• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.17 no.4
• /
• pp.315-322
• /
• 2011

The importance of aquafarming is increasing all over the world, however the coastal environment in the semi-closed inner bay has been aggravated due to the long term production and the high stocking density. For the sustainable aquafarming, there is a requirement for a eco-friendly fishery management by the estimation of ecological carrying capacity. The model development and application is still in the initial step, because it has to consider the whole ecosystem and all culture activities. As an alternative, there is a requirement for ecological indicator to assess the ecological performance. This study tried the estimation of ecological carrying capacity using ecological indicator. The production and the facility of the oyster farms was 4,935M/T, $49ind./m^3$ in Geoje-Hansan Bay(2008). Filtration pressure indicator was 0.203 which could provide a guidance on the present level of culture development. According to the environmental characteristics and the present oyster farms in Geoje-Hansan Bay, the newly assessed filtration pressure for the acceptable ecological carrying capacity was 0.102. Consequently, ecological carrying capacity in Geoje-Hansan Bay was 2,480M/T, $25ind./m^3$ and this represents the level of culture that can be introduced into Geoje-Hansan Bay without leading to significant changes to ecological process, species, populations or communities. Our study utilized the ecological indicator to estimate ecological carrying capacity of oyster farming for sustainable productivity and this could be the scientific basis for the eco-friendly fishery management.

• Journal of Korean Society of Environmental Engineers
• /
• v.30 no.4
• /
• pp.393-400
• /
• 2008

1,4-Dioxane($C_4H_8O_2$), which is used as a solvent stabilizer, could make harmful effects on ecosystem because of its higher solubility, toxicity and carcinogenic by US EPA. From 2011, its discharge limit to waterbody will be regulated at 5 mg/L by Ministry of Environment Republic of Korea. It was thus to investigate that the currently operating activated sludge in polyester manufacturing processes in Gumi can properly treat it to meet with the regulation standard. For that purpose, the removal rate of 1,4-dioxane and its microbial properties were assessed for a few companies(i.e. K, H and T). Its removal efficiency was the most highly recorded in H as 98% and then 77% for K, which met with the regulation standard. However, concentration of 1,4-dioxane of T was 23 mg/L in the effluent, which is more than the regulation standard. Aside from, microbial degradation test was done for 100 ppm of 1,4-dioxane in BSM (Basal salt medium) inoculated with each of activated sludge. After 7 days, 1,4-dioxane was completely removed in the test bottle inoculated with H sludge, 67% in T and 52% in K, which could confirm that the given activated sludge might have different biodegradability against the amount of 1,4-dioxane. Therefore, microbial diversity in each company was investigated by 16s rDNA cloning methods where a species, e.g. Methylibium petroleiphilum PM1, was the greatest observed from H and in lesser from K, but it was not detected from T. Methylibium petroleiphilum PM1 is known to efficiently degrade ether like methyl tertiary-butyl ether(MTBE). It is concluded that the activated sludge in H can be most effectively adopted for a biodegradation of 1,4-dioxane in the concern of industrial sector.

• Korean Journal of Ecology and Environment
• /
• v.43 no.2
• /
• pp.288-297
• /
• 2010

This study was to evaluate the ecological stream health through the Multimetric Fish Assessment Index (MFAI) along with fish fauna analysis based on the tolerance and trophic guilds at Miho stream in 2008 and 2009. Also, we analysed total mercury concentration in fish tissues to examine heavy metal contamination. Total sampled fish were 40 species and 2,557 individuals and Zacco platypus was the most dominant with 35% relative abundance. It was sampled with 11.4% RA for Korean endemic species (10 species 291 individuals) less than average RA 39.3% for the Geum river watersheds. According to the tolarance guild analysis, tolerant species was more dominant with 58.9% RA (15 species, 1,507 individuals) than sensitive species with 6.6% RA. Trophic guild analysis also suggested that omnivores were more dominant (60.5% RA) than insectivores (31.5% RA). Riffle-benthic species was also sampled with 7.7% RA. Ecological stream health based on the MFAI were averaged 25.3 (n=3) with fair-poor condition in 2008 and also 26.3 (n=3) with fair condition in 2009, just slightly increased than 2008. Qualitative habitat evaluation index was averaged 134 (n=3) with fair condition but most of sites had sediment accumulation that reflected substrate degradations proceeding. From the result of total mercury accumulation in fish tissues, kidney and liver tissues showed the highest but the lowest for gill tissues. Overall mercury concentration were not exceed the national standards by Korean Federation of Drug and Administration (KFDA). Consequently, our result could correspond with the characteristics of Miho stream where point sources such industrial complexes and wastewater treatment plant widely distributed around the stream along the gradient of up and downstream.

• Land and Housing Review
• /
• v.4 no.1
• /
• pp.77-87
• /
• 2013

About 1,800 villages have released from Greenbelt since Greenbelt-reform-policy for readjustment of the area was promoted after 1997. Even though the government intended to attract planned development & improvement of these lifted villages through District Unit Plan and designating the lifted area as low-rise and low-density zoning considering the characteristics of the Greenbelt region, there are still many problems to be solved: a lack of funds, insufficient capability for self-improvement and unexecuted SOCs in long-term etc. It seems that these problems are caused by focusing on the lifting areas itself instead of researching deeply the condition and characteristics of the villages and searching proper direction/plans of improvement before lifting Greenbelt In addition, the existing plan of village improvement and management was not considering physical and spacial characteristics of the areas, social and economic situation of residents and relationship between the villages and surrounding cities, though these conditions are different among each villages, and the related regulations are applied uniformly across all the villages and those have been causing many civil appeals and environmental problems. In these respects, this study aims to consider the problems of the lifted villages using the existing researches on them and to make typology by characteristics-data of the villages and to establish improvement strategies of each types. In this study, the villages were classified into 5 types as a result of cluster analysis on 424 villages among all 1,800 through variables of locational potentiality : location, accessibility, size and form of village, condition of regulations etc. According to function of the villages, they were divided into 4 types: urban-type, rural-type, industrial-type and neighborhood-centered-type. This study also drew 4 improvement-strategy-types by combination of locational potentiality and village-function : type of improving life-environment, type of improving production-infra, type of inducing-planned-improvement and type of constructing center-of living-circle. Finally, this study suggested the directions of the each 4 types to desirable improvement and management which could be used to make and complement plans for village improvement.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.8 no.3
• /
• pp.53-65
• /
• 2013

In Korea recently the consumption of coffee has been drastically increased and majority of people who are more than $20^{th}$ are drinking more than a cup of coffee every day. Nowadays coffee a kind of essential items in modern urban society. As the popularity of the coffee is increasing, As the coffee consumption is growing, the studies on coffee also have been increased. Many of the studies on coffee were focused on the consumer attitudes, coffee shops and franchise coffee shops, and coffee components or ingredients. As the products of the coffee are becoming diverse, the consumers of coffee also becoming diverse. There was a study showing that coffee has variety of types, and that motivations and attitudes for coffee consumption are different depend on demographic statistics such as age and life styles. On this study main focus was life style and consumer's motivation on coffee consumption. For this study the survey was conducted on the people living in Seoul City and Kyengkido from March 1, 2013 to March 31, 2013. 600 questionnaires were distributed and 480 were collected and 470 were used for analysis of this study. The statistics program used in this study was SPSS. The method used in the analysis wee factors analysis test, reliability test, validity test, t-testy, One-Way ANOVA, and regression analysis. In this study according to the factor analysis, the life styles were classified the following six categories ; wellbeing pursuit, taste pursuit, atmosphere pursuit, dine-out pursuit, instant pursuit, and economic value pursuit. The factors of coffee consumption motivation were 6; wellbeing consumption motivation, changing mood consumption motivation, social consumption motivation, habitual consumption motivation, and emotional consumption motivation. The demographic factors used in this study were age, marital status, occupation, educational background, residence, income, and eating-out expenses. The hypothesis used in this study were two. The first hypo-thesis was whether the coffee consumption was affected by the life styles. The second hypo-thesis was whether there was any statistical differences on the motivation of coffee consumption according to the characteristics of life style. The outcome of this study demonstrated that life styles had partial impact on coffee consumption motivations. According to the characteristics of the life style, except for the habitual consumption motivation, all the other factors showed statistical differences on coffee consumption motivations according the characteristics of life styles.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.171-183
• /
• 2012

In the development of technologies, the exhibition industry has received much attention from governments and companies as an important way of marketing activities. Also, the exhibitors have considered the exhibition as new channels of marketing activities. However, the growing size of exhibitions for net square feet and the number of visitors naturally creates the competitive environment for them. Therefore, to make use of the effective marketing tools in these environments, they have planned and implemented many promotion technics. Especially, through smart environment which makes them provide real-time information for visitors, they can implement various kinds of promotion. However, promotions ignoring visitors' various needs and preferences can lose the original purposes and functions of them. That is, as indiscriminate promotions make visitors feel like spam, they can't achieve their purposes. Therefore, they need an approach using STP strategy which segments visitors through right evidences (Segmentation), selects the target visitors (Targeting), and give proper services to them (Positioning). For using STP Strategy in the smart exhibition environment, we consider these characteristics of it. First, an exhibition is defined as market events of a specific duration, which are held at intervals. According to this, exhibitors who plan some promotions should different events and promotions in each exhibition. Therefore, when they adopt traditional STP strategies, a system can provide services using insufficient information and of existing visitors, and should guarantee the performance of it. Second, to segment automatically, cluster analysis which is generally used as data mining technology can be adopted. In the smart exhibition environment, information of visitors can be acquired in real-time. At the same time, services using this information should be also provided in real-time. However, many clustering algorithms have scalability problem which they hardly work on a large database and require for domain knowledge to determine input parameters. Therefore, through selecting a suitable methodology and fitting, it should provide real-time services. Finally, it is needed to make use of data in the smart exhibition environment. As there are useful data such as booth visit records and participation records for events, the STP strategy for the smart exhibition is based on not only demographical segmentation but also behavioral segmentation. Therefore, in this study, we analyze a case of the promotion methodology which exhibitors can provide a differentiated service to segmented visitors in the smart exhibition environment. First, considering characteristics of the smart exhibition environment, we draw evidences of segmentation and fit the clustering methodology for providing real-time services. There are many studies for classify visitors, but we adopt a segmentation methodology based on visitors' behavioral traits. Through the direct observation, Veron and Levasseur classify visitors into four groups to liken visitors' traits to animals (Butterfly, fish, grasshopper, and ant). Especially, because variables of their classification like the number of visits and the average time of a visit can estimate in the smart exhibition environment, it can provide theoretical and practical background for our system. Next, we construct a pilot system which automatically selects suitable visitors along the objectives of promotions and instantly provide promotion messages to them. That is, based on the segmentation of our methodology, our system automatically selects suitable visitors along the characteristics of promotions. We adopt this system to real exhibition environment, and analyze data from results of adaptation. As a result, as we classify visitors into four types through their behavioral pattern in the exhibition, we provide some insights for researchers who build the smart exhibition environment and can gain promotion strategies fitting each cluster. First, visitors of ANT type show high response rate for promotion messages except experience promotion. So they are fascinated by actual profits in exhibition area, and dislike promotions requiring a long time. Contrastively, visitors of GRASSHOPPER type show high response rate only for experience promotion. Second, visitors of FISH type appear favors to coupon and contents promotions. That is, although they don't look in detail, they prefer to obtain further information such as brochure. Especially, exhibitors that want to give much information for limited time should give attention to visitors of this type. Consequently, these promotion strategies are expected to give exhibitors some insights when they plan and organize their activities, and grow the performance of them.