• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1131-1131
• /
• 2001

To develop a nondestructive quality evaluation technique of fruits, a K-mean algorism is applied to near infrared (NIR) spectroscopy of apples. The K-mean algorism is one of neural network partition methods and the goal is to partition the set of objects O into K disjoint clusters, where K is assumed to be known a priori. The algorism introduced by Macqueen draws an initial partition of the objects at random. It then computes the cluster centroids, assigns objects to the closest of them and iterates until a local minimum is obtained. The advantage of using neural network is that the spectra at the wavelengths having absorptions against chemical bonds including C-H and O-H types can be selected directly as input data. In conventional multiple regression approaches, the first wavelength is selected manually around the absorbance wavelengths as showing a high correlation coefficient between the NIR $2^{nd}$ derivative spectrum and Brix value with a single regression. After that, the second and following wavelengths are selected statistically as the calibration equation shows a high correlation. Therefore, the second and following wavelengths are selected not in a NIR spectroscopic way but in a statistical way. In this research, the spectra at the six wavelengths including 900, 904, 914, 990, 1000 and 1016nm are selected as input data for K-mean analysis. 904nm is selected because the wavelength shows the highest correlation coefficients and is regarded as the absorbance wavelength. The others are selected because they show relatively high correlation coefficients and are revealed as the absorbance wavelengths against the chemical structures by B. G. Osborne. The experiment was performed with two phases. In first phase, a reflectance was acquired using fiber optics. The reflectance was calculated by comparing near infrared energy reflected from a Teflon sphere as a standard reference, and the $2^{nd}$ derivative spectra were used for K-mean analysis. Samples are intact 67 apples which are called Fuji and cultivated in Aomori prefecture in Japan. In second phase, the Brix values were measured with a commercially available refractometer in order to estimate the result of K-mean approach. The result shows a partition of the spectral data sets of 67 samples into eight clusters, and the apples are classified into samples having high Brix value and low Brix value. Consequently, the K-mean analysis realized the classification of apples on the basis of the Brix values.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.341-343
• /
• 2000

Traditionally electric power system are operated in such a way that the total fuel cost is minimized regardless of accounting for tie-lines transmission constraint and emissions produced. But tie-lines transmission and emissions constraint are very important issues in the operation and planning of electric power system. This paper presents the Two-Phase Neural Network(TPNN) to solve the Economic Load Dispatch (ELD) problem with tie-lines transmission and emissions constraint considering transmission losses. The transmission losses are obtained from the B-coefficient which approximate the system losses as s quadratic function of the real power generation. By applying the proposed algorithm to the test system, the usefulness of this algorithm is verified.

• 한국컴퓨터정보학회논문지
• /
• 제10권6호
• /
• pp.279-286
• /
• 2005

본 연구에서는 캐피탈시장에서의 고객신용예측을 위한 모형으로 여러 가지 인공신경망(Neural Network) 모형들을 유전자 알고리즘(Genetic Algorithm)을 이용하여 통합한 신용예측모형을 제안하였다. 10개의 학습된 인공신경망 모형들을 유전자알고리즘을 이용하여 종류별로 통합하여 MLP (Multi-Layered Perceptron), Linear, RBF(Radial Basis Function) 세 가지의 대표모델을 얻고 이를 다시 하나의 인공신경망 모델로 통합하였다. 이를 통합되기 이전의 각각의 인공신경망 모형들과 성능을 비교, 분석하여 본 연구에서 제안한 통합모형의 유효성과 통합방법의 타당성을 제시하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2674-2697
• /
• 2019

Identity authentication is a crucial line of defense for network security, and passwords are still the mainstream of identity authentication. So far trawling password attacking has been extensively studied, but the research related with personal information is always sporadic. Probabilistic context-free grammar (PCFG) and Markov chain-based models perform greatly well in trawling guessing. In this paper we propose a systematic targeted attacking model based on structure partition and string reorganization by migrating the above two models to targeted attacking, denoted as TG-SPSR. In structure partition phase, besides dividing passwords to basic structure similar to PCFG, we additionally define a trajectory-based keyboard pattern in the basic grammar and introduce index bits to accurately characterize the position of special characters. Moreover, we also construct a BiLSTM recurrent neural network classifier to characterize the behavior of password reuse and modification after defining nine kinds of modification rules. Extensive experimental results indicate that in online attacking, TG-SPSR outperforms traditional trawling attacking algorithms by average about 275%, and respectively outperforms its foremost counterparts, Personal-PCFG, TarGuess-I, by about 70% and 19%; In offline attacking, TG-SPSR outperforms traditional trawling attacking algorithms by average about 90%, outperforms Personal-PCFG and TarGuess-I by 85% and 30%, respectively.

• 한국광학회:학술대회논문집
• /
• 한국광학회 2003년도 하계학술발표회
• /
• pp.60-61
• /
• 2003

A new approach to reduce the computation time of genetic algorithm (GA) for making binary phase holograms is described. Synthesized holograms having diffraction efficiency of 75.8% and uniformity of 5.8% are proven in computer simulation and experimentally demonstrated. Recently, computer-generated holograms (CGHs) having high diffraction efficiency and flexibility of design have been widely developed in many applications such as optical information processing, optical computing, optical interconnection, etc. Among proposed optimization methods, GA has become popular due to its capability of reaching nearly global. However, there exits a drawback to consider when we use the genetic algorithm. It is the large amount of computation time to construct desired holograms. One of the major reasons that the GA' s operation may be time intensive results from the expense of computing the cost function that must Fourier transform the parameters encoded on the hologram into the fitness value. In trying to remedy this drawback, Artificial Neural Network (ANN) has been put forward, allowing CGHs to be created easily and quickly (1), but the quality of reconstructed images is not high enough to use in applications of high preciseness. For that, we are in attempt to find a new approach of combiningthe good properties and performance of both the GA and ANN to make CGHs of high diffraction efficiency in a short time. The optimization of CGH using the genetic algorithm is merely a process of iteration, including selection, crossover, and mutation operators [2]. It is worth noting that the evaluation of the cost function with the aim of selecting better holograms plays an important role in the implementation of the GA. However, this evaluation process wastes much time for Fourier transforming the encoded parameters on the hologram into the value to be solved. Depending on the speed of computer, this process can even last up to ten minutes. It will be more effective if instead of merely generating random holograms in the initial process, a set of approximately desired holograms is employed. By doing so, the initial population will contain less trial holograms equivalent to the reduction of the computation time of GA's. Accordingly, a hybrid algorithm that utilizes a trained neural network to initiate the GA's procedure is proposed. Consequently, the initial population contains less random holograms and is compensated by approximately desired holograms. Figure 1 is the flowchart of the hybrid algorithm in comparison with the classical GA. The procedure of synthesizing a hologram on computer is divided into two steps. First the simulation of holograms based on ANN method [1] to acquire approximately desired holograms is carried. With a teaching data set of 9 characters obtained from the classical GA, the number of layer is 3, the number of hidden node is 100, learning rate is 0.3, and momentum is 0.5, the artificial neural network trained enables us to attain the approximately desired holograms, which are fairly good agreement with what we suggested in the theory. The second step, effect of several parameters on the operation of the hybrid algorithm is investigated. In principle, the operation of the hybrid algorithm and GA are the same except the modification of the initial step. Hence, the verified results in Ref [2] of the parameters such as the probability of crossover and mutation, the tournament size, and the crossover block size are remained unchanged, beside of the reduced population size. The reconstructed image of 76.4% diffraction efficiency and 5.4% uniformity is achieved when the population size is 30, the iteration number is 2000, the probability of crossover is 0.75, and the probability of mutation is 0.001. A comparison between the hybrid algorithm and GA in term of diffraction efficiency and computation time is also evaluated as shown in Fig. 2. With a 66.7% reduction in computation time and a 2% increase in diffraction efficiency compared to the GA method, the hybrid algorithm demonstrates its efficient performance. In the optical experiment, the phase holograms were displayed on a programmable phase modulator (model XGA). Figures 3 are pictures of diffracted patterns of the letter "0" from the holograms generated using the hybrid algorithm. Diffraction efficiency of 75.8% and uniformity of 5.8% are measured. We see that the simulation and experiment results are fairly good agreement with each other. In this paper, Genetic Algorithm and Neural Network have been successfully combined in designing CGHs. This method gives a significant reduction in computation time compared to the GA method while still allowing holograms of high diffraction efficiency and uniformity to be achieved. This work was supported by No.mOl-2001-000-00324-0 (2002)) from the Korea Science & Engineering Foundation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.990-995
• /
• 1990

A minimum-time trajectory planning for two robot arms with designated paths and coordination is proposed. The problem considered in this paper is a subproblem of hierarchically decomposed trajectory planning approach for multiple robots : i) path planning, ii) coordination planning, iii) velocity planning. In coordination planning stage, coordination space, a specific form of configuration space, is constructed to determine collision region and collision-free region, and a collision-free coordination curve (CFCC) passing collision-free region is selected. In velocity planning stage, normal dynamic equations of the robots, described by joint angles, velocities and accelerations, are converted into simpler forms which are described by traveling distance along collision-free coordination curve. By utilizing maximum allowable torques and joint velocity limits, admissible range of velocity and acceleration along CFCC is derived, and a minimum-time velocity planning is calculated in phase plane. Also the planning algorithm itself is converted to simple numerical iterative calculation form based on the concept of neural optimization network, which gives a feasible approximate solution to this planning problem. To show the usefulness of proposed method, an example of trajectory planning for 2 SCARA type robots in common workspace is illustrated.

• Advances in nano research
• /
• 제13권5호
• /
• pp.499-512
• /
• 2022

This study investigates the efficiency of ensemble machine learning for predicting the lightweight-aggregate concrete (LWC) characteristics. A stacking ensemble (STEN) approach was proposed to estimate the dry density (DD) and 28 days compressive strength (Fc-28) of LWC using two meta-models called random forest regressor (RFR) and extra tree regressor (ETR), and two novel ensemble models called STEN-RFR and STEN-ETR, were constructed. Four standalone machine learning models including artificial neural network, gradient boosting regression, K neighbor regression, and support vector regression were used to compare the performance of the proposed models. For this purpose, a sum of 140 LWC mixtures with 21 influencing parameters for producing LWC with a density less than 1000 kg/m³, were used. Based on the experimental results with multiple performance criteria, it can be concluded that the proposed STEN-ETR model can be used to estimate the DD and Fc-28 of LWC. Moreover, the STEN-ETR approach was found to be a significant technique in prediction DD and Fc-28 of LWC with minimal prediction error. In the validation phase, the accuracy of the proposed STEN-ETR model in predicting DD and Fc-28 was found to be 96.79% and 81.50%, respectively. In addition, the significance of cement, water-cement ratio, silica fume, and aggregate with expanded glass variables is efficient in modeling DD and Fc-28 of LWC.

• Geomechanics and Engineering
• /
• 제31권2호
• /
• pp.129-147
• /
• 2022

The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R² = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R² = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.

• 전력전자학회논문지
• /
• 제4권4호
• /
• pp.357-367
• /
• 1999

매입형 영구자석 동기전동기와 인버터, 그리고 추진제어기로 구성된 추진시스템을 갖는 독립 구동형 전기자동차에 대하여 파라미터 변동특성을 반영하는 전동기 제어기법과 주행특성을 개선한 새로운 추진제어기 기법을 제시하였다. 기존의 방식과는 다르게 전동기의 등가파라미터인{{{{ { L}_{d } }} 와{{{{ { L}_{q } }} 의 변동을 전류의 크기뿐만 아니라 전류 위상각의 관점에서 고려하였으며, 해석적인 방법으로 전 영역에 대한 변동 곡선을 제시하였다. 그리고{{{{ { L}_{d } }}와 {{{{ { L}_{q } }}에 대한 변동을 신경회로망을 이용하여 추정기를 구성한 후 신경회로망 추정기를 갖는 매입형 영구자석 동기 전동기용 벡터제어 기법을 제시하였다. 또한, 추진제어기는 토크분배 기능과 토크약화제어 기능을 구비하도록 만들어졌으며, 선회 조종성과 슬립율이 안정 영역 내에서 운전 되도록 개선된 추진 제어기를 제시하였다. 제안된 제어기의 동특성을 실험과 모의 실험을 통하여 검증하였다.

• 인터넷정보학회논문지
• /
• 제22권1호
• /
• pp.23-30
• /
• 2021

본 논문은 다수의 오토인코더 모델들을 이용한 잡음에 강인한 이미지 분류 시스템을 제안한다. 딥러닝 기술의 발달로 이미지 분류의 정확도는 점점 높아지고 있다. 하지만 입력 이미지가 잡음에 의해서 오염된 경우에는 이미지 분류 성능이 급격히 저하된다. 이미지에 첨가되는 잡음은 이미지의 생성 및 전송 과정에서 필연적으로 발생할 수밖에 없다. 따라서 실제 환경에서 이미지 분류기가 사용되기 위해서는 잡음에 대한 처리 및 대응이 반드시 필요하다. 한편 오토인코더는 입력값과 출력값이 유사하도록 학습되어지는 인공신경망 모델이다. 입력데이터가 학습데이터와 유사하다면 오토인코더의 출력데이터와 입력데이터 사이의 오차는 작을 것이다. 하지만 입력 데이터가 학습데이터와 유사성이 없다면 오토인코더의 출력데이터와 입력데이터 사이의 오차는 클 것이다. 제안하는 시스템은 오토인코더의 입력데이터와 출력데이터 사이의 관계를 이용한다. 제안하는 시스템의 이미지 분류 절차는 2단계로 구성된다. 1단계에서 분류 가능성이 가장 높은 클래스 2개를 선정하고 이들 클래스의 분류 가능성이 서로 유사하면 2단계에서 추가적인 분류 절차를 거친다. 제안하는 시스템의 성능 분석을 위해 가우시안 잡음으로 오염된 MNIST 데이터셋을 대상으로 분류 정확도를 실험하였다. 실험 결과 잡음 환경에서 제안하는 시스템이 CNN(Convolutional Neural Network) 기반의 분류 기법에 비해 높은 정확도를 나타냄을 확인하였다.