• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.139-157
• /
• 2016

Bankruptcy involves considerable costs, so it can have significant effects on a country's economy. Thus, bankruptcy prediction is an important issue. Over the past several decades, many researchers have addressed topics associated with bankruptcy prediction. Early research on bankruptcy prediction employed conventional statistical methods such as univariate analysis, discriminant analysis, multiple regression, and logistic regression. Later on, many studies began utilizing artificial intelligence techniques such as inductive learning, neural networks, and case-based reasoning. Currently, ensemble models are being utilized to enhance the accuracy of bankruptcy prediction. Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving the generalization ability of the classifier. Base classifiers in the ensemble must be as accurate and diverse as possible in order to enhance the generalization ability of an ensemble model. Commonly used methods for constructing ensemble classifiers include bagging, boosting, and random subspace. The random subspace method selects a random feature subset for each classifier from the original feature space to diversify the base classifiers of an ensemble. Each ensemble member is trained by a randomly chosen feature subspace from the original feature set, and predictions from each ensemble member are combined by an aggregation method. The k-nearest neighbors (KNN) classifier is robust with respect to variations in the dataset but is very sensitive to changes in the feature space. For this reason, KNN is a good classifier for the random subspace method. The KNN random subspace ensemble model has been shown to be very effective for improving an individual KNN model. The k parameter of KNN base classifiers and selected feature subsets for base classifiers play an important role in determining the performance of the KNN ensemble model. However, few studies have focused on optimizing the k parameter and feature subsets of base classifiers in the ensemble. This study proposed a new ensemble method that improves upon the performance KNN ensemble model by optimizing both k parameters and feature subsets of base classifiers. A genetic algorithm was used to optimize the KNN ensemble model and improve the prediction accuracy of the ensemble model. The proposed model was applied to a bankruptcy prediction problem by using a real dataset from Korean companies. The research data included 1800 externally non-audited firms that filed for bankruptcy (900 cases) or non-bankruptcy (900 cases). Initially, the dataset consisted of 134 financial ratios. Prior to the experiments, 75 financial ratios were selected based on an independent sample t-test of each financial ratio as an input variable and bankruptcy or non-bankruptcy as an output variable. Of these, 24 financial ratios were selected by using a logistic regression backward feature selection method. The complete dataset was separated into two parts: training and validation. The training dataset was further divided into two portions: one for the training model and the other to avoid overfitting. The prediction accuracy against this dataset was used to determine the fitness value in order to avoid overfitting. The validation dataset was used to evaluate the effectiveness of the final model. A 10-fold cross-validation was implemented to compare the performances of the proposed model and other models. To evaluate the effectiveness of the proposed model, the classification accuracy of the proposed model was compared with that of other models. The Q-statistic values and average classification accuracies of base classifiers were investigated. The experimental results showed that the proposed model outperformed other models, such as the single model and random subspace ensemble model.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.20 no.1
• /
• pp.1-15
• /
• 2015

Impacts of Sea Surface Temperature (SST) assimilation to the prediction of upper ocean temperature is investigated by using a regional ocean forecasting system, in which 3-dimensional optimal interpolation is applied. In the present study, Sea Surface Temperature and Sea Ice Analysis (OSTIA) dataset is adopted for the daily SST assimilation. This study mainly compares two experimental results with (Exp. DA) and without data assimilation (Exp. NoDA). When comparing both results with OSTIA SST data during Sept. 2011, Exp. NoDA shows Root Mean Square Error (RMSE) of about $1.5^{\circ}C$ at 24, 48, 72 forecast hour. On the other hand, Exp. DA yields the relatively lower RMSE of below $0.8^{\circ}C$ at all forecast hour. In particular, RMSE from Exp. DA reaches $0.57^{\circ}C$ at 24 forecast hour, indicating that the assimilation of daily SST (i.e., OSTIA) improves the performance in the early SST prediction. Furthermore, reduction ratio of RMSE in the Exp. DA reaches over 60% in the Yellow and East seas. In order to examine impacts in the shallow costal region, the SST measured by eight moored buoys around Korean peninsula is compared with both experiments. Exp. DA reveals reduction ratio of RMSE over 70% in all season except for summer, showing the contribution of OSTIA assimilation to the short-range prediction in the coastal region. In addition, the effect of SST assimilation in the upper ocean temperature is examined by the comparison with Argo data in the East Sea. The comparison shows that RMSE from Exp. DA is reduced by $1.5^{\circ}C$ up to 100 m depth in winter where vertical mixing is strong. Thus, SST assimilation is found to be efficient also in the upper ocean prediction. However, the temperature below the mixed layer in winter reveals larger difference in Exp. DA, implying that SST assimilation has still a limitation to the prediction of ocean interior.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2000.04a
• /
• pp.5-5
• /
• 2000

액체 추진 로켓 엔진의 고주파 연소 불안정 관련 이론은 대체로 연소기 내부의 음향 공명 모드와 분무 연소 과정의 상호 작용을 구동 메커니즘으로 전제하며 Rayleigh Criterion의 재해석에 기초하여 불안정성 평가를 위한 매개변수를 도입하고 연소 불안정성을 예측한다. 여기에는 음향장 분석 이론, 음향 불안정 이론, 연소응답 및 기화반응 이론 등이 포함된다. 본 연구에서는 LOX/RPl 추진제 조합의 액체 추진 로켓 엔진 연소기를 대상으로 다차원 순수 음향장 해석과 연소-음향장 분석을 통해 대상 엔진의 고주파 연소 불안정 특성을 예측하였다. 수동 제어 기기인 음향공 설치에 따른 연소기의 음향장 및 연소-음향장의 특성 변화를 고찰하고 위 결과를 종합하여 음향공의 연소 불안정 억제 성능 및 대상 엔진의 연소 불안정성을 평가하였다. 연소기 형상 및 음향공 설치에 따른 다차원 순수 음향장 해석은 상용코드인 ANSYS를 사용하여 수행하였다. 내부 유체는 압축성, 비점성 유체로 유체의 평균 유동은 무시하며 위치에 관계없이 균일한 물성치를 부여하였다. 정상상태 연소과정을 가정하고 평형 화학을 이용한 분석 결과로부터 연소 기체의 관련 물성치를 결정하였다. 연소기 길이 방향, 반경 방향, 원주 방향 격자점들의 음향 특성을 주파수 영역에 대해 해석하고 3차원 음향 모드 형상을 토대로 음향장을 분석하였다. 연소-음향장 해석은 음향 불안정 이론 중 n- $\tau$ 2 매개변수 기법을 사용하였다. 연료 액적의 분무 연소 과정을 1차원적으로 가정하고 정상상태의 평형 화학 계산 결과를 이용하여 엔진의 연소면을 1차원적으로 설정하였다. 상류 연소응답과 중립 안정 곡선을 토대로 대상 엔진의 연소 불안정 특성을 분석하였다.구 분석 결과 기술적 문제점으로는 배기 가스온도가 낮은데 따른 출구 부분의 Bearing, Sealing이 문제가 될 수 있다고 판단되며 배기 가스 자체에 대기 공기중에 함유되어 있던 습기가 얼어붙는(Icing화) 문제가 발생하기 때문에 배기가스의 Icing을 방지하기 위하여 압축기 끝단에서 공기를 추출하여 배기부분에 송출할 필요성이 있는 것으로 판단되었다. 출구가스의 기체 유동속도가 매우 빠르므로 (100-l10m.sec) 이를 완화하기 위한 디퓨저의 설계가 요구된다고 판단된다. 또 연소기 후방에 물을 주입하는 경우 열교환기 및 기타 부분품에 발생할 수 있는 부식 및 열교환 효율 저하도 간과할 수 없는 문제로 파악되었다. 이러한 기술적 문제가 적절히 해결되는 경우 비활성 가스 제너레이터는 민수용으로는 대형 빌딩, 산림, 유조선 등의 화재에 매우 적절히 사용되어 질 수 있을 뿐 아니라 군사적으로도 군사작전 중 및 공군 기지의 화재 그리고 지하벙커에 설치되어 있는 고급 첨단 군사 장비 등의 화재 뿐 아니라 대간첩작전 등에 효과적으로 활용될 수 있을 것으로 판단된다.가 작으며, 본 연소관에 충전된 RDX/AP계 추진제의 경우 추진제의 습기투과에 의한 추진제 물성 변화는 미미한 것으로 나타났다.의 향상으로, 음성개선에 효과적이라고 사료되었으며, 이 방법이 편측 성대마비 환자의 효과적인 음성개선의 치료방법의 하나로 응용될 수 있으리라 생각된다..7%), 혈액투석, 식도부분절제술 및 위루술·위회장문합술을 시행한 경우가 각 1례(2.9%)씩이었다. 13) 심각한 합병증은 9례(26.5%)에서 보였는데 그중 식도협착증이 6례(17.6%), 급성신부전증 1례(2.9%), 종격동기흉과 폐염이 병발한 경우와 폐염이 각 1례(2.9%)였다. 14)

• 한국신재생에너지학회:학술대회논문집
• /
• 2010.11a
• /
• pp.130.2-130.2
• /
• 2010

2020년까지 대형 CCS (Carbon Capture and Storage) Demo Plant 시장 (100MW 이상) 이 형성될 전망이다. 발전 부문에서 대규모 CCS 실증 프로젝트는 총 44개이며 연소전(41%), 연소후(28%), 순산소(3%) 프로젝트가 계획되어 있다. 순산소 연소 기술은 실증진입단계, 연소후(USC) 기술은 상용화 추진단계, 연소전 (IGCC) 기술은 실증완료 이후 상용화 진입 단계이다. IGCC 발전의 석탄가스화 기술은 타 산업분야에 서 상용화 되어있어 기술신뢰성이 높다. IGCC 단위설비 기술 개발을 통한 성능개선 및 비용절감에 대한 잠재력을 가지고 있기 때문에 미래의 석탄발전기술로 고려되고 있다. IGCC 기술은 가장 상용화에 앞서있지만 아직까지 IGCC+CCS 대형 설비가 운전된 사례가 전 세계적으로 없으며 미국 EPRI 등에서 Feasibility Study 단계이다. 현재 국책과제로 수행중인 300MW급 태안 IGCC 플랜트를 대상으로 향후 CCS 설비를 적용했을 경우에 대해 기술 타당성 검증을 목적으로 IGCC+CCS 모델링을 수행하였다. 모델링은 스크러버 후단의 합성 가스를 대상으로 하였다. Water Gas Shift Reaction (WGSR) 공정 및 Selexol 공정을 구성하여 최종 단에서 수소 연료를 생산할 수 있도록 하였다. WGSR 공정은 Co/Mo 촉매반응기로 구성되었다. WGSR 모델링을 통하여 주입되는 스팀량 (1~2 mol-steam/mol-CO) 및 온도 변화 ($220-550^{\circ}C$)에 따른 CO가스의 전환율을 분석하여 경제적인 설계조건을 선정하였다. Selexol 공정은 $H_2S$ Absorber, $H_2S$ Stripper, $CO_2$ Absorber, $CO_2$ Flash Drum으로 구성된다. Selexol 공정의 $CO_2$와 $H_2S$ 선택도를 분석 하였으며 단위 설비별 설계 조건을 예측하였다. 모델링 결과 59kg/s의 합성가스($137^{\circ}C$, 41bar, 가스 조성은 $CO_2$ 1.2%, CO 57.2%, $H_2$ 23.2%, $H_2S$ 0.02%)가 WGSR Process를 통해 98% CO가 $CO_2$ 로 전환되었다. Selexol 공정을 통해 $H_2S$ 제거율은 99.9%, $CO_2$제거율은 96.4%이었고 14.9kg/s의 $H_2$(86.9%) 연료를 얻었다. 모델링 결과는 신뢰성 검증을 통해 IGCC+CCS 전체 플랜트의 성능예측과 Feasibility Study를 위한 자료로 활용될 예정이다.

• Korean Journal of Remote Sensing
• /
• v.31 no.3
• /
• pp.227-244
• /
• 2015

Synthetic Aperture Radar is able to provide images of wide coverage in day, night, and all-weather conditions. Recently, as the SAR image resolution improves up to the sub-meter level, their applications are rapidly expanding accordingly. Especially there is a growing interest in the use of geographic information of high resolution SAR images and the change detection will be one of the most important technique for their applications. In this paper, an automatic threshold tracking and change detection algorithm is proposed applicable to high-resolution SAR images. To detect changes within SAR image, a reference image is generated using log-ratio operator and its amplitude distribution is estimated through K-S test. Assuming SAR image has a non-gaussian amplitude distribution, a generalized thresholding technique is applied using Kittler and Illingworth minimum-error estimation. Also, MoLC parametric estimation method is adopted to improve the algorithm performance on rough ground target. The implemented algorithm is tested and verified on the simulated SAR raw data. Then, it is applied to the spaceborne high-resolution SAR images taken by Cosmo-Skymed and KOMPSAT-5 and the performances are analyzed and compared.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1249-1256
• /
• 2019

In this paper, we propose a new algorithm to remove acoustic feedback and noise in hearing aids. Instead of using the conventional FIR structure, this algorithm is a deep learning algorithm using neural network adaptive prediction filter to improve the feedback and noise reduction performance. The feedback canceller first removes the feedback signal from the microphone signal and then removes the noise using the Wiener filter technique. Noise elimination is to estimate the speech from the speech signal containing noise using the linear prediction model according to the periodicity of the speech signal. In order to ensure stable convergence of two adaptive systems in a loop, coefficient updates of the feedback canceller and noise canceller are separated and converged using the residual error signal generated after the cancellation. In order to verify the performance of the feedback and noise canceller proposed in this study, a simulation program was written and simulated. Experimental results show that the proposed deep learning algorithm improves the signal to feedback ratio(: SFR) of about 10 dB in the feedback canceller and the signal to noise ratio enhancement(: SNRE) of about 3 dB in the noise canceller than the conventional FIR structure.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.429-439
• /
• 2006

A desktop grid, which is a computing grid composed of idle computing resources in a large network of desktop computers, is a promising platform for compute-intensive distributed computing applications. However, due to reliability and unpredictability of computing resources, effective scheduling of parallel computing applications on such a platform is a difficult problem. This paper proposes a new scheduling method aimed at reducing the total execution time of a parallel application on a desktop grid. The proposed method is based on utilizing the histories of execution behavior of individual computing nodes in the scheduling algorithm. In order to test out the feasibility of this idea, execution trace data were collected from a set of 40 desktop workstations over a period of seven weeks. Then, based on this data, the execution of several representative parallel applications were simulated using trace-driven simulation. The simulation results showed that the proposed method improves the execution time of the target applications significantly when compared to previous desktop grid scheduling methods. In addition, there were fewer instances of application suspension and failure.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.119-125
• /
• 2015

A concentration meter is widely used at purification plants, sewage treatment plants and waste water treatment plants to sort and transfer high concentration sludge and to control the amount of chemical dosage. When the strange substance is contained in the sludge, however, the attenuation of ultrasonic wave could be increased or not be transmitted to the receiver. At that case, the value of concentration meter is higher than the actual density value or vibrated up and down. It has also been difficult to automate the residuals treatment process according to the problems as sludge attachment or damage of a sensor. Multi-beam ultrasonic concentration meter has been developed to solve these problems, but the failure of the ultrasonic beam of a specific concentration measurement value degrade the performance of the entire system. This paper proposes the method to improve the accuracy of sludge concentration rate by choosing reliable sensor values and learning them by proposed algorithm. The prediction algorithm is chosen as neuro-fuzzy model, which is tested by the various experiments.