• The Journal of Korean Institute of Information Technology
• /
• v.18 no.5
• /
• pp.55-64
• /
• 2020

Estimating the state of charge (SOC) of a battery is essential for increasing the stability and reliability of a photovoltaic system. In this study, battery SOC estimation methods were proposed using artificial neural networks (ANNs) with gradient descent (GD), Levenberg-Marquardt (LM), and scaled conjugate gradient (SCG), and an adaptive neuro-fuzzy inference system (ANFIS). The charge start voltage and the integrated charge current were used as input data and the SOC was used as output data. Four models (ANN-GD, ANN-LM, ANN-SCG, and ANFIS) were implemented for battery SOC estimation and compared using MATLAB. The experimental results revealed that battery SOC estimation using the ANFIS model had both the highest accuracy and highest convergence speed.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.2
• /
• pp.101-106
• /
• 2010

We propose an approach to estimate the real-time moving trajectory of an object in this paper. The object's position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Extended Kalman Filter(EKF) and neural networks are utilized cooperatively. Since the EKF needs to approximate a nonlinear system into a linear model in order to estimate the states, there still exist errors as well as uncertainties. To resolve this problem, in this approach the Kohonen networks, which have a high adaptability to the memory of the inputoutput relationship, are utilized for the nonlinear region. In addition to this, the Kohonen network, as a sort of neural network, can effectively adapt to the dynamic variations and become robust against noises. This approach is derived from the observation that the Kohonen network is a type of self-organized map and is spatially oriented, which makes it suitable for determining the trajectories of moving objects. The superiority of the proposed algorithm compared with the EKF is demonstrated through real experiments.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2005.11a
• /
• pp.191-194
• /
• 2005

본 논문에서는 방송 영상에서 조명효과와 크기변화 등에 강인한 얼굴패턴 검출기법을 제시한다. 제안된 얼굴검출 모델은 영상 전처리 과정과 얼굴패턴 검출 과정으로 이루어진다. 전처리 과정은 조명변화에 대한 보정기능과 다중필터에 의한 후보영역 선별기능으로 구분된다. 얼굴패턴 검출과정은 다단계의 특징지도 생성과정과 패턴분류 과정으로 이루어진다. 특징지도를 생성하기 위하여 가보(Gabor) 필터계층을 포함하는 CNN(Convolutional Neural Networks)모델을 도입하였다. 다양한 배경을 고려한 효과적인 학습을 위하여 본 논문에서는 억제성의 뉴런(Inhibitory neuron)을 포함하는 구조의 CNN모델을 적용한다. CNN으로부터 추출되는 특징집합은 최종 단계에서 WFMM(Weighted Fuzzy Min Max) 모델을 사용하여 분류된다. 이때 사용되는 특징집합의 크기는 분류기의 규모 및 계산량의 결정적인 역할을 준다. 이에 본 연구에서는 최종 분류 과정에 사용되는 특징의 수를 효과적으로 줄이기 위해 FMM모델을 사용하는 적응적인 특징 선별 기법을 제안한다. 또한 실제 영상을 통한 실험결과로부터 제안된 이론의 타당성을 고찰한다.

• Advances in nano research
• /
• v.16 no.6
• /
• pp.531-548
• /
• 2024

The study focuses on using remote sensing to gather data about the Earth's surface, particularly in urban environments, using satellites and aircraft-mounted sensors. It aims to develop a classification framework for road targets using multi-spectral imagery. By integrating Convolutional Neural Networks (CNNs) with XGBoost, the study seeks to enhance the accuracy and efficiency of road target identification, aiding urban infrastructure management and transportation planning. A novel aspect of the research is the incorporation of quantum sensors, which improve the resolution and sensitivity of the data. The model achieved high predictive accuracy with an MSE of 0.025, R-squared of 0.85, RMSE of 0.158, and MAE of 0.12. The CNN model showed excellent performance in road detection with 92% accuracy, 88% precision, 90% recall, and an f1-score of 89%. These results demonstrate the model's robustness and applicability in real-world urban planning scenarios, further enhanced by data augmentation and early stopping techniques.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.97-98
• /
• 2008

본 논문에서는 다중 출력을 가지는 퍼지 관계 기반 퍼지뉴럴네트워크를 설계한다. 퍼지 관계 기반 퍼지뉴럴네트워크는 선체 인력 변수에 따른 입력 공간을 분할함으로서 네트워크를 구성한다. 규칙의 전반부는 앞서 언급한 전체 입력 공간을 분할하여 표현하고, 규칙의 후반부는 다항식으로서 표현되며 오류역전파 알고리즘을 이용하여 연결가중치인 후반부 다항식을 학습한다. 또한, 각 입력에 대만 전반부 멤버쉽함수의 정점과 학습률 및 모멤텀 계수를 유전자 알고리즘을 이용하여 최적 동조한다. 따라서 유전자 알고리즘을 이용하여 퍼지뉴럴네트워크를 최적 설계한다. 마지막으로 제안된 모델은 표준 모델로서 널리 사용되는 수치적인 예를 통하여 평가한다.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.9-12
• /
• 2000

In this paper, we propose the auto-tunning method for the gradient of activation function using fuzzy inference. In order to verify the usefulness of the proposed method, we simulated it with one link manipulator system and confirmed the excellency,

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1968-1969
• /
• 2011

본 논문에서는 패턴 인식을 위한 다중 출력을 가지는 Interval Type-2 퍼지 집합을 이용한 퍼지 집합 기반 퍼지 뉴럴 네트워크를 소개한다. Interval Type-2 퍼지 집합 기반 퍼지 뉴럴 네트워크는 각 입력 변수에 따른 서로 분리된 입력 공간을 분할함으로서 네트워크 및 규칙을 구성한다. 규칙의 전반부는 퍼지 입력 공간을 개별적으로 분할하여 표현하고, 각 공간은 Interval Type-2 퍼지 집합으로 구성된다. 규칙의 후반부는 패턴 인식을 위한 다중 출력을 가지며 Interval 집합을 이용하여 다항식으로서 표현된다. 다항식의 계수인 연결가중치는 오류역 전파 알고리즘을 이용하여 학습한다. 또한 실수 코딩 유전자 알고리즘을 이용하여 제안된 네트워크를 최적화한다. 제안된 네트워크는 표준 모델로서 널리 사용되는 수치적인 예를 통하여 평가한다.

• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.797-799
• /
• 1999

In this paper, we design the Multi-FNN(Fuzzy-Neural Networks) using HCM Method. The proposed Multi-FNN uses simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rules. Also, We use HCM(Hard C-Means) method of clustering technique for improvement of output performance from pre-processing of input data. The parameters such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. We use the training and testing data set to obtain a balance between the approximation and the generalization of our model. Several numerical examples are used to evaluate the performance of the our model. From the results, we can obtain higher accuracy and feasibility than any other works presented previously.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.420-423
• /
• 2001

In this paper, the Multi-FNNs(Fuzzy-Neural Networks) architecture is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNNs architecture uses simplified inference and linear inference as fuzzy inference method and error back propagation algorithm as learning rules. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNNs according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNNs model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. To evaluate the performance of the proposed model we use the time series data for gas furnace and the NOx emission process data of gas turbine power plant.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.60 no.1
• /
• pp.6-12
• /
• 2011

In this study, we proposed a residential load modeling method based on neuro-fuzzy inference system by considering of various harmonics. The developed method was implemented by using harmonic information, fundamental frequency and voltage which are essential input factors in conventional method. Thus, the proposed method makes it possible to effectively estimate load characteristics in power lines with harmonics. To show the effectiveness, the proposed method has been intensively tested with various dataset acquired under the different frequency and voltage and compared it with a conventional method based on neural networks.