• 한국항해항만학회지
• /
• 제27권2호
• /
• pp.185-191
• /
• 2003

본 연구의 목적은 아시아 주요항만의 특성을 종합적으로 분석/분류하는 것이다. 특히, 본 연구에서는 기존연구가 지닌 연구대상 선정과 관련한 문제점을 극복하기 위해, 객관적인 지표에 의거하여 부산항이 속한 아시아 주요 대상 항만을 선정했다. 그리고, 연구 방법론의 측면에서 기존연구의 계층평가 알고리즘을 이용한 항만평가와 군집분석법을 이용한 연구의 경우 상호보완적인 장/단점을 지니고 있어, 두 가지 알고리즘을 연계하여 아시아 항만의 전체적인 판도와 항만의 경쟁력 순위 등을 종합적으로 고찰했다. 또한, 본 연구에서는 일반군집분석법에 퍼지 알고리즘을 적용한 FC<(Fuzzy C-Means)법을 이용하여, 기존 방법보다 다양한 고찰이 가능케 하였다. 분석결과, 아시아 16개 주요 항만들 중 10개 항만이 독자적이 위상을 가지고 6가지 항만군을 형성하고 있었으며, 순위면에서 싱가폴항, 홍콩항, 부산항 카오슝항이 높은 경쟁력을 가지고 있었다. 특히, 부산항과 카오슝은 여러 가지 특성에서 유사하여 동일 항만군으로 분류되었고, 싱가폴하엥 이어 2번째로 높은 경쟁력을 보유한 항만군을 형성하고 있는 것으로 파악되었으나, 경쟁력 면에서 싱가폴항과의 격차는 큰 것으로 파악되었다.

• 한국정보처리학회논문지
• /
• 제1권1호
• /
• pp.23-37
• /
• 1994

본 논문에서는 소프트웨어 부품을 분류하여 라이브러리에 저장하고, 사용자의 요 구에 따라 효율적으로 검색할 수 있도록 지원하는 확장된 패싯 분류 방식과 혼합형 검색 모델을 제안하고, 프로토타입 시스템을 설계하여 구현하였다. 분류 방식의 설계 를 위하여 부품들의 기본적인 클래스를 분석하여 필요한 항목을 식별한다음, 항목들의 특성을 분석하고 패싯을 결정하여 구품 식별자를 구성한다. 그리고 부품의 기본적인 특성을 기준으로 응용 영역별로 클러스터링시켜 라이브러리에 저장하고, 부품의 특성 을 표현하기 위하여 패싯과 항목들에 가중치를 할당하였다. 부품의 검색을 위하여, 질 의에 의한 검색 모델 및 유사한 바품들을 쉽게 검색할 수 있도록 가중치와 유사도를 이용하였다. 제안한 분류 방식과 검색 모델은 분류 과정이 간단하고, 유사한 부품을 쉽게 식별할 수 있었으며, 또한 질의 작성이 간단해지고, 출력될 부품들의 크기와 순 서의 조절이 가능하여 검색 효율이 개선되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권11호
• /
• pp.5568-5587
• /
• 2018

This research uses artificial intelligence methods for computer network intrusion detection system modeling. Primary classification is done using self-organized maps (SOM) in two levels, while the secondary classification of ambiguous data is done using Sugeno type Fuzzy Inference System (FIS). FIS is created by using Adaptive Neuro-Fuzzy Inference System (ANFIS). The main challenge for this system was to successfully detect attacks that are either unknown or that are represented by very small percentage of samples in training dataset. Improved algorithm for SOMs in second layer and for the FIS creation is developed for this purpose. Number of clusters in the second SOM layer is optimized by using our improved algorithm to minimize amount of ambiguous data forwarded to FIS. FIS is created using ANFIS that was built on ambiguous training dataset clustered by another SOM (which size is determined dynamically). Proposed hybrid model is created and tested using NSL KDD dataset. For our research, NSL KDD is especially interesting in terms of class distribution (overlapping). Objectives of this research were: to successfully detect intrusions represented in data with small percentage of the total traffic during early detection stages, to successfully deal with overlapping data (separate ambiguous data), to maximize detection rate (DR) and minimize false alarm rate (FAR). Proposed hybrid model with test data achieved acceptable DR value 0.8883 and FAR value 0.2415. The objectives were successfully achieved as it is presented (compared with the similar researches on NSL KDD dataset). Proposed model can be used not only in further research related to this domain, but also in other research areas.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2005년도 춘계학술대회논문집
• /
• pp.227-230
• /
• 2005

The paper presents the identification of dynamic property of a rotor system with a squeeze film damper (SFD) using magnetic fluid. An electromagnet is installed in the inner damper of the SFD. The magnetic fluid is well known as a functional fluid. Its rheological property can be changed by controlling the applied current to the fluid and the fluid can be used as lubricant. Basically, the proposed SFD has the characteristics of a conventional SFD without an applied current, while the damping and stiffness properties change according to the variation of the applied electric current. Therefore, when the applied current is changed, the whirling vibration of the rotor system can be effectively reduced. The clustering-based hybrid evolutionary algorithm (CHEA) is used to identify linear stiffness and damping coefficients of the SFD based on measured unbalance responses.

• 한국실내디자인학회논문집
• /
• 제20권2호
• /
• pp.47-54
• /
• 2011

In Alvar Aalto's designs, important factors of complex building designs including Wolfsburg cultural center are that they insinuate how to develop each architectural type and how to combine them in a building. The humane and physical background studies, and wholistic and systematic approaches are adopted to fulfill research purposes. Comparison with other buildings are necessary to reveal true meaning of this building. The result of analysis show characteristics of Wolfsburg cultural center as follows; hybrid composition of mass and elevation, spatial effect using level difference and light, massing variation of roof, and creating space for various activities. Wolfsburg cultural center designed in late 1950s has greatly affected Aalto's later works through various architectural experiments because it is the first cultural complex project that combined various architectural types. Especially library in the cultural center has shown transitional characteristics to famous fan-type libraries of 1960s while maintained features about Viipuri library. Wolfsburg cultural center act as an another type which present new principles of clustering, massing and exterior design. Its true meaning lies in forming a humanizing place beyond spatial configuration.

• Journal of Astronomy and Space Sciences
• /
• 제29권4호
• /
• pp.389-395
• /
• 2012

The problem of spacecraft attitude control is solved using an adaptive neuro-fuzzy inference system (ANFIS). An ANFIS produces a control signal for one of the three axes of a spacecraft's body frame, so in total three ANFISs are constructed for 3-axis attitude control. The fuzzy inference system of the ANFIS is initialized using a subtractive clustering method. The ANFIS is trained by a hybrid learning algorithm using the data obtained from attitude control simulations using state-dependent Riccati equation controller. The training data set for each axis is composed of state errors for 3 axes (roll, pitch, and yaw) and a control signal for one of the 3 axes. The stability region of the ANFIS controller is estimated numerically based on Lyapunov stability theory using a numerical method to calculate Jacobian matrix. To measure the performance of the ANFIS controller, root mean square error and correlation factor are used as performance indicators. The performance is tested on two ANFIS controllers trained in different conditions. The test results show that the performance indicators are proper in the sense that the ANFIS controller with the larger stability region provides better performance according to the performance indicators.

• 한국소음진동공학회논문집
• /
• 제15권11호
• /
• pp.1262-1267
• /
• 2005

The paper presents the identification of dynamic property of a rotor system with a squeeze film damper (SFD) using magnetic fluid. An electromagnet Is installed in the inner damper of the SFD. The magnetic fluid is well known as a functional fluid. Its rheological property can be changed by controlling the applied current to the fluid and the fluid can be used as lubricant. Basically, the proposed SFD has the characteristics of a conventional SFD without an applied current, while the damping and stiffness Properties change according to the variation of the applied electric current. Therefore, when the applied current is changed, the whirling vibration of the rotor system can be effectively reduced. The clustering-based hybrid evolutionary algorithm (CHEA) is used to identify linear stiffness and damping coefficients of the SFD based on measured unbalance responses.

• Nuclear Engineering and Technology
• /
• 제39권4호
• /
• pp.337-348
• /
• 2007

A fuzzy neural network model is presented to predict residual stress for dissimilar metal welding under various welding conditions. The fuzzy neural network model, which consists of a fuzzy inference system and a neuronal training system, is optimized by a hybrid learning method that combines a genetic algorithm to optimize the membership function parameters and a least squares method to solve the consequent parameters. The data of finite element analysis are divided into four data groups, which are split according to two end-section constraints and two prediction paths. Four fuzzy neural network models were therefore applied to the numerical data obtained from the finite element analysis for the two end-section constraints and the two prediction paths. The fuzzy neural network models were trained with the aid of a data set prepared for training (training data), optimized by means of an optimization data set and verified by means of a test data set that was different (independent) from the training data and the optimization data. The accuracy of fuzzy neural network models is known to be sufficiently accurate for use in an integrity evaluation by predicting the residual stress of dissimilar metal welding zones.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 추계학술대회
• /
• pp.96-98
• /
• 2014

무선 센서 네트워크(WSN)는 컴퓨팅 능력과 무선 통신 능력을 갖추고 있는 센서 노드로부터 획득한 정보를 무선으로 실시간 수집하며, 처리, 활용하는 기술로서 현재 그 응용 분야는 환경 모니터링, 헬스 케어, 보안, 스마트 홈, 스마트 그리드 등 매우 다양하다. 하지만 무선 센서 네트워크는 저가의 센서 노드를 구성하기 위해 저전력과 저용량이라는 제약조건을 갖고 있다. 그러므로 무선 센서 네트워크에서는 제한된 에너지와 용량을 효율적으로 사용하는 알고리즘이 요구된다. 본 논문에서는 노드간의 연결 상태와 남아있는 에너지의 양을 비교함으로써 하이브리드 형식의 클러스터 헤드 노드를 선정하고 클러스터링하는 알고리즘을 제안함으로서 무선 센서 네트워크의 효율성과 정확성 증대를 목표로 한다.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.440-449
• /
• 2022

In recent years, the air pollution and Air Quality Index (AQI) has been a pivotal point for researchers due to its effect on human health. Various research has been done in predicting the AQI but most of these studies, either lack dense temporal data or cover one or two air pollutant elements. In this paper, a hybrid Convolutional Neural approach integrated with recurrent neural network architecture (CNN-LSTM), is presented to find air pollution inference using a multivariate air pollutant elements dataset. The aim of this research is to design a robust and real-time air pollutant forecasting system by exploiting a neural network. The proposed approach is implemented on a 24-month dataset from Seoul, Republic of Korea. The predicted results are cross-validated with the real dataset and compared with the state-of-the-art techniques to evaluate its robustness and performance. The proposed model outperforms SVM, SVM-Polynomial, ANN, and RF models with 60.17%, 68.99%, 14.6%, and 6.29%, respectively. The model performs SVM and SVM-Polynomial in predicting O3 by 78.04% and 83.79%, respectively. Overall performance of the model is measured in terms of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE).