• Journal of the Korean Operations Research and Management Science Society
• /
• v.22 no.3
• /
• pp.163-173
• /
• 1997

Although numerous studies demonstrate that one technique outperforms the others for a given data set, it is hard to tell a priori which of these techniques will be the most effective to solve a specific problem. It has been suggested that the better approach to classification problem might be to integrate several different forecasting techniques by combining their results. The issues of interest are how to integrate different modeling techniques to increase the predictive performance. This paper proposes the post-model integration method, which tries to find the best combination of the results provided by individual techniques. To get the optimal or near optimal combination of different prediction techniques, Genetic Algorithms (GAs) are applied, which are particularly suitable for multi-parameter optimization problems with an object function subject to numerous hard and soft constraints. This study applies three individual classification techniques (Discriminant analysis, Logit model and Neural Networks) as base models for the corporate failure prediction. The results of composite predictions are compared with the individual models. Preliminary results suggests that the use of integrated methods improve the performance of business classification.

• Structural Engineering and Mechanics
• /
• v.25 no.2
• /
• pp.239-268
• /
• 2007

This paper deals with optimal stacking sequence design of laminate composite structures. The stacking sequence optimisation of laminate composites is formulated as a combinatorial problem and is solved using Simulated Annealing (SA), an algorithm devised based on inspiration of physical process of annealing of solids. The combinatorial constraints are handled using a correction strategy. The SA algorithm is strengthened by embedding Tabu search in order to prevent recycling of recently visited solutions and the resulting algorithm is referred to as tabu embedded simulated Annealing (TSA) algorithm. Computational performance of the proposed TSA algorithm is enhanced through cache-fetch implementation. Numerical experiments have been conducted by considering rectangular composite panels and composite cylindrical shell with different ply numbers and orientations. Numerical studies indicate that the TSA algorithm is quite effective in providing practical designs for lay-up sequence optimisation of laminate composites. The effect of various neighbourhood search algorithms on the convergence characteristics of TSA algorithm is investigated. The sensitiveness of the proposed optimisation algorithm for various parameter settings in simulated annealing is explored through parametric studies. Later, the TSA algorithm is employed for multi-criteria optimisation of hybrid composite cylinders for simultaneously optimising cost as well as weight with constraint on buckling load. The two objectives are initially considered individually and later collectively to solve as a multi-criteria optimisation problem. Finally, the computational efficiency of the TSA based stacking sequence optimisation algorithm has been compared with the genetic algorithm and found to be superior in performance.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.794-796
• /
• 1999

본 논문에서는 3상 유도전동기의 속도를 제어하는데 기존 제어기의 문제점을 해결하고 최적화하기 위해서 유전자 알고리즘을 이용한 하이브리드 퍼지 -PID(HFPID) 제어기를 고안하고, 이에 대한 파라미터 설정 방법을 제안한다. 유도전동기의 제어는 지연시간이 길고, 비선형성이 강하며, 부하변동이 잦은 프로세스이기 때문에, 기존의 제어방식으로는 만족할만한 결과를 얻을 수 없다. 제안한 하이브리드 퍼지-PID 제어기는 PID 제어기의 장점인 과도기의 우수성과 퍼지 제어기의 장점인 정상기의 우수성을 퍼지 변수로 결합시켜 설계한다. 이 제어기에 유전자 알고리즘을 적용하여 최적의 퍼지 및 PID 파라미터를 설정하다. 그리고 이 제어기를 3상 유도전동기의 속도 제어에 응용한다. 또한 속도오차에 대한 룩업 표를 만들어 온라인 실시간 제어를 가능하게 한다. 이상의 과정을 3상 유도전동기에서 컴퓨터 시뮬레이션 하였다. 시뮬레이션 결과를 비교해 볼 때, 하이브리드 퍼지-PID 제어기는 기존의 제어기 보다 전동기의 속도 및 토크성분 전류 둥의 특성에서 우수한 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.1-20
• /
• 2018

Service composition in the Inter-Cloud raises new challenges that are caused by the different Quality of Service (QoS) requirements of the users, which are served by different geo-distributed Cloud providers. This paper aims to explore how to select and compose such services while considering how to reach high efficiency on cost and response time, low network latency, and high reliability across multiple Cloud providers. A new hybrid multi-objective evolutionary algorithm to perform the above task called LS-NSGA-II-DE is proposed, in which the differential evolution (DE) algorithm uses the adaptive mutation operator and crossover operator to replace the those of the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) to get the better convergence and diversity. At the same time, a Local Search (LS) method is performed for the Non-dominated solution set F{1} in each generation to improve the distribution of the F{1}. The simulation results show that our proposed algorithm performs well in terms of the solution distribution and convergence, and in addition, the optimality ability and scalability are better compared with those of the other algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.372-372
• /
• 2000

In this paper, we propose Neuro Fuzzy Polynomial Networks(NFPN) based on Polynomial Neural Network(PNN) and Neuro-Fuzzy(NF) for model identification of complex and nonlinear systems. The proposed NFPN is generated from the mutually combined structure of both NF and PNN. The one and the other are considered as the premise part and consequence part of NFPN structure respectively. As the premise part of NFPN, NF uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. As the consequence part of NFPN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. NFPN is available effectively for multi-input variables and high-order polynomial according to the combination of NF with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. In order to evaluate the performance of proposed models, we use the nonlinear function. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.733-744
• /
• 2019

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.7
• /
• pp.378-388
• /
• 2000

In this paper, we propose Fuzzy Polynomial Neural Networks(FPNN) based on Polynomial Neural Networks(PNN) and Fuzzy Neural Networks(FNN) for model identification of complex and nonlinear systems. The proposed FPNN is generated from the mutually combined structure of both FNN and PNN. The one and the other are considered as the premise part and consequence part of FPNN structure respectively. As the consequence part of FPNN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. FPNN is available effectively for multi-input variables and high-order polynomial according to the combination of FNN with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. As the premise part of FPNN, FNN uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. And we use two kinds of FNN structure according to the division method of fuzzy space of input variables. One is basic FNN structure and uses fuzzy input space divided by each separated input variable, the other is modified FNN structure and uses fuzzy input space divided by mutually combined input variables. In order to evaluate the performance of proposed models, we use the nonlinear function and traffic route choice process. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously. And also performance index related to the approximation and prediction capabilities of model is evaluated and discussed.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.12
• /
• pp.471-480
• /
• 2016

Recently, the damage of cyber attack toward infra-system, national defence and security system is gradually increasing. In this situation, military recognizes the importance of cyber warfare, and they establish a cyber system in preparation, regardless of the existence of threaten. Thus, the study of Intrusion Detection System(IDS) that plays an important role in network defence system is required. IDS is divided into misuse and anomaly detection methods. Recent studies attempt to combine those two methods to maximize advantagesand to minimize disadvantages both of misuse and anomaly. The combination is called Hybrid IDS. Previous studies would not be inappropriate for near real-time network environments because they have computational complexity problems. It leads to the need of the study considering the structure of IDS that have high detection rate and low computational cost. In this paper, we proposed a Hybrid IDS which combines C4.5 decision tree(misuse detection method) and Weighted K-means algorithm (anomaly detection method) hierarchically. It can detect malicious network packets effectively with low complexity by applying mutual information and genetic algorithm based efficient feature selection technique. Also we construct upgraded the the hierarchical structure of IDS reusing feature weights in anomaly detection section. It is validated that proposed Hybrid IDS ensures high detection accuracy (98.68%) and performance at experiment section.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.271-280
• /
• 1999

인공신경망을 시계열예측에 적용하는 경우에 고려되어야 할 문제중, 특히 모형에 적합한 입력변수의 생성이 중요시되고 있는데, 이러한 분야는 인공신경망의 모형생성과정에서 입력변수에 대한 전처리기법으로써 다양하게 제시되어 왔다. 가장 최근의 입력변수 전처리기법으로써 제시되고 있는 신호처리기법은 전통적 주기분할처리방법인 푸리에변환기법(Fourier transforms)을 비롯하여 이를 확장시킨 개념인 웨이블릿변환기법(wavelet transforms) 등으로 대별될 수 있다. 이는 기본적으로 시계열이 다수의 주기(cycle)들로 구성된 상이한 시계열들의 집합이라는 가정에서 출발하고 있다. 전통적으로 이러한 시계열은 전기 또는 전자공학에서 주파수영역분할, 즉 고주파 및 저주파수를 분할하기 위한 기법에 적용되어 왔다. 그러나, 최근에는 이러한 연구가 다양한 분야에 활발하게 응용되기 시작하였으며, 그 중의 대표적인 예가 바로 경영분야의 재무시계열에 대한 분석이다. 전통적으로 재무시계열은 장, 단기의사결정을 가진 시장참여자들간의 거래특성이 시계열에 각기 달리 가격으로 반영되기 때문에 이러한 상이한 집단들의 고요한 거래움직임으로 말미암아 예를 들어, 주식시장이 프랙탈구조를 가지고 있다고 보기도 한다. 이처럼 재무시계열은 다양한 사회현상의 집합체라고 볼 수 있으며, 그만큼 예측모형을 구축하는데 어려움이 따른다. 본 연구는 이러한 시계열의 주기적 특성에 기반을 둔 신호처리분석으로서 기존의 시계열로부터 노이즈를 줄여 주면서 보다 의미있는 정보로 변환시켜줄 수 있는 웨이블릿분석 방법론을 새로운 필터링기법으로 사용하여 현재 많은 연구가 진행되고 있는 인공신경망의 모형결합을 통해 기존연구과는 다른 새로운 통합예측방법론을 제시하고자 한다. 본 연구에서는 제시하는 통합방법론은 크게 2단계 과정을 거쳐 예측모형으로 완성이 된다. 즉, 1차 모형단계에서 원시 재무시계열은 먼저 웨이브릿분석을 통해서 노이즈가 필터링 되는 동시에, 과거 재무시계열의 프랙탈 구조, 즉 비선형적인 움직임을 보다 잘 반영시켜 주는 다차원 주기요소를 가지는 시계열로 분해, 생성되며, 이렇게 주기에 따라 장단기로 분할된 시계열들은 2차 모형단계에서 신경망의 새로운 입력변수로서 사용되어 최종적인 인공 신경망모델을 구축하는 데 반영된다. 기존의 주기분할방법론은 모형개발자입장에서 여러 가지 통계기준치중에서 최적의 기준치를 합리적으로 선택해야 하는 문제가 추가적으로 발생하며, 본 연구에서는 이상의 제반 문제들을 개선시키기 위해 통합방법론으로서 기존의 인공신경망모형을 구조적으로 확장시켰다. 이 모형에서 기존의 입력층 이전단계에 새로운 층이 정의된다. 이렇게 해서 생성된 새로운 통합모형은 기존모형에서 생성되는 기본적인 학습파라미터와 더불어, 본 연구에서 새롭게 제시된 주기분할층의 파라미터들이 모형의 학습성과를 높이기 위해 함께 고려된다. 한편, 이러한 학습과정에서 추가적으로 고려해야 할 파라미터 갯수가 증가함에 따라서, 본 모델의 학습성과가 local minimum에 빠지는 문제점이 발생될 수 있다. 즉, 웨이블릿분석과 인공신경망모형을 모두 전역적으로 최적화시켜야 하는 문제가 발생한다. 본 연구에서는 이 문제를 해결하기 위해서, 최근 local minimum의 가능성을 최소화하여 전역적인 학습성과를 높여 주는 인공지능기법으로서 유전자알고리즘기법을 본 연구이 통합모델에 반영하였다. 이에 대한 실증사례 분석결과는 일일 환율예측문제를 적용하였을 경우, 기존의 방법론보다 더 나운 예측성과를 타나내었다.