• 산업기술연구
• /
• 제31권B호
• /
• pp.91-98
• /
• 2011

In this thesis, from the results of settlement measurement performed at the site where embankment earthwork was carried out on the ground consisting of highly plastic and silty soft soils interlayered with organic deposits, various methods of predicting the embankment settlement such as Hoshino's method, Asaoka's method, hyperbolic method, ${\sqrt{s}}$ method and Monden's method were used to investigate their applicability and the inverse method of finding the soil parameter related to consolidation was used to predict the consolidation behavior in the future. It was confirmed that reliable prediction of consolidation behavior under various conditions could be done to estimate soil parameter related to consolidation such as the consolidation index and consolidation coefficient by the inverse method of comparing the measured settlement with the predicted value by the settlement prediction methods.

• 방송공학회논문지
• /
• 제16권3호
• /
• pp.416-426
• /
• 2011

본 논문은 H.264/AVC의 인트라(Intra) 부호화에서 인트라 예측 모드를 병합하여 부호화 성능을 높일 수 있는 기술에 관한 것이다. 제안하는 기술은 기존의 인트라 부호화에서 예측 모드를 시그널링(Signaling) 하는 방법과 다르게 여러 블록의 예측 모드를 병합하는 방법을 사용하여 예측 모드를 시그널링 한다. 기설정한 경계값 이상의 블록이 주변 블록으로부터 예측된 모드와 같을 경우에는 제안된 방법을, 그렇지 않을 경우에는 기존의 방법을 사용하여 시그널링 하여 인트라 예측 모드 비트량을 줄임으로써 부호화 효율을 높이는 방법을 제안하였다. 실험 결과, 제안한 방법은 기존의 방법과 비교하여 약 0.05dB의 PSNR(Peak signal to-noise ratio) 증가, 약 1%의 비트율이 감소하였다. 특히 low bit-rate일 경우, 약 0.1dB의 PSNR 증가, 약 1.7%의 비트율이 감소시킴으로써 low bit-rate에서 효과적임을 알 수 있다.

• 실천공학교육논문지
• /
• 제14권2호
• /
• pp.305-312
• /
• 2022

본 논문에서는 기초적인 데이터 예측 모델을 만들고 최적화하는 교육에 초점을 맞추었다. 그리고 데이터 예측 모델을 최적화하는 데 널리 사용되는 머신러닝의 경사하강법 교육 방법을 제안하였다. 미분법을 적용하여 데이터 예측 모델에 필요한 파라미터 값들을 최적화하는 과정에 사용되는 경사하강법의 전체 동작과정을 시각적으로 보여주며, 수학의 미분법이 머신러닝에 효과적으로 사용되는 것을 교육한다. 경사하강법의 전체 동작과정을 시각적으로 설명하기위해, 스프레드시트로 경사하강법 SW를 구현한다. 본 논문에서는 첫번째로, 2변수 경사하강법 교육 방법을 제시하고, 오차 최소제곱법과 비교하여 2변수 데이터 예측모델의 정확도를 검증한다. 두번째로, 3변수 경사하강법 교육 방법을 제시하고, 3변수 데이터 예측모델의 정확도를 검증한다. 이후, 경사하강법 최적화 실습 방향을 제시하고, 비전공자 교육 만족도 결과를 통해, 제안한 경사하강법 교육방법이 갖는 교육 효과를 분석하였다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.172-177
• /
• 2004

Fatigue life prediction is based on fracture mechanics and database which is established from experimental method. Rubber material also uses the same way for fatigue life prediction. But the absence of standardization of rubber material, various way of composition by each rubber company and uncertainty of fracture criterion makes the design of fatigue life by experimental method almost impossible. Tearing energy which has its origin in energy release rate is evaluated as fracture criterion of rubber material and the applicability of fatigue life prediction method are considered. The system of measuring tearing energy using the principal of virtual crack extension method and fatigue life prediction by the minimum number of experiments are proposed.

• Journal of Electrical Engineering and Technology
• /
• 제8권5호
• /
• pp.1040-1048
• /
• 2013

In this paper, a sensorless pitch angle control method for a wind generation system is suggested. One-step-ahead prediction control law is adopted to control the pitch angle of a wind turbine in order for electric output power to track target values. And it is shown that this control scheme using the inverse dynamics of the controlled system enables us to predict current wind speed without an anemometer, to a considerable precision. The inverse input-output of the controlled system is realized by use of an artificial neural network. The proposed control and wind speed prediction method is applied to a Double-Feed Induction Generation system connected to a simple power system through computer simulation to show its effectiveness. The simulation results demonstrate that the suggested method shows better control performances with less control efforts than a conventional Proportional-Integral controller.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(1)
• /
• pp.69-72
• /
• 2001

Blind equalization of transmission channel is important in communication areas and signal processing applications because it does not need training sequence, nor does it require a priori channel information. Recently, Tong et al. proposed solutions for this problem exploit the diversity induced by antenna array or time oversampling, leading to the second order statistics techniques, fur example, subspace method, prediction error method, and so on. The linear prediction error method is perhaps the most attractive in practice due to the insensitive to blind equalizer length mismatch as well as for its simple adaptive filter implementation. Unfortunately, the previous one-step prediction error method is known to be limited in arbitrary delay. In this paper, we induce the optimal delay, and propose the adaptive blind equalizer with multi-step linear prediction using RLS-type algorithm. Simulation results are presented to demonstrate the proposed algorithm and to compare it with existing algorithms.

• Journal of Computing Science and Engineering
• /
• 제11권3호
• /
• pp.100-108
• /
• 2017

In the field of Internet of Things (IoT), smarter embedded devices offer functions via web services. The Quality-of-Service (QoS) prediction is a key measure that guarantees successful IoT service applications. In this study, a collaborative filtering method is presented for predicting response time of IoT service due to time-awareness characteristics of IoT. First, a calculation method of service response time similarity between different users is proposed. Then, to improve prediction accuracy, initial similarity values are adjusted and similar neighbors are selected by a similarity threshold. Finally, via a densified user-item matrix, service response time is predicted by collaborative filtering for current active users. The presented method is validated by experiments on a real web service QoS dataset. Experimental results indicate that better prediction accuracy can be achieved with the presented method.

• Journal of Information Technology Applications and Management
• /
• 제20권2호
• /
• pp.177-191
• /
• 2013

Social network has been expected to increase the value of social capital through online user interactions which remove geographical boundary. However, online users in social networks face challenges of assessing whether the anonymous user and his/her providing information are reliable or not because of limited experiences with a small number of users. Therefore. it is vital to provide a successful trust model which builds and maintains a web of trust. This study aims to propose a prediction method for the interpersonal trust which measures the level of trust about information provider in Facebook. To develop the prediction method. we first investigated behavioral research for trust in social science and extracted 5 antecedents of trust : lenience, ability, steadiness, intimacy, and similarity. Then we measured the antecedents from the history of interactive behavior and built prediction models using the two decision trees and a computational model. We also applied the proposed method to predict interpersonal trust between Facebook users and evaluated the prediction accuracy. The predicted trust metric has dynamic feature which can be adjusted over time according to the interaction between two users.

• 대한기계학회논문집
• /
• 제16권8호
• /
• pp.1536-1544
• /
• 1992

본 연구에서는 축하중 부하의 경우 위에서 언급한 표면균열의 진전특성에 대 한 저자들의 연구결과를 이용하면 비교적 간단하게 표면 균열의 진전거동을 예측할 수 있으리라 기대되어 균열진전거동 예측 방법을 제시하고 이 방법의 타당성을 검토하였 다.

• 디지털산업정보학회논문지
• /
• 제20권2호
• /
• pp.1-10
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis, a model can be constructed with various machine learning algorithms, including decision tree. And feature importance has been utilized in selecting better input features that can improve performance of data analysis models for several application areas. In this paper, a method of utilizing feature importance calculated from the MDI method and its effects are investigated in the credit card customer churn prediction problem with classification trees. Compared with several random feature selections from case data, a set of input features selected from higher value of feature importance shows higher predictive power. It can be an efficient method for classifying and choosing input features necessary for improving prediction performance. The method organized in this paper can be an alternative to the selection of input features using feature importance in composing and using classification trees, including credit card customer churn prediction.