• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.50-63
• /
• 2018

The rapid urbanization had led to a distortion of natural hydrological cycle system. The change in hydrological cycle structure is causing streamflow depletion, changing the existing use tendency of water resources. To manage such phenomena, a streamflow depletion impact assessment technology to forecast depletion is required. For performing such technology, it is indispensable to build GIS-based spatial data as fundamental data, but there is a shortage of related research. Therefore, this study was conducted to use the use of GIS-based time series spatial data for streamflow depletion assessment. For this study, GIS data over decades of changes on a national scale were constructed, targeting 6 streamflow depletion impact factors (weather, soil depth, forest density, road network, groundwater usage and landuse) and the data were used as the basic data for the operation of continuous hydrologic model. Focusing on these impact factors, the causes for streamflow depletion were analyzed depending on time series. Then, using distributed continuous hydrologic model based DrySAT, annual runoff of each streamflow depletion impact factor was measured and depletion assessment was conducted. As a result, the default value of annual runoff was measured at 977.9mm under the given weather condition without considering other factors. When considering the decrease in soil depth, the increase in forest density, road development, and groundwater usage, along with the change in land use and development, and annual runoff were measured at 1,003.5mm, 942.1mm, 961.9mm, 915.5mm, and 1003.7mm, respectively. The results showed that the major causes of the streaflow depletion were lowered soil depth to decrease the infiltration volume and surface runoff thereby decreasing streamflow; the increased forest density to decrease surface runoff; the increased road network to decrease the sub-surface flow; the increased groundwater use from undiscriminated development to decrease the baseflow; increased impervious areas to increase surface runoff. Also, each standard watershed depending on the grade of depletion was indicated, based on the definition of streamflow depletion and the range of grade. Considering the weather, the decrease in soil depth, the increase in forest density, road development, and groundwater usage, and the change in land use and development, the grade of depletion were 2.1, 2.2, 2.5, 2.3, 2.8, 2.2, respectively. Among the five streamflow depletion impact factors except rainfall condition, the change in groundwater usage showed the biggest influence on depletion, followed by the change in forest density, road construction, land use, and soil depth. In conclusion, it is anticipated that a national streamflow depletion assessment system to be develop in the future would provide customized depletion management and prevention plans based on the system assessment results regarding future data changes of the six streamflow depletion impact factors and the prospect of depletion progress.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Korean Journal of Heritage: History & Science
• /
• v.41 no.1
• /
• pp.5-19
• /
• 2008

Thirty six samples of Western asia glass vessel shards which were excavated from South Mound of Hwangnamdaechong were each measured for thickness, pore size and specific gravity and analyzed for ten major compositions and thirteen trace elements. The glass samples with colorless, greenish blue and dark purple blue were well classified by principal component analysis(PCA). All glass shards of Hwangnamdaechong belonged to Soda glass system ($Na_2O-CaO-SiO_2$) which have the range of 14~17% $Na_2O$ and 5~6% CaO. The corelation coefficients of (MgO, $K_2O$) and (MnO, CuO) showed above 0.90. The concentrations of thirteen trace elements apparently differentiated from colorless, greenish blue and dark blue glasses. We found that thirteen trace elements were very important indices for studying raw material of glass and the origin of glass making. Colorless glass : The specific gravity is $1.50{\pm}0.04$. Circle or oval circle pores are observed with regular direction in internal zone and the longest one is about 0.35 mm. The raw material of sodium must be the plant ash because sodium glasses contain HCLA(High CaO, Low $Al_2O_3$) and HMK(high MgO, high $K_2O$) and suggested to Sasanian glass. The total amount of coloring agent of colorless glass is below 1 % which is too small to attribute to the color. Greenish blue glass : The specific gravity is $1.58{\pm}0.04$. The fine pores which are 0.1~0.2mm are dispersed in internal zone. Sodium glasses are distributed to HCLA and HMK. Therefore the greenish blue glass also have used plant ash for raw material of sodium with the same as colorless glass. It was also suggested to the glass of Sasanian. The total amount of coloring agent of greenish blue glass is about 4% under the influence of working MnO, $Fe_2O_3$ and CuO. Dark purple blue glass : The specific gravity is $1.48{\pm}0.19$. There are rarely pores in internal zone. They are distributed to HCLA and LMK(Low MgO, Low $K_2O$) and suggested to Roman glass. The raw material of sodium is estimated to natron. The total amount of coloring agents of greenish blue is about 3% by $Fe_2O_3$ and CuO. These studies for western asia glass shards from South Mound of Hwangnamdaechong could be used in the future as the standard data which could be compared with those of other several graves in Korea and dispersed in foreign areas.

• The Journal of Korean Society for Radiation Therapy
• /
• v.31 no.1
• /
• pp.57-65
• /
• 2019

Purpose: The purpose is to clarify the effect of additional scattering ratio on the edge of the block according to the increasing block thickness with low melting point lead alloy and pure lead in electron beam therapy. Methods and materials: $10{\times}10cm^2$ Shielding blocks made of low melting point lead alloy and pure lead were fabricated to shield mold frame half of applicator. Block thickness was 3, 5, 10, 15, 20 (mm) for each material. The common irradiation conditions were set at 6 MeV energy, 300 MU / Min dose rate, gantry angle of $0^{\circ}$, and dose of 100 MU. The relative scattering ratio with increasing block thickness was measured with a parallel plate type ion chamber(Exradin P11) and phantom(RW3) by varying the position of the shielding block(cone and on the phantom), the position of the measuring point(surface ans depth of $D_{max}$), and the block material(lead alloy and pure lead). Results : When (depth of measurement / block position / block material) was (surface / applicator / pure lead), the relative value(scattering ratio) was 15.33 nC(+0.33 %), 15.28 nC(0 %), 15.08 nC(-1.31 %), 15.05 nC(-1.51 %), 15.07 nC(-1.37 %) as the block thickness increased in order of 3, 5, 10, 15, 20 (mm) respectively. When it was (surface / applicator / alloy lead), the relative value(scattering ratio) was 15.19 nC(-0.59 %), 15.25 nC(-0.20 %), 15.15 nC(-0.85 %), 14.96 nC(-2.09 %), 15.15 nC(-0.85 %) respectively. When it was (surface / phantom / pure lead), the relative value(scattering ratio) was 15.62 nC(+2.23 %), 15.59 nC(+2.03 %), 15.53 nC(+1.67 %), 15.48 nC(+1.31 %), 15.34 nC(+0.39 %) respectively. When it was (surface / phantom / alloy lead), the relative value(scattering ratio) was 15.56 nC(+1.83 %), 15.55 nC(+1.77 %), 15.51 nC(+1.51 %), 15.42 nC(+0.92 %), 15.39 nC(+0.72 %) respectively. When it was (depth of $D_{max}$ / applicator / pure lead), the relative value(scattering ratio) was 16.70 nC(-10.87 %), 16.84 nC(-10.12 %), 16.72 nC(-10.78 %), 16.88 nC(-9.93 %), 16.90 nC(-9.82 %) respectively. When it was (depth of $D_{max}$ / applicator / alloy lead), the relative value(scattering ratio) was 16.83 nC(-10.19 %), 17.12 nC(-8.64 %), 16.89 nC(-9.87 %), 16.77 nC(-10.51 %), 16.52 nC(-11.85 %) respectively. When it was (depth of $D_{max}$ / phantom / pure lead), the relative value(scattering ratio) was 17.41 nC(-7.10 %), 17.45 nC(-6.88 %), 17.34 nC(-7.47 %), 17.42 nC(-7.04 %), 17.25 nC(-7.95 %) respectively. When it was (depth of $D_{max}$ / phantom / alloy lead), the relative value(scattering ratio) was 17.45 nC(-6.88 %), 17.44 nC(-6.94 %), 17.47 nC(-6.78 %), 17.43 nC(-6.99 %), 17.35 nC(-7.42 %) respectively. Conclusions: When performing electron therapy using a shielding block, the block position should be inserted applicator rather than the patient's body surface. The block thickness should be made to the minimum appropriate shielding thickness of each corresponding using energy. Also it is useful that the treatment should be performed considering the influence of scattering dose varying with distance from the edge of block.

• Korean Journal of Heritage: History & Science
• /
• v.42 no.3
• /
• pp.4-24
• /
• 2009

This paper examined archaeological resources that discuss how Silla entered the Gangneung area, the coastal region along the East Sea that has been excavated most actively. Silla expanded its territories while organizing the its system as an ancient state and acquired several independent townships in various regions, stretching its forces to the East Sea area faster than any other ancient states of the time. In particular, many early relics and heritages of Silla have been found in Gangneung, the center of the East Sea area. Many archaeological resources prove these circumstances of that time and provide brief texts that are valuable for our interpretation of historical facts. In this respect, it was possible for me to examine these resources to answer my question as to why early relics and heritages of Silla are found in the Gangneung area. Based on my research on Silla's advancement into the Gangneung area, I have acquired the following results: How did Silla rule this area after conquering Yeguk in the Gangneung area? After conquering the Gangneung area, Silla attempted an indirect ruling at first. Later, Silla adopted a direct ruling system. I divided the indirect ruling period into two phases: introduction and settlement. In detail, Silla's earthenware and stone chamber tombs first appeared in Hasi-dong in the fourth quarter of the 4th Century and the tombs spread to Chodang-dong in the second quarter of the 5th Century. A belt with dragon pattern openwork, which seems to be from the second quarter of the 5th Century, was found to tell us that the Gangneung region began receiving rewards from Silla during this time. Thus, the period from the fourth quarter of the 4th Century to the second quarter of the 5th Century is designated as the 1st Phase (Introduction) of indirect ruling in terms of aechaeological findings. This is when Silla was first advanced to the Gangneung area and tolerated independent administration of the conquered. In the third and fourth quarters of the 5th Century, old mound tombs appeared and burials of relics that symbolized power emerged. In the third quarter of the 5th Century, stone chamber tombs were prevalent, but wooden chamber tombs, stone mounded wooden chamber tombs, and lateral entrance stone chamber tombs began to emerge. Also, tombs that were clustered in Hasi-dong and Chodang-dong began to scatter to Byeongsan-dong, Yeongjin-ri, and Bangnae-ri nearby. Steel pots were the symbol of power that emerged at this time. In the fourth quarter of the 5th Century, stone chamber tombs were still dominating, but wooden chamber tombs, stone mounded wooden chamber tombs, and lateral entrance stone chamber tombs became more popular. More crowns, crown ornaments, big daggers, and belts were bestowed by Silla, mostly in Chodang-dong and Byeongsan-dong. The period from the third quarter to the fourth quarter of the 5th Century was designated as the 2nd Phase (Settlement) of indirect ruling in terms of aechaeological findings. At this time, Silla bestowed items of power to the ruling class of the Gangneung area and gave equal power to the rulers of Chodang-dong and Byeongsan-dong to keep them restrained by each other. However, Silla converted the ruling system to direct ruling once it recognized the Gangneung area as the base of its expedition of conquest to the north. In the first quarter of the 6th Century, old mound tombs disappeared and small/medium-sized mounds appeared in the western inlands and the northern areas. In this period, the tunnel entrance stone chamber tombs were large enough for people to enter with doors. A cluster of several tunnel entrance stone chamber tombs was formed in Yeongjin-ri and Bangnae-ri at this time, probably with the influence of Silla's direct ruling. In the first quarter of the 6th Century, Silla dispatched officers from the central government to complete the local administration system and replaced the ruling class of Chodang-dong and Byeongsan-dong with that of Silla-friendly Yeonjin-ri and Bangnae-ri to reorganize the local administration system and gain full control of the Gangneung area.

• The Journal of Korean Society for Radiation Therapy
• /
• v.31 no.1
• /
• pp.33-41
• /
• 2019

Purpose : To evaluate the effectiveness of Jaw-tracking(JT) technique in Intensity-modulated radiation therapy(IMRT) and Volumetric-modulated arc therapy(VMAT) for radiation therapy of esophageal cancer by analyzing volume dose of perimetrical normal organs along with the low-dose volume regions. Materials and Method: A total of 27 patients were selected who received radiation therapy for esophageal cancer with using $VitalBeam^{TM}$(Varian Medical System, U.S.A) in our hospital. Using Eclipse system(Ver. 13.6 Varian, U.S.A), radiation treatment planning was set up with Jaw-tracking technique(JT) and Non-Jaw-tracking technique(NJT), and was conducted for the patients with T-shaped Planning target volume(PTV), including Supraclavicular lymph nodes(SCL). PTV was classified into whether celiac area was included or not to identify the influence on the radiation field. To compare the treatment plans, Organ at risk(OAR) was defined to bilateral lung, heart, and spinal cord and evaluated for Conformity index(CI) and Homogeneity index(HI). Portal dosimetry was performed to verify a clinical application using Electronic portal imaging device(EPID) and Gamma analysis was performed with establishing thresholds of radiation field as a parameter, with various range of 0 %, 5 %, and 10 %. Results: All treatment plans were established on gamma pass rates of 95 % with 3 mm/3 % criteria. For a threshold of 10 %, both JT and NJT passed with rate of more than 95 % and both gamma passing rate decreased more than 1 % in IMRT as the low dose threshold decreased to 5 % and 0 %. For the case of JT in IMRT on PTV without celiac area, $V_5$ and $V_{10}$ of both lung showed a decrease by respectively 8.5 % and 5.3 % in average and up to 14.7 %. A $D_{mean}$ decreased by $72.3{\pm}51cGy$, while there was an increase in radiation dose reduction in PTV including celiac area. A $D_{mean}$ of heart decreased by $68.9{\pm}38.5cGy$ and that of spinal cord decreased by $39.7{\pm}30cGy$. For the case of JT in VMAT, $V_5$ decreased by 2.5 % in average in lungs, and also a little amount in heart and spinal cord. Radiation dose reduction of JT showed an increase when PTV includes celiac area in VMAT. Conclusion: In the radiation treatment planning for esophageal cancer, IMRT showed a significant decrease in $V_5$, and $V_{10}$ of both lungs when applying JT, and dose reduction was greater when the irradiated area in low-dose field is larger. Therefore, IMRT is more advantageous in applying JT than VMAT for radiation therapy of esophageal cancer and can protect the normal organs from MLC leakage and transmitted doses in low-dose field.

• Korean Journal of Heritage: History & Science
• /
• v.45 no.3
• /
• pp.60-79
• /
• 2012

Environment of ancient Chinese Buddhist temple can be classified to three types such as regional society(鄕村), famous mountain(名山), and urban areas(都市). This made differences in environment where a temple existed and in turn, affected development of Buddhism. And this made another type in relationship between Buddhist temple and a society. This study explains influences which regional society gave on not only Buddhist temple and a monk but also existence and development of Buddhism. When temples are placed in different environmental position, that is, urban areas and regional society, among a social structure, they eventually should adapt to a different society externally and internally. As told in above, ancient Chinese Buddhist temple was located in regional society, famous mountain, and urban areas. Since Eastern Jin and Sixteen Kingdoms, as number of temple much increased, and temples and monks were concentrated on famous mountain, temples in famous mountains and urban areas had developed showing similar aspects each other. But because temples in regional society were influenced a little differently, this study focused on the point. There are four kinds of influences between temples and monks in regional areas. Monks in regional areas had a comparatively close relationship with a society because they came from same area or surrounding areas. Therefore,powers of regional areas restrict influences made by monk group in temple. Second, temples in regional areas shared their joys and sorrows depending on regional economy. Temples in regional areas became a public place for the society and often a market place. In fact, construction and existence of a temple originally became a driving force in regional economy. This is because construction of temple needs artisans and materials and some temples had visitors and included market economy like consumption of incense and candles, though the economic size was large or small. And when regional areas experienced natural disaster or man-made disaster or had poor harvest or economy was in depression, monks left temples and then, temples themselves could not exist. Third, the relationship between temples in regional areas and Buddhists was distinguished from the temples in urban areas and famous mountains. This is because temples in China were places where monks practiced and at the same time, places where general Buddhists worshipped. So there were always a number of Buddhists around the temples. Forth, Buddhism in resional areas was connected to regional Folk beliefs. As a result, Buddhism was spread across the nation, worship with local color often was changed to Buddhist belief or was tinged with Buddhism. While temples in regional areas maintained a close relationship with regional society.they were influenced by the region or gave influences. As a representative example, temples in regional areas showed model behaviors instead of roles of facilities related to various cultures with comparatively advanced level - for example, school, hospital etc. The temples highly affected funerary rites in regional areas. Chinese tombs were mainlymade in regional areas. After death,people living in urban areas were buried in hometown or at least, they were buried in suburbs not urban areas. Temples in regional areas generally participated in funerary rites. Above shows that though most of famous Buddhist temples were located in urban areas not in famous mountains,majority of temples were located in vast regional areas. Through mutual interaction between temples and regional society, the temples in the regional areas were related to Chinese people of over 90% and regional areas became the most important foundation for Buddhism in China. Mutual influences between temples in regional areas and the general public in regions were omnidirectional and spreaded to every aspects of social life in small or large degree. Thus Tombs in temple were widely spreaded across regional areas over time and space. This is enough to explain a close relationship between Buddhist temples and rural society in ancient China.

• Korean Journal of Heritage: History & Science
• /
• v.49 no.2
• /
• pp.172-189
• /
• 2016

In this research, literature research on the Odong material, mixture ratio, casting method and casting facility was conducted on contemporary documents, such as Cheongong Geamul. Also, a long sword was produced using the Odong inlay technique. The sword reproduction steps were as follows; Odong alloying, silver soldering alloying, Odong plate and Silver plate production, hilt and sheath production, metal frame and decorative elements, such as a Dugup (metal frame), production, Odong inlay assembly and final assembly. For the Odong alloy production, the mixture ratio of the true Odong, which has copper and gold ratio of 20:1, was used. This is traditional ratio for high quality product according to $17^{th}$ century metallurgy instruction manual. The silver soldering alloy was produced with silver and brass(Cu 7 : Zn 3) ratio of 5:1 for inlay purpose and 5:2 ratio for simple welding purpose. The true Odong alloy laminated with silver plate was used to produce hilt and sheath. The alloy went through annealing and forging steps to make it into 0.6 mm thick plate and its backing layer, which is a silver plate, had the matching thickness. After the two plates were adhered, the laminated plate went through annealing, forging, engraving, silver inlaying, shaping, silver welding, finishing and polishing steps. During the Odong colouring process, its red surface turns black by induced corrosion and different hues can be achieved depending on its quality. To accomplish the silver inlay Odong techniques, a Hanji saturated with thirty day old urine is wrapped around a hilt and sheath material, then it is left at warm room temperature for two to three hours. The Odong's surface will turn black when silver inlay remains unchanged. Various scientific analysis were conducted to study composition of recreated Odong panel, silver soldering, silver plate and the colouring agent on Odong's surface. The recreated Odong had average out at Cu 95.57 wt% Au 4.16wt% and Cu 98.04 wt% Au 1.95wt%, when documented ratio in the old record is Cu 95wt% and Au 5wt%. The recreated Odong was prone to surface breakage during manufacturing process unlike material made with composition ratio written in the old record. On the silver plate of the silver and Odong laminate, 100wt% Ag was detected and between the two layers Cu, Ag and Au were detected. This proves that the adhesion between the two layers was successfully achieved. The silver soldering had varied composition of Ag depending on the location. This shows uneven composition of the silver welding. A large quantities of S, that was not initially present, was detected on the surface of the black Odong. This indicates that presence of S has influence on Odong colour. Additional study on the chromaticity, additional chemical compounds and its restoration are needed for the further understanding of the origin of Odong colour. The result of Odong alloy testing and recreation, Odong silver inlay long sword production, scientific analysis of the Odong black colouring agent will form an important foundation of knowledge for conservation of Odong artifact.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.21-41
• /
• 2019

Thanks to the rapid development of information technologies, the data available on Internet have grown rapidly. In this era of big data, many studies have attempted to offer insights and express the effects of data analysis. In the tourism and hospitality industry, many firms and studies in the era of big data have paid attention to online reviews on social media because of their large influence over customers. As tourism is an information-intensive industry, the effect of these information networks on social media platforms is more remarkable compared to any other types of media. However, there are some limitations to the improvements in service quality that can be made based on opinions on social media platforms. Users on social media platforms represent their opinions as text, images, and so on. Raw data sets from these reviews are unstructured. Moreover, these data sets are too big to extract new information and hidden knowledge by human competences. To use them for business intelligence and analytics applications, proper big data techniques like Natural Language Processing and data mining techniques are needed. This study suggests an analytical approach to directly yield insights from these reviews to improve the service quality of hotels. Our proposed approach consists of topic mining to extract topics contained in the reviews and the decision tree modeling to explain the relationship between topics and ratings. Topic mining refers to a method for finding a group of words from a collection of documents that represents a document. Among several topic mining methods, we adopted the Latent Dirichlet Allocation algorithm, which is considered as the most universal algorithm. However, LDA is not enough to find insights that can improve service quality because it cannot find the relationship between topics and ratings. To overcome this limitation, we also use the Classification and Regression Tree method, which is a kind of decision tree technique. Through the CART method, we can find what topics are related to positive or negative ratings of a hotel and visualize the results. Therefore, this study aims to investigate the representation of an analytical approach for the improvement of hotel service quality from unstructured review data sets. Through experiments for four hotels in Hong Kong, we can find the strengths and weaknesses of services for each hotel and suggest improvements to aid in customer satisfaction. Especially from positive reviews, we find what these hotels should maintain for service quality. For example, compared with the other hotels, a hotel has a good location and room condition which are extracted from positive reviews for it. In contrast, we also find what they should modify in their services from negative reviews. For example, a hotel should improve room condition related to soundproof. These results mean that our approach is useful in finding some insights for the service quality of hotels. That is, from the enormous size of review data, our approach can provide practical suggestions for hotel managers to improve their service quality. In the past, studies for improving service quality relied on surveys or interviews of customers. However, these methods are often costly and time consuming and the results may be biased by biased sampling or untrustworthy answers. The proposed approach directly obtains honest feedback from customers' online reviews and draws some insights through a type of big data analysis. So it will be a more useful tool to overcome the limitations of surveys or interviews. Moreover, our approach easily obtains the service quality information of other hotels or services in the tourism industry because it needs only open online reviews and ratings as input data. Furthermore, the performance of our approach will be better if other structured and unstructured data sources are added.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.95-112
• /
• 2021

In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.