• 한국인공지능학회지
• /
• 제5권1호
• /
• pp.18-28
• /
• 2017

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.

• 한국인공지능학회지
• /
• 제5권1호
• /
• pp.1-9
• /
• 2017

Recently, the Q-Learning algorithm, which is one kind of reinforcement learning, is mainly used to implement artificial intelligence system in combination with deep learning. Many research is going on to improve the performance of Q-Learning. Therefore, purpose of theory try to improve the performance of Q-Learning algorithm. This Theory apply Cross Entropy Error to the loss function of Q-Learning algorithm. Since the mean squared error used in Q-Learning is difficult to measure the exact error rate, the Cross Entropy Error, known to be highly accurate, is applied to the loss function. Experimental results show that the success rate of the Mean Squared Error used in the existing reinforcement learning was about 12% and the Cross Entropy Error used in the deep learning was about 36%. The success rate was shown.

• International Journal of Advanced Culture Technology
• /
• 제8권3호
• /
• pp.38-44
• /
• 2020

Storytelling plays a very important role in emotional marketing recently. Storytelling marketing emphasizes a unique story and mythical meaning of the product, rather than its practical function. This is a faithful reflection of what the Dream Society has proposed. In this article, we are researching the consumption value system, and analyze various cases focusing on a coffee advertisement. In particular, by delivering a story, we will concentrate on advertising that appeals to utopian values and discusses the actual impact that it brings. If we communicate utopian values to consumers through various stories, business effects will be maximized, which will strengthen the brand image. The originality of this paper is to discuss the theory of consumption value system positively with the concept of storytelling. Therefore, we will draw conclusions as to which orientation is most ideal for storytelling in advertising. Understanding these business models will help you build an effective marketing strategy for the Dream Society.

• Asia Marketing Journal
• /
• 제18권3호
• /
• pp.47-63
• /
• 2016

Rational choice theory holds that the alternative with largest expected utility in the choice set should always be chosen. However, it is often observed that an alternative with the largest expected utility is not always chosen while the choice task itself being avoided. Such a choice phenomenon cannot be explained by the traditional expected utility maximization principle. The current study posits shows that such a phenomenon can be attributed to the gap between the expected perceived gain (or loss) and the expected perceived value. This study mathematically analyses the relationship between the expectation of an alternative's gains or losses over the reference point and its expected value, when the perceived gains or losses follow continuous probability distributions. The proposed expected value (EV) function can explain the effects of loss aversion and uncertainty on the evaluation of an alternative based on the prospect theory value function. The proposed function reveals why the expected gain of an alternative should exceed some positive threshold in order for the alternative to be chosen. The model also explains why none of the two equally or similarly attractive options is chosen when they are presented together, but either of them is chosen when presented alone. The EV function and EG-EV curve can extract and visualize the core tenets of the prospect theory more clearly than the value function itself.

• 산경연구논집
• /
• 제5권4호
• /
• pp.23-29
• /
• 2014

Purpose - This thesis aims to propose a method to help financial institutions improve their customers' convenience online and offline through a Bluetooth based App using the tool of a beacon. The emergence of smartphones in the 21st century and their increasing use makes it possible to search for information easily. Research design, data, and methodology - With the short-distance Bluetooth technology for smartphones, which finds users within a radius of 50m to provide the functions of message transmission and mobile payment, users can access information services and use mobile coupons in certain premises. Thus, beacon-based O2O technology has been developed. Results - This study offers a method of attracting customers through an O2O marketing strategy that overcomes the existing limitations of Web and Offline media. Conclusions -Since beacon technology has the advantage of more accurate positioning than GPS, financial institutions provide their product information for users through the basic function of a beacon, using an O2O (Online to Offline) marketing solution and, therefore, effectively enable customers to make relevant payments online and conduct their financial actions offline.

• 산경연구논집
• /
• 제11권2호
• /
• pp.49-59
• /
• 2020

Purpose: Online and social media and mobile shopping are increasing and companies are required to provide personal information in order to supplement the non-invasive characteristics of the channels. With the increased provision of personal information, consumers' personal and social concerns about the prevention of personal information infringement are also increasing, and in response, personal or opt-in marketing has emerged to compensate for reckless information abuse. Despite the background of this emergence, the existing prior studies are limited to ignoring the negative feelings of consumers in the real world, including only the net function and positive effect of the opt-in mail. Research design, data and methodology: The research framework was intended to utilize the impact of human marketing activities on consumer attitudes combined with positive and negative factors. Factors that positively affect attitudes toward permation marketing were presented, such as informality, and perceived risks were presented as negative impact factors. Also, based on previous prior research, the prior factors of opt-in marketing were to present the effect on purchase intent through the medium of attitude toward opt-in marketing. Results: In this study, we used the framework of a two factor theory to address positive and negative factors as a leading factor in the customer attitude toward opt-in mail advertising, and as a result, functionality and personalization have a positive effect on customer attitude and perceived risk have a negative impact on customer attitude. In addition, it was confirmed that the customer attitude formed this way affects the intention to purchase again. Conclusions: This study suggests that we have demonstrated that marketing, an opt-in marketing that has been recognized as part of marketing that is deployed after obtaining customer consent, has been applied without any other marketing methodology. E-mail advertising at this point also provides practical implications that the system safeguards are in place under an opt-in protocol or system, and that even if an e-mail advertisement is carried out, customers will need to look at the level of awareness about the risks, and suggests that they need to consider the customer's journey that could lead to purchase at the content level.

• 산업공학
• /
• 제16권4호
• /
• pp.400-410
• /
• 2003

Most of the demand forecasting which have been studied is about long-term time series over 15 years demand forecasting. In this paper, we set up the most optimal ARIMA model for the short-term time series demand forecasting and suggest demand forecasting system for short-term time series by appraising suitability and predictability. We are going to use the univariate ARIMA model in parallel with the bivariate transfer function model to improve the accuracy of forecasting. We also analyze the effect of advertisement cost, scale of branch stores, and number of clerk on the establishment of marketing policy by applying statistical methods. After then we are going to show you customer's needs, which are number of buying products. We have applied this method to forecast the annual sales of refrigerator in four branch stores of A company.

• 디지털산업정보학회논문지
• /
• 제14권1호
• /
• pp.1-14
• /
• 2018

The purpose of this study is to learn the current perception of Total Smart Mirror Display devised with IoT, focused on Hair beauty industry. In detail, this study is to analyze domestic and foreign precedented case studies and conditions of Smart Mirror in beauty industry, and to learn, through survey, the real condition of use of Hair Smart Mirror, which is devised and applied according to the actual state of our country. First, the mean comparison for Total Smart Mirror by gender showed that Function1, Technology 2 and 3 had differences. Second, the mean comparison each by age, external design, function, marketing and technologies showed that Function 4, Marketing 1 to 3, Technology 1 and 3 had differences.

• 한국조경학회지
• /
• 제34권6호
• /
• pp.87-100
• /
• 2007

This study analyzed the key words in Korea's leading apartment brands and newspaper advertisements to examine especially their view-oriented advertising characteristics and green marketing properties. Four study topics were established and examined for this purpose. The following are the results; 1. The key words on apartment brands and catch phrases are $\ulcorner$emotion-oriented$\lrcorner$ words, such as taste, pride, and happiness, and $\ulcorner$environment-oriented$\lrcorner$ to appeal to customers with beautiful views of the nature. Also key words on newspaper advertisement headlines stress views for $\ulcorner$environment-oriented$\lrcorner$ characteristics as well as $\ulcorner$emotion-oriented$\lrcorner$ characteristics for elegance and luxury, and $\ulcorner$function-oriented$\lrcorner$ characteristics for the future. Views, nature and park are key words and everything about illustration that are especially emphasized even on the headlines of newspaper advertisements. 2. Unlike brands or headlines, sub-headlines and body copies stress $\ulcorner$modern-oriented$\lrcorner$ characteristics for life, culture, and accessibility, followed by $\ulcorner$emotion-oriented$\lrcorner$ characteristics. Key words on caption were also highly $\ulcorner$modern-oriented$\lrcorner$, followed by $\ulcorner$environment-oriented$\lrcorner$ and $\ulcorner$function-oriented$\lrcorner$ characteristics for practical aspects. 3. In result of $X^2-test$, $\ulcorner$environment-oriented$\lrcorner$ key words that convey good views, naturalism, parks, and nature are the major representation of green marketing strategies of apartment brands and newspaper advertisements. However, brands were strongly $\ulcorner$emotion-oriented$\lrcorner$, whereas captions were $\ulcorner$modern-oriented$\lrcorner$ and body copies were $\ulcorner$investment-oriented$\lrcorner$. Both apartment brands and advertisements were consistently $\ulcorner$environment-oriented$\lrcorner$, but were not consistent in other factors. 4. Different parts of newspaper advertisements are focusing on green marketing strategies in terms of environmental protection, but are actually leaning toward modern-oriented lifestyles and accessibility. Thus, it is more well-being marketing rather than green marketing. To pursue true green marketing despite the limits of newspaper advertisements, it is necessary to present products and pricing strategies that represent sustainable.

• 한국유기농업학회지
• /
• 제12권3호
• /
• pp.317-331
• /
• 2004

Foci of this thesis arc an estimation of willingness to pay and an establishment of green marketing strategics for environment-friendly agricultural products(EFAR). Estimations of willingness to pay for grain, vegetables, fruit and processed food-stuffs arc respectively 20.6%, 20.2%, 19.3% and 17.2% higher than agricultural products produced by conventional farming method. And a green mark6ting mix for EFAP is as follows; Erst, a product strategy focuses on producing safe and high-quality foods by environment-friendly agriculture(EFA) to point to consumer’s health and desire for environmental preservation. Second, in a price strategy, the balance of three factors should be kept, namely the environmental value the true quality as food materials and the price of EFAP. Third, a place strategy is to reduce waste matters, resource and energy uses in marketing chain, and to simplify marketing channels. Also, it is necessary to choose the marketing channel for price discrimination. Fourth, a promotion strategy make use of programs that emphasize the multi-function of EFA.