[Retracted] Consumer Psychology of Ethnic Clothing Based on Artificial Intelligence Decision-Making and Internet of Things

Peng, Yu; Krutasaen, Watanapun

doi:https://doi.org/10.1155/2022/8805010

Wireless Communications and Mobile Computing

On this page

Abstract Introduction Analysis Conclusions Data Availability Conflicts of Interest Acknowledgments References Copyright Related Articles

Research Article Retraction

!

This article has been Retracted. To view the article details, please click the ‘Retraction’ tab above.

Special Issue

Machine Learning Enabled Signal Processing Techniques for Large Scale 5G and 5G Networks

View this Special Issue

Research Article | Open Access

Volume 2022 | Article ID 8805010 | https://doi.org/10.1155/2022/8805010

[Retracted] Consumer Psychology of Ethnic Clothing Based on Artificial Intelligence Decision-Making and Internet of Things

Yu Peng¹and Watanapun Krutasaen²

Academic Editor: Mohammad Farukh Hashmi

Received26 Jan 2022

Revised16 Mar 2022

Accepted23 Mar 2022

Published14 May 2022

Abstract

The consumer psychology and consumption behavior of ethnic clothing is often a special category of modern clothing consumption, which has a significant impact on the composition of future consumer culture. The research on the consumption psychology of ethnic costumes will help us to better grasp the legal direction of the development of cultural trends. The purpose of this paper is to study the consumer psychology of ethnic wear based on artificial intelligence decision-making and the Internet of Things. After an overview and theoretical analysis of the existing results, the framework of the research and the direction to start are determined. In order to understand the basic situation of the current market, the main multichannels of ethnic wear are classified, and the preference information for these functions is explored in the minds of consumers. Use decision-making process research tools to quantify decision-making process data for all ethnic apparel consumption. The research obtains specific data through questionnaires and grasps the mass psychology of ethnic costume consumption. And then build a scientific system to promote the consumption of national costumes. Research has proved that the creation of cultural scope and the enrichment of commodity types have a very positive impact on the consumption of ethnic clothing and can become one of the important breakthroughs in promoting the consumption of ethnic clothing.

1. Introduction

Artificial intelligence is the product of the development of information technology to a certain stage [1]. It selects the corresponding algorithm according to the actual needs to achieve the goal of saving manpower and improving decision-making efficiency [2]. People let the computer do some screening and filtering through the program, so as to give them some advanced human skills, such as environmental change, sports education, and sports decision-making [3]. The concept of the Internet of Things was proposed at the end of the last century, which advocates the use of sensors to connect all things that may be connected to the Internet, so as to achieve their efficient management [4] and then make further decisions through the process of analysis and consideration.

In the daily life of consumers, not everyone is indifferent to material and cultural enjoyment [5]. The consumption of clothing is an important part of consumption [6]. National costumes are the property of folk art in various countries, with simple and generous patterns, unique patterns, amazing artworks, and rich colors, reflecting the national characteristic language and national identity [7]. From the national costumes, we can observe the material and spiritual development of this nation, so it has extremely important cultural research value [8]. As a special consumption of clothing consumption, it has its own unique personality in many fields such as energy value, usage, and energy demand [9].

The fundamental rules of today’s consumer behavior are engagement, likeability, and scarcity [10]. How people behave and behave are cues and signals taken from the social interactions they have, mostly on social media, which adds to the melting pot of thought and action [11]. Through this paper, Ali attempts to understand the nuances of the psychological factors in the purchasing behavior of modern consumers [12]. Users who plan to buy go through a significantly different decision-making process compared to impulse purchases. Sebastian et al. conducted a qualitative study among users in several Asian markets, including China, Hong Kong, Taiwan, South Korea, and Thailand, to understand the factors that influence the brand selection process in a planned buying environment. Qualitative research has shown that packaging has a positive impact on the user’s brand selection process [13], while packaging rich in national culture has a stronger appeal.

This paper adopts the following research methods: first, the method of empirical research. This paper uses the method of empirical research to objectively analyze the current application of artificial intelligence in the decision-making of ethnic clothing consumption, and the obtained data are obtained through the actual investigation. In order to specifically illustrate the application of artificial intelligence in national clothing consumption decision-making, this paper studies a hybrid decision-making system that combines case reasoning and rule reasoning and analyzes the impact of artificial intelligence in ethnic clothing consumption decision-making reflected in specific cases, argumentation, and research [14–16].

2. Research on Consumer Psychology of Ethnic Clothing Based on Artificial Intelligence Decision-Making and Internet of Things

2.1. IoT Technology

The Internet of Things is an effective extension and expansion of today’s Internet, and it is a new generation of rapidly developing information technology that can connect different things together [17]. The Internet of Things technology uses a variety of technologies to collect background data in real time and publish it on the Internet, determine the information interaction between people and things, and realize information management, remote control, and intelligent monitoring. The Internet of Things has the following characteristics: visual data is constantly changing and updated, and it needs to collect data in real time to make big data for human decision-making applications [18]. Safe and efficient transmission equipment must be equipped to prevent data from being intercepted and lost; IoT systems must reduce human activities and complete intelligent data processing [19].

The IoT architecture can be divided into three layers: the idea layer, the network layer, and the application layer. The perception level is a small application of IoT technology [20]. It acquires data from multiple devices through technologies such as radio frequency identification, QR code scanners, sensors, embedded systems, and cameras and then transmits data through sensor network technologies, such as WiFi, Bluetooth, and Zigbee, and transmits it to the portal [21]. The network layer mainly transmits data to the visual layer within the network in a fast, stable, secure, and reliable way through wired or wireless networks [22–25]. The application layer is essential to analyze the efficiency, metrics, and data processes distributed through the network layer and then utilize software development techniques to create applications for users to consume. At present, IoT technology is widely used in many fields such as manufacturing and life, including smart logistics, smart environment, smart moving, smart agriculture, smart medical care, and smart home [26].

2.2. Theory of Consumer Consumption Behavior

Consumers’ consumption behavior can be divided into rational consumption and irrational consumption according to the degree of rational thinking and participation in the consumption process.

2.2.1. Rational Consumption Behavior

Rational consumption behavior refers to careful thinking and planning before consumption occurs and no regrets due to the impulse at that time after consumption occurs.

It can be seen that the whole process of rational consumption behavior has relatively clear stages. Consumers have thought about each stage and made the choice that is most beneficial to them in the context of the time. The analysis of this consumption behavior is relatively simple [27–30].

2.2.2. Irrational Consumption Behavior

Compared with rational consumption behavior, irrational consumption behavior is not worth mentioning in terms of thinking time. It can also be called the impulsive consumption behavior of consumers [31]. They just buy on the basis of temporary love. After they calm down, they will feel that the purchased goods are not necessary, and there will even be regrets.

From Table 1, we can see the obvious differences between rational consumption behavior and irrational consumption behavior in terms of “consumption target,” “involvement,” and “information processing capability.”

2.3. Intelligent Decision

Intelligent decision-making is a high-level level of information technology at the current stage. It emphasizes that intelligent terminals independently collect, compare and analyze data, and finally make scientific responses. This technology breaks through people’s long-established understanding of the application field of information technology and makes itself one of the “decision-makers” from “referencer.” This technology integrates the information modules of each area and selects the optimal plan to execute according to the established program.

The backbone of IDSS is data storage and processing technology. Various objects faced by intelligent decision-making will generate corresponding data. The difference in these data makes the design of intelligent decision-making necessarily different. Different understanding and decision-making systems have their own characteristics and application completion degrees. At the same time, the diversity of decision-making information sources also poses new problems for information integration. How to collect information from different perspectives to serve decision-making sites is a common problem in decision-making. It has gone through a process from simple positioning to optimization of the average line. Different levels of information can be achieved using intelligence, route optimization, decision trees, and virtual networks. Currently, there has been little progress in gathering information using unconventional computing techniques such as proof-of-concept and Bayesian networks. The immediate priority in this field is to find more general knowledge and thinking algorithms.

3. Investigation and Research on Consumer Psychology of Ethnic Clothing Based on Artificial Intelligence Decision-Making and Internet of Things

3.1. Experimental Subjects

The study randomly selected an urban center shopping mall in a minority autonomous prefecture as the research site. A total of 120 questionnaires were distributed within 3 days, and 98 questionnaires were recovered, with a recovery rate of 81.7%, of which 86 were valid responses. Since the core of this research lies in the consumption psychology of ethnic clothing, and the main force of ethnic clothing consumption is female buyers, the subjects of the questionnaire are all women, mainly young and middle-aged women.

3.2. Research Methods

The research adopts the method of combining questionnaire survey and data analysis. First, after careful design and careful argumentation, a questionnaire consisting of 18 questions was designed. The content of the questionnaire includes natural conditions, consumption willingness of ethnic costumes, and suggestions for the development of ethnic costumes consumption. After the questionnaires are collected, data analysis software is used to classify and compare the data, and an independent variable simulation system is constructed through two dimensions, which is a dynamic reference for the construction of the development system.

The hypothetical model of the research content of this work consists of 9 variables, which are described as follows: consumer attitude, consumption motivation, perceived risk, emotional factor, cultural factor, product factor, cognitive evaluation, purchase intention, and postmarket feedback. Among them, response or factors of production, namely, cognitive evaluation, market intention, and postmarket feedback, are dependent variables and are the purpose of research and surveys. In order to further verify the internal relationship between various variables, the study adopts the Pearson correlation analysis method, coordinates CBR and RBR, and builds a mixed decision-making system based on artificial intelligence decision-making and consumer psychology for ethnic clothing.

3.3. Case Similarity Measure

The CBR method exploits the high similarity between the target case and the pending case to obtain theoretically near-similar solutions. However, since it is impossible for various cases to be the same, only by listing the important nodes in the case as keywords and then using the matching degree of keywords between the target case and the case to be processed in terms of quantity and distribution area, the optimal selection is made which is the most suitable solution. In this study, let the similarity function as shown in

According to the fuzzy relation table, the fuzzy relational equation is used to realize the fuzzy reasoning between events through a specific fuzzy algorithm. The fuzzy equation is as follows:

4. Analysis and Research of National Costume Consumption Psychology Based on Artificial Intelligence Decision-Making and Internet of Things

4.1. Analysis of the Purchase Decision of Ethnic Costumes

The analysis results of perceived risk among individual influencing factors on cognitive evaluation, purchase intention, and postpurchase feedback are shown in Figure 1. The significant level is less than 0.05, and the correlation coefficient is negative, indicating that all are negatively correlated.

In Figure 2, we can see that risk perception has a very important impact on consumer behavior. That is, in the process of national costume consumption, rational consumption occupies the absolute mainstream. It proves that the consumption behavior of buyers of ethnic costumes has a high rationality.

In Table 2, it can be seen that the cultural environment has a positive impact on the consumption of ethnic clothing. The more intense the surrounding ethnic culture is, the easier it is for consumers to have the desire to buy ethnic clothing. And if you are in an area where the national color is relatively diluted, it will reduce the consumer’s desire to buy.

From the perspective of the design of Chinese national costumes, each age group has its own distinct characteristics. Through analysis, it is found that most ethnic costumes can be divided into 4 levels according to the age of consumers, namely under 18, 18-30 years old, 31-45 years old, and over 40 years old. In Table 3, you can see to the composition of the survey object. The “18-30 years old” and “31-45 years old” stages have the largest number of people, which are also the main force in the shopping mall. The least “under 18” in this age group are mainly students, so the opportunity to play the mall is limited.

In Figure 1, it can be seen that there will be significant differences in the consumption of ethnic clothing among different age groups. According to the data obtained from the survey, the first place is 18-30 years old, followed by 31-40 years old, over 40 years old, and under 18. The woman of 18-30 years old is at the age where she likes to show her personality, I like the beautiful national costumes very much and become the main force of purchase. And in the woman of under 18, most of them belong to the student class, and they choose to wear school uniforms or youthful clothes most of the time.

From Table 4, you can see the monthly income of the respondents. Among them, less than 5,000 yuan and 5,000 to 10,000 people occupy the vast majority. This is also the main force of national costume consumption.

As can be seen in Table 4 and Figure 3, there are also certain differences in the purchase behavior of ethnic clothing consumption in each income range. Those with an income of 5,001-10,000 yuan and those with an income of less than 5,000 yuan ranked in the top two. However, those with a monthly income of more than 10,000 are slightly less enthusiastic about purchasing ethnic clothing. For a long time, it can be found that the price of ethnic costumes in the county is mainly between 400 and 900 yuan, which just meets the needs of the first two in terms of purchasing power. However, high-end clothing, that is, ethnic clothing with a price of more than 1,000 yuan, is very limited in terms of the number of stores sold and clothing design styles, and high-income groups have less room for purchasing choices. This limits their purchasing desire to a certain extent.

4.2. Probe into the Deep Consumption Psychology of National Costumes

After obtaining the above basic data through questionnaires, the research explores the deep consumption psychology of ethnic clothing by integrating modules such as CBR and RBR.

CBR and RBR are strongly complementary, and there is no alternative between these two reasoning or knowledge representation methods. This set of cases cannot fully express the encoded and generalized rules, and what is contained in the widely distributed rough knowledge cases is extremely difficult or impossible to extract and restrict to rules.

When users use the system, they first enter the first-level decision makers, such as ethnic clothing style, ethnic clothing quality, ethnic clothing background, and secondary decision-making support factors, such as budget, age, annual income, and other personal information, as well as the purpose of purchase. The system preprocesses the level decision factors submitted by the user, selects the appropriate ethnic costumes, and feeds back to the user through the collaborative decision-making of RBR and CBR, and lists the basic parameters of ethnic costumes. Suggest and add user-approved decisions on a case-by-case basis. In this way, the CBR system coordinates with the RBR by sending requests to the RBR programming system to maintain the integrity of the individual units and system policy. CBR can invoke the RBR system to assist itself in its four different phases.

It mainly consists of the following parts. Intelligent human-computer system: used for human-computer interaction, problem formation and result display, to improve the efficiency of user input decision-making factors. Data preprocessing can decompose and transform the information submitted by users and send it to the CBR clothing decision support system for decision-making. CBR Ethnic Clothing Purchasing Decision System: using reasoning and assumptions to make purchasing decisions on market issues submitted by intelligent human-machine systems. Automobile market database: store various market-related parameter data and multimedia information to help the market decision-making system provide a richer market plan. RBR scheduling system: integrated programming of CBR and RBR subsystems, coordinating the work of both. RBR Ethnic Clothing Purchasing System Support: use rule-based logic to make purchasing decisions on market inquiries submitted by intelligent human-machine systems. Through the collaborative decision-making of RBR and CBR, the research provides an overall framework for promoting the consumption of ethnic clothing. From user input, through processes such as Buy Ethnic Costume Database and RBR National Costume Purchase Support System, return the analysis results to the intelligent man-machine system for aggregation, and finally make intelligent decisions.

4.3. Suggestions for Promoting National Costume Consumption

With the assistance of artificial intelligence decision-making and Internet of Things technology, the research and construction of suggestions that are more in line with the needs of the times and promote the consumption of ethnic clothing.

4.3.1. Pay Attention to the Contrast of National Cultural Atmosphere

By arranging decorations or publicity exhibits with ethnic cultural charm in the area where ethnic costumes are sold inside the shopping mall, a strong ethnic cultural atmosphere is created. Using the monitoring system constructed by artificial intelligence decision-making and the Internet of Things to find out the main travel trajectories of various groups of people in the mall, simulate the cultural environment that is most conducive to stimulating consumption, and then make adjustments according to actual needs.

4.3.2. Expand the Range of Products to Meet the Needs of People at Different Stages

The study found that the important factor affecting the consumption of ethnic costumes at this stage is that the target group is relatively narrow. Except for the young and middle-aged groups, it is difficult for women of other age groups to find their own national costumes. At the same time, some high-income groups have very limited choices. This requires us to accurately locate the needs of these consumers. Deeply excavate the data provided by artificial intelligence decision-making and the Internet of Things, have the courage to break through the traditional supply and marketing pattern, and expand the scope of goods.

5. Conclusions

As an external manifestation of the inheritance of national culture, national costumes reflect the inner essence of national culture to a large extent. In recent years, the Chinese government has vigorously promoted the construction of a national cultural system, hoping to counteract the cultural invasion of the West. In this context, promoting the consumption of ethnic costumes should become a force that we must pay attention to. The research first uses the method of questionnaire survey to grasp some specific data in the field of ethnic clothing consumption, then analyzes the existing problems according to the trends reflected in the data, and finally uses artificial intelligence decision-making and the Internet of Things system to put forward suggestions for promoting ethnic clothing consumption.

Data Availability

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Conflicts of Interest

It is declared by the authors that this article is free of conflict of interest.

Acknowledgments

This study was supported by the Innovation and Development of Hunan Huayao Cross-stitch Art Under The Trend of Digital Technology (XSP21YBC421), Innovative Research on the Cross-stitch Art of Xupu Huayao in Revitalizing the Rural Economy (19C1067), and Study on Dress Curve Patterns Unearthed in Mawangdui (XSP21YBC080).

References

Y. Shen, Y. Li, Q. Zhang, F. Li, and Z. Wang, “Consumer psychology based optimal portfolio design for demand response aggregators,” Journal of Modern Power Systems and Clean Energy, vol. 9, no. 2, pp. 431–439, 2021.
View at: Publisher Site | Google Scholar
R. K. Sett, “Inflexible microcredit contracts and their discontents: a theoretical perspective based on consumer psychology,” IIMB Management Review, vol. 32, no. 1, pp. 96–107, 2020.
View at: Publisher Site | Google Scholar
B. Harman, “Routledge international handbook of consumer psychology,” Qualitative Market Research, vol. 23, no. 2, pp. 329–332, 2020.
View at: Publisher Site | Google Scholar
Q. André, Z. Carmon, K. Wertenbroch et al., “Consumer choice and autonomy in the age of artificial intelligence and big data,” Customer Needs and Solutions, vol. 5, no. 1-2, pp. 28–37, 2018.
View at: Publisher Site | Google Scholar
W. Wu and B. Yin, “Personalized recommendation algorithm based on consumer psychology of local group purchase e-commerce users,” Journal of Intelligent Fuzzy Systems, vol. 37, no. 5, pp. 5973–5981, 2019.
View at: Publisher Site | Google Scholar
A. Costa, “PRIMEMEAL-using consumer psychology to promote healthier meal choices,” Impact, vol. 2018, no. 4, pp. 30–32, 2018.
View at: Publisher Site | Google Scholar
L. Polina, “Cross-cultural issues in consumer science and consumer psychology,” Foresight, vol. 20, no. 3, pp. 332-333, 2018.
View at: Publisher Site | Google Scholar
D. A. Briley, S. Danziger, and E. Li, “Promotional games: trick or treat?” Journal of Consumer Psychology, vol. 28, no. 1, pp. 99–114, 2018.
View at: Publisher Site | Google Scholar
N. R. Grossi, B. Batinic, and S. Moharitsch, “Sleep and health: examining the relation of sleep to burnout and well-being using a consumer fitness tracker,” Health and Technology, vol. 11, no. 6, pp. 1247–1257, 2021.
View at: Publisher Site | Google Scholar
J. C. Fendel, V. M. Aeschbach, A. S. Göritz, and S. Schmidt, “A mindfulness program to improve resident Physicians' personal and work-related well-being: a feasibility study,” Mindfulness, vol. 11, no. 6, pp. 1511–1519, 2020.
View at: Publisher Site | Google Scholar
V. R. Rao, G. J. Russell, H. Bhargava et al., “Emerging trends in product bundling: investigating consumer choice and firm behavior,” Customer Needs and Solutions, vol. 5, no. 1-2, pp. 107–120, 2018.
View at: Publisher Site | Google Scholar
M. Ali, “Influence of the sub conscious mind in consumer psychology of buying in contemporary ERA,” Shanlax International Journal of Commerce, vol. 7, no. 3, pp. 1–10, 2019.
View at: Publisher Site | Google Scholar
T. Sebastian, P. G. Yammiyavar, and S. Jones, “Brand selection in planned purchasing: an analysis of Asian user behavior,” IAFOR Journal of Psychology & the Behavioral Sciences, vol. 4, no. 2, pp. 3–14, 2018.
View at: Publisher Site | Google Scholar
C. Mi, J. Chen, Z. Zhang, S. Huang, and O. Postolache, “Visual sensor network task scheduling algorithm at automated container terminal,” IEEE Sensors Journal, vol. 22, pp. 6042–6051, 2022.
View at: Publisher Site | Google Scholar
X. Li, “Construction of an interactive sharing platform for competitive intelligence data of marine resources under the background of intelligence construction,” Journal of Coastal Research, vol. 103, no. sp1, pp. 990–994, 2020.
View at: Publisher Site | Google Scholar
A. Arif, “Application of the western art form based on artificial intelligence,” Acta Informatica Malaysia, vol. 4, no. 2, pp. 45-46, 2020.
View at: Publisher Site | Google Scholar
J. C. Hoffart, S. Olschewski, and J. Rieskamp, “Reaching for the star ratings: a Bayesian-inspired account of how people use consumer ratings,” Journal of Economic Psychology, vol. 72, no. JUN., pp. 99–116, 2019.
View at: Publisher Site | Google Scholar
Y. T. Hsu and M. S. Cheng, “fMRI neuromarketing and consumer learning theory: word-of-mouth effectiveness after product harm crisis,” European Journal of Marketing, vol. 52, no. 1/2, pp. 199–223, 2018.
View at: Publisher Site | Google Scholar
A. K. Sangaiah, H. Lu, and Q. Hu, “Cognitive science and artificial intelligence for human cognition and communication,” IEEE Consumer Electronics Magazine, vol. 9, no. 1, pp. 72-73, 2020.
View at: Publisher Site | Google Scholar
V. L. Mango, M. Sun, R. T. Wynn, and R. Ha, “Should we ignore, follow, or biopsy? Impact of artificial intelligence decision support on breast ultrasound lesion assessment,” American Journal of Roentgenology, vol. 214, no. 6, pp. 1445–1452, 2020.
View at: Publisher Site | Google Scholar
B. Unhelkar and T. Gonsalves, “Enhancing artificial intelligence decision making frameworks to support leadership during business disruptions,” IT Professional, vol. 22, no. 6, pp. 59–66, 2020.
View at: Publisher Site | Google Scholar
M. Hutson, “The opacity of artificial intelligence makes it hard to tell when decision-making is biased,” IEEE Spectrum, vol. 58, no. 2, pp. 40–45, 2021.
View at: Publisher Site | Google Scholar
M. Alberto, “Elements of music based on artificial intelligence,” Acta Informatica Malaysia, vol. 4, no. 2, pp. 30–32, 2020.
View at: Publisher Site | Google Scholar
K. G. Jugal and K. G. Sanjay, “Iot based statistical approach for human crowd density estimation-design and analysis,” Acta Informatica Malaysia, vol. 4, no. 1, pp. 22–25, 2020.
View at: Publisher Site | Google Scholar
I. Berlianty and D. Rachmawati, “Noise level measurement to reduce the risk of injury with the Internet of things and ergonomic approach,” RSF Conference Series: Engineering and Technology, vol. 1, no. 1, pp. 126–135, 2021.
View at: Publisher Site | Google Scholar
S. Bankins, “The ethical use of artificial intelligence in human resource management: a decision-making framework,” Ethics and Information Technology, vol. 23, no. 4, pp. 841–854, 2021.
View at: Publisher Site | Google Scholar
X. L. Qi, “Application of national costume style in modern costume design——comment on "National costume elements and fashion design",” Printing and Dyeing, vol. 47, no. 2, p. 2, 2021.
View at: Google Scholar
C. Zhang, “A brief analysis of China's diversified national costumes,” West Leather, vol. 40, no. 7, p. 1, 2018.
View at: Google Scholar
Z. Y. Liu, Let the Colorful National Costume Culture Enter the Classroom, 2021.
W. Pu, “Modern Hanfu: self-confidence in the practice of visual culture,” Popular Literature and Art: Academic Edition, no. 13, p. 2, 2021.
View at: Google Scholar
R. Li, “Cultural resources protection and industrial development of ethnic minority costumes,” Cotton Textile Technology, vol. 49, no. 8, p. 1, 2021.
View at: Google Scholar

Copyright

Copyright © 2022 Yu Peng and Watanapun Krutasaen. This 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.

PDF Download Citation

Download other formats

Order printed copies