Earticle

YouTube has become a popular platform for vlogs. Among various forms of vlogs, office worker vlogs, in which a person engaged in a specific job shows his/her work environment and daily routine, are gaining popularity. Thus, focusing on office worker vlogs, the present research investigates the effects of office worker vlogs’ characteristics (i.e., vlog content characteristics, vlogger characteristics) on the YouTube viewers’ educational value of the vlog and their job engagement. Specifically, this research examines whether (1) vlog content characteristics (i.e., usefulness, accessibility, and vividness) and (2) vlogger characteristics (i.e., job similarity, credibility, and expertise) influence the YouTube viewers’ educational value of the vlog. Moreover, this research examines how the YouTube viewers’ educational value of the vlog affects their job engagement. With a sample of YouTube viewers of office worker vlogs (N = 215), structural equation modelling was implemented to investigate the relationships in the proposed model. The results indicate that (1) perceived usefulness of the office worker vlog is positively associated with the educational value of the vlog; (2) perceived accessibility of the office worker vlog is positively associated with the educational value of the vlog, albeit marginally significant; (3) perceived vividness of the office worker vlog is positively associated with the educational value of the vlog; (4) perceived job similarity to the office worker vlogger is positively associated with the educational value of the vlog; (5) perceived credibility of the office worker vlogger is positively associated with the educational value of the vlog; (6) perceived expertise of the office worker vlogger is positively associated with the educational value of the vlog; and (7) the educational value of the office worker vlog is positively associated with the YouTube viewers’ job engagement. The findings provide important implications for the production and use of office worker vlog contents.

Recent information and communication technologies have already opened up new prospects for technology groups, especially in a knowledge-based society. A contemporary technological era, which can be stated as the hyper-connective Internet of Things surpassed the traditional service pattern and innovation pattern by conveying personalized, localized, and con-text-aware services close to different actors and users. The conventional boundary of the organization is disbanding as well as traditional innovation and research & development limits. This research article conducts a preliminary study about the hyper-connective Internet of Things technology portent with innovation 3.0 version based on an extended technological organization environment framework (E-TOEF). This article discusses the emergence of innovation 3.0 as a paradigm shift from a manufacturing paradigm to an actor-oriented paradigm. There is a need to shift from a manufacturing mindset to more user ergonomics and be aware of the potential of hyper-connective IoT on the revolution of innovation patterns to be more cooperative, open, and user-centered. Besides, this article would strain some conceptual approaches for the next-generation innovation paradigm known as “hyper-connective IoT” entitled innovation 3.0. This new innovation version goes beyond open innovation and undeniably clearly beyond closed innovation which was an earlier version.

The portable mobile devices with high performance and high speed 5G network activate and explode the demands for ubiquitous information services that remove the limitations of time for the communication and places to request for the information. NN (Nearest Neighbor) search is one of the most important types of queries to be processed efficiently in the information services. Various indexes have been proposed to support efficient NN search in the wireless broadcast system. The indexes adopting Hilbert curve, grid partition or Voronoi diagram enable the clients to search for NN quickly in the wireless broadcast channel. It is necessary that an efficient means to evaluate the performances of various indexes. In this paper, we propose an open framework that can adopt a variety of indexing schemes and evaluate and compare the performances of them. The proposed framework is organized with open and flexible structure that can adopt hybrid indexing schemes extensible to Voronoi diagram as well as simple indexing schemes. With the implemented framework, we demonstrate the efficiency and scalability and flexibility of the proposed framework by evaluating various indexing schemes for NN query.

This paper introduces a real-time face swapping system that enables video influencers to swap their faces with arbitrary generated face images of their choice. The system is implemented as a Django-based server that uses a REST request to communicate with the generative model, specifically the pretrained stable diffusion model. Once generated, the generated image is displayed on the front page so that the influencer can decide whether to use the generated face or not, by clicking on the accept button on the front page. If they choose to use it, both their face and the generated face are sent to the landmark extraction module to extract the landmarks, which are then used to swap the faces. To minimize the fluctuation of landmarks over time that can cause instability or jitter in the output, a temporal filtering step is added. Furthermore, to increase the processing speed the system works on a reduced set of the extracted landmarks.

The purpose of this study is to revitalize ESG tourism in Bhutan by comparing and analyzing the ESG tourism status in Bhutan and the ESG tourism status in Korea. Big data analysis using text mining was performed by selecting "Bhutan ESG Tourism" and "Korea ESG Tourism" as keywords. The top 30 keywords were extracted through word purification, and based on this, data visualization was conducted through network analysis and Concor analysis between each keyword. As a result of the analysis, it was confirmed that Bhutan, unlike Korea, did not utilize it even though it had elements to incorporate ESG and the tourism industry into the country itself. As a result, since it is necessary to combine ESG elements owned by Bhutan and combine them with the tourism industry, we would like to suggest the direction of combining ESG and the tourism industry through this study.

In accordance with the revision of “Special act on the safety control of publicly used establishments”, this study is aim to measure the change in evacuation time due to whether safety facilities, etc. are installed of a room escape cafe business and kids cafe business(hereinafter referred to as “New publicly used establishments”), which were added as new targets of the publicly used business from June 8, 2022. In the case of new publicly used establishments or publicly used establishments whose owners are changed after the revision of the relevant laws, safety facilities, etc. are installed and maintained under the “Special act on the safety control of publicly used establishments”, but in the case of existing businesses that have been operating even before the revision of the law, the business continues without safety facilities, etc. installed because the revised law is not retroactively applied. The purpose of this study is to compare and analyze the change in evacuation time by measuring the evacuation time to operating before the revision of the law to simulate evacuation at existing new publicly used establishments without safety facilities, etc. and measure the evacuation time at new publicly used establishments with safety facilities after the revision of the law

The purpose of this study is to measure the change in evacuation time at high schools according to the change in hallway width using an evacuation simulation program and to analyze the result of such change. In order to measure the evacuation time according to the change in the hallway width according to the 「Rules on the Standards for Evacuation and Fire Protection Structures of Buildings」 and to analyze the change in evacuation time resulted from the increase in the number of occupants, a scenario was constructed by applying the 「performance-oriented design method and standard for firefighting facilities, etc.」. As a result of the experiment, it was found that the evacuation time was the shortest when the width of the hallway was the widest, which was 3m. On the other hand, the evacuation time took the longest at 1.8m, which was the width of the second narrowest hallway. For the safety of high school students who spend a lot of time at school, it is necessary to secure a wide hallway width when building a new school or to provide periodic safety education in the case of an existing school whose hallways are considered narrow.

As a result of this study, the income generation effect of local universities on the local economy through the Daranee (1976) model was found to be 110.9 billion won (direct and indirect income 78 billion won, induced income 32.9 billion won). In the case of Korea, it has been verified through a number of previous studies that local universities play a role in preventing the outflow of local talent to the metropolitan area. Considering this, it seems that the government should make bold investments to foster local universities in terms of balanced national development. This is because the movement of local talents to the metropolitan area not only undermines the growth potential of the provinces and undermines the basis for regional existence, but also creates a vicious cycle that hinders balanced national development. To break this vicious cycle, the development of local universities is very important. It is judged that the horizon of balanced national development will be opened when local universities revitalize the local economy through the government's bold investment in local universities and are reborn as entities that provide various services based on the facilities and equipment of local universities.

As a result of this study, the income generation effect generatded by regional universities for the region is KRW 130.6 billion (direct and indirect income effect KRW 90.9 billion, induced income effect KRW 39.6 billion). In addition, it is estimated that the effect of regional universities on inducing employment in the region is 2,145 per year. Unless quality jobs are secured, the outflow of population to the metropolitan area will accelerate, and the disappearance of local areas will emerge as a social problem in the near future. Considering the effect of local universities on the local economy revealed through the results of this study, that is, the income and job creation effects, the government will be able to prevent local extinction by providing bold financial support to local universities. If it is difficult to afford it with government finances alone, it can be solved by opening the door to universities for admission through donations, which many advanced countries are introducing..

The purpose of this study is to empirically analyze the rational decision-making process and perception differences of housing transactions in the market environment. It was designed through an analysis of the factors influencing housing sales based on the rational behavior theory model. Objective evidence was provided for the impact factors affecting the attitude towards housing sales, with the spouse and children being identified as significant influencers. Additionally, children and friends were found to have an impact on subjective norms related to housing sales, especially for unmarried individuals under 40 years of age and those with low income, who were found to be more influenced by their parents. It was also discovered that the influence of these factors varied based on age and income levels. Younger individuals tended to rely more on their parents or friends, while those with high incomes showed stronger willingness to purchase homes. The presence of beneficial infrastructure for children was found to directly influence the decision to purchase a home. The study also provided objective evidence that the decision to purchase a home is influenced not only by economic factors but also by continuous encouragement and information from those around the buyer. These findings demonstrate the importance of the influence of close acquaintances in the rational decision-making process of home buyers. However, this study only investigated a limited portion of the factors influencing housing sales, as the market is affected by a variety of financial and governmental policies. Therefore, future research should consider various complex factors simultaneously when analyzing the influence of housing sales.

We would like to find out how restaurant start-up education affects restaurant start-ups. Recently, as low barriers to entry and endemics are approaching, more and more people want to start a restaurant business. However, while the market size of restaurant start-ups increases due to the high youth unemployment rate and changes in the social population structure, the probability of failure of start-ups is increasing due to the high competition rate. Therefore, this study aims to examine whether restaurant start-up education affects restaurant start-ups through entrepreneurship. This study conducted a survey on prospective start-ups. After that, demographic analysis and multiple regression analysis were performed using the SPSS 23.0 program. As a result, it was found that entrepreneurship had an effect on restaurant start-ups. However, in future studies, more research is needed on the direction of improving and developing restaurant start-up education.

This study aims to find out what tourists' interests and perceptions are like through online big data. Big data for a total of five years from 2018 to 2022 were collected using the Textom program. Sentiment analysis was performed with the collected data. Sentiment analysis expresses the necessity and emotions of city tours in online reviews written by tourists using city tours. The purpose of this study is to extract and analyze keywords representing satisfaction. The sentiment analysis program provided by the big data analysis platform "TEXTOM" was used to study positives and negatives based on sentiment analysis of tourists' online reviews. Sentiment analysis was conducted by collecting reviews related to the city tour. The degree of positive and negative emotions for the city tour was investigated and what emotional words were analyzed for each item. As a result of big data sentiment analysis to examine the emotions and sentiments of tourists about the city tour, 93.8% positive and 6.2% negative, indicating that more than half of the tourists are positively aware. This paper collects tourists' opinions based on the analyzed sentiment analysis, understands the quality characteristics of city tours based on the analysis using the collected data, and sentiment analysis provides important information to the city tour platform for each region.

With the continuous development of emerging technologies represented by VR technology, many game developers are declaring that they are constantly trying to break the "fourth wall" and break the boundaries between virtual and reality to create game immersion for players. new game. But for many gamers, a strong sense of immersion is not the focus of their pursuit. The sense of control and safe exploration during the game is also the game experience that many gamers are pursuing. Moreover, there is ambiguity in the definition of the concept of breaking the fourth wall in the field of academic theory. The purpose of breaking the fourth wall was to separate the real world from the virtual world, to remind the audience that the actors and the audience are in two different worlds, and to trigger the audience's thinking about drama and deeper philosophy. But in the current game, it has become a blurring of the boundary between virtual and reality, pulling players into the virtual world, and focusing on the immersive experience. In this paper, we will first sort out the concept of "breaking the fourth wall", and then conduct a comparative analysis of horizontal scroll games and VR games, and conclude that the "fourth wall" has an impact on players Great conclusion.

In this paper, we present a simple classification model based on statistical features and demonstrate the successful implementation of a brain-computer interface (BCI) based light on/off control system. This research shows study and development of light on/off control system based on BCI technology, which allows the users to control switching a lamp using electroencephalogram (EEG) signals. The logistic regression algorithm is used for classification of the EEG signal to convert it into light on, light off control commands. Training data were collected using 14-channel BCI system which records the brain signals of participants watching a screen with flickering lights and saves the data into .csv file for future analysis. After extracting a number of features from the data and performing classification using logistic regression, we created commands to switch on a physical lamp and tested it in a real environment. Logistic regression allowed us to quite accurately classify the EEG signals based on the user's mental state and we were able to classify the EEG signals with 82.5% accuracy, producing reliable commands for turning on and off the light.

In this study, we propose a big data set of strawberry pests collected directly for diagnosis model learning and an automatic pest diagnosis model architecture based on deep learning. First, a big data set related to strawberry pests, which did not exist anywhere before, was directly collected from the web. A total of more than 12,000 image data was directly collected and classified, and this data was used to train a deep learning model. Second, the deep-learning-based automatic pest diagnosis module is a module that classifies what kind of pest or disease corresponds to when a user inputs a desired picture. In particular, we propose a model architecture that can optimally classify pests based on a convolutional neural network among deep learning models. Through this, farmers can easily identify diseases and pests without professional knowledge, and can respond quickly accordingly.

Smart agriculture is a rapidly growing field that seeks to optimize crop yields and reduce risk through the use of advanced technology. A key challenge in this field is the need to create a comprehensive smart farm system that can effectively monitor and control the growth environment of crops, particularly when cultivating new varieties. This is where fuzzy theory comes in, enabling the collection and analysis of external environmental factors to generate a rule-based system that considers the specific needs of each crop variety. By doing so, the system can easily set the optimal growth environment, reducing trial and error and the user's risk burden. This is in contrast to existing systems where parameters need to be changed for each breed and various factors considered. Additionally, the type of house used affects the environmental control factors for crops, making it necessary to adapt the system accordingly. While developing such a framework requires a significant investment of labour and time, the benefits are numerous and can lead to increased productivity and profitability in the field of smart agriculture. We developed an AI platform for optimal control of facility houses by integrating data from mushroom crops and environmental factors, and analysing the correlation between optimal control conditions and yield. Our experiments demonstrated significant performance improvement compared to the existing system.

As a new trend in the development of urban public spaces, the use of right-angle LED screens perfectly combines building facades with naked-eye 3D visual effects, providing designers with a brand-new creative platform. How to create a realistic naked-eye 3D effect on a right-angle LED screen and bring an immersive visual experience to the audience has become a question worth exploring. So far, production companies have yet to announce the relevant design ideas and complete production methods. In order to explore the production principle and production process of the naked-eye 3D effect of the right-angle LED screen, we summarize the basic production principle of the naked-eye 3D impact of the right-angle LED screen through case analysis. Based on understanding the production principle, the actual case production test was carried out, and a complete production process of the naked eye 3D visual effect of the right-angle led screen was tried to be provided by off-line rendering. For the problem of how to deal with image deformation, we provide two production methods: post-production software correction and UV mapping. Among them, the UV mapping method is more efficient and convenient. Referring to this paper can help designers quickly understand the production principle of the naked eye 3D effect of right-angle LED screens. The production process proposed in this paper can provide a reference for production method for related project producers.

In the current world, with the massive scale of SOC construction, it is difficult to diagnose and check all of a bridge's abnormal states with even the experts' eyes for maintenance. It is because we should spend huge costs and time on maintenance. Still, there are not many alternative ways to inspect bridges remotely regarding accuracy or reality. Therefore, we remark on the advantages and disadvantages of previous methods through practices in SOC maintenance. To inspect the abnormal state of the Bridge, we suggest inspecting bridges with an Augmented Reality (AR) mechanism to reduce cost, human resource consumption, and the risk of work. Through the proposed approach, we expect that it provides ways to solve massive construction problems with software-based technologies.

Fractal geometry, a relatively new branch of mathematics, was first introduced by Benoit Mandelbrot in 1975. Since then, its applications have expanded into various fields of natural science. In fact, it has been recognized as one of the three significant scientific discoveries of the mid-20th century, along with the Dissipative System and Chaos Theory. With the help of fractal geometry, designers can create intricate and expressive artistic patterns, using the concept of self-similarity found in nature. The impact of fractal geometry on the digital art world is significant and its exploration could lead to new avenues for creativity and expression. This paper aims to explore and analyze the development and applications of fractal geometry in digital art design. It also aims to showcase the benefits of applying fractal geometry in art creation and paves the way for future research on sacred geometry.

With the development of VR technology, the visual immersion of VR games has been greatly enhanced nowadays. There has been an issue that has been troubling players in previous VR games, which is motion sickness. Therefore, VR games have been limited in terms of game mechanics, game duration, and game scale, greatly reducing the immersive experience of visual immersion. However, <Half-Life: Alyx> is different from previous VR games in that players can actually perform spatial displacement in the game scene, rather than being fixed in one place for 360-degree observation and interaction. At the same time, compared to traditional games, VR games no longer need to rely on screens, and the complete visual immersion enhances the fun and playability of the game. This research focuses on the VR game <Half-Life: Alyx> to explore its immersive factors in terms of visual perception. Through in-depth analysis of elements such as color, texture mapping, lighting, etc. in VR games, it was found that the game creates a strong sense of visual immersion in these aspects. Through analysis, it is helpful to gain a deeper understanding of the factors that contribute to visual immersion in VR games, which has certain reference value for game developers and related professionals.

Sarcopenia is a phenomenon in which muscle function, including muscle strength, deteriorates as muscle mass decreases in the process of increasing age. The diagnosis of sarcopenia utilizes total muscle mass and limb muscle mass, and limb muscle mass is expressed as height squared, body weight, and BMI. Each divided value is used as an index, mainly less than 7.23 kg/m2 for men and less than 5.67 kg/m2 for women. Grip strength, standing up from a chair, and walking speed were mainly used as physical function factors, and grip strength less than 27 kg for men and less than 16 kg for women were used as indicators. The limb muscle mass showed a decreasing trend after peaking in the mid-20s in men, and maintaining a gradual peak in women from the mid-20s to the mid-40s, showing a more rapid decline in men. The rate of decrease in muscle mass and strength continues to increase after the age of 20, and muscle strength rapidly decreases after the age of 80. In Korean men, total muscle mass and limb muscle mass show a decreasing trend from the mid-30s, and a more markedly rapid decrease from the age of 60. For women, it remains constant from the age of 30 to the age of 50, then gradually decreases after the mid-50s, and shows a rather rapid decrease after the mid-70s, showing a more gradual decrease than that of men. Men show a sharp decrease from the mid-40s when limb muscle mass is divided by height squared, and women show a marked decrease after 70 years old when limb muscle mass is divided by height squared. Exercise for the prevention and treatment of sarcopenia results in an increase in protein assimilation hormone, an increase in antioxidant activity, a decrease in inflammation, an increase in muscle insulin sensitivity, and an increase in protein synthesis. Resistance exercise is basically used, and aerobic exercise and equilibrium A combination of exercises is effective. In addition, for a more efficient effect of sarcopenia through resistance exercise, it is necessary to supplement nutrition including protein.

In recent years, virtual reality (VR) technology has been widely used in many industrial fields, especially in the fields of medical treatment, games, film and television, to improve the interaction between medical teaching and practical treatment. On the gaming side, the production of virtual reality gaming screens and scenes became increasingly popular, greatly expanding the form of the visual experience. But VR is no longer confined to the health care, education and entertainment industries. During this time, the news media industry has also begun to integrate virtual reality into interviews and user interactions. This study aims to analyze the development of VR technology from the perspectives of immersive VR news experience, real reporting, and prospects, and analyze and think about the interactive participation of media users, the transformation of traditional media, and the upgrading of practitioners' roles.

This study aims to analyze the correlation between semiconductor innovation and market dominance in the mobility electric vehicle industry. To this end, the study presents strategies that provide low-price competitiveness along with high-value creation in the electric vehicle and semiconductor markets. The first change in the era of high interest rates is to overcome the crisis of survival for value. Furthermore, the study acknowledges the ongoing second wave of change as the digital technology's value continues to rise, and companies experience decreased productivity due to rising ESG labor costs. The study analyzed price competitiveness in the context of the increased adoption of electric vehicles and the integration of semiconductor prices, proving that Tesla and Samsung Semiconductor have developed technology to dominate the market, with appropriate low-cost strategies applied as the value of innovation declines.

The purpose of this study is to develop a physical activity program for problem drinkers living in side rooms(Jjok-bang) based on the health belief model. In order to develop a physical activity program suitable for and applicable to the characteristics of the problem drinkers, the detailed components of the health belief model and the learning goals for each program were linked. It consists of a total of 10 activities, and in the introductory stage of each program, physical examination and gymnastics were conducted, and in the development stage, 10 physical activities were conducted to help the movement of large and small muscles and concentration. In the final stage of organizing, it consisted of time to express one's emotions through writing and painting and to reflect. The developed program was commissioned by an expert to derive the content validity coefficient (CVI=.75). Through the physical activity program developed in this study, it is believed that the problem drinking behavior of problem drinkers living in side rooms can be gradually reduced. The physical activity program developed in this study is expected to gradually reduce the problems of problem drinkers living in Jjock-bang. In the next step, we propose a study that quantitatively and qualitatively analyzes the intervention effect by applying this program to clients.

In Korea, we still use function point based cost estimations for software size and cost of a project. The current problem is that we make difficultly calculating function points with requirements and also have less accurate. That is, it is difficult for non-experts to analyze requirements and calculate function point values with them, and even experts often derive different function points. In addition, all stakeholders strongly make the validity and accuracy of the function point values of the project before /after the development is completed. There are methods for performing function point analysis using source code [1][2][3][4] and some researchers [5][6][7] attempt empirical verification of function points about the estimated cost. There is no research on automatic cost validation with source code after the final development is completed. In this paper, we propose automatically how to calculate Function Points based on natural language requirements before development and prove FP calculation based on the final source code after development. We expect validation by comparing the function scores calculated by forward engineering and reverse engineering methods.

Online marketing is a rapidly growing industry that heavily depends on digital technologies and data analysis to effectively reach and engage consumers. For that, artificial intelligence (AI) has emerged as a crucial tool for online marketers, enabling marketers to analyze extensive consumer data and automate decision-making processes. The purpose of this study was to investigate the ethical implications of using AI in online marketing, focusing on its impact on consumer privacy and decision-making. AI has created new possibilities for personalized marketing but raises concerns about the collection and use of consumer data, transparency and accountability of decision-making, and the impact on consumer autonomy and privacy. In this study, we reviewed the relevant literature and case studies to assess the potential risks and make recommendations for improving consumer protection. The findings provide insights into ethical considerations and offer a roadmap for balancing the advantages of AI in online marketing with the protection of consumer rights. Companies should consider these ethical issues when implementing AI in their marketing strategies. In this study, we explored the concerns and provided insights into the challenges posed by AI in online marketing, such as the collection and use of consumer data, transparency, and accountability of decision-making, and the impact on consumer autonomy and privacy.

In this study, in order to efficiently detect data patterns and outliers in time series data, outlier detection processing is performed for each section based on a smart contract in the data preprocessing process, and parameters for the ARIMA model are determined by generating and reflecting the significance and outlierrelated parameters of the data. It was created and applied to the modified arithmetic expression to lower the data abnormality. To evaluate the performance of this study, the normality of the data was compared and evaluated when the parameters of the general ARIMA model and the ARIMA model through this study were applied, and a performance improvement of more than 6% was confirmed.

Nowadays, with the spread of the Internet and the emergence of high-performance computers and various peripheral devices, our society is undergoing great changes. In the field of education, various types of education using smart education infrastructure are being conducted. The spread of the Internet and the development of various devices have problems that can lead to addiction due to excessive Internet use. Most of the problems that appear in adolescence are immersed in games, which can affect academic achievement. Therefore, in this study, the effect of excessive Internet use on students' academic achievement was studied. The survey for the study was conducted through a questionnaire survey, and the subjects of the survey were high school students majoring in humanities. As a result, the relationship between academic achievement and Internet addiction was low in the middle, upper, and lower groups in the general user group. Also, in the highrisk user group, it appeared high in the order of middle, low, and high.

Recently, the cross-model strategy of using male models in advertisements for women's cosmetics has been increasingly utilized. Academics have begun to discuss and study cross-model advertisements, but most of the studies have focused on the effects of the presence of a cross model. We investigated the effects of a crossmodel’s product demonstration as an advertising creative strategy on consumer's attitudes toward the ad. We examined the effects of a male model demonstrating the advertised products for women's cosmetics on female consumers' attitudes toward the ad. As a result, we found that when a male model demonstrated a product in a women's product advertisement, consumers' attitudes toward the ad were more positive the higher their product involvement. Therefore, product involvement was found to be a moderating variable in the effect of cross-model product demonstration on attitudes toward the ad. This study contributes to the line of research on the effect of cross-model and product demonstration advertising, providing practical implications for advertising practitioners.

A common approach to the problem of predicting student test scores is based on the student's previous educational history. In this study, high school transcripts of about two thousand candidates, who took the High-school Student Assessment (HSA) were collected. The data were estimated through building a regression model - Random Forest and optimizing the model's parameters based on Genetic Algorithm (GA) to predict the HSA scores. The RMSE (Root Mean Square Error) measure of the predictive models was used to evaluate the model’s performance.