• Applied Biological Chemistry
• /
• v.13 no.3
• /
• pp.207-218
• /
• 1970

Studies were carried out to develope the most economical and practical methods of packaging and preservation of kimchi, so commercialization of kimchi manufacture could proceed rapidly. The results obtained may be summarized as following. (1) It is generally established that the acceptable range of lactic acid content of kimchi is between 0.4% and 0.75%. Based on sensory evaluation, kimchi having lactic acid content below 0.4% and above 0.75% was not edible, and the time of optimum taste corresponded to the vicinity of 0.5% of lactic acid content. For the refrigeration storage with or without preservatives, the packaging kimchi in plastic film must be done at the lactic acid content of 0.45%, for lactic acid fermentation will continue slowly after the packaging. However, for the heat sterilized kimchi the packaging should be done at the 0.5% of lactic acid content for the best because lactic acid fermentation is completely stopped after the packaging. (2) Polyethylene, polypropylene, and polycello were chosen as suitable packaging materials. Polyethylene is cheapest among them but kimchi packaged in this film was damaged frequently in handling process and gave off kimchi flavor. On the other hand polypropylene also gave off kimchi flavor, but its higher mechanical strength gave better protection to kimchi and it had superior display effect due to the transparancy. Therefore polypropylene made much better packaging material. Polycello proved to be the best packaging material from the standpoint of physical characteristics but its price is higher than that of other plastic films. To be effective, the thickness of plastic films for packaging kimchi must exceed 0.08mm. (3) Keeping property of kimchi appeared to be excellent by means of freezing. However, by the time the frozen kimchi was thawed out at room temperature, moisture loss due to drip was extensive, rendering the kimchi too stringy. (4) Preservation of kimchi at refrigerated temperatures proved to be the best method and under the refrigerated condition the kimchi remained fresh as long as 3 months. The best results were obtained when kimchi was held at $0^{\circ}C$. (5) In general, preservatives alone were not too elective in preserving kimchi. Among them potassium sorbate appeared to be most effective with the four fold extension of self-life at $20^{\circ}C$ and two fold extension at $30^{\circ}C$. (6) In heat sterilization the thickness of packaged kimchi product had a geat effect upon the rate of heat penetration. When the thickness ranged from 1.5 to 1.8cm, the kimchi in such package could be sterilized at $65^{\circ}C$ for 20 minutes. Kimchi so heat treated could be kept at room temperature as long as one month without apparent changes in quality. (7) Among combination methods, preservation at refrigerated and heat sterilization could be favorably combined. When kimchi was stored at $4^{\circ}C$ after being sterilized at $65^{\circ}C$ for 20 minutes, it was possible to preserve the kimchi for more than 4 months.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.305-316
• /
• 2011

Recommender system is the system which, by using automated information filtering technology, recommends products or services to the customers who are likely to be interested in. Those systems are widely used in many different Web retailers such as Amazon.com, Netfix.com, and CDNow.com. Various recommender systems have been developed. Among them, Collaborative Filtering (CF) has been known as the most successful and commonly used approach. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. However, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting in advance whether the performance of CF recommender system is acceptable or not is practically important and needed. In this study, we propose a decision making guideline which helps decide whether CF is adoptable for a given application with certain transaction data characteristics. Several previous studies reported that sparsity, gray sheep, cold-start, coverage, and serendipity could affect the performance of CF, but the theoretical and empirical justification of such factors is lacking. Recently there are many studies paying attention to Social Network Analysis (SNA) as a method to analyze social relationships among people. SNA is a method to measure and visualize the linkage structure and status focusing on interaction among objects within communication group. CF analyzes the similarity among previous ratings or purchases of each customer, finds the relationships among the customers who have similarities, and then uses the relationships for recommendations. Thus CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. Under the assumption that SNA could facilitate an exploration of the topological properties of the network structure that are implicit in transaction data for CF recommendations, we focus on density, clustering coefficient, and centralization which are ones of the most commonly used measures to capture topological properties of the social network structure. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. We explore how these SNA measures affect the performance of CF performance and how they interact to each other. Our experiments used sales transaction data from H department store, one of the well?known department stores in Korea. Total 396 data set were sampled to construct various types of social networks. The dependant variable measuring process consists of three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used UCINET 6.0 for SNA. The experiments conducted the 3-way ANOVA which employs three SNA measures as dependant variables, and the recommendation accuracy measured by F1-measure as an independent variable. The experiments report that 1) each of three SNA measures affects the recommendation accuracy, 2) the density's effect to the performance overrides those of clustering coefficient and centralization (i.e., CF adoption is not a good decision if the density is low), and 3) however though the density is low, the performance of CF is comparatively good when the clustering coefficient is low. We expect that these experiment results help firms decide whether CF recommender system is adoptable for their business domain with certain transaction data characteristics.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.351-360
• /
• 2018

The LWR (Locally Weighted Regression) model, which is traditionally a lazy learning model, is designed to obtain the solution of the prediction according to the input variable, the query point, and it is a kind of the regression equation in the short interval obtained as a result of the learning that gives a higher weight value closer to the query point. We study on an incremental ensemble learning approach for LWR, a form of lazy learning and memory-based learning. The proposed incremental ensemble learning method of LWR is to sequentially generate and integrate LWR models over time using a genetic algorithm to obtain a solution of a specific query point. The weaknesses of existing LWR models are that multiple LWR models can be generated based on the indicator function and data sample selection, and the quality of the predictions can also vary depending on this model. However, no research has been conducted to solve the problem of selection or combination of multiple LWR models. In this study, after generating the initial LWR model according to the indicator function and the sample data set, we iterate evolution learning process to obtain the proper indicator function and assess the LWR models applied to the other sample data sets to overcome the data set bias. We adopt Eager learning method to generate and store LWR model gradually when data is generated for all sections. In order to obtain a prediction solution at a specific point in time, an LWR model is generated based on newly generated data within a predetermined interval and then combined with existing LWR models in a section using a genetic algorithm. The proposed method shows better results than the method of selecting multiple LWR models using the simple average method. The results of this study are compared with the predicted results using multiple regression analysis by applying the real data such as the amount of traffic per hour in a specific area and hourly sales of a resting place of the highway, etc.

• Food Science and Preservation
• /
• v.23 no.2
• /
• pp.259-266
• /
• 2016

Bitter melon powder (BMP) was used in the preparation of rice nuruk (RN) and makgeolli as one of raw materials. RN containing BMP (BMP-RN) was prepared by adding 0~2.0% (w/w) BMP into rice. Fermentative microbial, and antioxidant characteristics of makgeolli were determined during the fermentation process. pH during fermentation decreased from 4.52 (0% BMP-RN), 4.93 (0.5%), 4.80 (1.0%), and 4.88 (2.0%) on the initial fermentation day (day 0) to 4.15, 4.30, 4.57, and 4.59, respectively, corresponding to increases in acidity from 0.64~0.70% to 1.17~1.28%, respectively. Soluble solid contents increased from an initial 2.2~4.4 g/L (day 0) to 9.0~9.3 g/L, and alcohol level increased up to 13.0% by the end of fermentation (day 7). Soluble phenolic contents increased from 0.92, 1.01, 1.32, and 1.41 mg/mL on day 0, to 1.85, 2.03, 2.24, and 2.48 mg/mL on day 7, respectively, while the levels of 2,2-diphenyl-1-picrylhydrazyl (DPPH) and 2,2'-azino-bis(3-ethylbenzthiazoline-6-sulfonic acid) diammonium salt (ABTS) radical scavenging activities and ferric reducing/antioxidant power (FRAP) assay increased from 46.95~70.04%, 55.33~74.13%, and 0.629~1.243 on day 0, respectively, to 54.98~83.4%, 70.34~92.39%, and 0.964~1.455 on day 7, respectively. Makgeolli made with BMP-RN had higher soluble phenolic contents and antioxidant activity than those of makgeolli made without BMP-RN. These results suggested that BNP-RN made a functional makgeolli.

• Food Science and Preservation
• /
• v.22 no.4
• /
• pp.498-504
• /
• 2015

The purpose of the present study is to provide preliminary data for turning sweetpotato leaves into dehydrated vegetables. To achieve this goal, we have gone through the process of hot-air drying the leaves of sweetpotato that are usually thrown away and examined the drying speed and rehydration resilience, then made a comparative analysis of the general ingredients, lutein, $\beta$-carotene and chromaticity. The drying speed reached the peak at a temperature of $70^{\circ}C$. As for other general ingredients, there was no significant difference according to temperature. The content of lutein, which is a functional ingredient, was large in Shinmi with $171.59{\mu}g/g$ at a temperature of $40^{\circ}C$; small in Hayanmi with $73.75{\mu}g/g$ at a temperature of $70^{\circ}C$. The content of $\beta$-carotene was large in Shinmi with $379.59{\mu}g/g$ at a temperature of $40^{\circ}C$; small in Hayanmi with $170.78{\mu}g/g$ at a temperature of $70^{\circ}C$. The content of functional materials was the largest at a temperature of $40^{\circ}C$, and decreased in the order of temperatures at $50^{\circ}C$, $60^{\circ}C$, and $70^{\circ}C$. As for rehydration stability, rehydration rate in both Shinmi and Hayanmi was the highest at a temperature of $40^{\circ}C$ with 233.93% and 223.47% respectively. To summarize, the quality of dried sweet potato leaf was more affected by temperature than by drying time, and low temperature drying resulted in better product value.

• Food Science and Preservation
• /
• v.16 no.3
• /
• pp.405-411
• /
• 2009

The manufacturing process and quality properties of Lactococcus lactis-fermented yakchobugak (LFY) containing some colored agro-food products were investigated to develop a good organoleptic bugak from the leaf of the medicinal herb. The de-oiling rate of LFY by centrifugation was 37.6%, which was significantly different to the 3.5% value obtained after standing and the 8.9% value obtained with the beating method (p<0.05). Reducing power (RS) increased with addition of increasing levels of ethanol extracts from agro-food powders. The RS of green tea extract-supplemented LFY had the highest value of 0.97 at $500{\mu}g/mL$, and this was significantly different to values obtained using other extracts (p<0.05). At 83.84%, the DPPH (2,2-diphenyl-1-picrylhydrazyl) free-radical scavenging activity of green tea extract-supplemented LFY was the greatest of all samples tested, followed by LFY with woolgeom at 39.48%, LFY with black rice at 28.45%, and LFY with bokbunja at 22.24% all ethanol extracts were added at $50{\mu}g/mL$ (p<0.05). Acid values of green tea and bokbunja LFYs stored in transparent PE bags at $60^{\circ}C$ for 7 days were 1.82% and 2.03%, respectively. Textural hardness values of LFYs were less than 250.62, except for LFYs with black rice and woolgeom, but these values increased $2{\sim}3$-fold after lactic acid fermentation. Carbohydrate and protein content of LFYs were in the ranges $58.95{\sim}64.63%$ and $7.50{\sim}8.68%$, respectively. Lipid and calorie contents of woolgeom LFY had the lowest values of 22.02% and 490 Kcal, respectively.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.12 no.3
• /
• pp.95-111
• /
• 2004

This research sought to determine the status of the installation and operation of composting facilities of domestic public resource-making facilities and come up with corresponding improvement measures. The composting facilities were the most extensively installed of related facilities with over a 0.5 ton treated volume per day. The monthly and yearly carry-in volume of food waste were found to stand at 1,101.7 tons per day and 930.9 tons per day, thus falling short of the average planned volume of 1,270.9 tons. Many composting facilities, which were installed in areas for which factory registration were not approved, did not get approvals. Composting facilities underwent operation stoppage mainly due to faulty fermentation and crushing equipment. Mainly metals contained in food waste caused faults to the crushing equipment, thus requiring a facility designing against faults and corrosion. The initial water content was found to stand at 50-60%, thus complying with the requirement. However, since the composting food waste had an appropriate mixture of sawdust, food waste, and returned compost, it should meet the initial conditions. For fermentation facilities, the duration time for fermentation was 15 days, and post-fermentation tanks required 21 days of duration time, thus establishing the minimum criteria. However, some facilities did not meet the requirements, taking more time in decomposition, thus suggesting a need to determine the duration time according to facilities. In composting food waste, microorganism-based thermal oxidizer-operated fermentation tanks should be used to ensure an economic operation. On the contrary, 14 out of 25 survey targets heated fermentation tanks in any form. These thermal facilities contain the growth of bacteria, lowering chemical reaction in composting; thus composting facilities should be basically designed to use microorganism-based thermal oxidizers in drying water. An average daily volume of food waste and supplementary materials that was injected in producing compost was 22.8 tons. This volume produced 7.3 tons of compost per day, decreasing 68%. Properties of produced compost were analyzed by its color, absence or presence of remaining decomposition heat, and smell, to assess the quality. As a result, the composting process was not properly installed nor operated in about 50% of composting facilities. Compost should be produced to be soil-friendly.

• Journal of Global Scholars of Marketing Science
• /
• v.17 no.4
• /
• pp.113-139
• /
• 2007

This study aims to, looking from a standpoint of network, has investigated the shipping industry's B2B e-marketplace, the characteristics that can earn electronic trust from the users, and characteristics of the web-site. It has examined the mechanism whereby electronic trust be earned and how it affects web-site involvement and service transaction intention. Ultimately, The study attempts to make proposals whereby such trust can lead for a cooperative trading community in the shipping industry's B2B e-marketplace The Covalence structural equation modeling was designed and empirically tested for the shipping industry's B2B e-marketplace. The shipping industry employees were given questionnaires and data were analyzed. Except for perceived security of the three characteristic factors on the web-site, the perceived site quality and characteristics factors in operation only affected co-variables. Transaction Fairness was determined to be the most important factor among exogenous factors increasing electronic trust. With regards to transaction rules, if a transaction is beneficial only to one side, then no long term transaction will not take place. If the concerned parties properly recognize that transaction fairness is crucial to electronic transaction, then it will enormously contribute to successful operations of shipping e-marketplace. Also, Perceived efficiency in transaction also affects electronic trust. This reduces transaction costs and speeds up and simplifies the transaction process. It has reduced greater time and costs than existing off-line transaction, and would positively affect electronic trust. By making an open forum for participants to obtain information for transaction, they can gather useful information, and at the same time, the web-site operator can provide information, which, in turn, will increase electronic trust in electronic transaction. Furthermore, such formation of trust in electronic transaction influences shipping companies in such a way that they will want to continuously participate in the transaction, raising web-site involvement. The result of increased trust is that shipping companies in the future will do business with each other and form a foundation for continuous transactions amongst themselves. Consequently, the formation of trust in electronic transaction greatly influences web-site involvement and service transaction intention. The results of the study have again proved that in order to maintain continuous business relationship with the current clients, electronic trust in virtual space, which operates the shipping industry's B2B e-marketplace, is important for the interested parties.