• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.27-42
• /
• 2020

Traditional companies with offline stores were unable to secure large display space due to the problems of cost. This limitation inevitably allowed limited kinds of products to be displayed on the shelves, which resulted in consumers being deprived of the opportunity to experience various items. Taking advantage of the virtual space called the Internet, online shopping goes beyond the limits of limitations in physical space of offline shopping and is now able to display numerous products on web pages that can satisfy consumers with a variety of needs. Paradoxically, however, this can also cause consumers to experience the difficulty of comparing and evaluating too many alternatives in their purchase decision-making process. As an effort to address this side effect, various kinds of consumer's purchase decision support systems have been studied, such as keyword-based item search service and recommender systems. These systems can reduce search time for items, prevent consumer from leaving while browsing, and contribute to the seller's increased sales. Among those systems, recommender systems based on association rule mining techniques can effectively detect interrelated products from transaction data such as orders. The association between products obtained by statistical analysis provides clues to predicting how interested consumers will be in another product. However, since its algorithm is based on the number of transactions, products not sold enough so far in the early days of launch may not be included in the list of recommendations even though they are highly likely to be sold. Such missing items may not have sufficient opportunities to be exposed to consumers to record sufficient sales, and then fall into a vicious cycle of a vicious cycle of declining sales and omission in the recommendation list. This situation is an inevitable outcome in situations in which recommendations are made based on past transaction histories, rather than on determining potential future sales possibilities. This study started with the idea that reflecting the means by which this potential possibility can be identified indirectly would help to select highly recommended products. In the light of the fact that the attributes of a product affect the consumer's purchasing decisions, this study was conducted to reflect them in the recommender systems. In other words, consumers who visit a product page have shown interest in the attributes of the product and would be also interested in other products with the same attributes. On such assumption, based on these attributes, the recommender system can select recommended products that can show a higher acceptance rate. Given that a category is one of the main attributes of a product, it can be a good indicator of not only direct associations between two items but also potential associations that have yet to be revealed. Based on this idea, the study devised a recommender system that reflects not only associations between products but also categories. Through regression analysis, two kinds of associations were combined to form a model that could predict the hit rate of recommendation. To evaluate the performance of the proposed model, another regression model was also developed based only on associations between products. Comparative experiments were designed to be similar to the environment in which products are actually recommended in online shopping malls. First, the association rules for all possible combinations of antecedent and consequent items were generated from the order data. Then, hit rates for each of the associated rules were predicted from the support and confidence that are calculated by each of the models. The comparative experiments using order data collected from an online shopping mall show that the recommendation accuracy can be improved by further reflecting not only the association between products but also categories in the recommendation of related products. The proposed model showed a 2 to 3 percent improvement in hit rates compared to the existing model. From a practical point of view, it is expected to have a positive effect on improving consumers' purchasing satisfaction and increasing sellers' sales.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.175-196
• /
• 2022

Information and communication and home appliance industries, which were one of South Korea's main industries, are gradually losing their export share as their export competitiveness is weakening. This study objectively analyzed export competitiveness and suggested export-promising countries in order to help South Korea's information communication and home appliance industries improve exports. In this study, network properties, centrality, and structural hole analysis were performed during network analysis to evaluate export competitiveness. In order to select promising export countries, we proposed a new variable that can take into account the characteristics of an already established International Trade Network (ITN), that is, the Global Value Chain (GVC), in addition to the existing economic factors. The conditional log-odds for individual links derived from the Exponential Random Graph Model (ERGM) in the analysis of the cross-border trade network were assumed as a proxy variable that can indicate the export potential. In consideration of the possibility of ERGM linkage, a parametric approach and a non-parametric approach were used to recommend export-promising countries, respectively. In the parametric method, a regression analysis model was developed to predict the export value of the information and communication and home appliance industries in South Korea by additionally considering the link-specific characteristics of the network derived from the ERGM to the existing economic factors. Also, in the non-parametric approach, an abnormality detection algorithm based on the clustering method was used, and a promising export country was proposed as a method of finding outliers that deviate from two peers. According to the research results, the structural characteristic of the export network of the industry was a network with high transferability. Also, according to the centrality analysis result, South Korea's influence on exports was weak compared to its size, and the structural hole analysis result showed that export efficiency was weak. According to the model for recommending promising exporting countries proposed by this study, in parametric analysis, Iran, Ireland, North Macedonia, Angola, and Pakistan were promising exporting countries, and in nonparametric analysis, Qatar, Luxembourg, Ireland, North Macedonia and Pakistan were analyzed as promising exporting countries. There were differences in some countries in the two models. The results of this study revealed that the export competitiveness of South Korea's information and communication and home appliance industries in GVC was not high compared to the size of exports, and thus showed that exports could be further reduced. In addition, this study is meaningful in that it proposed a method to find promising export countries by considering GVC networks with other countries as a way to increase export competitiveness. This study showed that, from a policy point of view, the international trade network of the information communication and home appliance industries has an important mutual relationship, and although transferability is high, it may not be easily expanded to a three-party relationship. In addition, it was confirmed that South Korea's export competitiveness or status was lower than the export size ranking. This paper suggested that in order to improve the low out-degree centrality, it is necessary to increase exports to Italy or Poland, which had significantly higher in-degrees. In addition, we argued that in order to improve the centrality of out-closeness, it is necessary to increase exports to countries with particularly high in-closeness. In particular, it was analyzed that Morocco, UAE, Argentina, Russia, and Canada should pay attention as export countries. This study also provided practical implications for companies expecting to expand exports. The results of this study argue that companies expecting export expansion need to pay attention to countries with a relatively high potential for export expansion compared to the existing export volume by country. In particular, for companies that export daily necessities, countries that should pay attention to the population are presented, and for companies that export high-end or durable products, countries with high GDP, or purchasing power, relatively low exports are presented. Since the process and results of this study can be easily extended and applied to other industries, it is also expected to develop services that utilize the results of this study in the public sector.

• Korean Journal of Environment and Ecology
• /
• v.32 no.5
• /
• pp.469-477
• /
• 2018

Hanabusaya asiatica is an endemic species whose distribution is limited in the mid-eastern part of the Korean peninsula. Due to its narrow range and small population, it is necessary to protect its habitats by identifying it as Key Biodiversity Areas (KBAs) adopted by the International Union for Conservation of Nature (IUCN). In this paper, we estimated potential natural habitats for H. asiatica using maximum entropy model (MaxEnt) and identified candidate sites for KBA based on the model results. MaxEnt is a machine learning algorithm that can predict habitats for species of interest unbiasedly with presence-only data. This property is particularly useful for the study area where data collection via a field survey is unavailable. We trained MaxEnt using 38 locations of H. asiatica and 11 environmental variables that measured climate, topography, and vegetation status of the study area which encompassed all locations of the border region between South and North Korea. Results showed that the potential habitats where the occurrence probabilities of H. asiatica exceeded 0.5 were $778km^2$, and the KBA candidate area identified by taking into account existing protected areas was $1,321km^2$. Of 11 environmental variables, elevation, annual average precipitation, average precipitation in growing seasons, and the average temperature in the coldest month had impacts on habitat selection, indicating that H. asiatica prefers cool regions at a relatively high elevation. These results can be used not only for identifying KBAs but also for the reference to a protection plan for H. asiatica in preparation of Korean reunification and climate change.

• Progress in Medical Physics
• /
• v.20 no.4
• /
• pp.269-276
• /
• 2009

Radiation treatment techniques using photon beam such as three-dimensional conformal radiation therapy (3D-CRT) as well as intensity modulated radiotherapy treatment (IMRT) demand accurate dose calculation in order to increase target coverage and spare healthy tissue. Both jaw collimator and multi-leaf collimators (MLCs) for photon beams have been used to achieve such goals. In the Pinnacle3 treatment planning system (TPS), which we are using in our clinics, a set of model parameters like jaw collimator transmission factor (JTF) and MLC transmission factor (MLCTF) are determined from the measured data because it is using a model-based photon dose algorithm. However, model parameters obtained by this auto-modeling process can be different from those by direct measurement, which can have a dosimetric effect on the dose distribution. In this paper we estimated JTF and MLCTF obtained by the auto-modeling process in the Pinnacle3 TPS. At first, we obtained JTF and MLCTF by direct measurement, which were the ratio of the output at the reference depth under the closed jaw collimator (MLCs for MLCTF) to that at the same depth with the field size $10{\times}10\;cm^2$ in the water phantom. And then JTF and MLCTF were also obtained by auto-modeling process. And we evaluated the dose difference through phantom and patient study in the 3D-CRT plan. For direct measurement, JTF was 0.001966 for 6 MV and 0.002971 for 10 MV, and MLCTF was 0.01657 for 6 MV and 0.01925 for 10 MV. On the other hand, for auto-modeling process, JTF was 0.001983 for 6 MV and 0.010431 for 10 MV, and MLCTF was 0.00188 for 6 MV and 0.00453 for 10 MV. JTF and MLCTF by direct measurement were very different from those by auto-modeling process and even more reasonable considering each beam quality of 6 MV and 10 MV. These different parameters affect the dose in the low-dose region. Since the wrong estimation of JTF and MLCTF can lead some dosimetric error, comparison of direct measurement and auto-modeling of JTF and MLCTF would be helpful during the beam commissioning.

• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.193-206
• /
• 2017

In this paper, we propose a rate control method based on the $R-{\lambda}$ model that supports a parallel encoding structure in GOP levels or IDR period levels for 4K UHD input video in real-time. For this, a slice-level bit allocation method is proposed for parallel encoding instead of sequential encoding. When a rate control algorithm is applied in the GOP level or IDR period level parallelism, the information of how many bits are consumed cannot be shared among the frames belonging to a same frame level except the lowest frame level of the hierarchical B structure. Therefore, it is impossible to manage the bit budget with the existing bit allocation method. In order to solve this problem, we improve the bit allocation procedure of the conventional ones that allocate target bits sequentially according to the encoding order. That is, the proposed bit allocation strategy is to assign the target bits in GOPs first, then to distribute the assigned target bits from the lowest depth level to the highest depth level of the HEVC hierarchical B structure within each GOP. In addition, we proposed a processing method that is used to improve subjective image qualities by allocating the bits according to the coding complexities of the frames. Experimental results show that the proposed bit allocation method works well for frame-level parallel HEVC software encoders and it is confirmed that the performance of our rate controller can be improved with a more elaborate bit allocation strategy by using the preprocessing results.

• Tunnel and Underground Space
• /
• v.30 no.4
• /
• pp.320-334
• /
• 2020

This study presents an application of hydro-mechanical coupled Particle Flow Code 3D (PFC3D) to simulation of fluid injection induced fault slip experiment conducted in Mont Terri Switzerland as a part of a task in an international research project DECOVALEX-2019. We also aimed as identifying the current limitations of the modelling method and issues for further development. A fluid flow algorithm was developed and implemented in a 3D pore-pipe network model in a 3D bonded particle assembly using PFC3D v5, and was applied to Mont Terri Step 2 minor fault activation experiment. The simulated results showed that the injected fluid migrates through the permeable fault zone and induces fault deformation, demonstrating a full hydro-mechanical coupled behavior. The simulated results were, however, partially matching with the field measurement. The simulated pressure build-up at the monitoring location showed linear and progressive increase, whereas the field measurement showed an abrupt increase associated with the fault slip We conclude that such difference between the modelling and the field test is due to the structure of the fault in the model which was represented as a combination of damage zone and core fractures. The modelled fault is likely larger in size than the real fault in Mont Terri site. Therefore, the modelled fault allows several path ways of fluid flow from the injection location to the pressure monitoring location, leading to smooth pressure build-up at the monitoring location while the injection pressure increases, and an early start of pressure decay even before the injection pressure reaches the maximum. We also conclude that the clay filling in the real fault could have acted as a fluid barrier which may have resulted in formation of fluid over-pressurization locally in the fault. Unlike the pressure result, the simulated fault deformations were matching with the field measurements. A better way of modelling a heterogeneous clay-filled fault structure with a narrow zone should be studied further to improve the applicability of the modelling method to fluid injection induced fault activation.

• Management & Information Systems Review
• /
• v.39 no.3
• /
• pp.1-16
• /
• 2020

The current tariff return system requires tax officials to calculate tax amount by themselves and pay the tax amount on their own responsibility. In other words, in principle, the duty and responsibility of reporting payment system are imposed only on the taxee who is required to calculate and pay the tax accurately. In case the tax payment system fails to fulfill the duty and responsibility, the additional tax is imposed on the taxee by collecting the tax shortfall and imposing the tax deduction on For this reason, item classifications, together with tariff assessments, are the most difficult and could pose a significant risk to entities if they are misclassified. For this reason, import reports are consigned to customs officials, who are customs experts, while paying a substantial fee. The purpose of this study is to classify HS items to be reported upon import declaration and to indicate HS codes to be recorded on import declaration. HS items were classified using the attached image in the case of item classification based on the case of the classification of items by the Korea Customs Service for classification of HS items. For image classification, CNN was used as a deep learning algorithm commonly used for image recognition and Vgg16, Vgg19, ResNet50 and Inception-V3 models were used among CNN models. To improve classification accuracy, two datasets were created. Dataset1 selected five types with the most HS code images, and Dataset2 was tested by dividing them into five types with 87 Chapter, the most among HS code 2 units. The classification accuracy was highest when HS item classification was performed by learning with dual database2, the corresponding model was Inception-V3, and the ResNet50 had the lowest classification accuracy. The study identified the possibility of HS item classification based on the first item image registered in the item classification determination case, and the second point of this study is that HS item classification, which has not been attempted before, was attempted through the CNN model.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1117-1132
• /
• 2019

Forest covers 30% of the Earth's land area and plays an important role in global carbon flux through its ability to store much greater amounts of carbon than other terrestrial ecosystems. The Gross Primary Production (GPP) represents the productivity of forest ecosystems according to climate change and its effect on the phenology, health, and carbon cycle. In this study, we estimated the daily GPP for a forest ecosystem using remote-sensed data from Moderate Resolution Imaging Spectroradiometer (MODIS) and machine learning algorithms Support Vector Machine (SVM). MODIS products were employed to train the SVM model from 75% to 80% data of the total study period and validated using eddy covariance measurement (EC) data at the six flux tower sites. We also compare the GPP derived from EC and MODIS (MYD17). The MODIS products made use of two data sets: one for Processed MODIS that included calculated by combined products (e.g., Vapor Pressure Deficit), another one for Unprocessed MODIS that used MODIS products without any combined calculation. Statistical analyses, including Pearson correlation coefficient (R), mean squared error (MSE), and root mean square error (RMSE) were used to evaluate the outcomes of the model. In general, the SVM model trained by the Unprocessed MODIS (R = 0.77 - 0.94, p < 0.001) derived from the multi-sites outperformed those trained at a single-site (R = 0.75 - 0.95, p < 0.001). These results show better performance trained by the data including various events and suggest the possibility of using remote-sensed data without complex processes to estimate GPP such as non-stationary ecological processes.

• Korean Journal of Remote Sensing
• /
• v.24 no.2
• /
• pp.189-194
• /
• 2008

Middle-infrared (MIR) spectral region between 3.0 and $5.0\;{\mu}m$ in wavelength is useful for observing high temperature events such as volcanic activities and forest fire. However, atmospheric effects and sun irradiance in day time has not been well studied for this MIR spectral band. The objectives of this basic study is to evaluate atmospheric effects and eventually to estimate surface temperature from a single channel MIR image, although a typical approach utilize split-window method using more than two channels. Several parameters are involved for the correction including various atmospheric data and sun-irradiance at the area of interest. To evaluate the effect of sun irradiance, MODIS MIR images acquired in day and night times were used for comparison. Atmospheric parameters were modeled by MODTRAN, and applied to a radiative transfer model for estimating the sea surface temperature. MODIS Sea Surface Temperature algorithm based upon multi-channel observation was performed in comparison with results from the radiative transfer model from a single channel. Temperature difference of the two methods was $0.89{\pm}0.54^{\circ}C$ and $1.25{\pm}0.41^{\circ}C$ from the day-time and night-time images, respectively. It is also shown that the emissivity effect has by more largely influenced on the estimated temperature than atmospheric effects. Although the test results encourage using a single channel MR observation, it must be noted that the results were obtained from water body not from land surface. Because emissivity greatly varies on land, it is very difficult to retrieval land surface temperature from a single channel MIR data.