Prediction of Behaviour in Older Adults in Nursing Homes
Liling Zhao and Zhaomiao Gong
*
Chongqing Medical and Pharmaceutical College, Chongqing, 400001, China
Keywords: Behavior, Data Mining, Bead House, Middle-Aged and Senior People, Calculate.
Abstract: The prediction of behavior in people throughout their middle years and beyond is critical in gerocomium,
however it has an issue with erroneous performance positioning. The typical Shortest path algorithm is unable
to address the phase limit issue in gerocomium, and the result is insufficient. As a result, a Behavioral data-
mining methods-based prediction of older adult behaviors in nursing homes is provided, and the prediction of
older adult behaviors in nursing homes is assessed. To begin, the support vector machine theory is used to
discover the influencing elements, and the indicators are split based on the prediction of behavior in people
throughout their middle years and beyond's needs to decrease interference factors in the prediction of behavior
in people throughout their middle years and beyond. The support vector machine theory is then used to create
a Behavioral data-mining methods prediction of behavior in people throughout their middle years and beyond
scheme, and the outcomes of the prediction of behavior in people throughout their middle years and beyond
are thoroughly examined. The MATLAB simulation results reveal that, under particular evaluation
conditions, the Behavioral data-mining methods outperforms the standard Shortest path algorithm in terms
of prediction of behavior in people throughout their middle years and beyond accuracy and time of influencing
variables.
1 INTRODUCTION
The prediction of behavior in people throughout their
middle years and beyond is a very important part of
the gerocomium (Li and Jinyuan, et al. 2024), which
can make the precise control of the aging
performance evaluation model faster and faster.
However, in the process of prediction of behavior in
people throughout their middle years and beyond
(Tian and Shan, et al. 2024), The prediction of
behavior in people throughout their middle years and
beyond scheme suffers from a lack of precision,
which has a detrimental impact on the prediction of
behavior in people throughout their middle years and
beyond (Zhang and Chen, et al. 2015). According to
certain researchers (Pan, 2015), the prediction of
behavior in people throughout their middle years and
beyond scheme can be successfully analyzed and the
prediction of behavior in people throughout their
middle years and beyond may be supported by using
Behavioral data-mining methods to the study of the
aging performance assessment mode (Liu Mengxiao
and Zhou Bo, et al. 2018). In order to maximize the
prediction of behavior in people throughout their
middle years and beyond scheme and confirm the
model's efficacy, a Behavioral data-mining methods
is suggested based on this information (Zhang, 2019).
2 RELATED CONCEPTS
2.1 The Behavioral Data-Mining
Methods is Described
Mathematically
The Behavioral data-mining methods will improve
the prediction of behavior in people throughout their
middle years and beyond scheme using computer
technology and the index parameters in the prediction
of behavior in people throughout their middle years
and beyond, it is
i
y
found that the unqualified value
parameters in the prediction of behavior in people
throughout their middle years and beyond is
i
z
, and
the prediction of behavior in people throughout their
middle years and beyond scheme is
(
iij
tol y t⋅ ）
integrated with the function to finally judge the
feasibility of the prediction of behavior in people
518
Zhao, L. and Gong, Z.
Prediction of Behaviour in Older Adults in Nursing Homes.
DOI: 10.5220/0013547900004664
Paper published under CC license (CC BY-NC-ND 4.0)
In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 1, pages 518-525
ISBN: 978-989-758-763-4
Proceedings Copyright © 2025 by SCITEPRESS – Science and Technology Publications, Lda.
throughout their middle years and beyond, and the
calculation is shown in Equation (1).
1
lim( ) , , max( 2)
i ij n ij ij
x
yt X Xy t
→∞
⋅= ≥ ÷
(1)
Equation illustrates the evaluation of outliers
among them.(2).
2
max( ) ( 2 ) 2( 4)
ij ij ij ij
x
ttt t
μ
σ
−
=∂ + ⋅ +
(2)
The Behavioral data-mining methods combines
the benefits of computer technology and quantifies
the prediction of behavior in people throughout their
middle years and beyond, which may increase the
prediction of behavior in people throughout their
middle years and beyond's accuracy (Wang and Hu,
et al. 2024).
Suppose I The requirements of the prediction of
behavior in people throughout their middle years and
beyond is
i
t
that the prediction of behavior in people
throughout their middle years and beyond scheme is
i
set
, the technique for satisfying the prediction of
behavior in people throughout their middle years and
beyond is
i
y
, and the judgment function of the
prediction of behavior in people throughout their
middle years and beyond the scheme is
(0)
i
Ft≈
as
shown by Equation (3).
1
() 2 7
ii i
Fd t y
n
ξ
=⋅→⋅
(3)
2.2 Selection of Prediction of Behavior
in People Throughout their Middle
Years and Beyond Scheme
Hypothesis II The prediction of behavior in people
throughout their middle years and beyond function is
()
i
gt
, The weighting factor is
i
w
, The unqualified
prediction of behavior in people throughout their
middle years and beyond, as indicated in Equation, is
thus required by the prediction of behavior in people
throughout their middle years and beyond. (4).
(4)
The full function of the prediction of behavior in
people throughout their middle years and beyond
(Wang and Zhou, et al. 2010), according to
assumptions I and II of the prediction of behavior in
people throughout their middle years and beyond can
be obtained, and the results is shown in Equation (5).
(5
)
To increase the efficacy of the prediction of
behavior in people throughout their middle years and
beyond, all data must be standardized, and the results
are presented in Equation (6).
2
1
() ( ) ( )( 4
)
n
ii i ij
i
gt Fd X X t
=
+↔ − +
(6
)
2.3 Analysis of Prediction of Behavior
in People Throughout their Middle
Years and Beyond Scheme
Before carrying out the Behavioral data-mining
methods, the prediction of behavior in people
throughout their middle years and beyond scheme
should be analyzed in all aspects, and the prediction
of behavior in people throughout their middle years
and beyond requirements should be mapped to the
prediction of behavior in people throughout their
middle years and beyond library, and the unqualified
prediction of behavior in people throughout their
middle years and beyond scheme should be
eliminated (Zhao and Cheng, 2024). The anomaly
assessment system may be given using Equation (6),
and the outcomes is
()
i
No t
shown in Equation(7).
1
() ( )
() , ,
(4)
ii
in
ij
gt Fd
No t X X
mean t
+
=
+
(7
)
Among them, it is
() ( )
1
(4)
ii
ij
gt Fd
mean t
+
≤
+
specified that the scheme must be
()
i
Z
ht
suggested;
otherwise, the scheme integration is necessary; the
outcome is illustrated in Equation (8).
(8
)
()= ( )
ii i i
dy
gt x z Fd w
dx
⋅−Φ
∏
lim ( ) ( ) max( )
ii ij
x
gt Fd t
→∞
+≤
() lim[ () ( )]lim
iii
xx
Zh t g t F d
→∞ →∞
=+
Prediction of Behaviour in Older Adults in Nursing Homes
519
The prediction of behavior in people throughout
their middle years and beyond is
()
i
accur t
thoroughly examined, and the threshold and index
weight of the prediction of behavior in people
throughout their middle years and beyond scheme are
established to assure the Behavioral data-mining
methods's correctness (JPG, 2022). The prediction of
behavior in people throughout their middle years and
beyond is
()
i
unno t
a systematic test prediction of
behavior in people throughout their middle years and
beyond scheme that must be thoroughly examined. If
the prediction of behavior in people throughout their
middle years and beyond has a non-normal
distribution, the prediction of behavior in people
throughout their middle years and beyond scheme
will be influenced, lowering the total prediction of
behavior in people throughout their middle years and
beyond's accuracy, as stated in Equation (9).
[()()]
1
( ) 100
%
() ( )
ii
i
ii
gt Fd
accur t
n
gt Fd
+
=×
+
(9
)
The analysis of the prediction of behavior in
people throughout their middle years and beyond
scheme reveals that the scheme displays a multi-
dimensional distribution, which is consistent with
objective facts. The prediction of behavior in people
throughout their middle years and beyond has no
directional, suggesting that the scheme has great
unpredictability, and hence it is
()
i
randon t
considered as a high analytical research. If the
prediction of behavior in people throughout their
middle years and beyond's stochastic function is, then
the computation of equation (9) may be represented
as equation (10).
1
min[ ( ) ( )]
() (
1
() ( )
2
n
ii
ii
i
i
ii
gt Fd
accur t X randon t
gt Fd
=
+
=+
+
(10)
Among them, the prediction of behavior in people
throughout their middle years and beyond meets the
standard requirements, owing to computer
technology that adjusts the prediction of behavior in
people throughout their middle years and beyond,
removes duplicate and irrelevant schemes, and
supplements the default scheme, resulting in a strong
dynamic correlation of the entire prediction of
behavior in people throughout their middle years and
beyond scheme.
3 PREDICTION OF BEHAVIOR
IN PEOPLE THROUGHOUT
THEIR MIDDLE YEARS AND
BEYOND OPTIMIZATION
APPROACH
To achieve the scheme optimization of the prediction
of behavior in people throughout their middle years
and beyond, the Behavioral data-mining methods
uses a random optimization method for the prediction
of behavior in people throughout their middle years
and beyond and modifies the Internet information
parameters. The evolutionary algorithm separated the
prediction of behavior in people throughout their
middle years and beyond into multiple stages and
then randomly picked alternative methods. The
prediction of behavior in people throughout their
middle years and beyond scheme of various
prediction of behavior in people throughout their
middle years and beyond grades is improved and
examined throughout the iterative process. Following
the completion of the optimization study, the
prediction of behavior in people throughout their
middle years and beyond level of various schemes is
composed, and the best prediction of behavior in
people throughout their middle years and beyond is
recorded.
4 PRACTICAL EXAMPLES OF
PREDICTION OF BEHAVIOR
IN PEOPLE THROUGHOUT
THEIR MIDDLE YEARS AND
BEYOND
4.1 Introduction to the Prediction of
Behavior in People Throughout
Their Middle Years and Beyond
The prediction of behavior in people throughout their
middle years and beyond in complex cases is used as
the research object, with 12 paths and a test time of
12 hours, and the prediction of behavior in people
throughout their middle years and beyond scheme of
the specific prediction of behavior in people
throughout their middle years and beyond is shown in
Table 1.
INCOFT 2025 - International Conference on Futuristic Technology
520
Table 1: Prediction of behavior in people throughout their
middle years and beyond prediction of behavior in people
throughout their middle years and beyond requirements
Scope of
application
Grade Accuracy prediction
of
behavior
in people
throughout
their
middle
years and
b
e
y
on
d
Analysis of
behavioral
p
atterns
I 87.54 89.78
II 90.93 87.21
Psychological
assessment
I 89.56 91.02
II 88.75 89.00
Cognitive
assessment
I 89.41 85.93
II 91.33 90.02
The prediction of behavior in people throughout
their middle years and beyond process in Table I. is
shown in Figure 1.
Behavior
Excavate
Data
Technique
Resthome
Behavior
Middle
Figure 1: Analysis process of prediction of behavior in
people throughout their middle years and beyond
The prediction of behavior in people throughout
their middle years and beyond scheme of the
Behavioral data-mining methods, which includes the
Shortest path algorithm , is closer to the real
prediction of behavior in people throughout their
middle years and beyond needs. The Behavioral data-
mining methods outperforms the Shortest path
algorithm in terms of logic and accuracy of the
prediction of behavior in people throughout their
middle years and beyond. The accuracy and
reliability of the Behavioral data-mining methods are
improved by changing the prediction of behavior in
people throughout their middle years and beyond
scheme in Figure II. As a result, the evolutionary
algorithm's prediction of behavior in people
throughout their middle years and beyond scheme has
improved in terms of speed, accuracy, and summation
stability.
4.2 Prediction of Behavior in People
Throughout their Middle Years
and Beyond
The prediction of behavior in people throughout their
middle years and beyond scheme of the Behavioral
data-mining methods, which includes the Shortest
path algorithm , is closer to the real prediction of
behavior in people throughout their middle years and
beyond needs. The Behavioral data-mining methods
outperforms the Shortest path algorithm in terms of
logic and accuracy of the prediction of behavior in
people throughout their middle years and beyond.
The accuracy and reliability of the Behavioral data-
mining methods are improved by changing the
prediction of behavior in people throughout their
middle years and beyond scheme in Figure 2. As a
result, the evolutionary algorithm's prediction of
behavior in people throughout their middle years and
beyond scheme has improved in terms of speed,
accuracy, and summation stability.
Table 2: The overall situation of the prediction of behavior
in people throughout their middle years and beyond scheme
Category Random
data
Reliability Analysis
rate
Analysis of
behavioral
p
atterns
95.19 89.82 88.55
Psychological
assessment
89.91 89.29 90.88
Cognitive
assessment
90.15 88.97 93.70
Mean 85.86 89.45 93.64
X6 91.29 87.90 91.31
P=1.249
4.3 Prediction of Behavior in People
Throughout Their Middle Years
and Beyond and Stability
In order to test the Behavioral data-mining methods's
correctness,, the prediction of behavior in people
throughout their middle years and beyond scheme is
comprised with the Shortest path algorithm , and the
prediction of behavior in people throughout their
middle years and beyond scheme is shown in Figure
2.
Prediction of Behaviour in Older Adults in Nursing Homes
521
Figure 2: Evaluation model of aging performance of
different algorithms
Figure 2 shows that the prediction of behavior in
people throughout their middle years and beyond of
the Behavioral data-mining methods is higher than
that of the Shortest path algorithm , but the error rate
is lower, indicating that the Behavioral data-mining
methods's prediction of behavior in people
throughout their middle years and beyond is relatively
stable, whereas the Shortest path algorithm 's
prediction of behavior in people throughout their
middle years and beyond is uneven. Table 3 depicts
the average prediction of behavior in people
throughout their middle years and beyond scheme of
the three methods discussed previously.
Table 3: Compares the accuracy of several prediction of
behavior in people throughout their middle years and
beyond.
Algorithm Surve
y data
prediction
of
behavior
in people
throughou
t their
middle
years and
b
eyon
d
Magnitud
e of
change
Error
Behaviora
l data-
mining
methods
88.21 86.82 87.37 88.3
3
Shortest
path
al
g
orithm
90.19 89.01 91.09 87.6
5
P 92.40 89.80 92.96 92.2
7
Table 3 shows that the Shortest path algorithm
has flaws in the accuracy of the prediction of behavior
in people throughout their middle years and beyond,
and the prediction of behavior in people throughout
their middle years and beyond varies dramatically
with a large error rate. The Behavioral data-mining
methods produced better prediction of behavior in
people throughout their middle years and beyond than
the ant colony approach. At the same time, the
Behavioral data-mining methods's prediction of
behavior in people throughout their middle years and
beyond is higher than 90%, and the accuracy has not
altered much. To confirm the supremacy of
Behavioral data-mining methods. To further validate
the efficiency of the suggested technique, the
Behavioral data-mining methods was generally
examined using various methodologies, as shown in
Figure 3.
Figure 3: Prediction of behavior in people throughout their
middle years and beyond of Behavioral data-mining
methods
Figure 3 shows that the prediction of behavior in
people throughout their middle years and beyond of
the Behavioral data-mining methods is significantly
better than the Shortest path algorithm . This is
because the Behavioral data-mining methods
increases the prediction of behavior in people
throughout their middle years and beyond's
adjustment coefficient and sets the threshold of
Internet information to eliminate the prediction of
behavior in people throughout their middle years and
beyond scheme that does not meet the requirements.
4.4 Rationality of Prediction of
Behavior in People Throughout
their Middle Years and Beyond
The prediction of behavior in people throughout their
middle years and beyond scheme is integrated with
INCOFT 2025 - International Conference on Futuristic Technology
522
the Shortest path algorithm to check the correctness
of the Behavioral data-mining methods, and the
prediction of behavior in people throughout their
middle years and beyond scheme is depicted in Figure
4.
Figure 4: Evaluation model of aging performance of
different algorithms
Figure 4 shows that the rationality of the
Behavioral data-mining methods's prediction of
behavior in people throughout their middle years and
beyond is superior to that of the Shortest path
algorithm , and that the rationality of the prediction of
behavior in people throughout their middle years and
beyond can be increased by improving the prediction
of behavior in people throughout their middle years
and beyond using the Behavioral data-mining
methods. With the inclusion of Behavioral data-
mining methods, a decentralized data storage and
administration platform may be created, guaranteeing
that findings are safely stored and kept. A unique
identification may be generated for each using
Behavioral data-mining methods, and the appropriate
data and scheme can be stored on the Behavioral data-
mining methods.
4.5 Validity of Prediction of Behavior
in People throughout Their Middle
Years and beyond
In order to confirm the effectiveness of the
Behavioral data-mining methods, the prediction of
behavior in people throughout their middle years and
beyond scheme is comprised with the Shortest path
algorithm , and the prediction of behavior in people
throughout their middle years and beyond scheme is
shown in Figure 5 shown.
Figure 5: Prediction of behavior in people throughout their
middle years and beyond of different algorithms
Figure 5 shows that the prediction of behavior in
people throughout their middle years and beyond of
the Behavioral data-mining methods is higher than
that of the Shortest path algorithm , but the error rate
is lower, indicating that the Behavioral data-mining
methods's prediction of behavior in people
throughout their middle years and beyond is relatively
stable, whereas the Shortest path algorithm 's
prediction of behavior in people throughout their
middle years and beyond is uneven. Table IV depicts
the average prediction of behavior in people
throughout their middle years and beyond scheme of
the three methods discussed previously.
Table 4: Compares the efficacy of several prediction of
behavior in people throughout their middle years and
beyond.
Algorithm Surve
y data
prediction
of
behavior
in people
throughou
t their
middle
years and
b
e
y
on
d
Magnitud
e of
change
Error
Behaviora
l data-
mining
methods
89.02 92.55 86.94 90.3
1
Shortest
path
algorithm
89.08 89.12 88.40 91.8
7
P 91.63 91.22 90.25 86.1
4
Prediction of Behaviour in Older Adults in Nursing Homes
523
Table 4 shows that the Shortest path algorithm
has flaws in the accuracy of the prediction of behavior
in people throughout their middle years and beyond
in terms of prediction of behavior in people
throughout their middle years and beyond, and the
prediction of behavior in people throughout their
middle years and beyond varies dramatically and has
a high error rate. The Behavioral data-mining
methods produced better prediction of behavior in
people throughout their middle years and beyond than
the ant colony approach. At the same time, the
Behavioral data-mining methods's prediction of
behavior in people throughout their middle years and
beyond is higher than 90%, and the accuracy has not
altered much. To confirm the supremacy of
Behavioral data-mining methods. The Behavioral
data-mining methods was typically examined by
numerous approaches to further validate the efficacy
of the suggested method, as illustrated in Figure 6.
Figure 6: Behavioral data-mining methods prediction of
behavior in people throughout their middle years and
beyond
Figure 6 shows that the prediction of behavior in
people throughout their middle years and beyond of
the Behavioral data-mining methods is significantly
better than the Shortest path algorithm. This is
because the Behavioral data-mining methods
increases the prediction of behavior in people
throughout their middle years and beyond's
adjustment coefficient and sets the threshold of
Internet information to eliminate the prediction of
behavior in people throughout their middle years and
beyond scheme that does not meet the requirements.
5 CONCLUSIONS
To address the issue that the prediction of behavior in
people throughout their middle years and beyond is
not optimal, this research presents a Behavioral data-
mining methods that uses computer technology to
enhance the prediction of behavior in people
throughout their middle years and beyond.
Simultaneously, the correctness and reliability of the
prediction of behavior in people throughout their
middle years and beyond are thoroughly examined,
and the Internet information collecting is built. The
findings demonstrate that the Behavioral data-mining
methods can increase the prediction of behavior in
people throughout their middle years and beyond's
accuracy, and the generic prediction of behavior in
people throughout their middle years and beyond may
be used for the prediction of behavior in people
throughout their middle years and beyond. However,
too much emphasis is placed on the examination of
the prediction of behavior in people throughout their
middle years and beyond throughout the Behavioral
data-mining methods process, resulting in
irrationality in the selection of prediction of behavior
in people throughout their middle years and beyond
indicators.
REFERENCES
Li Yun Feng, Jinyuan, Xu Ruohua, etc. A method and
device for user behavior analysis and prediction based
on data mining: CN202210114460.1 [P].
CN202210114460.1[2024-01-23].
Tian Daxin, Shan Xiongyu, Wang Yunpeng, et al. A
method for the prediction and evaluation of vehicle
residence behavior patterns based on data mining:
CN201611187064.2 [P]. CN106649709A[2024-01-
23].
Zhang Rui, Chen Changxiang, Chen Xiuling, et al. Effect
of daily health behaviors and living ability on the
depressed mood of elderly people in nursing homes [J].
Chinese Journal of Gerontology,
2015(12):2.DOI:10.3969/j.issn.1005-
9202.2015.12.108.
Pan Longdan. Study on the characteristics of elderly in
nursing homes in Nanjing [J]. Sports World: Academic
Edition, 2015(11):3.DOI:CNKI:SUN:TYSJ.0.2015-
11-019.
Liu Mengxiao, Zhou Bo, Luan Yifei. The influence of
extroversion and introversion of elderly behavior on
pension space [J]. Architectural Practice,
2018,1(2):5.DOI:CNKI:SUN:JZZS.0.2018-12-017.
Jess Zhang. Data mining methods for student behavior
understanding [D]. University of Science and
Technology of China, 2019.
INCOFT 2025 - International Conference on Futuristic Technology
524
Wang Nanping, Hu Xingyue, Tian Hua, et al. Survey on
Dietary behavior and nutritional status of the elderly in
nursing homes [C] / / Research progress of geriatric
nutrition and standardization of nutritional meal supply
for the elderly and study class on progress of medical
nutrition treatment of diabetic nephropathy. 0[2024-01-
23].
Wang Xiaohong, Zhou Bo, Gao Lihua, et al. Survey of
nutrition knowledge, attitudes and behavior of the
elderly in nursing homes [J]. Chinese community
physicians: a comprehensive version,
2010,000(009):P.192-193.
Zhao Keke, Cheng Weihong. Method and device of credit
behavior prediction based on neural network:
201910684149 [P] [2024-01-23].
JPG. Data mining method based on swarm intelligence and
its application in CRM [J]. 2022.
Prediction of Behaviour in Older Adults in Nursing Homes
525
