• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.19-38
• /
• 2017

Collaborative filtering (CF) algorithm has been popularly used for implementing recommender systems. Until now, there have been many prior studies to improve the accuracy of CF. Among them, some recent studies adopt 'hybrid recommendation approach', which enhances the performance of conventional CF by using additional information. In this research, we propose a new hybrid recommender system which fuses CF and the results from the social network analysis on trust and distrust relationship networks among users to enhance prediction accuracy. The proposed algorithm of our study is based on memory-based CF. But, when calculating the similarity between users in CF, our proposed algorithm considers not only the correlation of the users' numeric rating patterns, but also the users' in-degree centrality values derived from trust and distrust relationship networks. In specific, it is designed to amplify the similarity between a target user and his or her neighbor when the neighbor has higher in-degree centrality in the trust relationship network. Also, it attenuates the similarity between a target user and his or her neighbor when the neighbor has higher in-degree centrality in the distrust relationship network. Our proposed algorithm considers four (4) types of user relationships - direct trust, indirect trust, direct distrust, and indirect distrust - in total. And, it uses four adjusting coefficients, which adjusts the level of amplification / attenuation for in-degree centrality values derived from direct / indirect trust and distrust relationship networks. To determine optimal adjusting coefficients, genetic algorithms (GA) has been adopted. Under this background, we named our proposed algorithm as SNACF-GA (Social Network Analysis - based CF using GA). To validate the performance of the SNACF-GA, we used a real-world data set which is called 'Extended Epinions dataset' provided by 'trustlet.org'. It is the data set contains user responses (rating scores and reviews) after purchasing specific items (e.g. car, movie, music, book) as well as trust / distrust relationship information indicating whom to trust or distrust between users. The experimental system was basically developed using Microsoft Visual Basic for Applications (VBA), but we also used UCINET 6 for calculating the in-degree centrality of trust / distrust relationship networks. In addition, we used Palisade Software's Evolver, which is a commercial software implements genetic algorithm. To examine the effectiveness of our proposed system more precisely, we adopted two comparison models. The first comparison model is conventional CF. It only uses users' explicit numeric ratings when calculating the similarities between users. That is, it does not consider trust / distrust relationship between users at all. The second comparison model is SNACF (Social Network Analysis - based CF). SNACF differs from the proposed algorithm SNACF-GA in that it considers only direct trust / distrust relationships. It also does not use GA optimization. The performances of the proposed algorithm and comparison models were evaluated by using average MAE (mean absolute error). Experimental result showed that the optimal adjusting coefficients for direct trust, indirect trust, direct distrust, indirect distrust were 0, 1.4287, 1.5, 0.4615 each. This implies that distrust relationships between users are more important than trust ones in recommender systems. From the perspective of recommendation accuracy, SNACF-GA (Avg. MAE = 0.111943), the proposed algorithm which reflects both direct and indirect trust / distrust relationships information, was found to greatly outperform a conventional CF (Avg. MAE = 0.112638). Also, the algorithm showed better recommendation accuracy than the SNACF (Avg. MAE = 0.112209). To confirm whether these differences are statistically significant or not, we applied paired samples t-test. The results from the paired samples t-test presented that the difference between SNACF-GA and conventional CF was statistical significant at the 1% significance level, and the difference between SNACF-GA and SNACF was statistical significant at the 5%. Our study found that the trust/distrust relationship can be important information for improving performance of recommendation algorithms. Especially, distrust relationship information was found to have a greater impact on the performance improvement of CF. This implies that we need to have more attention on distrust (negative) relationships rather than trust (positive) ones when tracking and managing social relationships between users.

• The Korean Journal of Financial Management
• /
• v.27 no.2
• /
• pp.169-204
• /
• 2010

This paper examines the dynamic relationship between fund flow and market risk at the aggregate level and explores whether sudden sharp changes in fund flow (fund run) can cause a systemic risk in the Korean financial markets. We use daily and weekly data and regression and VAR analysis. Main results of the paper are as follows: First, in the stock market, a concurrent and a lagged unexpected fund flows have a positive relationship with market volatility. A positive shock in fund flow predicts an increase in stock market volatility. In the bond market, an unexpected fund flow has a negative relationship with the default risk premium, but a positive relationship with the term premium. And an unexpected fund flow of the money market fund has a negative relationship with the liquidy risk, but the explanatory power is very low. Second, for examining whether changes in fund flow induce a systemic risk, we construct a spillover index based on the forecast error variance decomposition of VAR model. A spillover index represents that how much the shock in fund flow can explain the change of market risk in a market. In general, explanatory powers from spillover indexes are so fluctuant and low. In the stock market, the impact of shocks in fund flow on market risk is relatively high and persistent during the period from the end of 2007 to 2008, which is the subprime-mortgage crisis period. In bond market, since the end of 2008, the impact of shocks in fund flow spreads to default risk continually, while in the money market, such a systematic effect doesn't take place. The persistent patterns of spillover effect appearing around a certain period in the stock market and the bond market suggest that the shock to the unexpected fund flow may increase the market risk and can be a cause of systemic risk in the financial markets. However, summarizing the results of regression and VAR model analysis, and considering the very low explanatory power of spillover index analysis, we can conclude that changes in fund flow have a very limited power in explaining changes in market risk and it is not very likely to induce the systemic risk by a fund run in the Korean financial markets.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.1-23
• /
• 2014

Market forecasting aims to estimate the sales volume of a product or service that is sold to consumers for a specific selling period. From the perspective of the enterprise, accurate market forecasting assists in determining the timing of new product introduction, product design, and establishing production plans and marketing strategies that enable a more efficient decision-making process. Moreover, accurate market forecasting enables governments to efficiently establish a national budget organization. This study aims to generate a market growth curve for ICT (information and communication technology) goods using past time series data; categorize products showing similar growth patterns; understand markets in the industry; and forecast the future outlook of such products. This study suggests the useful and meaningful process (or methodology) to identify the market growth pattern with quantitative growth model and data mining algorithm. The study employs the following methodology. At the first stage, past time series data are collected based on the target products or services of categorized industry. The data, such as the volume of sales and domestic consumption for a specific product or service, are collected from the relevant government ministry, the National Statistical Office, and other relevant government organizations. For collected data that may not be analyzed due to the lack of past data and the alteration of code names, data pre-processing work should be performed. At the second stage of this process, an optimal model for market forecasting should be selected. This model can be varied on the basis of the characteristics of each categorized industry. As this study is focused on the ICT industry, which has more frequent new technology appearances resulting in changes of the market structure, Logistic model, Gompertz model, and Bass model are selected. A hybrid model that combines different models can also be considered. The hybrid model considered for use in this study analyzes the size of the market potential through the Logistic and Gompertz models, and then the figures are used for the Bass model. The third stage of this process is to evaluate which model most accurately explains the data. In order to do this, the parameter should be estimated on the basis of the collected past time series data to generate the models' predictive value and calculate the root-mean squared error (RMSE). The model that shows the lowest average RMSE value for every product type is considered as the best model. At the fourth stage of this process, based on the estimated parameter value generated by the best model, a market growth pattern map is constructed with self-organizing map algorithm. A self-organizing map is learning with market pattern parameters for all products or services as input data, and the products or services are organized into an $N{\times}N$ map. The number of clusters increase from 2 to M, depending on the characteristics of the nodes on the map. The clusters are divided into zones, and the clusters with the ability to provide the most meaningful explanation are selected. Based on the final selection of clusters, the boundaries between the nodes are selected and, ultimately, the market growth pattern map is completed. The last step is to determine the final characteristics of the clusters as well as the market growth curve. The average of the market growth pattern parameters in the clusters is taken to be a representative figure. Using this figure, a growth curve is drawn for each cluster, and their characteristics are analyzed. Also, taking into consideration the product types in each cluster, their characteristics can be qualitatively generated. We expect that the process and system that this paper suggests can be used as a tool for forecasting demand in the ICT and other industries.

• Journal of Korean Society of Transportation
• /
• v.34 no.5
• /
• pp.437-448
• /
• 2016

Some previous researches suggested a transit trip destination inference method by constructing trip chains with incomplete(missing destination) smart card dataset obtained on the entry fare control systems. To explore the feasibility of the transit trip destination inference method, the transit trip chains are constructed from the pre-paid smart card tagging data collected in Busan on October 2014 weekdays by tracing the card IDs, tagging times(boarding, alighting, transfer), and the trip linking distances between two consecutive transit trips in a daily sequences. Assuming that most trips in the transit trip chains are linked successively, the individual transit trip destination zones are inferred as the consecutive linking trip's origin zones. Applying the model to the complete trips with observed OD reveals that about 82% of the inferred trip destinations are the same as those of the observed trip destinations and the inference error defined as the difference in distance between the inferred and observed alighting stops is minimized when the trip linking distance is less than or equal to 0.5km. When applying the model to the incomplete trips with missing destinations, the overall destination missing rate decreases from 71.40% to 21.74% and approximately 77% of the destination missing trips are the single transit trips for which the destinations can not be inferable. In addition, the model remarkably reduces the destination missing rate of the multiple incomplete transit trips from 69.56% to 6.27%. Spearman's rank correlation and Chi-squared goodness-of-fit tests showed that the ranks for transit trips of each zone are not significantly affected by the inferred trips, but the transit trip distributions only using small complete trips are significantly different from those using complete and inferred trips. Therefore, it is concluded that the model should be applicable to derive a realistic transit trip patterns in cities with the incomplete smart card data.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.17 no.4
• /
• pp.384-398
• /
• 2015

In this paper, the high-resolution Weather Research and Forecasting/Noah-MultiParameterization (WRF/Noah-MP) modeling system is configured for the Cheongmicheon Farmland site in Korea (CFK), and its performance in land and atmospheric simulation is evaluated using the observed data at CFK during the 2014 special observation period (21 August-10 September). In order to explore the usefulness of turning on Noah-MP dynamic vegetation in midterm simulations of surface and atmospheric variables, two numerical experiments are conducted without dynamic vegetation and with dynamic vegetation (referred to as CTL and DVG experiments, respectively). The main results are as following. 1) CTL showed a tendency of overestimating daytime net shortwave radiation, thereby surface heat fluxes and Bowen ratio. The CTL experiment showed reasonable magnitudes and timing of air temperature at 2 m and 10 m; especially the small error in simulating minimum air temperature showed high potential for predicting frost and leaf wetness duration. The CTL experiment overestimated 10-m wind and precipitation, but the beginning and ending time of precipitation were well captured. 2) When the dynamic vegetation was turned on, the WRF/Noah-MP system showed more realistic values of leaf area index (LAI), net shortwave radiation, surface heat fluxes, Bowen ratio, air temperature, wind and precipitation. The DVG experiment, where LAI is a prognostic variable, produced larger LAI than CTL, and the larger LAI showed better agreement with the observed. The simulated Bowen ratio got closer to the observed ratio, indicating reasonable surface energy partition. The DVG experiment showed patterns similar to CTL, with differences for maximum air temperature. Both experiments showed faster rising of 10-m air temperature during the morning growth hours, presumably due to the rapid growth of daytime mixed layers in the Yonsei University (YSU) boundary layer scheme. The DVG experiment decreased errors in simulating 10-m wind and precipitation. 3) As horizontal resolution increases, the models did not show practical improvement in simulation performance for surface fluxes, air temperature, wind and precipitation, and required three-dimensional observation for more agricultural land spots as well as consistency in model topography and land cover data.

• The Journal of Korean Society for Radiation Therapy
• /
• v.28 no.2
• /
• pp.149-159
• /
• 2016

Purpose : To evaluate the usefulness of the breathing exercise,we analyzed the change in the RPM signal and the diaphragm imagebefore 4D respiratory gated radiation therapy planning of lung cancer patients. Materials and Methods : The breathing training was enforced on 11 patients getting the 4D respiratory gated radiation therapy from April, 2016 until August. At the same time, RPM signal and diaphragm image was obtained respiration training total three steps in step 1 signal acquisition of free-breathing state, 2 steps respiratory signal acquisition through the guide of the respiratory signal, 3 steps, won the regular respiration signal to the description and repeat training. And then, acquired the minimum value, maximum value, average value, and a standard deviation of the inspiration and expiration in RPM signal and diaphragm image in each steps. Were normalized by the value of the step 1, to convert the 2,3 steps to the other distribution ratio (%), by evaluating the change in the interior of the respiratory motion of the patient, it was evaluated breathing exercise usefulness of each patient. Results : The mean value and the standard deviation of each step were obtained with the procedure 1 of the RPM signal and the diaphragm amplitude as a 100% reference. In the RPM signal, the amplitudes and standard deviations of four patients (36.4%, eleven) decreased by 18.1%, 27.6% on average in 3 steps, and 2 patients (18.2%, 11 people) had standard deviation, It decreased by an average of 36.5%. Meanwhile, the other four patients (36.4%, eleven) decreased by an average of only amplitude 13.1%. In Step 3, the amplitude of the diaphragm image decreased by 30% on average of 9 patients (81.8%, 11 people), and the average of 2 patients (18.2%, 11 people) increased by 7.3%. However, the amplitudes of RPM signals and diaphragm image in 3steps were reduced by 52.6% and 42.1% on average from all patients, respectively, compared to the 2 steps. Relationship between RPM signal and diaphragm image amplitude difference was consistent with patterns of movement 1, 2 and 3steps, respectively, except for No. 2 No. 10 patients. Conclusion : It is possible to induce an optimized respiratory cycle when respiratory training is done. By conducting respiratory training before treatment, it was possible to expect the effect of predicting the movement of the lung which could control the patient's respiration. Ultimately, it can be said that breathing exercises are useful because it is possible to minimize the systematic error of radiotherapy, expect more accurate treatment. In this study, it is limited to research analyzed based on data on respiratory training before treatment, and it will be necessary to verify with the actual CT plan and the data acquired during treatment in the future.

• Journal of Food Hygiene and Safety
• /
• v.32 no.3
• /
• pp.206-210
• /
• 2017

This study was performed to develope mathematical models for predicting growth kinetics of Staphylococcus aureus in the processed meat product, pyeonyuk. Growth patterns of S. aureus in pyeonyuk were determined at the storage temperatures of 4, 10, 20, and $37^{\circ}C$ respectively. The number of S. aureus in pyeonyuk increased at all the storage temperatures. The maximum specific growth rate (${\mu}_{max}$) and lag phase duration (LPD) values were calculated by Baranyi model. The ${\mu}_{max}$ values went up, while the LPD values decreased as the storage temperature increased from $4^{\circ}C$ to $37^{\circ}C$. Square root model and polynomial model were used to develop the secondary models for ${\mu}_{max}$ and LPD, respectively. Root Mean Square Error (RMSE) was used to evaluate the developed model and the fitness was determind to be 0.42. Therefore the developed predictive model was useful to predict the growth of S. aureus in pyeonyuk and it will help to prevent food-born disease by expanding for microbial sanitary management guide.

• Journal of Radiation Protection and Research
• /
• v.20 no.1
• /
• pp.45-52
• /
• 1995

This study is to compare A point doses in human pelvic phantom by film dosimetry, computer planning and manual calculation by using of along-away table. We developed tissue equivalent human pelvic phantom composed of four pieces of cylindrical acryl tubes with water, to simulate intracavitary radiation (ICR) in patients with cervix cancer. When the phantom assembled from 4 pieces, it has a small space for inserting Fletcher-Suit-Delclos applicator like a human vagina. Fletcher-Suit-Delclos applicator inserted into the space was packed tightly with furacin gauzes, and three $^{137}Cs$ sources with radioactivity of $15.7mg\;Ra-eq$ were inserted into the tandem. For the film dosimetry, two pieces of X-OMAT V film (Kodak Co.) of which planes include point A, were arranged orthogonally in the slits between phantoms. A point dose and iso-dose curves were measured by means of optical densitometer. A point doses by film dosimetry, RTP system and manual calculation by using of along-away table were compared, and iso-dose curves by film dosimetry and computer planning were also compared. The dose of A point was 51.2cGy/hr by film dosimetry, 46.7cGy/hr by RTP system and 47.9 cGy/hr by along-away table. A point dose by computer planning was similar to the dose by calculation using of along-away table with acceptable accuracy $({\pm}3%)$, however, the dose by film dosimetry was different from two others with about 10% error. Since most clinical beams contains a scatter component of low energy photons, the correlation between optical density and dose becomes tenuous. In addition, film suffers from several potential errors such as changes in processing conditions, interfilm emulsion differences, and artifacts caused by air pockets adjacent to the film. For these reasons, absolute dosimetry with film is impractical, however, it is very useful for checking qualitative patterns of a radiation distribution. In future, solid state dosimeter such as TLD must be used for the dosimetry of ionizing radiation. When considerable care is used, precision of approximately 3% may be obtained using TLD.

• Progress in Medical Physics
• /
• v.20 no.3
• /
• pp.132-138
• /
• 2009

Studies on target motion in 4-dimensional radiotherapy are being world-widely conducted to enhance treatment record and protection of normal organs. Prediction of tumor motion might be very useful and/or essential for especially free-breathing system during radiation delivery such as respiratory gating system and tumor tracking system. Neural network is powerful to express a time series with nonlinearity because its prediction algorithm is not governed by statistic formula but finds a rule of data expression. This study intended to assess applicability of neural network method to predict tumor motion in 4-dimensional radiotherapy. Scaled Conjugate Gradient algorithm was employed as a learning algorithm. Considering reparation data for 10 patients, prediction by the neural network algorithms was compared with the measurement by the real-time position management (RPM) system. The results showed that the neural network algorithm has the excellent accuracy of maximum absolute error smaller than 3 mm, except for the cases in which the maximum amplitude of respiration is over the range of respiration used in the learning process of neural network. It indicates the insufficient learning of the neural network for extrapolation. The problem could be solved by acquiring a full range of respiration before learning procedure. Further works are programmed to verify a feasibility of practical application for 4-dimensional treatment system, including prediction performance according to various system latency and irregular patterns of respiration.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.5
• /
• pp.338-343
• /
• 2004

Purpose: The purpose of this study was to develop a small animal PET using dual layer phoswich detector to minimize parallax error that degrades spatial resolution at the outer part of field-of-view (FOV). Materials and Methods: A simulation tool GATE (Geant4 Application for Tomographic Emission) was used to derive optimal parameters of small PET, and PET was developed employing the parameters. Lutetium Oxyorthosilicate (LSO) and Lutetium-Yttrium Aluminate-Perovskite(LuYAP) was used to construct dual layer phoswitch crystal. $8{\times}8$ arrays of LSO and LuYAP pixels, $2mm{\times}2mm{\times}8mm$ in size, were coupled to a 64-channel position sensitive photomultiplier tube. The system consisted of 16 detector modules arranged to one ring configuration (ring inner diameter 10 cm, FOV of 8 cm). The data from phoswich detector modules were fed into an ADC board in the data acquisition and preprocessing PC via sockets, decoder block, FPGA board, and bus board. These were linked to the master PC that stored the events data on hard disk. Results: In a preliminary test of the system, reconstructed images were obtained by using a pair of detectors and sensitivity and spatial resolution were measured. Spatial resolution was 2.3 mm FWHM and sensitivity was 10.9 $cps/{\mu}Ci$ at the center of FOV. Conclusion: The radioactivity distribution patterns were accurately represented in sinograms and images obtained by PET with a pair of detectors. These preliminary results indicate that it is promising to develop a high performance small animal PET.