• 생물정신의학
• /
• 제30권1호
• /
• pp.24-30
• /
• 2023

Objectives Alzheimer's disease (AD) is the most common form of dementia in older adults, damaging the brain and resulting in impaired memory, thinking, and behavior. The identification of differentially expressed genes and related pathways among affected brain regions can provide more information on the mechanisms of AD. The aim of our study was to identify differentially expressed genes associated with AD and combined biomarkers among them to improve AD risk prediction accuracy. Methods Machine learning methods were used to compare the performance of the identified combined biomarkers. In this study, three publicly available gene expression datasets from the hippocampal brain region were used. Results We detected 31 significant common genes from two different microarray datasets using the limma package. Some of them belonged to 11 biological pathways. Combined biomarkers were identified in two microarray datasets and were evaluated in a different dataset. The performance of the predictive models using the combined biomarkers was superior to those of models using a single gene. When two genes were combined, the most predictive gene set in the evaluation dataset was ATR and PRKCB when linear discriminant analysis was applied. Conclusions Combined biomarkers showed good performance in predicting the risk of AD. The constructed predictive nomogram using combined biomarkers could easily be used by clinicians to identify high-risk individuals so that more efficient trials could be designed to reduce the incidence of AD.

• 한국공간구조학회논문집
• /
• 제23권4호
• /
• pp.81-88
• /
• 2023

Numerous factors contribute to the deterioration of reinforced concrete structures. Elevated temperatures significantly alter the composition of the concrete ingredients, consequently diminishing the concrete's strength properties. With the escalation of global CO2 levels, the carbonation of concrete structures has emerged as a critical challenge, substantially affecting concrete durability research. Assessing and predicting concrete degradation due to thermal effects and carbonation are crucial yet intricate tasks. To address this, multiple prediction models for concrete carbonation and compressive strength under thermal impact have been developed. This study employs seven machine learning algorithms-specifically, multiple linear regression, decision trees, random forest, support vector machines, k-nearest neighbors, artificial neural networks, and extreme gradient boosting algorithms-to formulate predictive models for concrete carbonation and thermal impact. Two distinct datasets, derived from reported experimental studies, were utilized for training these predictive models. Performance evaluation relied on metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analytical outcomes demonstrate that neural networks and extreme gradient boosting algorithms outshine the remaining five machine learning approaches, showcasing outstanding predictive performance for concrete carbonation and thermal effect modeling.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.530-535
• /
• 2004

This paper considers a state set estimation (SSE) based model predictive control (MPC) for linear parameter- varying (LPV) systems with input constraint. We estimate, at each time instant, a feasible set of all states which are consistent with system model, measurements and a priori information, rather than the state itself. By combining a state-feedback MPC and an SSE, we design an SSE-based MPC algorithm that stabilizes the closed-loop system. The proposed algorithm is solved by semi-de�nite program involving linear matrix inequalities. A numerical example is included to illustrate the performance of the proposed algorithm.

• Communications for Statistical Applications and Methods
• /
• 제28권1호
• /
• pp.21-37
• /
• 2021

There is a direct connection between linear discriminant analysis (LDA) and linear regression since the direction vector of the LDA can be obtained by the least square estimation. The connection motivates the penalized LDA when the model is high-dimensional where the number of predictive variables is larger than the sample size. In this paper, we study the penalized LDA for a class of penalties, called the moderately clipped LASSO (MCL), which interpolates between the least absolute shrinkage and selection operator (LASSO) and minimax concave penalty. We prove that the MCL penalized LDA correctly identifies the sparsity of the Bayes direction vector with probability tending to one, which is supported by better finite sample performance than LASSO based on concrete numerical studies.

• 한국음향학회지
• /
• 제23권4호
• /
• pp.333-339
• /
• 2004

본 논문에서는 벡터 양자화기와 피라미드 벡터 양자화기를 직렬로 결합하여 16차 벡터 소스에 대한 vector quantizer-pyramid vector quantizer (VQ-PVQ)를 개발하였으며, 예측 구조와 세이프티-넷 (safety-net) 개념을 결합시켜 광대역 음성 부호화기용 LPC 계수 양자화 기를 설계하였다. 본 양자화기의 성능은 AMR-WB(ITRT-T G.722.2)의 LPC양자화기 성능과 비교하였는데, 스펙트럼 왜곡 및 메모리 요구량에서 상당한 이득을 얻었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1905-1910
• /
• 2003

It is well known that parameter uncertainties and time-delays cannot be avoided in practice and result in poor performance and even instability. Nevertheless, to the authors' best knowledge, there exist few results on model predictive control (MPC) handling explicitly uncertain time-delayed systems. In this paper, we present an MPC algorithm for uncertain time-varying systems with input constraints and state-delay. An optimization problem is suggested to find a memoryless state-feedback MPC law and the closed-loop stability is established under feasibility and certain conditions.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1305-1308
• /
• 2003

A new technique is presented to construct a predictive model of plasma etch process. This was accomplished by combining a backpropagation neural network (BPNN) and a genetic algorithm (GA). The predictive model constructed in this way is referred to as a GA-BPNN. The GA played a role of controlling training factors simultaneously. The training factors to be optimized are the hidden neuron, training tolerance, initial weight magnitude, and two gradients of bipolar sigmoid and linear functions. Each etch response was optimized separately. The proposed scheme was evaluated with a set of experimental plasma etch data. The etch process was characterized by a $2^3$ full factorial experiment. The etch responses modeled are aluminum (A1) etch rate, silica profile angle, A1 selectivity, and dc bias. Additional test data were prepared to evaluate model appropriateness. The GA-BPNN was compared to a conventional BPNN. Compared to the BPNN, the GA-BPNN demonstrated an improvement of more than 20% for all etch responses. The improvement was significant in the case of A1 etch rate.

• 전기학회논문지
• /
• 제67권2호
• /
• pp.308-313
• /
• 2018

In this paper, we propose a sampled-data model predictive tracking control deign for leader-following control of multi-mobile robot system. The error dynamics of leader-following robots is modeled as a Linear Parameter Varying (LPV) model. Also, the Lyapunov function is presented to guarantee stability of the networked control system. Based on the stabilization condition using a quadratic Lyapunov function approach, model predictive sampled-data controller is designed. Finally, the leader-following control of multi mobile robots is simulated to show effectiveness of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.377-382
• /
• 2005

This paper presents a new method for the attitude control of planar space robots. In order to control highly constrained non-linear system such as a 3D space robot, the analytical formulation for the system with complex dynamics and effective control methodology based on the formulation, are not always obtainable. In the proposed method, correspondingly, a non-analytical but effective self-organizing modeling method for controlling a highly constrained system is proposed based on a polynomial data mining algorithm. In order to control the attitude of a planar space robot, it is well known to require inputs characterized by a special pattern in time series with a non-deterministic length. In order to correspond to this type of control paradigm, we adopt the Model Predictive Control (MPC) scheme where the length of the non-deterministic horizon is determined based on implementation cost and control performance. The optimal solution to finding the size of the input pattern is found by a solving two-stage programming problem.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2081-2086
• /
• 2005

This paper proposes the receding horizon $H_{\infty}$ predictive control (RHHPC) for systems with a state-delay. We first proposes a new cost function for a finite horizon dynamic game problem. The proposed cost function includes two terminal weighting terns, each of which is parameterized by a positive definite matrix, called a terminal weighting matrix. Secondly, we derive the RHHPC from the solution to the finite dynamic game problem. Thirdly, we propose an LMI condition under which the saddle point value satisfies the well-known nonincreasing monotonicity. Finally, we shows the asymptotic stability and $H_{\infty}$-norm boundedness of the closed-loop system controlled by the proposed RHHPC. Through a numerical example, we show that the proposed RHHC is stabilizing and satisfies the infinite horizon $H_{\infty}$-norm bound.