لخّصلي

5 (3) TABLE 1.The cost h was configure with (VY - 0 : 01 + 0 : 950%-1 it set high at the stant, then decreased with cach reputation, mentioned here with h. Reputation was then performed for optimization. The global extreme rates E obtained by this algorithm are considered the optimal parameters for the SBGC-LSTM model. to avoid habit of usage smoking. The proposed method able to control the discase by taking these values and minimise the severity of disease using fuzzy rule-based system. The noral and abnormal values are provided below table 1. The table also shows its consequences. D. FUZZY LOGIC AND FUZZY RULES In this phase, we discuss the use of fuzzy rulcs and the proposed multi-ncural network in the classilication process in detail. First, it explores fuzzy rules and justifications. Fuzzy logic, which contains a varicty of data types, is used to handle the ambiguity of healthcare records. In fuzzy logic, language terms are utilized to help dccide between the various types of records. The fuzzy rules are created by using the language words and distances from 0 to 1 for cach term. In this study. trapczoidal fuzzy mcmbership was used. The malc paticnt described the severity of his symptoms using the language temms in Table 1. ""Action-2." Here, the pain level of the supra-public is thought of as "Action-l." and ""Action-3" because the scriousness of the experience is not known. In this study, five different methods of identifying a condition based on the amount of pain were examined (29]. Furthermore, the results for cach object are not the same as the results for any other object. The fuzzy rules are fine-tuned by using fuzzification on the input factors. The prompted fuzzy rules can be used to determine the fuzzy sct of the output. 3) chd prevention system through diabetes DiSEASe To maintain.Different parameter normal/ abnormal values and some effects in abnormal conditions.- Ba bra +aM (9) SNo Parameter Normal Abnormal Complications Glucose 90-110 140-200 Damage normal mg/di mg/dl functionality of organs Cholesterol 140 150 mg/dl l increase the mg/ll CHD risk percentage 30-35 20-25 BMI Afiects the daily kg/m2 kg/m2 activities Blood 120/80 140190 Feill abnormal condition Pressure mmHg mmHg like and dizziness stroke Smoking Falure of lugs pac/week pac/week and and its its normal functionality i= l; 2: ....n. d = 1, 2.the model having sell-repon to estimate a probability of disease with outcome variables as a binary estimated in cq (25 and 26).The value of migration is expressed as #, which was obtained from the antennae of Eurygaster.were assigned.Subsequently.... . 26).

5
(3)
TABLE 1. Different parameter normal/ abnormal values and some effects
in abnormal conditions.-
Ba
bra +aM
(9)
SNo Parameter Normal Abnormal Complications
Glucose
90-110
140-200
Damage normal
mg/di mg/dl
functionality of
organs
Cholesterol 140
150 mg/dl l increase
the
mg/ll
CHD
risk
percentage
30-35
20-25
BMI
Afiects the daily
kg/m2 kg/m2
activities
Blood
120/80 140190
Feill
abnormal
condition
Pressure mmHg mmHg
like
and
dizziness
stroke
Smoking
Falure of lugs
pac/week pac/week and and its its normal
functionality
i= l; 2: ....n. d = 1, 2. ... . D. and jis for each repetition.
The value of migration is expressed as #, which was obtained
from the antennae of Eurygaster. The signs a and
in
E4. (23 and 24) are the loosening factor and immobility
weight, respectively. This may have modified the limitations
of this study. The encounter size is specified by idi and id2.
where rfi and rf2 denote the random functions. In the initial
stage, we designed the environmental model. The outcome
points were chosen as inputs for the given environment.
Attributes of the EOA algorithms such as a, $, idi. and
id? were assigned. Fast Sy and its status B, are also
assigned randomly in the design. The active function of each
Eurygaster was then simplified, and the rate in the extreme
individual of Eurygaster was sct to Ey. T he minimal cost
was determined from the E, extreme individual rate and the
extreme global Eg identified. Subsequently. we fixed the
Eurygaster swarm attributes using Eq.(21 to 24). The extreme
and global extreme rate E, were modified by the
rate
fitness funetion calculation. The cost h was configure with
(VY - 0 : 01 + 0 : 950%-1 it set high at the stant,
then decreased with cach reputation, mentioned here with h.
Reputation was then performed for optimization. The global
extreme rates E obtained by this algorithm are considered
the optimal parameters for the SBGC-LSTM model.
to avoid habit of usage smoking. The proposed method able
to control the discase by taking these values and minimise the
severity of disease using fuzzy rule-based system. The noral
and abnormal values are provided below table 1. The table
also shows its consequences.
D. FUZZY LOGIC AND FUZZY RULES
In this phase, we discuss the use of fuzzy rulcs and the
proposed multi-ncural network in the classilication process in
detail. First, it explores fuzzy rules and justifications. Fuzzy
logic, which contains a varicty of data types, is used to handle
the ambiguity of healthcare records. In fuzzy logic, language
terms are utilized to help dccide between the various types
of records. The fuzzy rules are created by using the language
words and distances from 0 to 1 for cach term. In this study.
trapczoidal fuzzy mcmbership was used. The malc paticnt
described the severity of his symptoms using the language
temms in Table 1. Here, the pain level of the supra-public
is thought of as "Action-l." ""Action-2." and ""Action-3"
because the scriousness of the experience is not known. In this
study, five different methods of identifying a condition based
on the amount of pain were examined (29]. Furthermore, the
results for cach object are not the same as the results for
any other object. The fuzzy rules are fine-tuned by using
fuzzification on the input factors. The prompted fuzzy rules
can be used to determine the fuzzy sct of the output.
3) chd prevention system through diabetes DiSEASe
To maintain. and keep good health, need to control% diabetes to
avoid complication like CHD. the model having sell-repon
to estimate a probability of disease with outcome variables as
a binary estimated in cq (25 and 26). 26). In In this this model, Peiis a
dependent variable. is estimated by
(25)
P'mpXtee
if patient not having diabetes
(26)
if patient with diabetie
4) link between diabetes And heARt dISeAse
CHD most dangerous disease cause of death or disability in
people with type 2 diabetes (T2D). um wanted glucose level
from diabetes can harm blood vessels and the nerves that
control our heant and blood vessels. This damage can lead
to heart disease at younger age. Manage our diabetes also
helps to lower chances of having heart disease. The other
scenario for heart attack is to have habit of smoking. Once it is
conformed CHD disease you can control risk of getting heart
attack by control glucose level and daily activity of paticnt
along medita four things
medication, if the person with CHD and Diabetes,
need to control four things to avoid complication of hcart
discasc. They need to focus on 1) glucose level in blood 2)
bad cholesterol in blood, 3) Body Mass Index of the patient
and 4) high blood pressure ete, along these, the paticnt nced
E. FUZZY INFERENCE SYSTEM (FIS)
The FIS combines the input and output spaces. It can
be involved in decision making. The aim of FIS is gives
conclusion while considcring on IF-THAN rules, and also,
FIS were used "AND/OR" links for conforming required
actions. FIS is a major part of fuzzy-logic rule-based systems.
The system accepts input as fuzzy. somctimes uncqual, but
the output consists of a fuzzy set from the FIS. FIS is triggered
26690
2024