• Korean Journal of Remote Sensing
• /
• v.39 no.6_2
• /
• pp.1565-1576
• /
• 2023

An atmospheric correction algorithm based on the radiative transfer model is required to obtain remote-sensing reflectance (R_rs) from the Geostationary Ocean Color Imager-II (GOCI-II) observed at the top-of-atmosphere. This R_rs derived from the atmospheric correction is utilized to estimate various marine environmental parameters such as chlorophyll-a concentration, total suspended materials concentration, and absorption of dissolved organic matter. Therefore, an atmospheric correction is a fundamental algorithm as it significantly impacts the reliability of all other color products. However, in clear waters, for example, atmospheric path radiance exceeds more than ten times higher than the water-leaving radiance in the blue wavelengths. This implies atmospheric correction is a highly error-sensitive process with a 1% error in estimating atmospheric radiance in the atmospheric correction process can cause more than 10% errors. Therefore, the quality assessment of R_rs after the atmospheric correction is essential for ensuring reliable ocean environment analysis using ocean color satellite data. In this study, a Quality Assurance (QA) algorithm based on in-situ R_rs data, which has been archived into a database using Sea-viewing Wide Field-of-view Sensor (SeaWiFS) Bio-optical Archive and Storage System (SeaBASS), was applied and modified to consider the different spectral characteristics of GOCI-II. This method is officially employed in the National Oceanic and Atmospheric Administration (NOAA)'s ocean color satellite data processing system. It provides quality analysis scores for R_rs ranging from 0 to 1 and classifies the water types into 23 categories. When the QA algorithm is applied to the initial phase of GOCI-II data with less calibration, it shows the highest frequency at a relatively low score of 0.625. However, when the algorithm is applied to the improved GOCI-II atmospheric correction results with updated calibrations, it shows the highest frequency at a higher score of 0.875 compared to the previous results. The water types analysis using the QA algorithm indicated that parts of the East Sea, South Sea, and the Northwest Pacific Ocean are primarily characterized as relatively clear case-I waters, while the coastal areas of the Yellow Sea and the East China Sea are mainly classified as highly turbid case-II waters. We expect that the QA algorithm will support GOCI-II users in terms of not only statistically identifying R_rs resulted with significant errors but also more reliable calibration with quality assured data. The algorithm will be included in the level-2 flag data provided with GOCI-II atmospheric correction.

• Sim-seong Yeon-gu
• /
• v.32 no.1
• /
• pp.1-16
• /
• 2017

The purpose of this paper is to illustrate the nature of Objective Psyche based on island related case materials. Theoretical background starts with psychological meaning of islands, a kind affective symbol rather than cognitive image, and creation myths as the story of man's awareness of the world; Chaos as archaic identity (unconscious), islands as emergence of the ego from unconscious. In alchemical symbolism, island related to coagulatio, the operation which turns something into earth, the realm of ego. In addition, related parts of Hindu creation myths, Korean giant woman creator Sulmoonde-halmang, and legends of "Relocation of Island/Mountain" will be presented to integrate with case materials. Case A : Starts with a dream of killing a huge dragon and dead body became an island. The dragon in the water was seen as Spirit of Mercurius, the autonomous spirit, connecting of the ego with the Self. The act of killing related to Primeval being which needs to be killed to be transformed. Myths of Eskimo, The Eagle's Gift, the giant woman creator in Korea, and Marduk, the Babylonian hero will be integrated. Case B : Prior to introduce six island images in sand trays, a dream of a giant serpent (python) wound around her body will be presented to portray her situation. By relating Jung's "The Sermons to the Dead," her effort to make the solid island regarded as an act of bringing order out of original oneness (pleroma). Then stresses the importance to coagulate archetypal image Case C : A vignette of active imagination seminar where island image emerged will be described. Her endeavor of focusing on inner image related to the Hindu Creator, Cherokee creation myth, as well as Sulmoonde-halmang. As a motif of growing island, Samoan creation myth, and Legend of Mountain, Mai were incorporated. Colors in her art work regarded as expression of inner need, and importance of expressing inner feeling images as a mean to coagulate volatile emotional and spiritual content. Case D : A dream and art work of terminally ill woman; embracing the tip of the island with gushing up water will be presented. Her island and replenishing water image regard as "an immortal body," corresponds to the Philosophers' Stone for she accepted her death peacefully after the dream. Also related to "The Mercurial Fountain" in Rosarium Philosophorum, and aqua permanence, an allegory of God.

• Korean Journal of Heritage: History & Science
• /
• v.57 no.3
• /
• pp.116-137
• /
• 2024

This study quantitatively explored the interrelationship between water features and surrounding waterscape elements through a literature review and observational study targeting nine waterscapes of Suzhou Classical Garden in Jiangsu Province, China, which is designated as a UNESCO World Heritage Site. The purpose was to understand the objective characteristics of classical Chinese gardens and seek a basis for their differences from Korean gardens. The average area of water space in Suzhou gardens was 1,680.7㎡, which accounted for 21.3% of the total garden area, showing large variation by garden. Most of the Suzhou Gardens use springs and wells as their water sources. The Surging Waves Pavillion uses surface water, and Retreat & Reflection Garden uses seasonal water as its water source. The water pipes in Suzhou Garden are divided into a water outlet and a water outlet(water holes). Of these, the water outlet is a water outlet that imitates the water outlet just to induce a visual effect, and focuses on the meaning of the water system. It is judged to have been combined with the trend of Suzhou gardens. In addition, it was confirmed that, semantically, the arrangement of the water polo in Suzhou Garden is based on the traditional 'Gamyeo(堪輿) theory'. Meanwhile, there are five types of methods for bringing water to Suzhou Garden: Jiginbeop(直引法), Myeonggeobeop(明渠法), Invasionbeop(滲透法), Gwandobeop(管道法), and Chakjeongbeop(鑿井法). Suzhou Classical Garden mainly applies the infiltration method and the irrigation method as a method of securing water in the garden, which can be classified and defined as the water catchment method(集水法) and the water pulling method(引水法) in the domestic classification method. Among the watering techniques in Korean traditional gardens, watering methods such as 'suspension waterfall(懸瀑)', 'flying waterfall(飛瀑)' and water eluted(湧出), have not been found, and it is believed that they mainly 'rely on hide with dignity(姿逸)' and 'submerged current(潛流)' techniques. As for the watering technique, no watering technique was found that uses a Muneomi, which is applied in traditional Korean gardens. As this was applied, the seal method, penetration method, and Gwandobeop were also used in water extraction techniques. And at the inlet and outlet of Suzhou Garden, the main static water bodies were lakes, swamps, and dams. While the eastern water bodies are classified into streams, waterfalls, and springs, the water spaces in the three gardens reflect the centrifugal distributed arrangement, and the water spaces in the six places reflect the water landscape effect due to the centripetal concentrated arrangement. And as a water space landscape design technique, the techniques of 'Gyeok(隔)' and 'Pa(破)' were mainly applied at the inlet, and the techniques of 'Eom(隔)' and 'Pa(破)' were mainly applied at the outlet. For example, most bridges were built around the inlet, and sa(榭), heon(軒), gak(閣), pavilion(亭), and corridor(廊) were built, and the outlet was concealed with a stone wall. Therefore, it is understood to have embodied Suzhou Garden's idea of water(理水), which says, "Although it was created by humans, it is as if the sky is mine(雖由人作，宛自天開)."A trend was detected. Lastly, as a result of analyzing the degree of concealment and exposure in the visual composition of the inlet and outlet, it was confirmed that the water outlet was exposed only at the Eobijeong and Mountain Villa with Embracing Beauty view points of The Surging Waves Pavillion and the water outlet was hidden at other view points. Looking at these results, the 'Hyang-Hyang-Ba-Mi-Bob(向向發微法)' from the perspective of left-orientation theory of Feng Shui, which is applied in Korean traditional gardens in classical Chinese garden water management, "makes water visible as it comes in, but invisible as it goes out." It is judged that the technique was barely matched.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Journal of Global Scholars of Marketing Science
• /
• v.18 no.3
• /
• pp.89-114
• /
• 2008

Most of the extant studies on communication effects have been devoted to the typical issue, "what types of communication activities are more effective for brand awareness or brand attitudes?" However, little research has addressed another question on communication decisions, "what makes communication activities less effective?" Our study focuses on factors negatively influenced on the efficiency of communication activities, especially of Advertising. Some studies have introduced concepts closely related to our topic such as consumer confusion, brand confusion, or belief confusion. Studies on product belief confusion have found some factors misleading consumers to misunderstand the physical features of products. Studies on brand confusion have uncovered factors making consumers confused on brand names. Studies on advertising confusion have tested the effects of ad models' employed by many other firms for different products on communication efficiency. We address a new concept, Ad noises, which are any factors interfering with consumers exposed to a particular advertisement in understanding messages provided by advertisements. The objective of this study is to understand the effects of ad noises caused by ad models on brand awareness and brand attitude. There are many different types of AD noises. Particularly, we study the effects of AD noises generated from ad model selection decision. Many companies want to employ celebrities as AD models while the number of celebrities who command a high degree of public and media attention are limited. Inevitably, several firms have been adopting the same celebrities as their AD models for different products. If the same AD model is adopted for TV commercials for different products, consumers exposed to those TV commercials are likely to fail to be aware of the target brand due to interference of TV commercials, for other products, employing the same AD model. This is an ad noise caused by employing ad models who have been exposed to consumers in other advertisements, which is the first type of ad noises studied in this research. Another type of AD noises is related to the decision of AD model replacement for the same product advertising. Firms sometimes launch another TV commercial for the same products. Some firms employ the same AD model for the new TV commercial for the same product and other firms employ new AD models for the new TV commercials for the same product. The typical problem with the replacement of AD models is the possibility of interfering with consumers in understanding messages of the TV commercial due to the dissimilarity of the old and new AD models. We studied the effects of these two types of ad noises, which are the typical factors influencing on the effect of communication: (1) ad noises caused by employing ad models who have been exposed to consumers in other advertisements and (2) ad noises caused by changing ad models with different images for same products. First, we measure the negative influence of AD noises on brand awareness and attitudes, in order to provide the importance of studying AD noises. Furthermore, our study unveiled the mediating conditions(variables) which can increase or decrease the effects of ad noises on brand awareness and attitudes. We study the effects of three mediating variables for ad noises caused by employing ad models who have been exposed to consumers in other advertisements: (1) the fit between product image and AD model image, (2) similarity between AD model images in multiple TV commercials employing the same AD model, and (3) similarity between products of which TV commercial employed the same AD model. We analyze the effects of another three mediating variables for ad noises caused by changing ad models with different images for same products: (1) the fit of old and new AD models for the same product, (2) similarity between AD model images in old and new TV commercials for the same product, and (3) concept similarity between old and new TV commercials for the same product. We summarized the empirical results from a field survey as follows. The employment of ad models who have been used in advertisements for other products has negative effects on both brand awareness and attitudes. our empirical study shows that it is possible to reduce the negative effects of ad models used for other products by choosing ad models whose images are relevant to the images of target products for the advertisement, by requiring ad models of images which are different from those of ad models in other advertisements, or by choosing ad models who have been shown in advertisements for other products which are not similar to the target product. The change of ad models for the same product advertisement can positively influence on brand awareness but positively on brand attitudes. Furthermore, the effects of ad model change can be weakened or strengthened depending on the relevancy of new ad models, the similarity of previous and current ad models, and the consistency of the previous and current ad messages.

• The Journal of Korean Society for Radiation Therapy
• /
• v.24 no.2
• /
• pp.157-165
• /
• 2012

Purpose: We evaluated usefulness of abdominal compressor for stereotactic body radiotherapy (SBRT) with unresectable hepatocellular carcinoma (HCC) patients and hepato-biliary cancer and metastatic liver cancer patients. Materials and Methods: From November 2011 to March 2012, we selected HCC patients who gained reduction of diaphragm movement >1 cm through abdominal compressor (diaphragm control, elekta, sweden) for HT (Hi-Art Tomotherapy, USA). We got planning computed tomography (CT) images and 4 dimensional (4D) images through 4D CT (somatom sensation, siemens, germany). The gross tumor volume (GTV) included a gross tumor and margins considering tumor movement. The planning target volume (PTV) included a 5 to 7 mm safety margin around GTV. We classified patients into two groups according to distance between tumor and organs at risk (OAR, stomach, duodenum, bowel). Patients with the distance more than 1 cm are classified as the 1st group and they received SBRT of 4 or 5 fractions. Patients with the distance less than 1 cm are classified as the 2nd group and they received tomotherapy of 20 fractions. Megavoltage computed tomography (MVCT) were performed 4 or 10 fractions. When we verify a MVCT fusion considering priority to liver than bone-technique. We sent MVCT images to Mim_vista (Mimsoftware, ver .5.4. USA) and we re-delineated stomach, duodenum and bowel to bowel_organ and delineated liver. First, we analyzed MVCT images to check the setup variation. Second we compared dose difference between tumor and OAR based on adaptive dose through adaptive planning station and Mim_vista. Results: Average setup variation from MVCT was $-0.66{\pm}1.53$ mm (left-right) $0.39{\pm}4.17$ mm (superior-inferior), $0.71{\pm}1.74$ mm (anterior-posterior), $-0.18{\pm}0.30$ degrees (roll). 1st group ($d{\geq}1$) and 2nd group (d<1) were similar to setup variation. 1st group ($d{\geq}1$) of $V_{diff3%}$ (volume of 3% difference of dose) of GTV through adaptive planing station was $0.78{\pm}0.05%$, PTV was $9.97{\pm}3.62%$, $V_{diff5%}$ was GTV 0.0%, PTV was $2.9{\pm}0.95%$, maximum dose difference rate of bowel_organ was $-6.85{\pm}1.11%$. 2nd Group (d<1) GTV of $V_{diff3%}$ was $1.62{\pm}0.55%$, PTV was $8.61{\pm}2.01%$, $V_{diff5%}$ of GTV was 0.0%, PTV was $5.33{\pm}2.32%$, maximum dose difference rate of bowel_organ was $28.33{\pm}24.41%$. Conclusion: Despite we saw diaphragm movement more than 5 mm with flouroscopy after use an abdominal compressor, average setup_variation from MVCT was less than 5 mm. Therefore, we could estimate the range of setup_error within a 5 mm. Target's dose difference rate of 1st group ($d{\geq}1$) and 2nd group (d<1) were similar, while 1st group ($d{\geq}1$) and 2nd group (d<1)'s bowel_organ's maximum dose difference rate's maximum difference was more than 35%, 1st group ($d{\geq}1$)'s bowel_organ's maximum dose difference rate was smaller than 2nd group (d<1). When applicating SBRT to HCC, abdominal compressor is useful to control diaphragm movement in selected patients with more than 1 cm bowel_organ distance.

• The Journal of Korean Society for Radiation Therapy
• /
• v.27 no.2
• /
• pp.157-166
• /
• 2015

Purpose : Cyber-Knife tumor tracking system, based on the correlation relationship between the position of a tumor which moves in response to the real time respiratory cycle signal and respiration was obtained by the LED marker attached to the outside of the patient, the location of the tumor to predict in advance, the movement of the tumor in synchronization with the therapeutic device to track real-time tumor, is a system for treating. The purpose of this study, in the cyber knife tumor tracking radiation therapy, trying to evaluate the accuracy of tumor tracking radiation therapy system due to the change in the form of unpredictable sudden breathing due to cough and sleep. Materials and Methods : Breathing Log files that were used in the study, based on the Respiratory gating radiotherapy and Cyber-knife tracking radiosurgery breathing Log files of patients who received herein, measured using the Log files in the form of a Sinusoidal pattern and Sudden change pattern. it has been reconstituted as possible. Enter the reconstructed respiratory Log file cyber knife dynamic chest Phantom, so that it is possible to implement a motion due to respiration, add manufacturing the driving apparatus of the existing dynamic chest Phantom, Phantom the form of respiration we have developed a program that can be applied to. Movement of the phantom inside the target (Ball cube target) was driven by the displacement of three sizes of according to the size of the respiratory vertical (Superior-Inferior) direction to the 5 mm, 10 mm, 20 mm. Insert crosses two EBT3 films in phantom inside the target in response to changes in the target movement, the End-to-End (E2E) test provided in Cyber-Knife manufacturer depending on the form of the breathing five times each. It was determined by carrying. Accuracy of tumor tracking system is indicated by the target error by analyzing the inserted film, additional E2E test is analyzed by measuring the correlation error while being advanced. Results : If the target error is a sine curve breathing form, the size of the target of the movement is in response to the 5 mm, 10 mm, 20 mm, respectively, of the average $1.14{\pm}0.13mm$, $1.05{\pm}0.20mm$, with $2.37{\pm}0.17mm$, suddenly for it is variations in breathing, respective average $1.87{\pm}0.19mm$, $2.15{\pm}0.21mm$, and analyzed with $2.44{\pm}0.26mm$. If the correlation error can be defined by the length of the displacement vector in the target track is a sinusoidal breathing mode, the size of the target of the movement in response to 5 mm, 10 mm, 20 mm, respective average $0.84{\pm}0.01mm$, $0.70{\pm}0.13mm$, with $1.63{\pm}0.10mm$, if it is a variant of sudden breathing respective average $0.97{\pm}0.06mm$, $1.44{\pm}0.11mm$, and analyzed with $1.98{\pm}0.10mm$. The larger the correlation error values in both the both the respiratory form, the target error value is large. If the motion size of the target of the sine curve breathing form is greater than or equal to 20 mm, was measured at 1.5 mm or more is a recommendation value of both cyber knife manufacturer of both error value. Conclusion : There is a tendency that the correlation error value between about target error value magnitude of the target motion is large is increased, the error value becomes large in variation of rapid respiration than breathing the form of a sine curve. The more the shape of the breathing large movements regular shape of sine curves target accuracy of the tumor tracking system can be judged to be reduced. Using the algorithm of Cyber-Knife tumor tracking system, when there is a change in the sudden unpredictable respiratory due patient coughing during treatment enforcement is to stop the treatment, it is assumed to carry out the internal target validation process again, it is necessary to readjust the form of respiration. Patients under treatment is determined to be able to improve the treatment of accuracy to induce the observed form of regular breathing and put like to see the goggles monitor capable of the respiratory form of the person.

• Journal of Distribution Research
• /
• v.17 no.2
• /
• pp.1-28
• /
• 2012

I. Introduction : The purpose of this study is to test empirically hypothetical causality among constructs used in previous studies to build the model of relational market behavior on customers' participation and consumer-brand relationship after introducing theories of relationship marketing, loyalty program, consumer-brand relationship, customers' participation in service marketing as previous studies with regard to relational market behavior, which Bagozzi(1995) and Peterson(1995) commented on constructs and definition suggested by Sheth and Parvatiyar (1995). For this purpose, loyalty program by the service provider, customers' participation and consumer-brand relationship as preceding variables explain relational market behavior defined by Sheth and Parvatiyar(1995). This study proposes that loyalty program as a tool of relationship marketing will be effective in that consumers' participation in marketing relationship results in a narrow range of choice(Sheth and Parvatiyar, 1995) because consumers think that their participation motive result in benefits(Peterson, 1995). Also, it is proposed that the quality of consumer-brand relationship explain the performance of relationship as well as the intermediary effect because the loyalty program could be evaluated based on relationship with customers. We reviewed the variables with regard to performance of relationship based on relation maintain in marketing literature, and then tested our hypotheses related to several performance variables including loyalty and intention of relation maintain based on the previous studies and constructs(Bendapudi and Berry, 1997 ; Bettencourt, 1997 ; Palmatier, Dant, Grewal and Evans, 2006 ; You Jae Yi and Soo Jin Lee, 2006). II. Study Model : Analyses about hypothetical causality were proceeded. The marketing effect of loyalty program on relational market behavior was empirically tested in study regarding a service provider. The research model in according to the path hypotheses (loyalty program ${\rightarrow}$ customers' participation ${\rightarrow}$ consumer-brand relationship ${\rightarrow}$ relational market behavior and loyalty program ${\rightarrow}$ consumer-brand relationship, and loyalty program ${\rightarrow}$ relational market behavior and customers' participation ${\rightarrow}$ consumer-brand relationship, and customers' participation ${\rightarrow}$ relational market behavior) proceeded as an activity for customer relation management was suggested. The main purpose of study is to see if relational market behavior could be brought as a result of developing relationship between consumers and a corporate into being stronger and more valuable when a corporate or a service provider try aggressively to build the relationship with customers (Bettencourt, 1997; Palmatier, Dant, Grewal and Evans, 2006; Sheth and Parvatiyar, 1995). III. Conclusion : The results of research into the membership fitness club, one of service areas with high level of customer participation (Bitner, Faranda, Hubbert and Zeithaml, 1997; Chase, 1978; Kelley, Donnelly, Jr. and Skinner, 1990) are as follows: First, causalities in according to path hypotheses were tested, after the preceding variables affecting relational market behavior and conceptual frame were suggested. In study, all hypotheses were supported as expected. This result confirms the proposition suggested by Sheth and Parvatiyar(1995), who claimed that intention of consumer and corporate to participate in marketing relationship brings high level of marketing productivity. Also, as a corporate or a service provider try aggressively to build relationship with customers, the relationship between consumers and a corporate can be developed into stronger and more valuable one (Bettencourt, 1997; Palmatier, Dant, Grewal and Evans, 2006). This finding supports the logic of relationship marketing. Second, because the question regarding the path hypothesis of consumer-brand relationship ${\rightarrow}$ relational market behavior are still at issue, the further analyses were conducted. In particular, there existed the mediating effects of consumer-brand relationship toward relational market behavior. Also, multiple regressions were conducted to see if which one strongly influences relational market behavior among specific question items with regard to consumer-brand relationship. As a result, the influence between items composing consumer-brand relationship and ones composing relational market behavior was different. Among items composing consumer-brand relationship, intimacy was an influence of sustaining relationship, word of mouth, and recommendation, intimacy and interdependence were influences of loyalty, intimacy and self-connection were influences of tolerance and advice. Notably, commitment among items measuring consumer-brand relationship had the negative influence with relational market behavior. This means that bringing relational market behavior is not consumer-brand relationship without personal commitment, but effort to build customer relationship like intimacy, interdependence, and self-connection. This finding confirms the results of Breivik and Thorbjornsen(2008). They reported that six variables composing the quality of consumer-brand relationship have higher explanation in regression model directly affecting performance of consumer-brand relationship. As a result of empirical analysis, among the constructs with regard to consumer-brand relationship, intimacy(B=0.512), interdependence(B=0.196), and quality of partner(B=0.153) had the effects on relation maintain. On the contrary, self-connection, love and passion, and commitment had little effect and did not show the statistical significance(p<0.05). On the other hand, intimacy(B=0.668) and interdependence(B=0.181) had the high regression estimates on word of mouth and recommendation. Regarding the effect on loyalty, explanation level of the model was high(R2=0.515), intimacy(0.538), interdependence(0.223), and quality of partner(0.177) showed the statistical significance(p<0.05). Furthermore, intimacy(0.441) had the strong effect as well as self-connection(0.201) and interdependence (0.163) had the effect on tolerance and forgive. And these three variables showed effects even on advice and suggestion, intimacy(0.373), self-connection(0.270), interdependence (0.155) respectively. Third, in study with regard to the positive effect(loyalty program ${\rightarrow}$ customers' participation, loyalty program ${\rightarrow}$ consumer-brand relationship, loyalty program ${\rightarrow}$ relational market behavior, customers' participation ${\rightarrow}$ consumer-brand relationship, customers' participation ${\rightarrow}$ relational market behavior, consumer-brand relationship ${\rightarrow}$ relational market behavior), the path hypothesis of customers' participation ${\rightarrow}$ consumer-brand relationship, was supported. The fact that path hypothesis of customers' participation ${\rightarrow}$ consumer-brand relationship was supported confirms assertion by Bitner(1995), Fournier(1994), Sheth and Parvatiyar(1995) about consumer relationship to participate in marketing relationship.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.227-252
• /
• 2018

The evolution of instant communication has mirrored the development of the Internet and messenger applications are among the most representative manifestations of instant communication technologies. In messenger applications, senders use emoticons to supplement the emotions conveyed in the text of their messages. The fact that communication via messenger applications is not face-to-face makes it difficult for senders to communicate their emotions to message recipients. Emoticons have long been used as symbols that indicate the moods of speakers. However, at present, emoticon-use is evolving into a means of conveying the psychological states of consumers who want to express individual characteristics and personality quirks while communicating their emotions to others. The fact that companies like KakaoTalk, Line, Apple, etc. have begun conducting emoticon business and sales of related content are expected to gradually increase testifies to the significance of this phenomenon. Nevertheless, despite the development of emoticons themselves and the growth of the emoticon market, no suitable emoticon recommendation system has yet been developed. Even KakaoTalk, a messenger application that commands more than 90% of domestic market share in South Korea, just grouped in to popularity, most recent, or brief category. This means consumers face the inconvenience of constantly scrolling around to locate the emoticons they want. The creation of an emoticon recommendation system would improve consumer convenience and satisfaction and increase the sales revenue of companies the sell emoticons. To recommend appropriate emoticons, it is necessary to quantify the emotions that the consumer sees and emotions. Such quantification will enable us to analyze the characteristics and emotions felt by consumers who used similar emoticons, which, in turn, will facilitate our emoticon recommendations for consumers. One way to quantify emoticons use is metadata-ization. Metadata-ization is a means of structuring or organizing unstructured and semi-structured data to extract meaning. By structuring unstructured emoticon data through metadata-ization, we can easily classify emoticons based on the emotions consumers want to express. To determine emoticons' precise emotions, we had to consider sub-detail expressions-not only the seven common emotional adjectives but also the metaphorical expressions that appear only in South Korean proved by previous studies related to emotion focusing on the emoticon's characteristics. We therefore collected the sub-detail expressions of emotion based on the "Shape", "Color" and "Adumbration". Moreover, to design a highly accurate recommendation system, we considered both emotion-technical indexes and emoticon-emotional indexes. We then identified 14 features of emoticon-technical indexes and selected 36 emotional adjectives. The 36 emotional adjectives consisted of contrasting adjectives, which we reduced to 18, and we measured the 18 emotional adjectives using 40 emoticon sets randomly selected from the top-ranked emoticons in the KakaoTalk shop. We surveyed 277 consumers in their mid-twenties who had experience purchasing emoticons; we recruited them online and asked them to evaluate five different emoticon sets. After data acquisition, we conducted a factor analysis of emoticon-emotional factors. We extracted four factors that we named "Comic", Softness", "Modernity" and "Transparency". We analyzed both the relationship between indexes and consumer attitude and the relationship between emoticon-technical indexes and emoticon-emotional factors. Through this process, we confirmed that the emoticon-technical indexes did not directly affect consumer attitudes but had a mediating effect on consumer attitudes through emoticon-emotional factors. The results of the analysis revealed the mechanism consumers use to evaluate emoticons; the results also showed that consumers' emoticon-technical indexes affected emoticon-emotional factors and that the emoticon-emotional factors affected consumer satisfaction. We therefore designed the emoticon recommendation system using only four emoticon-emotional factors; we created a recommendation method to calculate the Euclidean distance from each factors' emotion. In an attempt to increase the accuracy of the emoticon recommendation system, we compared the emotional patterns of selected emoticons with the recommended emoticons. The emotional patterns corresponded in principle. We verified the emoticon recommendation system by testing prediction accuracy; the predictions were 81.02% accurate in the first result, 76.64% accurate in the second, and 81.63% accurate in the third. This study developed a methodology that can be used in various fields academically and practically. We expect that the novel emoticon recommendation system we designed will increase emoticon sales for companies who conduct business in this domain and make consumer experiences more convenient. In addition, this study served as an important first step in the development of an intelligent emoticon recommendation system. The emotional factors proposed in this study could be collected in an emotional library that could serve as an emotion index for evaluation when new emoticons are released. Moreover, by combining the accumulated emotional library with company sales data, sales information, and consumer data, companies could develop hybrid recommendation systems that would bolster convenience for consumers and serve as intellectual assets that companies could strategically deploy.