• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.8
• /
• pp.664-674
• /
• 2001

In this paper, as a new category of fuzzy-neural networks architecture, we propose Fuzzy Polynomial Neural Networks (FPNN) and discuss a comprehensive design methodology related to its architecture. FPNN dwells on the ideas of fuzzy rule-based computing and neural networks. The FPNN architecture consists of layers with activation nodes based on fuzzy inference rules. Here each activation node is presented as Fuzzy Polynomial Neuron(FPN). The conclusion part of the rules, especially the regression polynomial, uses several types of high-order polynomials such as linear, quadratic and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership functions are studied. It is worth stressing that the number of the layers and the nods in each layer of the FPNN are not predetermined, unlike in the case of the popular multilayer perceptron structure, but these are generated in a dynamic manner. With the aid of two representative time series process data, a detailed design procedure is discussed, and the stability is introduced as a measure of stability of the model for the comparative analysis of various architectures.

• Biomolecules & Therapeutics
• /
• v.28 no.3
• /
• pp.267-271
• /
• 2020

Gut microbiota produce dietary metabolites such as short-chain fatty acids, which exhibit anti-inflammatory effects. Free fatty acid receptor 2 (FFA2, formerly known as GPR43) is a specific receptor for short-chain fatty acids, such as acetate that regulates inflammatory responses. However, the therapeutic potential of FFA2 agonists for treatment of atopic dermatitis has not been investigated. We investigated the efficacy of the FFA2 agonist, 4-chloro-α-(1-methylethyl)-N-2-thiazoylylbenzeneacetanilide (4-CMTB), for treatment of atopic dermatitis induced by 2,4-dinitrochlorobenzene (DNCB). Long-term application of DNCB to the ears of mice resulted in significantly increased IgE in the serum, and induced atopic dermatitis-like skin lesions, characterized by mast cell accumulation and skin tissue hypertrophy. Treatment with 4-CMTB (10 mg/kg, i.p.) significantly suppressed DNCB-induced changes in IgE levels, ear skin hypertrophy, and mast cell accumulation. Treatment with 4-CMTB reduced DNCB-induced increases in Th2 cytokine (IL-4 and IL-13) levels in the ears, but did not alter Th1 or Th17 cytokine (IFN-γ and IL-17) levels. Furthermore, 4-CMTB blocked DNCB-induced lymph node enlargement. In conclusion, activation of FFA2 ameliorated DNCB-induced atopic dermatitis, which suggested that FFA2 is a therapeutic target for atopic dermatitis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5212-5230
• /
• 2016

How to determine the right number of small base stations to activate in multi-cell uplinks to match traffic from a fixed quantity of K users is an open question. This paper analyses the uplink cooperative that jointly receives base stations activation to explore this question. This paper is different from existing works only consider transmitting power as optimization objective function. The global objective function is formulated as a summation of two terms: transmitting power for data and coordinated overhead for control. Then, the joint base stations activation and beamforming problem is formulated as a mixed integer second order cone optimization. To solve this problem, we develop two polynomial-time distributed methods. Method one is a two-stage solution which activates no more than K small base stations (SBSs). Method two is a heuristic algorithm by dual decomposition to MI-SOCP that activates more SBSs to obtain multiple-antennae diversity gains. Thanks to the parallel computation for each node, our methods are more computationally efficient. The strengths and weaknesses of these two proposed two algorithms are also compared using numerical results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2568-2588
• /
• 2021

Shared mesh protection (SMP) protects traffic against failures occurring in a working path, as with linear protection, and allows resource sharing of protection paths with different endpoints. The SMP mechanism coordinates multiple protection paths that require shared resources when failures occur on multiple working paths. When multiple failures occur in SMP networks sharing limited resources, activation can fail because some of the resources in the protection path are already in use. In this case, a node confirming that a resource is not available has the option to wait until the resource is available or to withdraw activation of the protection path. In this study, we recognize that the protection switching time and the number of protected services can be different, depending on which option is used for SMP networks. Moreover, we propose a detailed design for the implementation of SMP by considering options and algorithms that are commonly needed for network nodes. A simulation shows the performance of an SMP system implemented with the proposed design and utilizing two options. The results demonstrate that resource utilization can be increased or protection switching time can be shortened depending on the option selected by the network administrator.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.163.1-163
• /
• 2001

In this paper, we use time-frequency localization analysis method to analize the target function and the area of the target space. When we analize the function with the time and frequency axis simultaneously, the characteristic of the function is shown more precisely and the area is covered by a certain block. After we analize the target function in the time-frequency space, we can decide the activation functions and compose the hidden layer of the RBFN by choosing the radial basis function which can represent the characteristic of the target function, RBFN made by this method, designs the good structure proper to the target problem because we can decide the number of hidden node first.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.2
• /
• pp.189-199
• /
• 1999

This paper presents an optimization algorithm for a stable Self Dynamic Neural Network(SDNN) using genetic algorithm. Optimized SDNN is applied to a problem of controlling nonlinear dynamical systems. SDNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. The real-time implementation is very important, and thus the neuro controller also needs to be designed such that it converges with a relatively small number of training cycles. SDW has considerably fewer weights than DNN. Since there is no interlink among the hidden layer. The object of proposed algorithm is that the number of self dynamic neuron node and the gradient of activation functions are simultaneously optimized by genetic algorithms. To guarantee convergence, an analytic method based on the Lyapunov function is used to find a stable learning for the SDNN. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed optimized SDNN considering stability is demonstrated by case studies.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.6
• /
• pp.767-772
• /
• 2018

Recently, some meta-heuristic algorithms, such as GA(Genetic Algorithm) and GP(Genetic Programming), have been used to optimize CNN(Convolutional Neural Network). The CNN, which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, the recent attempts to automatically construct CNN architectures are investigated and analyzed. First, two GA based methods are summarized. One is the optimization of CNN structures with the number and size of filters, connection between consecutive layers, and activation functions of each layer. The other is an new encoding method to represent complex convolutional layers in a fixed-length binary string, Second, CGP(Cartesian Genetic Programming) based method is surveyed for CNN structure optimization with highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.217-220
• /
• 2000

This paper describes the application of a neural network based adaptive line enhancer (ALE) for enhancement of the weak QRS complex corrupted with background noise. Modified fully-connected recurrent neural network is used as a nonlinear adaptive filter in the ALE. The connecting weights between network nodes as well as the parameters of the node activation function are updated at each iteration using the gradient descent algorithm. The real ECG signal buried with moderate and severe background noise is applied to the ALE. Simulation results show that the neural network based ALE performs well the enhancement of the QRS complex from noisy ECG signals.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.27 no.4
• /
• pp.289-300
• /
• 2001

Telomerase is a ribonucleoprotein that synthesizes telomere repeats. It has been reported that activation of telomerase was associtated with immortalization, proliferative activity and carcinogenesis. Recently, telomerase activity has been extensively studied in many kinds of malignant tumors for clinical diagnostic and/or prognostic utilities. In neuroblastoma, breast carcinoma, gastric carcinoma, non-small cell lung carcinoma, close relationship has been reported between high telomerase activity and lymph node metastasis, tumor aggressiveness and poor prognosis. The purpose of this study is to investigate the clinical implication of telomerase activity assay as an adjunctive factor in decision-making on neck node management, speedy pre-operative judging on histologic malignancy grading. Thus we performed semi-quantitative assay of telomerase activity using Telomerase PCR ELISA $kit^{(R)}$(Boeringer Manheim, Germany) and evaluated correlation between telomerase activity and tumor size, neck node metastasis, Anneroth malignancy score and influence of pre-operative chemotherapy on its activity in 27 cases of oral squamous cell carcinomas and 18 cases of normal oral epithelium. Also, correlation between telomerase activities and PCNA indices was evaluated. The results were obtained as follows: 1. The telomerase activities were detected in 24 specimens out of 27 oral squamous cell carcinoma specimens (88.9%) and in 5 specimens out of 18 normal oral epithelium specimens (27.8%). The mean value of telomerase activities was $0.9793{\pm}0.3428$ in 24 oral squamous cell carcinoma specimens and $0.4855{\pm}0.1117$ in 5 normal oral epithelium specimens. The positivity rate and mean value of telomerase activities in oral squamous cell carcinoma specimens were significantly higher than those of normal oral epithelium specimens (p<0.05). 2. There was no significant correlation between total Anneroth malignancy score and telomerase activity (p>0.05), but points of mitosis index and depth of invasion were significantly correlated with telomerase activities (p<0.05). 3. The positive immunohistochemical staining for PCNA(proliferating cell nuclear antigen) was observed in 26 specimens out of 27 oral squamous cell carcinoma specimens and mean value of PCNA indices of 26 specimens was $53.67{\pm}26.46$. PCNA indices were significantly correlated with telomerase activities (p<0.05). 4. The mean value of telomerase activities was significantly higher in pathologic T3/T4 group than in T1/T2 group (p<0.01). There was no significant difference of mean value of telomerase activities between pathologic neck node positive group and negative group (p> 0.05). Pre-operative chemotherapy significantly lowered the telomerase activities (p<0.05). The above results suggested telomerase activity could be used as diagnostic marker and adjunctive parameter for judging on histologic malignancy in oral squamous cell carcinoma.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.511-516
• /
• 2002

The neural networks may have problem such that the amount of calculation for the network learning goes too big according to the dimension of the dimension. To overcome this problem, the wavelet neural networks(WNN) which use the orthogonal basis function in the hidden node are proposed. One can compose wavelet functions as activation functions in the WNN by determining the scale and center of wavelet function. In this paper, when we compose the WNN using wavelet functions, we set a single scale function as a node function together. We intend that one scale function approximates the target function roughly, the other wavelet functions approximate it finely During the determination of the parameters, the wavelet functions can be determined by the global search for solutions suitable for the suggested problem using the genetic algorithm and finally, we use the back-propagation algorithm in the learning of the weights.