• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.101-116
• /
• 2015

Recently, due to the development of smart devices and social media, vast amounts of information with the various forms were accumulated. Particularly, considerable research efforts are being directed towards analyzing unstructured big data to resolve various social problems. Accordingly, focus of data-driven decision-making is being moved from structured data analysis to unstructured one. Also, in the field of recommendation system, which is the typical area of data-driven decision-making, the need of using unstructured data has been steadily increased to improve system performance. Approaches to improve the performance of recommendation systems can be found in two aspects- improving algorithms and acquiring useful data with high quality. Traditionally, most efforts to improve the performance of recommendation system were made by the former approach, while the latter approach has not attracted much attention relatively. In this sense, efforts to utilize unstructured data from variable sources are very timely and necessary. Particularly, as the interests of users are directly connected with their needs, identifying the interests of the user through unstructured big data analysis can be a crew for improving performance of recommendation systems. In this sense, this study proposes the methodology of improving recommendation system by measuring interests of the user. Specially, this study proposes the method to quantify interests of the user by analyzing user's internet usage patterns, and to predict user's repurchase based upon the discovered preferences. There are two important modules in this study. The first module predicts repurchase probability of each category through analyzing users' purchase history. We include the first module to our research scope for comparing the accuracy of traditional purchase-based prediction model to our new model presented in the second module. This procedure extracts purchase history of users. The core part of our methodology is in the second module. This module extracts users' interests by analyzing news articles the users have read. The second module constructs a correspondence matrix between topics and news articles by performing topic modeling on real world news articles. And then, the module analyzes users' news access patterns and then constructs a correspondence matrix between articles and users. After that, by merging the results of the previous processes in the second module, we can obtain a correspondence matrix between users and topics. This matrix describes users' interests in a structured manner. Finally, by using the matrix, the second module builds a model for predicting repurchase probability of each category. In this paper, we also provide experimental results of our performance evaluation. The outline of data used our experiments is as follows. We acquired web transaction data of 5,000 panels from a company that is specialized to analyzing ranks of internet sites. At first we extracted 15,000 URLs of news articles published from July 2012 to June 2013 from the original data and we crawled main contents of the news articles. After that we selected 2,615 users who have read at least one of the extracted news articles. Among the 2,615 users, we discovered that the number of target users who purchase at least one items from our target shopping mall 'G' is 359. In the experiments, we analyzed purchase history and news access records of the 359 internet users. From the performance evaluation, we found that our prediction model using both users' interests and purchase history outperforms a prediction model using only users' purchase history from a view point of misclassification ratio. In detail, our model outperformed the traditional one in appliance, beauty, computer, culture, digital, fashion, and sports categories when artificial neural network based models were used. Similarly, our model outperformed the traditional one in beauty, computer, digital, fashion, food, and furniture categories when decision tree based models were used although the improvement is very small.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.87-109
• /
• 2020

Currently, thanks to the major stride made in developing wired and wireless communication technology, a variety of IT services are available on land. This trend is leading to an increasing demand for IT services to vessels on the water as well. And it is expected that the request for various IT services such as two-way digital data transmission, Web, APP, etc. is on the rise to the extent that they are available on land. However, while a high-speed information communication network is easily accessible on land because it is based upon a fixed infrastructure like an AP and a base station, it is not the case on the water. As a result, a radio communication network-based voice communication service is usually used at sea. To solve this problem, an additional frequency for digital data exchange was allocated, and a ship ad-hoc network (SANET) was proposed that can be utilized by using this frequency. Instead of satellite communication that costs a lot in installation and usage, SANET was developed to provide various IT services to ships based on IP in the sea. Connectivity between land base stations and ships is important in the SANET. To have this connection, a ship must be a member of the network with its IP address assigned. This paper proposes a SANET-CC protocol that allows ships to be assigned their own IP address. SANET-CC propagates several non-overlapping IP addresses through the entire network from land base stations to ships in the form of the tree. Ships allocate their own IP addresses through the exchange of simple requests and response messages with land base stations or M-ships that can allocate IP addresses. Therefore, SANET-CC can eliminate the IP collision prevention (Duplicate Address Detection) process and the process of network separation or integration caused by the movement of the ship. Various simulations were performed to verify the applicability of this protocol to SANET. The outcome of such simulations shows us the following. First, using SANET-CC, about 91% of the ships in the network were able to receive IP addresses under any circumstances. It is 6% higher than the existing studies. And it suggests that if variables are adjusted to each port's environment, it may show further improved results. Second, this work shows us that it takes all vessels an average of 10 seconds to receive IP addresses regardless of conditions. It represents a 50% decrease in time compared to the average of 20 seconds in the previous study. Also Besides, taking it into account that when existing studies were on 50 to 200 vessels, this study on 100 to 400 vessels, the efficiency can be much higher. Third, existing studies have not been able to derive optimal values according to variables. This is because it does not have a consistent pattern depending on the variable. This means that optimal variables values cannot be set for each port under diverse environments. This paper, however, shows us that the result values from the variables exhibit a consistent pattern. This is significant in that it can be applied to each port by adjusting the variable values. It was also confirmed that regardless of the number of ships, the IP allocation ratio was the most efficient at about 96 percent if the waiting time after the IP request was 75ms, and that the tree structure could maintain a stable network configuration when the number of IPs was over 30000. Fourth, this study can be used to design a network for supporting intelligent maritime control systems and services offshore, instead of satellite communication. And if LTE-M is set up, it is possible to use it for various intelligent services.

• Journal of KIISE:Databases
• /
• v.32 no.4
• /
• pp.345-361
• /
• 2005

A transform-space index indexes objects represented as points in the transform space An advantage of a transform-space index is that optimization of join algorithms using these indexes becomes relatively simple. However, the disadvantage is that these algorithms cannot be applied to original-space indexes such as the R-tree. As a way of overcoming this disadvantages, the authors earlier proposed the transform-space view join algorithm that joins two original- space indexes in the transform space through the notion of the transform-space view. A transform-space view is a virtual transform-space index that allows us to perform join in the transform space using original-space indexes. In a transform-space view join algorithm, the order of accessing disk pages -for which various space filling curves could be used -makes a significant impact on the performance of joins. In this paper, we Propose a new space filling curve called the adaptive row major order (ARM order). The ARM order adaptively controls the order of accessing pages and significantly reduces the one-pass buffer size (the minimum buffer size required for guaranteeing one disk access per page) and the number of disk accesses for a given buffer size. Through analysis and experiments, we verify the excellence of the ARM order when used with the transform-space view join. The transform-space view join with the ARM order always outperforms existing ones in terms of both measures used: the one-pass buffer size and the number of disk accesses for a given buffer size. Compared to other conventional space filling curves used with the transform-space view join, it reduces the one-pass buffer size by up to 21.3 times and the number of disk accesses by up to $74.6\%$. In addition, compared to existing spatial join algorithms that use R-trees in the original space, it reduces the one-pass buffer size by up to 15.7 times and the number of disk accesses by up to $65.3\%$.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.43 no.3
• /
• pp.77-91
• /
• 2015

This study aims to suggest adequate soil management through the analysis of physicochemical properties of soil in the planting grounds of Incheon International Airport, which was constructed on a massive land reclamation site. Study areas were 5 sites at the international business complex, the passenger terminal, the airport support complex, the free trade zone, and the access road. Soil profile analysis showed that 9 plots out of the 27 plots were hardpan and heterospere within 80cm from the soil surface. The earth laid on the ground was categorized as gravel based soil(4 plots), dredged soil from the sea bottom and mixed reclamation materials(2 plots), clay with poor permeability(3 plots) and waste construction material(1 plot). Average soil hardness was $11.5kg/cm^2$ and soil textures were sandy soil, sandy loam and loamy sand. Average soil pH was 6.7 and average organic matter content was 0.7%. Electrical conductivity was 0.0dS/m and exchangeable cation concentrations were $Ca^{2+}$ 3.4cmol/kg, $Mg^{2+}$ 1.5cmol/kg, $K^+$ 0.3cmol/kg and $Na^+$ 1.0cmol/kg. Average cation exchange capacity was 11.0cmol/kg. Although average figures in Solum mostly meet the landscape design criteria, properties of each soil layer showed various values sometimes over the limit. Base saturations were $Ca^{2+}$ 29.9%, $Mg^{2+}$ 13.3% and $K^+$ 3.7% for lower soil, $Ca^{2+}$ 33.3%, $Mg^{2+}$ 17.0% and $K^+$ 2.7% for mid-soil and $Ca^{2+}$ 32.6%, $Mg^{2+}$ 12.2% and $K^+$ 1.9% for upper soil. Exchangeable sodium percentages were 16.4% for lower soil, 7.5% for mid-soil and 4.7% upper soil. Sodium adsorption rates were 0.8 for lower soil, 0.3 for mid-soil and 0.2 for upper soil. Factors affecting to the vegetation growth were heterogeneity and poorness of solum, disturbance of dredged soils, high soil hardness including hardpan in the subsurface soil layer and shallow effective soil depth, high soil acidity, imbalance of base contents, low organic matter content and low available phosphate levels in the soil.

• The KIPS Transactions:PartD
• /
• v.13D no.7 s.110
• /
• pp.985-996
• /
• 2006

As the internet technologies develop, the geographic information system environment is changing to the web-based service. Since geospatial information of the existing Web-GIS services were developed independently, there is no interoperability to support diverse map formats. In spite of the same geospatial information object it can be used for various proposes that is duplicated in GIS separately. It needs intelligent strategies for optimal replica selection, which is identification of replication geospatial information objects. And for management of replication objects, OMG, GLOBE and GRID computing suggested related frameworks. But these researches are not thorough going enough in case of geospatial information object. This paper presents a model of location service, which is supported for optimal selection among replication and management of replication objects. It is consist of tree main services. The first is binding service which can save names and properties of object defined by users according to service offers and enable clients to search them on the service of offers. The second is location service which can manage location information with contact records. And obtains performance information by the Load Sharing Facility on system independently with contact address. The third is intelligent selection service which can obtain basic/performance information from the binding service/location service and provide both faster access and better performance characteristics by rules as intelligent model based on rough sets. For the validity of location service model, this research presents the processes of location service execution with Graphic User Interface.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Korean Journal of Veterinary Service
• /
• v.28 no.2
• /
• pp.121-146
• /
• 2005

Newcastle disease (ND), infectious bronchitis (IB), low pathogenic avian Influenza (LPAI) and fowl typhoid (FT) have been known as egg drop laying diseases because of the serious layer damage from mass zone layer. In this study, such egg drop laying diseases were investigated. To access this study, we peformed to evaluate antibody titers in serum and isolated bacteria and virus from organs and feces on May, July and September in 2003. The distribution of ND from January to May, IB and LPAI from October to February of the next year, and FT from March to September were inspected by the question survey in 21 farms. ND revealed to be positive rates of 490 to 474 $(96.7\%)$ in May, 510 to 506 $(99.2\%)$ in July and 510 to 510 $(100\%)$ in September with hemagglutination inhibition (HI) test. The mean antibody titers were 10.2, 9.9 and 10.2, respectively. With regard to IB, 484 out of 490 samples $(98.7\%)$ in May, 508 of 510 $(99.6\%)$ in July and 509 of 510 $(99.8\%)$ in September showed positive results and the mean antibody titers were gradually increased with 8.2, 9.0 and 9.4, respectively. According to HI test of LPAI, the positive results were shown in 442 of 480 $(92.1\%)$, 394 of 494 $(79.8\%)$ and 402 of 483 $(83.2\%)$ in May, July and September, respectively The mean antibody titers were decreased with 4.6, 4.3 and 4.0. The distribution of LPAI also elicited the positive rates of 480 to 475 $(99.0\%)$ in May, 494 to 485$(98.2\%)$ in July, 483 to 472 $(97.7\%)$ in September as determined by ELISA and the mean S/P ratio were 2.319, 2.557 and 2.380, respectively. Compared ELISA results with HI test of LPAI the positive results were 480 to 422 $(92.1\%),\;475(99.0\%),\;494\;to\;394 (79.8\%),\;485 (98.2\%)\;and\;483\;to\;402(83.2\%),\;472(97.7\%)$. Therefore, the positive rate determined by ELISA was higher than that of HI test with 6.9, 18.4 and $14.5\%$, respectively. When performed RT-PCR for ND using organ and feces samples, the pathotypes were detected $5(15.6\%)\;in\;May,\; 2(5.3\%) in\;July,\;2(7.1\%)$ in September but there is no samples showing positive band for LPAI. In attempt to isolate Salmonella gallinarum, bacteria were obtained from 4 cases (12.5%) in May, 9 (23.6%) in July, 5 (17.8%) in September. Thus the highest rate for isolation revealed to be shown in July When evaluated the antimicrobial susceptibility to 18 isolated strains of 5. gallinarum, bacteria were sensitive to trimethoprim/sulfamethox$(61.1\%),\;kanamycin\;(55.5\%),\;ampicillin\;(55.5\%)$ and amoxacillin/clavulanic acid $(55.5\%)$, cephalothin $(50.0\%)$, but resistant to penicillin $(88.9\%)$, streptomycin $(88.9\%)$, erythromycin $(83_4\%)$ and tetracycline $(61.1\%)$. According to HI test of ND and LPAI using captured 164 wild Korean tree sparrows (Passer nontanus), the positive rates were $47.6\%\;and\;57.3\%$, and the mean HI titers were 5.32 and 4.02, respectively. 71 $(43.2\%)\;and\;58(35.3\%)$ in captured sparrows also showed more than 4 titers for HI test to ND and LPAI, respectively However, the attempt for isolation of viruses failed in all samples.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.1
• /
• pp.76-87
• /
• 2019

The purpose of this study was to evaluate the performance of and to derive future maintenance-management measures of the constructed alternative habitat for the Kaloula borealis at the University of Seoul, examining the period between 2015-2017. The research was constructed in 2014 and in a $191m^2$ area. The performance evaluation was divided into maintaining the habitat of the target species, maintaining the population and reproduction rates of the target species, maintaining the habitat of the wild species, the resilience of natural ecosystems, and the harmony with the surrounding environment. In terms of maintaining the habitat of the target species, soil collected from the existing habitat of the Kaloula borealis and was the depth was increased to 30cm in the alternative habitat. An artificial water supply was required every year during the supporting the spawning and hatching of other amphibians along with the Kaloula borealis. The sources of water of the alternative habitat were both rain and tap water, as it cannot be maintained naturally. Additionally, the Kaloula borealis thrived because it inhabited the research site and the average temperature was $26.2^{\circ}C$ from April-June, which is when the Kaloula borealis spawns. In terms of maintaining the population and reproduction rates of the Kaloula borealis, they were evaluated to have stable rates of reproduction. In terms of maintaining the habitat of the wild species, studies on vegetation and the structure of the characteristics of prey or predators will be needed. Also, alien species, such as Humulus japonicus and Bidens frondosa needed to be removed to maintain the wetland ecosystem of the wild species. In the assessment of the resilience of the natural ecosystems, the mud was monitored, noting the changes in the depth of water, with steps taken to reduce the leakage of water. The mud collected from the Haneul Pond wetland, which is located around the research site was piled up. Also, partial mowing management and the inducement of a natural vegetation colony was required for vegetation management. It was also necessary to create porous spaces, such as old trees and tree branches to create a habitat with hiding places and feeding and spawning places for small organisms. In terms of the harmony with the surrounding environment, the following threat factors needed to be managed: amphibian roadkill by vehicles and pedestrians and artificial draining due to nearby user access. Based on the monitoring results, alternative habitat management measures presented the promoting various waterside structures, in which amphibians can spawn and hide in, managing the water environment consistently, managing the vegetation, focused on the habitat of the wild species, and managing the surrounding environment for the habitat. The creation of an alternative habitat should be managed through monitoring, reflecting the characteristics of the changes in the site. Also continuing efforts are also needed to improve the habitat of the target species.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.40 no.1
• /
• pp.1-14
• /
• 2022

This study focused on examining the location characteristics of Mujang-Eupchi(茂長邑治), a traditional city of Joseon Dynasty, and shedding light on its prototype landscape. The findings were summarized as follows: Mujang-Eupchi showed a Confucian space system with Munmyo(文廟) within Hyanggyo(鄕校) in the east, Sajikdan(社稷壇) in the west, Seonghwangsa(城隍祠) in the fortress and Yeodan(厲壇) and Seonghwangdan(城隍壇) in Jinsan(鎭山) in the north around the Mujang-Eupseong(茂長邑城), an old fortress, built in the 17th year of King Taejong(1417). It seemed that Seonghwangdan located in Jinsan maintained a coexistence system with Seonghwangsa(城隍祠) within the Eupseong. A Pungsu(風水) stream in a V-shape ran before the southern gate of Eupseong, forming a Sugu(水口) in front of Namsan(南山) that was an Ansan(案山). They dug a southern pond called Hongmunje(紅門堤) to protect the vitality of the village and built Gwanpungjeong(觀豊亭). In the 19th century, Hongmunje and Gwanpungjeong were renamed into Muheungje(茂興堤) and Muheungdang(茂興堂), respectively. Eupsu(邑藪) were planted in front of the southern pond including Wondo(圓島), and Songdeokbi(頌德碑), Dangsanmok(堂山木), and Dangsanseok(堂山石) served as a Sugumagi(水口막이) and protected the entrance of Eupchi. After the Liberation, the southern pond was buried in 1955, and a market was formed at the site, which resulted in the disappearance of its prototype. The study also investigated the name and location of Chilgeori(七거리) in the village as it was lost following the unification of Bu(府), Gun(郡), and Myeon(面) titles in 1914 during the Japanese colonial period. Chilgeori Dangsan was based on Yin and Yang theory and became the subject of the organization mainly composed of Grandfather Dangsan menhir and Grandmother Dangsan tree. Chilgeori Dangsan was a religious place of the community to guard the village, serving as seven gateways to control access at the village boundary and it had a locational feature of protecting the inner mountain ranges of Eupchi.