira loyihasi
loyihasi mavsum
faolyatining oqibatlari
asosiy adabiyotlar
fakulteti ahborot
ahborot havfsizligi
havfsizligi kafedrasi
fanidan bo’yicha
fakulteti iqtisodiyot
boshqaruv fakulteti
chiqarishda boshqaruv
ishlab chiqarishda
iqtisodiyot fakultet
multiservis tarmoqlari
fanidan asosiy
Uzbek fanidan
mavzulari potok
asosidagi multiservis
'aliyyil a'ziym
billahil 'aliyyil
illaa billahil
quvvata illaa
falah' deganida
Kompyuter savodxonligi
bo’yicha mustaqil
'alal falah'
Hayya 'alal
'alas soloh
Hayya 'alas
mavsum boyicha


yuklab olish