• 한국통신학회논문지
• /
• 제34권10C호
• /
• pp.929-936
• /
• 2009

기존의 MIMO 다중 송수신기들이 협대역 flat 채널을 공유하고 있는 환경에서 오버레이 MIMO 시스템의 디자인을 고려한다. 오버레이 시스템의 수신기로 수신되는 기존 시스템 신호의 2nd-order 통계량과 오버레이 송신단으로부터 기존 시스템들의 수신단 사이의 채널이 모두 알려져 있다고 가정한다. 평균 송신 전력 제약과 이미 관심대역을 차지하고 있는 기존 시스템들의 수신단에 간섭을 일으키지 않는다는 제약 아래 오버레이 시스템의 각 수신안테나 출력에서의 데이터 심볼의 평균 제곱 오차 (MSE: mean-squared error)의 합인 전체 MSE를 최소화 하는 최적 오버레이 시스템의 선형 precoding과 decoding 행렬을 유도한다. 최적 해가 존재하기 위한 필요충분 조건 또한 유도하고, 제안된 시스템의 성능에 대한 모의 실험 결과를 제공한다.

• 한국지능시스템학회논문지
• /
• 제20권6호
• /
• pp.755-760
• /
• 2010

일반적으로 이산 최적화에서의 라그랑지안 방법은 제약조건을 쉽게 다루기 위한 기법이다. 이 방법은 전형적으로 분지한계법에서 상한을 찾을 때 사용한다. 본 논문은 여러 개의 제약조건이 있는 다중 배낭 문제를 위한 새로운 라그랑지안 방법을 제안한다. 기존 라그랑지안 접근법과는 달리 제안한 방법은 라그랑지안 벡터의 새로운 특징에 기초하여 품질 좋은 하한(즉, 가능 해)을 효율적으로 찾을 수 있다. 잘 알려진 큰 규모의 벤치마크 데이터에서 실험을 하였고 제안한 라그랑지안 방법은 기존 방법의 성능을 개선하였다.

• 설비공학논문집
• /
• 제23권11호
• /
• pp.754-761
• /
• 2011

The present study numerically investigates two-dimensional flow and heat transfer in the multiple confined impinging slot jet. Numerical simulations are performed for the different Reynolds numbers(Re=100 and 200) in the range of nozzles from 1 to 9 and height ratios(H/D) from 2 to 5, where H/D is the ratio of the channel height to the slot width. The vector plots of velocity profile, stagnation and averaged Nusselt number distributions are presented in this paper. The dependency of thermal fields on the Reynolds number, nozzle number and height ratio can be clarified by observing the Nusselt number as heat transfer characteristic at the stagnation point and impingement surface. The Nusselt number at the stagnation point of the central slot shows unsteadiness at H/D=3 and Re=200. The value of Nusselt number at the stagnation point of the central slot decreases with higher Reynolds number and number of nozzle although overall area averaged Nusselt number increases. Hence careful selection of geometrical parameters and number of nozzle are necessary for optimization of the heat transfer performance of multiple slot impinging jet.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2014년도 제50차 하계학술대회논문집 22권2호
• /
• pp.1-4
• /
• 2014

인텔 Many Integrated Core (MIC) 아키텍쳐는 61개의 코어가 하나의 칩에 결합되어 있다. Xeon Phi 로 명명된 인텔 MIC는 인텔 E5 Xeon CPU 보다 2배의 single precision GFLOPs 성능을 제공한다. 인텔 MIC 는 수치연산에 최적화 되어 있는 아키텍쳐이다. 우리는 Xeon Phi 7120P를 가지고 벤치마킹을 하였고 클락스피드 1.238GHz, 61Core 이고 한 개의 코어당 4쓰레드를 사용하며 이론상 최고 성능은 Peak Double Precision(GFLOP)는 약 2-TFlops 이다. 이에 우리는 인텔 X86 아키텍쳐에서 openMP 와 인텔 MKL(Math kernel library) 라이브러리를 이용한 병렬프로그램을 작성하여 쓰레드 수를 증가 시키면서 인텔 Xeon Phi 와 E5 Xeon CPU에서 single precision 성능을 벤치마킹 하여, Xeon Phi 와 Xeon E5 의 이론적인 성능을 비교해 보고자 한다. 또한 openMP와 인텔 MKL라이브러리를 사용한 병렬환경에서 CPU의 성능 지표인 클락스피드와 코어수 외에 Vector unit size 의 크기가 성능에 어떤 영향을 미치는지 살펴보았다.

• 대한전자공학회논문지SD
• /
• 제39권9호
• /
• pp.37-44
• /
• 2002

학습된 신경망(Pre-trained neural network)은 고정된 가중치(weight)를 갖는다. 이 논문에서는 이러한 특성을 이용하여 신경망의 효과적인 디지털 하드웨어의 설계방법을 제안한다. 이를 위해 신경망의 PEs(Processing Elements)연산은 행렬-벡터 곱셈으로 표하고 고정된 가중치와 입력 데이터의 관계를 비트-레벨 어레이(array) 구조로 표현하여, 노드 소거와 가중치 비트 패턴에 따른 공유 노드 설정을 통한 최적화로 연산에 필요한 노드를 최소화한다. FPGA 시뮬레이션 결과, 완전한 정확성에 기반한 하드웨어를 설계하는 경우, 하드웨어 비용을 상당부분 줄였고 동작 주파수가 높다는 것을 확인하였다. 또한, 제안한 설계방법은 한정된 공간 내에서 많은 수의 PEs 구현이 가능함으로, 큰 신경망 모델에 대한 온-칩(on-chip) 구현이 가능하다.

• Journal of Information Processing Systems
• /
• 제8권4호
• /
• pp.621-652
• /
• 2012

Software Estimations provide an inclusive set of directives for software project developers, project managers, and the management in order to produce more realistic estimates based on deficient, uncertain, and noisy data. A range of estimation models are being explored in the industry, as well as in academia, for research purposes but choosing the best model is quite intricate. Estimation by Analogy (EbA) is a form of case based reasoning, which uses fuzzy logic, grey system theory or machine-learning techniques, etc. for optimization. This research compares the estimation accuracy of some conventional data mining models with a hybrid model. Different data mining models are under consideration, including linear regression models like the ordinary least square and ridge regression, and nonlinear models like neural networks, support vector machines, and multivariate adaptive regression splines, etc. A precise and comprehensible predictive model based on the integration of GRA and regression has been introduced and compared. Empirical results have shown that regression when used with GRA gives outstanding results; indicating that the methodology has great potential and can be used as a candidate approach for software effort estimation.

• 한국기계기술학회지
• /
• 제20권6호
• /
• pp.809-817
• /
• 2018

The model predictive controller performance of the mobile robot is set to an arbitrary value because it is difficult to select an accurate value with respect to the controller parameter. The general model predictive control uses a quadratic cost function to minimize the difference between the reference tracking error and the predicted trajectory error of the actual robot. In this study, we construct a predictive controller by transforming it into a quadratic programming problem considering velocity and acceleration constraints. The control parameters of the predictive controller, which determines the control performance of the mobile robot, are used a simple weighting matrix Q, R without the reference model matrix $A_r$ by applying a quadratic cost function from which the reference tracking error vector is removed. Therefore, we designed the predictive controller 1 and 2 of the mobile robot considering the constraints, and optimized the controller parameters of the predictive controller using a genetic algorithm with excellent optimization capability.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.285-291
• /
• 2022

The number of people enrolling in universities is rising due to the simplicity of applying and the benefit of earning a bachelor's degree. However, the on-time graduation rate has declined since plenty of students fail to complete their courses and take longer to get their diplomas. Even though there are various reasons leading to the aforementioned problem, it is crucial to emphasize the cause originating from the management and care of learners. In fact, understanding students' difficult situations and offering timely Number of Test data and advice would help prevent college dropouts or graduate delays. In this study, we present a machine learning-based method for early detection at-risk students, using data obtained from graduates of the Faculty of Information Technology, Dainam University, Vietnam. We experiment with several fundamental machine learning methods before implementing the parameter optimization techniques. In comparison to the other strategies, Random Forest and Grid Search (RF&GS) and Random Forest and Random Search (RF&RS) provided more accurate predictions for identifying at-risk students.

• 한국공간구조학회논문집
• /
• 제23권3호
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• ETRI Journal
• /
• 제45권3호
• /
• pp.448-461
• /
• 2023

This article performs a detailed data scrutiny on a chronic kidney disease (CKD) dataset to select efficient instances and relevant features. Data relevancy is investigated using feature extraction, hybrid outlier detection, and handling of missing values. Data instances that do not influence the target are removed using data envelopment analysis to enable reduction of rows. Column reduction is achieved by ranking the attributes through feature selection methodologies, namely, extra-trees classifier, recursive feature elimination, chi-squared test, analysis of variance, and mutual information. These methodologies are ranked via Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using weight optimization to identify the optimal features for model building from the CKD dataset to facilitate better prediction while diagnosing the severity of the disease. An efficient hybrid ensemble and novel similarity-based classifiers are built using the pruned dataset, and the results are thereafter compared with random forest, AdaBoost, naive Bayes, k-nearest neighbors, and support vector machines. The hybrid ensemble classifier yields a better prediction accuracy of 98.31% for the features selected by extra tree classifier (ETC), which is ranked as the best by TOPSIS.