• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2891-2893
• /
• 2005

In this paper, we introduce a new category of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multi-layer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. The conventional SOFPNN algorithm leads to a tendency to produce overly complex networks as well as a repetitive computation load by the trial and error method and/or the a repetitive parameter adjustment by designer. In order to generate a structurally and parametrically optimized network, such parameters need to be optimal. In this study, in solving the problems with the conventional SOFPNN, we introduce a new design approach of evolutionary optimized SOFPNN. Optimal parameters design available within FPN (viz. the no. of input variables, the order of the polynomial, input variables, and the no. of membership function) lead to structurally and parametrically optimized network which is more flexible as well as simpler architecture than the conventional SOFPNN. In addition, we determine the initial apexes of membership functions by genetic algorithm.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2627-2629
• /
• 2003

In this paper, we propose a new architecture of Genetic Algorithms(GAs)-based Self-Organizing Polynomial Neural Networks(SOPNN). The conventional SOPNN is based on the extended Group Method of Data Handling(GMDH) method and utilized the polynomial order (viz. linear, quadratic, and modified quadratic) as well as the number of node inputs fixed (selected in advance by designer) at Polynomial Neurons (or nodes) located in each layer through a growth process of the network. Moreover it does not guarantee that the SOPNN generated through learning has the optimal network architecture. But the proposed GA-based SOPNN enable the architecture to be a structurally more optimized networks, and to be much more flexible and preferable neural network than the conventional SOPNN. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented with using nonlinear system data.

• Smart Structures and Systems
• /
• v.33 no.4
• /
• pp.253-262
• /
• 2024

Current-based mechanical fault diagnosis is more convenient and low cost since additional sensors are not required. However, it is still challenging to achieve this goal due to the weak fault information in current signals. In this paper, a dual-loss convolutional neural network (DLCNN) is proposed to implement the intelligent bearing fault diagnosis via current signals. First, a novel similarity loss (SimL) function is developed, which is expected to maximize the intra-class similarity and minimize the inter-class similarity in the model optimization operation. In the loss function, a weight parameter is further introduced to achieve a balance and leverage the performance of SimL function. Second, the DLCNN model is constructed using the presented SimL and the cross-entropy loss. Finally, the two-phase current signals are fused and then fed into the DLCNN to provide more fault information. The proposed DLCNN is tested by experiment data, and the results confirm that the DLCNN achieves higher accuracy compared to the conventional CNN. Meanwhile, the feature visualization presents that the samples of different classes are separated well.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.235-238
• /
• 1996

In this paper, a new optimization method which is a kind of random searching is presented. The proposed method is called RasVal which is an abbreviation of Random Search Method with Variable Seaxch Length and it can search for a global minimum based on the probability density functions of searching, which can be modified using informations on success or failure of the past searching in order to execute intensified and diversified searching. By applying the proposed method to a nonlinear crane control system which can be controlled by the Universal Learning Network with radial basis function(R.B.P.), it has been proved that RasVal is superior in performance to the commonly used back propagation learning algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.221-224
• /
• 2001

In this paper, we propose the initial optimized structure of the Radial Basis Function Network which is more simple in the part on the structure and converges more faster than Neural Network with the analysis method using Time-Frequency Localization and genetic algorithm. When we construct the hidden node with the Radial Basis Function whose localization is similar with an approximation target function in the plane of the Time and Frequency, we have initial structure of RBFN, After that, we evaluate the parameters of RBF in the network and the parameters needed for the network is more a few. Finally, we make a good decision of the initial structure having an ability of approximation.

• Journal of Mechanical Science and Technology
• /
• v.20 no.11
• /
• pp.1873-1880
• /
• 2006

The results of this study suggest the use of a Back Propagation Network (BPN) algorithm for the detection of esophageal erosions or abnormalities - which are the important signs of esophagitis - in the analysis of the color and textural aspects of clinical images obtained by endoscopy. The authors have investigated the optimization of the learning condition by the number of neurons in the hidden layer within the structure of the neural network. By optimizing learning parameters, we learned and have validated esophageal erosion images and/or ulcers functioning as the critical diagnostic criteria for esophagitis and associated abnormalities. Validation was established by using twenty clinical images. The success rates for detection of esophagitis during calibration and during validation were 97.91% and 96.83%, respectively.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1356-1358
• /
• 1996

Hopfield's suggestion of a neural network model for associative memory aroused the interest of many scientists and led to efforts of mathematical analyses. But the Hopfield Network has several disadvantages such as spurious states and capacity limitation. In that sense many scientists and engineers are trying to use a new optimization algorithm called genetic algorithm. But it is hard to use this algorithm in Hopfileld Network because of the fixed architecture. In this paper we introduce another method to determine the weight of Hopfield type network using Genetic Algorithm.

• Journal of Internet of Things and Convergence
• /
• v.9 no.3
• /
• pp.61-67
• /
• 2023

In order to optimize the pulse electroforming copper process, a double hidden layer BP (Back Propagation) neural network is constructed. Through sample training, the mapping relationship between electroforming copper process conditions and target properties is accurately established, and the prediction of microhardness and tensile strength of the electroforming layer in the pulse electroforming copper process is realized. The predicted results are verified by electrodeposition copper test in copper pyrophosphate solution system with pulse power supply. The results show that the microhardness and tensile strength of copper layer predicted by "3-4-3-2" structure double hidden layer neural network are very close to the experimental values, and the relative error is less than 2.32%. In the parameter range, the microhardness of copper layer is between 100.3~205.6MPa and the tensile strength is between 112~485MPa.When the microhardness and tensile strength are optimal,the corresponding process conditions are as follows: current density is 2A-dm-2, pulse frequency is 2KHz and pulse duty cycle is 10%.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.161-172
• /
• 2017

In the paper, a hybrid technique is proposed for detecting the location and capacity of distributed generation (DG) sources like wind and photovoltaic (PV) in power system. The novelty of the proposed method is the combined performance of both the Biography Based Optimization (BBO) and Particle Swarm Optimization (PSO) techniques. The mentioned techniques are the optimization techniques, which are used for optimizing the optimum location and capacity of the DG sources for radial distribution network. Initially, the Artificial Neural Network (ANN) is applied to obtain the available capacity of DG sources like wind and PV for 24 hours. The BBO algorithm requires radial distribution network voltage, real and power loss for determining the optimum location and capacity of the DG. Here, the BBO input parameters are classified into sub parameters and allowed as the PSO algorithm optimization process. The PSO synthesis the problem and develops the sub solution with the help of sub parameters. The BBO migration and mutation process is applied for the sub solution of PSO for identifying the optimum location and capacity of DG. For the analysis of the proposed method, the test case is considered. The IEEE standard bench mark 33 bus system is utilized for analyzing the effectiveness of the proposed method. Then the proposed technique is implemented in the MATLAB/simulink platform and the effectiveness is analyzed by comparing it with the BBO and PSO techniques. The comparison results demonstrate the superiority of the proposed approach and confirm its potential to solve the problem.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.115-119
• /
• 2006

The channel is one of the precious and limited resources in wireless networks. There are many researches on the channel management. Recently, the optimization problem of guard channels has been an important issue. In this paper, we propose an intelligent channel management technique based on the neural networks. An SRN channel alteration model is developed to generate the learning data for the neural networks and the performance analysis of system. In the proposed technique, the neural network is trained to generate optimal guard channel number g, using backpropagation supervised learning algorithm. The optimal g is computed using the neural network and compared to the g computed by the SRN model. The numerical results show that the difference between the value of g by backpropagation and that value by SRN model is ignorable.