http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
The expectation–maximization approach for Bayesian additive Cox regression with current status data
Cui Di,Tee Clarence 한국통계학회 2023 Journal of the Korean Statistical Society Vol.52 No.2
In this paper, we propose a Bayesian additive Cox model for analyzing current status data based on the expectation–maximization variable selection method. This model concurrently estimates unknown parameters and identifies risk factors, which effi-ciently improves model interpretability and predictive ability. To identify risk fac-tors, we assign appropriate priors on the indicator variables which denote whether the risk factors are included. By assuming partially linear effects of the covariates, the proposed model offers flexibility to account for the relationship between risk factors and survival time. The baseline cumulative hazard function and nonlinear effects are approximated via penalized B-splines to reduce the dimension of param-eters. An easy to implement expectation–maximization algorithm is developed using a two-stage data augmentation procedure involving latent Poisson variables. Finally, the performance of the proposed method is investigated by simulations and a real data analysis, which shows promising results of the proposed Bayesian variable selection method.
특정 용도 하이브리드 광학 네트워크-온-칩에서의 에너지/응답시간 최적화를 위한 토폴로지 설계 기법
최적(Di Cui),이재훈(Jae Hoon Lee),김현중(Hyun Joong Kim),한태희(Tae Hee Han) 대한전자공학회 2014 전자공학회논문지 Vol.51 No.11
최근 수년간 전기적 상호 연결 (electrical interconnect, EI) 기반 네트워크-온-칩 (Network-on-Chip, NoC) 에 대한 연구가 활발히 진행되고 있는 가운데, 궁극적으로 금속 배선은 대역폭, 응답 시간(latency), 전력 소모 등에서 물리적 한계에 직면할 것으로 예상된다. 실리콘 포토닉스(silicon photonics) 기술 발전으로 광학적 상호 연결(optical interconnect, OI)을 결합한 하이브리드 광학 네트워크-온-칩(Hybrid Optical NoC, HONoC)이 이러한 문제를 극복하기 위한 유망한 해결책으로 부각되고 있다. 한편 시스템-온-칩(System-on-Chip, SoC)은 높은 에너지 효율을 위하여 이기종 멀티 코어(Heterogeneous multi-core)로 구성되고 있어서 정형화된 토폴로지 기반 NoC 아키텍처의 확장이 필요하다. 본 논문에서는 타깃 애플리케이션 트래픽 특성을 고려한 에너지 및 응답 시간 최적화 하이브리드 광학 네트워크-온-칩의 토폴로지 설계 기법을 제안한다. 유전자 알고리즘을 이용하여 구현하였고, 실험 결과 평균 전력손실은 13.84%, 평균 응답 시간은 28.14% 각각 감소하였다. It is a widespread concern that electrical interconnection based network-on-chip (NoC) will ultimately face the limitation in communication bandwidth, transmission latency and power consumption in the near future. With the development of silicon photonics technology, a hybrid optical network-on-chip (HONoC) which embraces both electrical- and optical interconnect, is emerging as a promising solution to overcome these problems. Today"s leading edge systems-on-chips (SoCs) comprise heterogeneous many-cores for higher energy efficiency, therefore, extended study beyond regular topology based NoC is required. This paper proposes an energy and latency optimization topology design technique for HONoC taking into account the traffic characteristics of target applications. The proposed technique is implemented with genetic algorithm and simulation results show the reduction by 13.84% in power loss and 28.14% in average latency, respectively.
The Relative Influence of Diet and Physical Activity on Obesity in China
Cui Zhao-Hui,Li Yan-Ping,Di Yu-Feng,Ba Lei,Hu Xiaoqi,Ma Guan-Sheng The Korean Society of Community Nutrition 2004 Journal of community nutrition Vol.6 No.3
The purpose of this study is to investigate the relative influence of diet and physical activity on obesity. The subjects were 155 adults aged 35-52 years from 24 neighborhood committees in 4 urban districts of Beijing (male : 78, female : 77). They were divided into normal weight, overweight and obese groups according to their BMI. The general information of the subjects was collected by interview-administered questionnaire. Dietary intake was obtained by three-day(two weekdays and one weekend day) food weighted method, physical activity was assessed by a validated combination of data obtained from activity monitors, bicycling information and activity records. There were no significant differences of age, gender, height, educational, family economic level, smoking and drinking between different groups. The proportion of flour intake was higher in obese group compared to normal weight and overweight groups, and that of vegetables is lower in obese group. The physical activity (PAL) was not significantly different between two groups of the normal, overweight and obese groups. After the adjustment for confounding factors using logistic regression model, we found that the proportion of flour intake was positively associated with obesity, while the proportion of vegetable intake was inversely associated with obesity. It is concluded that dietary patterns were associated with obesity and diets composed of more vegetables and less staple combined with physical activities could contribute to obesity prevention.
Di Tang,Shiyi Bao,Binbin Lv,Hao Cui,Lijia Luo,Min Xu 대한기계학회 2019 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.33 No.6
Shedding vortices in cross flow are of much practical importance in the analysis of flow induced vibrations of a steam generator. However, studies of shedding vortex are still few in present, especially in shedding patterns and its influences on lift performances. In this paper, five basic shedding patterns were investigated by numerical simulations of a 2D unsteady flow around a bundle with 253 cylinders. The numerical results clearly demonstrated that flow in line is the most common pattern. On the hand, the other four shedding patterns, cross in line, cross near line near, cross near line far and cross far line near, appear randomly. Influences of shedding vortices on lift performances were concluded as lift enhancement, lift pit and lift lag. These numerical results can provide a basic knowledge of shedding vortices for cylinders and can precisely quantify their influences on unsteady lift performances.
Trajectory Tracking Control of Intelligent Vehicles
Cui Guangzhen,Zhao Di,Xiao Yanqiu,Fang Zhanpeng,Yao Lei 대한전기학회 2024 Journal of Electrical Engineering & Technology Vol.19 No.1
In this paper a combined lateral and longitudinal control algorithm based on model predictive control is proposed. In the lateral controllers, feedforward control based on model prediction and feedback of heading error and yaw angle error are used to improve the tracking accuracy of the front wheels. According to the anti-interference ability of the active disturbance rejection controller, the yaw rate is taken as the input to compensate the front wheel angle of the vehicle, improving the tracking stability of the vehicle. In the design process of the longitudinal control system, we use a hierarchical controller. The upper controller is a model predictive controller with a constraint function, that obtains the desired acceleration based on the reference speed. The lower controller is an inverse longitudinal dynamics model, which obtains the fnal control amount of the vehicle based on the output of the upper controller. This proposed method was validated on the co-simulation platform constructed by CarSim and MATLAB/Simulink. The experimental and simulation results demonstrate the efectiveness and superiority of the improved model predictive controller in tracking accuracy and steering smoothness.
Genetic Algorithm for Eight-Queen Problem
Wu Di,Jingxuan Jin,Rongyi Cui 한국어정보학회 2006 한국어정보학 Vol.8 No.1
This paper uses the real‐coding genetic algorithm to solve the 8‐queen problem that is the constraint problem of classic AI, and the good simulated result is given by MATLAB.