Hindawi

Computational Intelligence and Neuroscience

Volume 2023, Article ID 9843565, 1 page
https://doi.org/10.1155/2023/9843565

Retraction
Retracted: Design of Residents’ Sports Nutrition Data Monitoring
System Based on Genetic Algorithm

Computational Intelligence and Neuroscience

Received 25 July 2023; Accepted 25 July 2023; Published 26 July 2023

Copyright © 2023 Computational Intelligence and Neuroscience. Tis is an open access article distributed under the Creative
Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the
original work is properly cited.

Tis article has been retracted by Hindawi following an We wish to credit our own Research Integrity and Re-
investigation undertaken by the publisher [1]. Tis in- search Publishing teams and anonymous and named ex-
vestigation has uncovered evidence of one or more of the ternal researchers and research integrity experts for
following indicators of systematic manipulation of the contributing to this investigation.
publication process: Te corresponding author, as the representative of all
authors, has been given the opportunity to register their
(1) Discrepancies in scope
agreement or disagreement to this retraction. We have kept
(2) Discrepancies in the description of the research a record of any response received.
reported
(3) Discrepancies between the availability of data and References
the research described
[1] J. Zhou, “Design of Residents’ Sports Nutrition Data Moni-
(4) Inappropriate citations toring System Based on Genetic Algorithm,” Computational
(5) Incoherent, meaningless and/or irrelevant content Intelligence and Neuroscience, vol. 2022, Article ID 9002713,
included in the article 10 pages, 2022.
(6) Peer-review manipulation
Te presence of these indicators undermines our con-
fdence in the integrity of the article’s content and we cannot,
therefore, vouch for its reliability. Please note that this notice
is intended solely to alert readers that the content of this
article is unreliable. We have not investigated whether au-
thors were aware of or involved in the systematic manip-
ulation of the publication process.
In addition, our investigation has also shown that one or
more of the following human-subject reporting re-
quirements has not been met in this article: ethical approval
by an Institutional Review Board (IRB) committee or
equivalent, patient/participant consent to participate, and/or
agreement to publish patient/participant details (where
relevant).
Wiley and Hindawi regrets that the usual quality checks
did not identify these issues before publication and have
since put additional measures in place to safeguard research
integrity.
Hindawi
Computational Intelligence and Neuroscience
Volume 2022, Article ID 9002713, 10 pages
https://doi.org/10.1155/2022/9002713

Research Article
Design of Residents’ Sports Nutrition Data Monitoring System
Based on Genetic Algorithm

E D
Jianwei Zhou
Institute of Physical Education, Xuchang University, Xuchang, Henan 461000, China

Correspondence should be addressed to Jianwei Zhou; [email protected]

Received 2 June 2022; Accepted 25 July 2022; Published 4 October 2022

Academic Editor: Jun Ye

C T
A
Copyright © 2022 Jianwei Zhou. 'is is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.
With the development of modern Internet technology, the health assessment model based on computer technology has gradually

R
become a research hotspot. In the process of studying the health level of residents, exercise status and diet nutrition are important
factors affecting their health. 'erefore, based on the idea of the genetic algorithm, this paper establishes a resident sports nutrition
data monitoring system. In this system, the data feature selection method of the genetic algorithm, which simulates the process of
biological evolution, is used in the key technology of real-time motion data processing of residents, and it is improved to interfere
with the data cross process of the genetic algorithm, to seek the local optimal solution. Two different types of data sets and different

T
data classifiers are selected to verify the system’s performance. It is proved that compared with the traditional filter class feature
selection method, this method can achieve more effective data feature recognition. In addition, some samples are selected to test
the residents’ sports nutrition data monitoring system, mainly through the analysis and quantification of the exercise process,
eating habits, physique, and other data of the athletes; to evaluate the impact of their sports and eating habits on physical health;
and to obtain the best sports guidance scheme, to guide the adjustment and improvement of their later sports and eating plans.

E
'rough the analysis of the existing residents’ health status, the monitoring and management strategies of residents’ health status
are summarized, which provides a certain reference for the improvement of residents’ physical health under the background of
artificial intelligence.

R
1. Introduction to this phenomenon, many studies have shown that most
chronic diseases and other health problems are caused by
With the development of modern science and technology bad living habits, among which the most common are lack of
and the progress of medical technology, more and more exercise and irregular diet [4]. Lack of exercise will lead to
health problems have become the focus of academic research decreased physical function and weakened overall resistance.
[1]. At the same time, with the pressure of life and work, the An irregular diet will lack the most basic source of nutrition,
physical health of residents has also been threatened. In making it difficult for the body to recover quickly. In ad-
particular, chronic diseases caused by lack of physical ex- dition, the assessment of health status is not only carried out
ercise and irregular diet have gradually become one of the from the physiological aspects but also includes the indi-
most common diseases [2]. A number of studies have shown vidual’s mental health and social relations, which is a
that the health problems represented by chronic diseases complex whole [5]. 'erefore, it is of great significance for
have shown a younger trend in recent years, including modern society to establish a scientific resident health
common diseases such as hypertension, hyperlipidemia, evaluation model system.
cervical spondylosis, gastropathy, and so on. 'is phe- Under the background of Internet promotion, it has
nomenon is particularly common in developed cities [3]. become a reality to monitor residents’ health status with the
Young and middle-aged chronic diseases have the charac- help of artificial intelligence and machine learning [6]. In
teristics of high prevalence and slow cure effect. In response particular, the application of data mining technology in
2 Computational Intelligence and Neuroscience

individual disease early warning can establish a data massive data to improve the efficiency of the system [15]. In
anomaly early warning model through the analysis of users’ the literature, a feature activity measure is proposed to
daily activity data, so as to find abnormal data in advance analyze the relationship between data sets, and an improved

D
and monitor physical abnormalities. In the existing research genetic algorithm based on adaptive features is designed to
on sports data, it is found that users are more concerned solve the problem of the lack of search ability of the classical
about the real-time effect of sports and lack a certain un- genetic algorithm [16]. In this paper, the algorithm is tested
derstanding of the appropriate exercise intensity for indi- systematically, and it is verified that it has certain advantages
viduals [7]. Different intensities and duration of exercise for the system to improve the data accuracy and recognition

E
have different effects on health. At the same time, in the rate.
process of motion data monitoring, because the real-time In the process of sports, exercise intensity needs to
monitoring system will produce concurrency problems in adapt to the actual situation of individuals. For example, it
the scene used by a large number of users, it is difficult to is mentioned in the literature that if the exercise intensity

T
obtain real-time motion data and conduct detailed analysis is small and the energy consumption of the human body is
[8]. 'erefore, it is required that the health monitoring small, the effect on metabolism is not obvious; However, if
system can select and classify the features of massive data. the amount of exercise is too large, the process of energy
'e data feature selection and equalization method based on consumption is not conducive to the normal metabolism
a genetic algorithm is of great significance for real-time of the body, and it will also cause certain damage to the

C
sports monitoring. In addition to the impact of exercise, the joints [17]. Especially, people with basic diseases may also
residents’ eating habits, nutrition acquisition, and physical lead to sudden death and other emergencies, which is not
function indicators monitoring are important reference data conducive to health. 'erefore, many scholars began to
for their health evaluation system, which is also one of the study the relationship between sports and residents’
research focuses of this paper [9]. physique. For example, it is mentioned in the literature

A
that sports are an important factor affecting the level of
2. Related Work human health [18]. In addition, adults’ occupation, living
habits, and living environment are also important factors
Because modern society attaches importance to medical care affecting their physical changes. Literature research shows
and living habits, more people hope to know their health that there are great differences between men and women

R
status in a timely and comprehensive manner and adjust in sports. Men are more dominant in endurance and
their daily work and rest and fitness activities according to strength sports, and men of normal stature have lower
physical changes, so as to reduce the occurrence of diseases body fat than men; women are much better than men in
as much as possible [10]. For example, the real-time video coordination and flexibility, and their bone mineral

T
monitoring method is used in the literature. With the help of density is relatively lower. In addition, age is also an
the image recognition method, the gray value of the video important indicator of the health status of residents. For
image is analyzed to monitor the real-time motion trajectory example, it is mentioned in the literature that the younger
of the target user in the moving area, so as to analyze its the age, the lower the body mass index, so the exercise
motion status [11]. 'e literature introduces that the real- ability is stronger, and the agility and flexibility are higher.

E
time monitoring technology can be used in sports training or According to the literature, the health status of urban
events. 'rough the real-time monitoring of athletes, the residents in recent years is far worse than that in the last
standardization of their movements can be analyzed [12]. century, which may be due to the greater pressure of
However, the literature points out that the movement of the modern social life and the general reduction of people’s

R
target can be observed through real-time video monitoring, exercise due to the birth of electronic products. According
but it is difficult to obtain the relevant change data of human to the literature, eating habits are also an important factor
function during the movement, and the real-time moni- affecting the health of residents. For For example, in some
toring has high requirements for system equipment, so it is places, people eat more high protein and high calorie
difficult to popularize. In the literature, a multiperson foods, resulting in obesity, overweight and other health
physiological parameter recording and detecting instrument problems frequent ly occurring in these areas. However, in
is used, and combined with Bluetooth transmission tech- the areas where grain is the main crop, these problems will
nology, the monitoring and analysis of multitarget physi- be relatively avoided, but malnutrition such as anemia and
ological parameters in the same period are realized [13]. trace element deficiency may occur, which is also not
Aiming at the high concurrency problem in the real-time conducive to healthy development. Literature studies the
monitoring network, the literature studies the complex balanced diet model represented by Japan and believes
characteristics of concurrency problems in network appli- that the consumption of animal and plant food should be
cations and emphasizes that in the process of multiobjective balanced, and it is necessary to meet the energy, protein,
real-time monitoring, it is necessary to use the application of lipid, and other nutrients required by the human body at
multiple computer algorithms to deal with the identification the same time. After analyzing the health-related factors
of a large number of data in real-time monitoring [14]. In the of residents’ exercise and nutrition, a relatively complete
literature, a variety of genetic algorithms have been used to residents’ health evaluation system has been established,
improve the classification accuracy of data, especially the which provides a certain reference for residents’ health
algorithm that can be used for multilabel feature selection of evaluation and monitoring in modern society.
Computational Intelligence and Neuroscience 3

3. Research on Key Technologies of Data 'e linear relationship between the two feature data is
Processing Based on Genetic Algorithm called the Pearson correlation coefficient. 'e value range of
data features is −1 to 1, where 0 means that there is no linear

D
3.1. Data Filtering Feature Selection Method. In the analysis correlation between the two features, 1 means full positive
of data features, the filter class feature selection method is correlation, and −1 means full negative correlation. As-
one of the common methods. 'e filter feature selection suming that X and Y are two features, the relationship is
method is to use rules to evaluate each dimension feature of expressed as follows:
data, give them different weights, sort them, and select

E
􏽐​ (X − X)(Y − Y)
feature subsets according to the order. 'erefore, it is also c � 􏽱������������������. (7)
called the filter feature selection method, which is a basic 􏽐​ (X − X)2 (Y − Y)2
data feature selection method.
In the filter feature selection method, the calculation Spearman refers to the monotonic correlation between

T
method of Euclidean distance is shown in the following the two features, that is, the degree to which the two features
formula, that is, the distance between two points in m-di- Y increase or decrease with the increase of X. 'e calculation
mensional space: formula is shown in the following formula:
􏽶�����������
􏽴 6 􏽐 d2i
m
ρ�1− . (8)

C
2
Euclidean(X, Y) � 􏽘 xi − yi 􏼁 . (1) n􏼐 n 2 − 1 􏼑
i�1

Manhattan distance refers to the sum of the absolute

wheelbase of two points in the standard coordinate system. 3.2. Data Feature Selection Method Based on Genetic

A
Its calculation method is shown in the following formula: Algorithm. 'is paper uses the data feature selection
m 􏼌 method of genetic algorithm that simulates the process of
􏼌 􏼌􏼌 􏼌􏼌 􏼌􏼌 􏼌􏼌 􏼌􏼌
Manhattan(X, Y) � 􏽘􏼐􏼌􏼌x1 − y1 􏼌􏼌 +􏼌􏼌x2 − y2 􏼌􏼌 + .. . +􏼌􏼌xm − ym 􏼌􏼌􏼑. biological evolution. First, the problem should be coded to
i�1 simulate the process of biological evolution and generate a
(2) population randomly. 'en, similar to chromosome iterative

R
selection, crossover, and mutation, the optimal solution can
Chebyshev distance refers to the maximum absolute be generated. 'e basic flow of the genetic algorithm is
value of the difference between the values of each coordinate shown in Figure 1.
between two points. 'e calculation formula is as follows: f all refers to the fitness of all chromosome individuals in
􏼌􏼌 􏼌􏼌 􏼌􏼌 􏼌􏼌 􏼌􏼌 􏼌􏼌 the randomly generated population, that is, the probability

T
Chebyshev(X, Y) � max􏼐􏼌􏼌x1 − y1 􏼌􏼌, 􏼌􏼌x2 − y2 􏼌􏼌, .. ., 􏼌􏼌xm − ym 􏼌􏼌􏼑.
of chromosome individuals passing on to the next gener-
(3) ation. Improving the chromosome fitness can improve the
probability of their selection. 'e calculation method of fall is
In the filter feature selection method, the similarity of the
shown in the following formula:

E
two probability distributions is expressed by the Babbitt
distance. 'e calculation method of the Babbitt distance is M

shown in formula (4), where p and q, respectively, represent fall � 􏽘 fi . (9)

i�1
the two discrete probability distributions in the X number
field, namely P i represents the probability that each chromosome

R
􏽱�������� individual is selected. 'e calculation method is shown in
⎝􏽘
Bhattacharya(p, q) � −ln⎛ ⎠.
p(x)q(x) ⎞ (4) formula (10). 'e selected chromosome individual can be
x∈X determined by the region where the random number
appears.
In the definition of information theory, relative entropy
refers to the difference in information entropy between two fi
Pi � . (10)
probability distributions, and the asymmetric measure of the fall
difference between two probability distributions is called
relative entropy distance. 'e calculation formula is as follows: 'e particle swarm optimization algorithm simulates the
data selection problem as different “particles” in space. 'e
p(x) initial values of the two attributes of the speed and position
Kullback − Leibler(p, q) � 􏽘 p(x)log . (5)
x∈X
q(x) of each particle are random, and its speed update is shown in
the following formula:
'e calculation method of information entropy is shown
in the following formula: vt+1
i � ω ∗ vti + c1 ∗ r ∗ 􏼐p best − xti 􏼑 + c2 ∗ r ∗ 􏼐g best − xti 􏼑.
(11)
n
H(X) � − 􏽘 Pi log2 Pi . (6) 'e position update formula is shown in the following
i�1 formula:
4 Computational Intelligence and Neuroscience

Start

D
Population initialization

E
Calculate the individual fitness value of the population

T
Reach the final No
generation Genetic selection

Yes Genetic crossover

C
Output optimal individual
Genetic variation

A
End t=t+1

Figure 1: Basic flow chart of genetic algorithm.

xt+1 � xti + vt+1 H(x) refers to multiple strong classifiers with strong

R
i i . (12)
classification performance; H(x) refers to multiple weak
In the discrete particle swarm optimization algorithm, classifiers with poor classification performance; and H(x)
the sigmoid function is introduced to discretize the position calculates its error rate EM after multiple rounds of iteration
of particles. At this time, the velocity update formula of and updates its initial weight value. 'e update method is

T
particles is the same as (11), and the calculation formula of shown in the following formula:
the sigmoid function is as follows: 1 1 − em
αm � ln . (17)
1 2 em
Sigmoid vi 􏼁 � . (13)
1 + e− vi

E
As can be seen from formula (17), the smaller the error
'e calculation formula of particle position is as follows: rate em, the stronger the weak classifier will play in the final
1 construction of a strong classifier. 'en update the weight of
Sigmoid vi 􏼁 � . (14) the data as shown in the following formulae:
1 + e− vi

R
Dm+1 � 􏼐wm+1,1 , wm+1,2 , . . . , wm+1,l 􏼑, (18)

3.3. Data Classifier. For feature selection of data, the process wm,i − αm yi h(xi )
wm+1,i � e , i � 1, 2, . . . , l, (19)
of subset selection with the genetic algorithm is inseparable Zm
from the verification of the classifier. 'e data feature subset
is input into the classifier, and the subset with higher ac- l

curacy of the classifier model can be recognized as the Zm � 􏽘 w −αm yi h(xi ) , (20)
m,ie
i�1
optimal subset. In this paper, the AdaBoost data classifier
used in system testing is to build a more comprehensive where Zm represents the normalization factor, which can
strong classifier with the help of several different weak make the sample weight reunified.
classifiers. In the process of classification, each data in the 'e method of constructing strong classifiers is shown in
data set must be given an initial weight with the same weight the following formula:
value. 'e method is shown in the following formulae:
M
D1 � 􏼐w1,1 , w1,2 , . . . , w1,l 􏼑, (15) ⎝ 􏽘 α h(x)⎞
H(x) � sign⎛ ⎠, (21)
m
m�1

1
w1,i � , i � 1, 2, . . . , l. (16) where m is the number of classifiers and αm represents
l the weight of a weak classifier.
Computational Intelligence and Neuroscience 5

Finally, loss function L(θ) is minimized, and then the 'e motion information table is used to record the main
parameter θ is obtained. 'e calculation method is shown in types of motion performed by the user, as shown in Table 3.
the following formula: 'e food entity information table is used to record the

D
entity information of food, as shown in Table 4.
z
θ�θ−α· L(θ). (22)
zθ
4.3. Analysis of Simulation Experiment Results

E
4. Implementation of Intelligent Resident 4.3.1. System Multidimensional Data Processing Performance
Results. According to the system requirements, the
Sports Nutrition Health Data multidimensional data recognition and processing per-
Monitoring System formance of the system are verified. 'e main indicators
include the recognition accuracy, recall, and F1 param-

T
4.1. System Core Architecture. 'e resident health moni-
eters of the classifier. 'ere are two data sets selected in
toring system used in this paper is the integration of
this paper. One of them is the traffic accident data set,
computer technology, communication technology, and
which has a large number of data sets, many sample types,
medical technology. 'rough the monitoring of human
and uneven distribution, and belongs to the multi-
motion status and physiological indicators, it provides

C
classification problem. 'e other is the sonar device data
users with a motion information display platform and
set, which has a small number of samples and many
real-time health monitoring services. 'e core architec-
feature dimensions, and belongs to the problem of binary
ture of the system is shown in Figure 2, which is divided
classification.
into three layers: background service layer, personal
'e accuracy rate is calculated as follows:
service layer, and perception layer. 'e background ser-

A
vice layer is mainly responsible for system management, TP
Precision � . (23)
service response, and data storage analysis and is re- TP + FP
sponsible for basic data management functions. 'e
personal service layer responds to the system decision, 'e recall rate is calculated as follows:
monitors the user’s movement status in real time, diag- TP

R
Recall � . (24)
noses the physiological information, and timely finds the TP + FN
problems in the user’s movement process; Finally, the
sensing layer preprocesses the data collected by motion 'e new parameter F1 value can be calculated by
sensors and physiological sensors. In this process, long- combining the accuracy rate and recall rate to reconcile the
average value. 'e larger F1 is, the better the combination

T
distance wireless transmission modes, such as 4G and
WLAN, are used between the background service layer performance of the classifier is. 'e calculation formula is
and the personal service layer, and short-distance wireless shown in the following formula:
transmission modes, such as Bluetooth and ZigBee, are 2Precision.Recall×
used between the personal service layer and the percep- F1 � ,

E
Precision + Recall
tion layer. (25)
2TP
� .
2TP + FP + FN
4.2. System Database Table Design. According to the core
'e calculation formula of information entropy is as

R
architecture design of the system, the intelligent resident
follows:
health monitoring system used in this paper can analyze the
n
user’s movement and basic physical condition. At the same
time, you can also record your daily exercise, diet, sleep, and H(x) � − 􏽘 p xi 􏼁logp xi 􏼁. (26)
i�1
other data with the help of the smartphone and upload them
to the cloud server for storage and subsequent viewing, and 'e five data classifiers are random forest algorithm,
you can have a comprehensive understanding of your basic decision tree algorithm, gradient boosting algorithm, Ada-
physical condition. According to the basic requirements of Boost algorithm, and XGboost algorithm. 'e classification
the residents’ health monitoring system, this paper uses the accuracy of the traffic accident data set is calculated as shown
relational database MySQL to record users’ health data. It in Figure 3.
supports multiple development languages and covers a 'e recognition effect of the sonar device data set
variety of user data modules. 'e main database forms are classifier is shown in Figure 4.
shown in Table 1.
In addition, the basic database table also includes basic
user information table, sports information table, food entity 4.3.2. Evaluation and Analysis of Health Data of Sports
information table, and so on. Individuals. In the health evaluation model of this paper, the
'e user table is used to record the basic information of health of sports individuals is evaluated based on the energy
users, including user names and passwords, as shown in consumption rate of users. 'e time set in this paper is 10
Table 2. minutes, and the exercise energy consumption of users is
6 Computational Intelligence and Neuroscience

System Data storage and

Background service layer Service response
management analysis

D
Long distance wireless transmission

Decision Man-machine
Alarm module
module interactive module

E
Personal service layer

Motion state Historical motion Physiological

T
recognition status queue information module

Short distance wireless transmission

C
Perception Data preprocessing module
layer

Angular Blood
Acceleration Heart rate Temperature
velocity pressure ...
sensor sensor sensor
sensor sensor

A
Motion sensor Physiological sensor

Figure 2: System core architecture.

R
Table 1: Main database forms.
Serial number Table name Describe Correlation
1 Site Store user information —

T
2 Type Classify the type of exercise —
3 Bodex Store user physical indicator information Site
4 Category Store food entity information —
5 Dietary Store user diet -related information Site
6 Achievement Store user historical movement results Type

E
7 Config Storage system default configuration —

Table 2: Basic user information.

R
Serial number Field description Field name Field type Can it be blank Remark
1 ID ID int(11) N Primary key
2 Username Username varchar(20) N —
3 Age Age int(11) N —
4 Gender Gender varchar(20) N —
5 Password Userpassword varchar(255) N —
6 Telephone Phone int(11) Y —
7 Height Height varchar(20) Y —
8 Weight Weight varchar(20) Y —
9 Blood sugar level Blood sugar float(255,0) Y —
10 Upload date Collect date datetime(0) Y —
11 Remark BZ varchar(50) Y —

calculated every 30 seconds. According to the time of energy consumption rate is counted, and then the health
physical overdraft when users actually participate in exercise evaluation model used in this paper is used to evaluate the
and the average value of energy consumed, the stable energy user’s recommended exercise time and give reasonable
consumption rate is selected as 5.6 kcal every 30 seconds. suggestions. 'e result of the energy consumption rate of a
According to this limit energy consumption rate, the user’s sports user is shown in Figure 5.
Computational Intelligence and Neuroscience 7

Table 3: Movement information table.

Serial number Field description Field name Field type Can it be blank Remark
1 ID ID int(11) N Primary key

D
2 Sports Sport varchar(20) N —
3 Exercise time Time varchar(255) N —
4 Number of exercise Frequency varchar(20) N —
5 Exercise date Date datetime(0) Y —
6 Remark BZ varchar(50) Y —

Serial number
1
2
3
4
Field description
ID
Food name
Food
Food description
Table 4: Food entity information form.
Field name
ID
Name
Category-id
Description
Field type
int(11)
varchar(20)
varchar(255)
datetime(0)

T
Can it be blank
N
N
N
Y
E Remark
Primary key
—
—
—

C
5 Energy Energy varchar(20) N —
6 Protein Protein varchar(20) N —
7 Fat Fat varchar(20) N —
8 Vitamin Vitamin varchar(20) N —
9 Food weight Scale varchar(50) N —
10 Remark BZ varchar(50) Y —

A
Energy consumption rate (kcal/30 s)

Traffic accident
100.00 8

R
95.00 7
6
Accuracy (%)

90.00
5
85.00 4
3

T
80.00
2
75.00 1
70.00 0
Random Decision tree Gradient Adaboost Xgboost 30 60 120 180 240 300 360 420 480 540 600
forest Boosting

E
Time (s)
Classifier
Energy consumption rate
Data Filter DF+DPSO
DF+GA DF+GDA Ultimate energy consumption rate

Figure 3: Classification accuracy of traffic accident data set. Figure 5: User energy consumption rate and limit energy con-

R
sumption rate.

4.3.3. Evaluation Results of Physical Fitness Indicators of

Sonar
Individual Athletes. Weight data is an important indicator
100.00 for residents’ health evaluation and also a comprehensive
95.00 reflection of human tissues. 'erefore, the increase in
physical fitness can reflect the nutritional intake and diet of
Accuracy (%)

90.00
residents for a certain period of time to a certain extent. In
85.00
this paper, 30 user samples of different ages were randomly
80.00
selected for investigation, and some residents’ body weight
75.00 and BMI index were mastered. 'e results are shown in
70.00 Table 5.
Random Decision Gradient Adaboost Xgboost
forest tree Boosting
In addition, a dietary survey was conducted for some
residents, and t value and P value tests were conducted. 'e
Classifier
results are shown in Table 6 (t � 24.08, p < 0.05, which proves
Data Filter DF+DPSO that the sample has statistical significance).
DF+GA DF+GDA
'e energy and nutrient supply of some residents were
Figure 4: Recognition effect of sonar data set classifier. investigated, and the T value and P value were tested. 'e
8 Computational Intelligence and Neuroscience

Table 5: Statistical results of body weight and BMI index of residents.

Masculine Woman
Age
Number of samples Weight (kg) BMI Number of samples Weight (kg) BMI

D
20–24 4 75.23 ± 6.28 27.98 ± 4.07 4 57.71 ± 7.74 22.25 ± 5.07
25–35 5 77.27 ± 11.4 26.21 ± 4.23 4 59.43 ± 8.69 27.97 ± 3.39
36–45 3 78.42 ± 16.7 27.02 ± 2.77 3 62.36 ± 14.3 26.09 ± 2.94
46–55 2 73.12 ± 25.6 26.02 ± 2.71 2 66.54 ± 17.8 22.21 ± 1.89

E
56 and above 2 76.21 ± 33.0 24.87 ± 3.51 1 65.33 ± 37.2 23.67 ± 2.93

Table 6: Statistics of basic energy intake of residents. According to literature research, the physical condition of
Chinese residents is closely related to exercise and lifestyle.
Male Female Overall

T
t P 'erefore, physical exercise is an important way for people
average average average
to develop a healthy physique. People should improve their
Energy (Kcal) 2,063.0 1,901.7 1,972.54 24.08 0.022
Protein (g) 78.17 81.59 80.19 45.77 0.013 understanding of exercise and form a good lifestyle. At
Carbohydrate present, the forms of sports are rich and colorful. 'e best
304.13 240.21 271.82 8.34 0.042 sports effect can be achieved only by finding suitable sci-
(g)

C
Fat (g) 88.45 81.83 84.46 25.22 0.024 entific sports methods, reasonably arranging exercise time,
and making more use of leisure time after work and study. In
addition to their own physical exercise, they should take part
in more collective activities; regulate their own work and rest
Table 7: Statistics of energy supply nutrient intake of residents. habits; reduce the number of bad lifestyles such as staying up

A
Male Female late, overeating, smoking, and drinking; and also obtain a
Total t P
average average healthy lifestyle to a certain extent.
Dietary fiber (g) 12.48 10.98 11.67 15.34 0.041 'rough the analysis of the residents’ diet and nutrition
Amarantine intake in this paper, it is generally found that the following
0.69 0.77 0.72 21.70 0.028
(mg) problems exist in the residents’ nutrition status in the study area.

R
Niacin (mg) 11.87 13.99 12.85 11.97 0.047 'e first is the low intake of dietary fiber. According to
Vitamin E (mg) 11.5 14.36 13.17 8.72 0.042 data statistics, the average daily dietary fiber intake of the
Retosol (μg) 353.59 492.3 441.36 5.97 0.044 sample residents in this paper is only 11.67 g, which is far
Nuclelin (mg) 0.61 0.65 0.63 31.85 0.019 lower than the recommended dietary intake of 25 g. Most
Condoric acid

T
61.95 66.06 63.92 30.55 0.017 residents do not meet the recommended dietary fiber intake.
(mg)
Vegetables and fruits are rich in dietary fiber, and the intake
of vegetables and fruits by residents obviously does not reach
the recommended intake standard, which may be caused by
results are shown in Table 7 (t � 15.34, p < 0.05, which proves the low intake of vegetables and fruits. 'e low intake of high

E
that the sample has statistical significance). dietary fiber foods is an important reason for the insufficient
intake of dietary fiber, which is common among urban
5. Development Strategy of Artificial residents in China.
Intelligence Resident Health Monitoring and 'e second is the low intake of vitamins and calcium.

R
Efficient Management 'e long-term lack of calcium in the body will cause os-
teoporosis, joint pain, and other diseases. 'is disease is very
5.1. Analysis of Residents’ Health Status. Developing good common in modern society, especially among middle-aged
physical exercise habits in daily life can help people establish and elderly people. In recent years, it has shown a younger
a healthy and positive life attitude and lifestyle. For example, trend. With the growth of age, most middle-aged and elderly
although different transportation modes will not affect the people suffer from the decline of some physical functions
adult physique, in the dimension of physical activity, bi- and insufficient absorption of nutrients. At the same time,
cycles, walking, and other modes have significant advan- there may be an imbalance in food intake, especially meat,
tages, which will provide more leisure sports time for eggs, and milk, which further affects the health of residents.
residents. In modern society, due to the accelerated pace of Meat, egg, and milk are important sources of energy and
life, most people will choose private cars or take public nutrients. 'e lack of meat, egg, and milk intake is one of the
transport. Exercise through leisure time is an important reasons for the lack of nutrients for most groups. 'erefore,
factor affecting the quality of physical fitness. Although no matter what age, a balanced diet is an important guar-
adults understand that sports have a positive effect on antee of a healthy body.
physical health, most adults still do not choose exercise. 'e
more people participate in sports, the better their body
quality. 'e less they participate in sports, the worse their 5.2. Residents’ Health Status Management and Optimization
physique. Regular exercise can help individuals improve Adjustment Strategy. Big data technology is more and more
their physical fitness and form healthy psychology. widely used. At present, physiological indicators have been
Computational Intelligence and Neuroscience 9

monitored to judge the physical condition. However, for provided to help R & D personnel further improve their
general physical characteristics, behavior habits affecting technical level, build communication channels, and realize
physical health, mental health status, emotional status, or resource sharing.

D
family genetics, no relevant normalization monitoring Talent training is the driving force for the development
means have been taken to prevent the occurrence of dis- of health monitoring. R & D personnel should not only
eases. At present, in most cases, the monitoring of phys- master machine learning and artificial intelligence tech-
iological indicators can only be carried out in the hospital, nology but also understand human health knowledge.
and most people go to the hospital to test their physical 'erefore, health monitoring and school education can be

E
condition after the occurrence of diseases or when carrying combined to establish a multidisciplinary health man-
out a routine physical examination, so it is easy to cause the agement training system. In the field of medicine and
problem of lagging behind in disease diagnosis and computer technology, we should increase discipline co-
treatment. Normalized health monitoring means collecting operation and integration, change the traditional profes-

T
health status in daily life, analyzing the collected data and sional training mode in colleges and universities, and form
information, and helping people to pay attention to their a multidisciplinary training system that combines medical
health and prevent diseases through health early warning. disciplines such as pathophysiology, psychology, and ep-
At present, some researchers have designed a physical idemiology with computer disciplines such as artificial
health early warning model and achieved good results in intelligence and machine learning. At the same time,

C
the young and middle-aged health early warning experi- traditional Chinese medicine culture can also be applied to
ment. 'erefore, we should set up and improve the in- health monitoring, further explore the application sce-
novation mechanism based on the actual life needs, narios and methods of traditional Chinese medicine, de-
encourage and guide professional technicians to carry out velop traditional Chinese medicine culture, form a health
the development and research of early warning systems, monitoring and training mechanism with Chinese char-

A
stimulate the enthusiasm of R & D personnel, and con- acteristics, and provide residents with a comprehensive,
stantly meet people’s demand for health early warning scientific, and reasonable integrated service mode of health
monitoring equipment in the new era. supervision. In addition, through new media and other
Scientific use of the disease early warning model can means, guide the masses to actively participate in sports,
prevent the occurrence of chronic diseases. At this stage, popularize the correct scientific sports methods, and in-

R
government departments should increase the financial crease the investment in basic sports facilities to provide a
support and policy support of computer technology such as good sports environment for residents.
machine learning in the field of disease prevention and
early warning, establish a perfect support mechanism, and

T
guide start-ups or professional teams to participate in the 6. Conclusion
development and innovation in this field, encourage large
and medium-sized enterprises to increase capital invest- At this stage, due to the increasing pressure of life and
ment, guide the technical investment of universities and work, the health of residents has been threatened. Based on
research institutions, and improve the policy support for the Internet background, this paper analyzes the needs of

E
the development of disease early warning in the financial residents’ health monitoring at this stage and designs a
field. 'e innovative research of disease early warning residents’ sports nutrition data monitoring system based
technology is inseparable from policy support and financial on the genetic algorithm to store and analyze users’ sports
guarantee. 'e use of machine learning technology such as status and eating habits, so as to provide more scientific

R
genetic algorithm and big data artificial intelligence health guidance and evaluation. Because the system may be
technology has laid a technical foundation for improving in a crowd movement scenario, the system server will face
the health of residents. At the same time, it also puts the demand for simultaneous access to a large amount of
forward higher technical requirements for R & D per- data. 'erefore, in order to meet the load demand of the
sonnel. How to optimize genetic algorithm and other system, this paper uses the data feature selection method of
machine learning technologies to build a more accurate genetic algorithm simulating the biological evolution
disease early warning model still needs further exploration. process and introduces the dragonfly algorithm to inter-
In the system research, we should also do a good job in vene to seek the local optimal solution. Simulation results
health big data analysis, protection of residents’ personal show that this method can achieve effective data feature
information, supervision of health big database, and so on. recognition. In addition, some samples were selected to test
In particular, the protection of residents’ personal infor- the residents’ sports nutrition data monitoring system,
mation and privacy in the context of the Internet has always mainly through the collection and analysis of the athletes’
been a concern of all parts. Government departments need sports data, combined with the limit time and energy
to create a good atmosphere for innovation and entre- consumption rate of individual sports, the best sports
preneurship, cultivate new forms of innovation, build a guidance scheme was obtained. Finally, it summarizes the
comprehensive resident health monitoring service plat- monitoring and management strategies of residents’ health
form, and promote the use of new products and equipment status, hoping to provide some reference for the im-
such as artificial intelligence disease early warning systems. provement of residents’ physical health and the develop-
At the same time, professional training services are ment of the service system at this stage.
10 Computational Intelligence and Neuroscience

Data Availability [13] R. Shahriyar, M. F. Bari, G. Kundu, S. I. Ahamed, and

M. M. Akbar, “Intelligent mobile health monitoring system
'e data used to support the findings of this study are (IMHMS),” in International Conference on Electronic
available from the corresponding author upon request. Healthcare, vol. 27pp. 5–12, Berlin, Heidelberg, 2009.

D
[14] C. Doukas and I. Maglogiannis, “Bringing IoT and cloud
computing towards pervasive healthcare,” in Proceedings of
Conflicts of Interest the 2012 Sixth International Conference on Innovative Mobile
and Internet Services in Ubiquitous Computing, pp. 922–926,
'e authors declare that they have no conflicts of interest.

E
Palermo, Italy, July 2012.
[15] C. M. Fonseca and P. J. Fleming, “Genetic algorithms for
Acknowledgments multiobjective optimization: formulation discussion and
generalization,” in Proceedings of the 5th International Con-
'is paper was supported by the General Project of Henan ference on Genetic Algorithms, vol. 1, pp. 416–423, San

T
Education Science in the 13th Five Year Plan for 2020 (No. Francisco, CA, USA, July 1993.
2020yb0230). [16] C. Fernandes, R. Tavares, C. Munteanu, and A. Rosa, “Using
assortative mating in genetic algorithms for vector quanti-
zation problems,” in Proceedings of the ACM Symposium on
References Applied Computing (SAC’01), pp. 361–365, ACM, Las Vegas,

C
NV, USA, March 2001.
[1] S. R. Steinhubl, E. D. Muse, and E. J. Topol, “'e emerging [17] Q. Hu, “Evaluation of the effect of different intensity physical
field of mobile health,” Science Translational Medicine, vol. 7, exercises on improving the mental health and mental
no. 283, Article ID 283rv3, 2015. toughness of college students,” Chinese School Health, vol. 40,
[2] M. Ng, T. Fleming, M. Robinson et al., “Global, regional, and no. 01, pp. 89–91, 2019.
national prevalence of overweight and obesity in children and [18] G. Cheng and X. Lu, “Analysis on the influence of physical
adults during 1980–2013: a systematic analysis for the global

A
exercise on the subjective well-being of young people,”
burden of disease study 2013,” <e Lancet, vol. 384, no. 9945, Contemporary Sports Science and Technology, vol. 5, no. 024,
pp. 766–781, 2014. pp. 156-157, 2015.
[3] S. Newman, L. Steed, and K. Mulligan, “Self-management
interventions for chronic illness,” <e Lancet, vol. 364,
no. 9444, pp. 1523–1537, 2004.

R
[4] G. Foster, S. J. C. Taylor, S. E. Eldridge, J. Ramsay, and
C. J. Griffiths, “Self-management education programmes by
lay leaders for people with chronic conditions,” Cochrane
Database of Systematic Reviews, vol. 4, Article ID CD005108,
2007.

T
[5] J. Tingting, L. Xiaozuo, and F. Linjie, “Design and imple-
mentation of physical health management system,” Electronic
Design Engineering, vol. 23, no. 4, pp. 44–46, 2015.
[6] F. Deng and W. Shaoyi, “Research on teaching counter-

E
measures based on the analysis of college students’ physical
health test data,” Contemporary Sports Science and Technology,
vol. 10, no. 2, pp. 129–131, 2020.
[7] Z. Chonglin, S. Wang, H. Wang, and H. Dadao, “Physical
health knowledge discovery of college students in physical
exercise behavior stage based on association rule data min-

R
ing,” Journal of Jinggangshan University: Natural Science
Edition, vol. 41, no. 3, pp. 5–18, 2020.
[8] P. Yan, “'oughts and Enlightenment on the application of
data mining in students’ physical health test in China,” Science
and Technology Information, vol. 15, no. 22, pp. 199-200, 2017.
[9] D. Jea and M. B. Srivastava, “A remote medical monitoring
and interaction system,” in Proceedings of the 4th Interna-
tional Conference on Mobile Systems, Applications, and Ser-
vices (MobiSys’06)Uppsala, Sweden, June 2006.
[10] C. Pisinger, U. Toft, M. Aadahl, C. Glümer, and T. Jørgensen,
“'e relationship between lifestyle and self-reported health in
a general population,” Preventive Medicine, vol. 49, no. 5,
pp. 418–423, 2009.
[11] H. Meng, N. E. Pears, and C. Bailey, “FPGA Based Video
Processing System for Ubiquitous Applications,” Perspectives
in Pervasive Computing, pp. 57–63, 2005.
[12] B. E. Reddy, T. V. S. Kumar, and G. Ramu, “An efficient cloud
framework for health care monitoring system,” in Interna-
tional Symposium on Cloud and Services Computing,
pp. 113–117, 2012.