• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.2
• /
• pp.51-63
• /
• 2024

While the government policy to fully adopt BIM in the construction sector is being implemented, the construction and utilization of landscape BIM models are facing challenges due to problems such as limitations in BIM authoring tools, difficulties in modeling natural materials, and a shortage in BIM content including libraries. In particular, plants, fundamental design elements in the field of landscape architecture, must be included in BIM models, yet they are often omitted during the modeling process, or necessary information is not included, which further compromises the quality of the BIM data. This study aimed to contribute to the construction and utilization of landscape BIM models by developing a plant library that complies with BIM standards and is applicable to the landscape industry. The plant library of trees and shrubs was developed in Revit by modeling 3D shapes and collecting attribute items. The geometric information is simplified to express the unique characteristics of each plant species at LOD200, LOD300, and LOD350 levels. The attribute information includes properties on plant species identification, such as species name, specifications, and quantity estimation, as well as ecological attributes and environmental performance information, totaling 24 items. The names of the files were given so that the hierarchy of an object in the landscape field could be revealed and the object name could classify the plant itself. Its usability was examined by building a landscape BIM model of an apartment complex. The result showed that the plant library facilitated the construction process of the landscape BIM model. It was also confirmed that the library was properly operated in the basic utilization of the BIM model, such as 2D documentation, quantity takeoff, and design review. However, the library lacked ground cover, and had limitations in those variables such as the environmental performance of plants because various databases for some materials have not yet been established. Further efforts are needed to develop BIM modeling tools, techniques, and various databases for natural materials. Moreover, entities and systems responsible for creating, managing, distributing, and disseminating BIM libraries must be established.

• Journal of Wetlands Research
• /
• v.26 no.2
• /
• pp.147-159
• /
• 2024

Lack of streamflow observations makes model calibration difficult and limits model performance improvement. Satellite-based remote sensing products offer a new alternative as they can be actively utilized to obtain hydrological data. Recently, several studies have shown that artificial intelligence-based solutions are more appropriate than traditional conceptual and physical models. In this study, a data-driven approach combining various recurrent neural networks and decision tree-based algorithms is proposed, and the utilization of satellite remote sensing information for AI training is investigated. The satellite imagery used in this study is from MODIS and SMAP. The proposed approach is validated using publicly available data from 25 watersheds. Inspired by the traditional regionalization approach, a strategy is adopted to learn one data-driven model by integrating data from all basins, and the potential of the proposed approach is evaluated by using a leave-one-out cross-validation regionalization setting to predict streamflow from different basins with one model. The GRU + Light GBM model was found to be a suitable model combination for target basins and showed good streamflow prediction performance in ungauged basins (The average model efficiency coefficient for predicting daily streamflow in 25 ungauged basins is 0.7187) except for the period when streamflow is very small. The influence of satellite remote sensing information was found to be up to 10%, with the additional application of satellite information having a greater impact on streamflow prediction during low or dry seasons than during wet or normal seasons.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.4
• /
• pp.225-232
• /
• 2024

This study focuses on the determination of the fracture mode in composite laminates using deep learning. With the increase in the use of laminated composites in numerous engineering applications, the insurance of their integrity and performance is of paramount importance. However, owing to the complex nature of these materials, the identification of fracture modes is often a tedious and time-consuming task that requires critical domain knowledge. Therefore, to alleviate these issues, this study aims to utilize modern artificial intelligence technology to automate the fractographic analysis of laminated composites. To accomplish this goal, scanning electron microscopy (SEM) images of fractured tensile test specimens are obtained from laminated composites to showcase various fracture modes. These SEM images are then categorized based on numerous fracture modes, including fiber breakage, fiber pull-out, mix-mode fracture, matrix brittle fracture, and matrix ductile fracture. Next, the collective data for all classes are divided into train, test, and validation datasets. Two state-of-the-art, deep learning-based pre-trained models, namely, DenseNet and GoogleNet, are trained to learn the discriminative features for each fracture mode. The DenseNet models shows training and testing accuracies of 94.01% and 75.49%, respectively, whereas those of the GoogleNet model are 84.55% and 54.48%, respectively. The trained deep learning models are then validated on unseen validation datasets. This validation demonstrates that the DenseNet model, owing to its deeper architecture, can extract high-quality features, resulting in 84.44% validation accuracy. This value is 36.84% higher than that of the GoogleNet model. Hence, these results affirm that the DenseNet model is effective in performing fractographic analyses of laminated composites by predicting fracture modes with high precision.

• Proceedings of the KOR-BRONCHOESO Conference
• /
• 1982.05a
• /
• pp.17.2-19
• /
• 1982

The sinus tympani is subject to great variability in the size, shape and posterior extent. A heavy compact bony zone, especially in the posterior portion and the narrow space between the facial nerve and posterior semicircular canal are the limitation of surgical approach. The facial recess should be opened, creating a wide connection between the mesotympanum and mastoid in the Intact canal wall tympanoplasty with mastoidectomy. The surgically created limits of the facial recess are the facial nerve medially, the chorda tympani laterally and the bone adjacent to the incus superiorly. Using adult Korean's thirty-five temporal bones, the authors measured the osteologic reslationship in the posterior tympanum, especially sinus tympani and facial recess. The result was as followed. 1. The average distance from the anterior end of the pyramidal eminence. 1) to the edge of the sinus tympani directly posterior was 2.54(1.05-5.40)mm. 2) to the maximum posterior extent was 3.22(1.25-7.45)mm. 3) to the maximum cephaled extent was 0.67 (0.40-1.75)mm. 2. The boundary of the sinus tympani was 82.9% from the lower margin oval window to the upper margin round window niche. 3. The deepest part of the sinus tympani was 62.9% in the mid portion, between the ponticulus and subiculum. 4. The oblique dimension from the fossa incudis above to the hypotympanum below was 8.13(7.90-9.55)mm. 5. The transverse dimensions midway between the oval window above and round window below was 3.00(2.85-3.45)mm. 6. The transverse dimension at the level of the fossa incudis was 1.81(1.40-2.15)mm. 7. The facial nerve dehiscence was 14.3%. 8. Anterior-posterior diameter of the footplate was 2.98(2.85-3.05) mm. 9. The average distance from the footplate. 1) to the cochleariform process was 1.42(1.35-1.55) mm. 2) to the round window niche was 1.85(1.45-2.10) mm.

• Journal of radiological science and technology
• /
• v.30 no.3
• /
• pp.205-212
• /
• 2007

To evaluate the feasibility and efficacy of a pulsatile aortic aneurysm phantoms for in-vitro study. The phantoms consisted of a pulsating motor part(heart part) and an aortic aneurysm part, which mimicked true physiologic conditions. The heart part was created from a high-pressured water pump and a pulsatile flow solenoid valve for the simulation of aortic flow. The aortic aneurysm part was manufactured from paper clay, which was placed inside a acrylic plastic square box, where liquid silicone was poured. After the silicone was formed, the clay was removed, and a silicone tube was used to connect the heart and aneurysm part. We measured the change in pressure as related to the opening time(pulse rate, Kruskal-Wallis method) and pressure before and after the stent-graft implantation(n = 5, Wilcoxon's signed ranks test). The changes in blood pressures according to pulse rate were all statistically significant(p<0.05). The systolic/diastolic pressures at the proximal aorta, the aortic aneurysm, and the distal aorta of the model were $157.80{\pm}1.92/130.20{\pm}1.92$, $159.40{\pm}1.14/134.00{\pm}2.92$, and $147.20{\pm}1.480/129.60{\pm}2.70\;mmHg$, respectively, when the pulse rate was 0.5 beat/second. The pressures changed to $161.40{\pm}1.34/90.20{\pm}1.64$, $175.00{\pm}1.58/93.00{\pm}1.58$, and $176.80{\pm}1.48/90.80{\pm}1.92\;mmHg$, respectively, when the pulse rate was 1.0 beat/second, and $159.40{\pm}1.82/127.20{\pm}1.48$, $166.60{\pm}1.67/138.00{\pm}1.87$, and $161.00{\pm}1.22/135.40{\pm}1.67\;mmHg$, respectively, when it was 1.5 beat/second. When pulse rate was set at 1.0 beat/second, the pressures were $143.60{\pm}1.67/90.20{\pm}1.64$, $147.20{\pm}1.92/84.60{\pm}1.82$, and $137.40{\pm}1.52/88.80{\pm}1.64\;mmHg$ after stent-graft implantation. The changes of pressure before and after stent-graft implantation were statistically significant(p<0.05) except the diastolic pressures at the proximal(p =1.00) and distal aorta(p=0.157). The aortic aneurysm phantoms seems to be useful for the evaluation of the efficacy of stent-graft before animal or clinical studies because of its easy reproducibility and ability to display a wide range of pressures.

• The Korean Nurse
• /
• v.20 no.4 s.112
• /
• pp.39-49
• /
• 1981

기존 간호 영역 내 간호는 질적으로, 양적으로 급격히 팽창 확대되어 가고 있다. 많은 나라에서 건강관리체계가 부적절하게 분배되어 있으며 따라서 많은 사람들이 적절한 건강관리를 제공받지 못하고 있어 수준 높은 양질의 건강관리를 전체적으로 확대시키는 것이 시급하다. 혹 건강관리의 혜택을 받는다고 해도 이들 역시 보다 더 양질의 인간적인 간호를 요하고 있는 실정이다. 간호는 또한 간호영역 자체 내에서도 급격히 확대되어가고 있다. 예를들면, 미국같은 선진국가의 건강간호사(Nurse practitioner)는 간호전문직의 새로운 직종으로 건강관리체계에서 독자적인 실무자로 그 두각을 나타내고 있다. 의사의 심한 부족난으로 고심하는 발전도상에 있는 나라들에서는 간호원들에게 전통적인 간호기능 뿐 아니라 건강관리체계에서 보다 많은 역할을 수행하도록 기대하며 일선지방의 건강센터(Health center) 직종에 많은 간호원을 투입하고 있다. 가령 우리 한국정부에서 최근에 시도한 무의촌지역에서 졸업간호원들이 건강관리를 제공할 수 있도록 한 법적 조치는 이러한 구체적인 예라고 할 수 있다. 기존 간호영역내외의 이런 급격한 변화는 Melvin Toffler가 말한 대로 ''미래의 충격''을 초래하게 되었다. 따라서 이러한 역동적인 변화는 간호전문직에 대하여 몇가지 질문을 던져준다. 첫째, 미래사회에서 간호영역의 특성은 무엇인가? 둘째, 이러한 새로운 영역에서 요구되는 간호원을 길러내기 위해 간호교육자는 어떤 역할을 수행해야 하는가? 셋째 내일의 간호원을 양성하는 간호교육자를 준비시키기 위한 실질적이면서도 현실적인 전략은 무엇인가 등이다. 1. 미래사회에서 간호영역의 특성은 무엇인가? 미래의 간호원은 다음에 열거하는 여러가지 요인으로 인하여 지금까지의 것과는 판이한 환경에서 일하게 될 것이다. 1) 건강관리를 제공하는 과정에서 컴퓨터화되고 자동화된 기계 및 기구 등 새로운 기술을 많이 사용할 것이다. 2) 1차건강관리가 대부분 간호원에 의해 제공될 것이다. 3) 내일의 건강관리는 소비자 주축의 것이 될 것이다. 4) 간호영역내에 많은 새로운 전문분야들이 생길 것이다. 5) 미래의 건강관리체계는 사회적인 변화와 이의 요구에 더 민감한 반응을 하게 될 것이다. 6) 건강관리체계의 강조점이 의료진료에서 건강관리로 바뀔 것이다. 7) 건강관리체계에서의 간호원의 역할은 의료적인 진단과 치료계획의 기능에서 크게 탈피하여 병원내외에서 보다 더 독특한 실무형태로 발전될 것이다. 이러한 변화와 더불어 미래 간호영역에서 보다 효과적인 간호를 수행하기 위해 미래 간호원들은 지금까지의 간호원보다 더 광범위하고 깊은 교육과 훈련을 받아야 한다. 보다 발전된 기술환경에서 전인적인 접근을 하기위해 신체과학이나 의학뿐 아니라 행동과학 $\cdot$ 경영과학 등에 이르기까지 다양한 훈련을 받아야 할 필요가 있다. 또한 행동양상면에서 전문직인 답게 보다 진취적이고 표현적이며 자동적이고 응용과학적인 역할을 수행하도록 훈련을 받아야 한다. 그리하여 간호원은 효과적인 의사결정자$\cdot$문제해결자$\cdot$능숙한 실무자일 뿐 아니라 소비자의 건강요구를 예리하게 관찰하고 이 요구에 효과적인 존재를 발전시켜 나가는 연구자가 되어야 한다. 2. 미래의 간호교육자는 어떤 역할을 수행해야 하는가? 간호교육은 전문직으로서의 실무를 제공하기 위한 기초석이다. 이는 간호교육자야말로 미래사회에서 국민의 건강요구를 충족시키기는 능력있는 간호원을 공급하는 일에 전무해야 함을 시사해준다. 그러면 이러한 일을 달성하기 위해 간호교육자는 무엇을 해야 하는가? 우선 간호교육자는 두가지 측면에서 이 일을 수정해야 된다고 본다. 그 하나는 간호교육기관에서의 측면이고 다른 하나는 간호교육자 개인적인 측면엣서이다. 우선 간호교육기관에서 간호교육자는 1) 미래사회에서 요구되는 간호원을 교육시키기 위한 프로그램을 제공해야 한다. 2) 효과적인 교과과정의 발전과 수정보완을 계속적으로 진행시켜야 한다. 3) 잘된 교과과정에 따라 적절한 훈련을 철저히 시켜야 한다. 4) 간호교육자 자신이 미래의 예측된 현상을 오늘의 교육과정에 포함시킬 수 있는 자신감과 창의력을 가지고 모델이 되어야 한다. 5) 연구 및 학생들의 학습에 영향을 미치는 중요한 의사결정에 학생들을 참여시키도록 해야한다. 간호교육자 개인적인 측면에서는 교육자 자신들이 능력있고 신빙성있으며 간호의 이론$\cdot$실무$\cdot$연구면에 걸친 권위와 자동성$\cdot$독창성, 그리고 인간을 진정으로 이해하려는 자질을 갖추도록 계속 노력해야 한다. 3. 미래의 간호원을 양성하는 능력있는 간호교육자를 준비시키기 위한 실질적이면서도 현실적인 전략은 무엇인가? 내일의 도전을 충족시킬 수 있는 능력있는 간호교육자를 준비시키기 위한 실질적이고 현실적인 전략을 논함에 있어 우리나라의 실정을 참조하겠다. 전문직 간호교육자를 준비하는데 세가지 방법을 통해 할 수 있다고 생각한다. 첫째는 간호원 훈련수준을 전문직 실무를 수행할 수 있는 단계로 면허를 높이는 것이고, 둘째는 훈련수준을 더 향상시키기 위하여 학사 및 석사간호교육과정을 발전시키고 확대하는 것이며, 셋째는 현존하는 간호교육 프로그램의 질을 높이는 것이다. 첫째와 둘째방법은 정부의 관할이 직접 개입되는 방법이기 때문에 여기서는 생략하고 현존하는 교과과정을 발전시키고 그 질을 향상시키는 것에 대해서만 언급하고자 한다. 미래의 여러가지 도전에 부응할 수 있는 교육자를 준비시키는 교육과정의 발전을 두가지 면에서 추진시킬 수 있다고 본다. 첫째는 국제간의 교류를 통하여 idea 및 경험을 나눔으로서 교육과정의 질을 높일 수 있다. 서로 다른 나라의 간호교육자들이 정기적으로 모여 생각과 경험을 교환하고 연구하므로서 보다 체계적이고 효과적인 발전체인(chain)이 형성되는 것이다. ICN같은 국제적인 조직에 의해 이러한 모임을 시도하는 것인 가치있는 기회라고 생각한다. 국가간 또는 국제적인 간호교육자 훈련을 위한 교육과정의 교환은 한 나라안에서 그 idea를 확산시키는데 효과적인 영향을 미칠 수 있다. 충분한 간호교육전문가를 갖춘 간호교육기관이 새로운 교육과정을 개발하여 그렇지 못한 기관과의 연차적인 conference를 가지므로 확산시킬 수도 있으며 이런 방법은 경제적인 면에서도 효과적일 뿐만 아니라 그 나라 그 문화상황에 적합한 교과과정 개발에도 효과적일 수 있다. 간호교육자를 준비시키는 둘째전략은 현존간호교육자들이 간호이론과 실무$\cdot$연구를 통합하고 발전시키는데 있어서 당면하는 여러가지 요인-전인적인 간호에 적절한 과목을 이수하지 못하고 임상실무경험의 부족등-을 보충하는 방법이다. 이런 실제적인 문제를 잠정적으로 해결하기 위하여 1) 몇몇 대학에서 방학중에 계속교육 프로그램을 개발하여 현직 간호교육자들에게 필요하고 적절한 과목을 이수하도록 한다. 따라서 임상실무교육도 이때 실시할 수 있다. 2) 대학원과정 간호교육프로그램의 입학자의 자격에 2$\~$3년의 실무경험을 포함시키도록 한다. 결론적으로 교수와 학생간의 진정한 동반자관계는 자격을 구비한 능력있는 교수의 실천적인 모델을 통하여서 가능하게 이루어 질수 있다고 믿는 바이다.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.25-38
• /
• 2019

Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.85-107
• /
• 2019

Online consumers browse products belonging to a particular product line or brand for purchase, or simply leave a wide range of navigation without making purchase. The research on the behavior and purchase of online consumers has been steadily progressed, and related services and applications based on behavior data of consumers have been developed in practice. In recent years, customization strategies and recommendation systems of consumers have been utilized due to the development of big data technology, and attempts are being made to optimize users' shopping experience. However, even in such an attempt, it is very unlikely that online consumers will actually be able to visit the website and switch to the purchase stage. This is because online consumers do not just visit the website to purchase products but use and browse the websites differently according to their shopping motives and purposes. Therefore, it is important to analyze various types of visits as well as visits to purchase, which is important for understanding the behaviors of online consumers. In this study, we explored the clustering analysis of session based on click stream data of e-commerce company in order to explain diversity and complexity of search behavior of online consumers and typified search behavior. For the analysis, we converted data points of more than 8 million pages units into visit units' sessions, resulting in a total of over 500,000 website visit sessions. For each visit session, 12 characteristics such as page view, duration, search diversity, and page type concentration were extracted for clustering analysis. Considering the size of the data set, we performed the analysis using the Mini-Batch K-means algorithm, which has advantages in terms of learning speed and efficiency while maintaining the clustering performance similar to that of the clustering algorithm K-means. The most optimized number of clusters was derived from four, and the differences in session unit characteristics and purchasing rates were identified for each cluster. The online consumer visits the website several times and learns about the product and decides the purchase. In order to analyze the purchasing process over several visits of the online consumer, we constructed the visiting sequence data of the consumer based on the navigation patterns in the web site derived clustering analysis. The visit sequence data includes a series of visiting sequences until one purchase is made, and the items constituting one sequence become cluster labels derived from the foregoing. We have separately established a sequence data for consumers who have made purchases and data on visits for consumers who have only explored products without making purchases during the same period of time. And then sequential pattern mining was applied to extract frequent patterns from each sequence data. The minimum support is set to 10%, and frequent patterns consist of a sequence of cluster labels. While there are common derived patterns in both sequence data, there are also frequent patterns derived only from one side of sequence data. We found that the consumers who made purchases through the comparative analysis of the extracted frequent patterns showed the visiting pattern to decide to purchase the product repeatedly while searching for the specific product. The implication of this study is that we analyze the search type of online consumers by using large - scale click stream data and analyze the patterns of them to explain the behavior of purchasing process with data-driven point. Most studies that typology of online consumers have focused on the characteristics of the type and what factors are key in distinguishing that type. In this study, we carried out an analysis to type the behavior of online consumers, and further analyzed what order the types could be organized into one another and become a series of search patterns. In addition, online retailers will be able to try to improve their purchasing conversion through marketing strategies and recommendations for various types of visit and will be able to evaluate the effect of the strategy through changes in consumers' visit patterns.

• The Korean Journal of Air & Space Law and Policy
• /
• v.25 no.2
• /
• pp.139-162
• /
• 2010

In terms of the international air transport, the open skies policy implies freedom in the sky or opening the sky. In the normative respect, the open skies policy is a kind of open-door policy which gives various forms of traffic right to other countries, but on the other hand it is a policy of free competition in the international air transport. Since the Airline Deregulation Act of 1978, the United States has signed an open skies agreement with many countries, starting with the Netherlands, so that competitive large airlines can compete in the international air transport market where there exist a lot of business opportunities. South Korea now has an open skies agreement with more than 20 countries. The frequent flyer program (FFP) is part of a broad-based marketing alliance which has been used as an airfare strategy since the U.S. government's airline deregulation. The membership-based program is an incentive plan that provides mileage points to customers for using airline services and rewards customer loyalty in tangible forms based on their accumulated points. In its early stages, the frequent flyer program was focused on marketing efforts to attract customers, but now in the environment of intense competition among airlines, the program is used as an important strategic marketing tool for enhancing business performance. Therefore, airline companies agree that they need to identify customer needs in order to secure loyal customers more effectively. The outcomes from an airline's frequent flyer program can have a variety of effects on international competition. First, the airline can obtain a more dominant position in the air flight market by expanding its air route networks. Second, the availability of flight products for customers can be improved with an increase in flight frequency. Third, the airline can preferentially expand into new markets and thus gain advantages over its competitors. However, there are few empirical studies on the airline frequent flyer program. Accordingly, this study aims to explore the effects of the program on international competition, after reviewing the types of strategic alliance between airlines. Making strategic airline alliances is a worldwide trend resulting from the open skies policy. South Korea also needs to be making open skies agreements more realistic to promote the growth and competition of domestic airlines. The present study is about the performance of the airline frequent flyer program and international competition under the open skies policy. With a sample of five global alliance groups (Star, Oneworld, Wings, Qualiflyer and Skyteam), the study was attempted as an empirical study of the effects that the resource structures and levels of information technology held by airlines in each group have on the type of alliance, and one-way analysis of variance and regression analysis were used to test hypotheses. The findings of this study suggest that both large airline companies and small/medium-size airlines in an alliance group with global networks and organizations are able to achieve high performance and secure international competitiveness. Airline passengers earn mileage points by using non-flight services through an alliance network with hotels, car-rental services, duty-free shops, travel agents and more and show high interests in and preferences for related service benefits. Therefore, Korean airline companies should develop more aggressive marketing programs based on multilateral alliances with other services including hotels, as well as with other airlines.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.