• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.372-372
• /
• 2000

In this paper, we propose Neuro Fuzzy Polynomial Networks(NFPN) based on Polynomial Neural Network(PNN) and Neuro-Fuzzy(NF) for model identification of complex and nonlinear systems. The proposed NFPN is generated from the mutually combined structure of both NF and PNN. The one and the other are considered as the premise part and consequence part of NFPN structure respectively. As the premise part of NFPN, NF uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. As the consequence part of NFPN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. NFPN is available effectively for multi-input variables and high-order polynomial according to the combination of NF with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. In order to evaluate the performance of proposed models, we use the nonlinear function. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.

• Advances in materials Research
• /
• 제11권1호
• /
• pp.75-90
• /
• 2022

In this paper, functionality of soft computing algorithms such as Group method of data handling (GMDH), Random forest (RF), Random tree (RT), Linear regression (LR), M5P, and artificial neural network (ANN) have been looked out to predict the compressive strength of concrete mixed with marble powder. Assessment of result suggests that, the overall performance of ANN based model gives preferable results over the different applied algorithms for the estimate of compressive strength of concrete. The results of coefficient of correlation were maximum in ANN model (0.9139) accompanied through RT with coefficient of correlation (CC) value 0.8241 and minimum root mean square error (RMSE) value of ANN (4.5611) followed by RT with RMSE (5.4246). Similarly, other evaluating parameters like, Willmott's index and Nash-sutcliffe coefficient value of ANN was 0.9458 and 0.7502 followed by RT model (0.8763 and 0.6628). The end result showed that, for both subsets i.e., training and testing subset, ANN has the potential to estimate the compressive strength of concrete. Also, the results of sensitivity suggest that the water-cement ratio has a massive impact in estimating the compressive strength of concrete with marble powder with ANN based model in evaluation with the different parameters for this data set.

• 제어로봇시스템학회논문지
• /
• 제7권8호
• /
• 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.

• Computers and Concrete
• /
• 제22권2호
• /
• pp.197-207
• /
• 2018

In the present study, group method of data handling networks (GMDH) are adopted and evaluated for shear strength prediction of both FRP-reinforced concrete members with and without stirrups. Input parameters considered for the GMDH are altogether 12 influential geometrical and mechanical parameters. Two available and very recently collected comprehensive datasets containing 112 and 175 data samples are used to develop new models for two cases with and without shear reinforcement, respectively. The proposed GMDH models are compared with several codes of practice. An artificial neural network (ANN) model and an ANFIS based model are also developed using the same databases to further assessment of GMDH. The accuracy of the developed models is evaluated by statistical error parameters. The results show that the GMDH outperforms other models and successfully can be used as a practical and effective tool for shear strength prediction of members without stirrups ($R^2=0.94$) and with stirrups ($R^2=0.95$). Furthermore, the relative importance and influence of input parameters in the prediction of shear capacity of reinforced concrete members are evaluated through parametric and sensitivity analyses.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권8호
• /
• pp.551-560
• /
• 2004

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms (GAs). The proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series), A comparative analysis reveals that the proposed SOFPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literatures.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2762-2764
• /
• 2001

In this study, we introduce and investigate a class of dynamic perceptron architectures, discuss a comprehensive design methodology and carry out a series of numeric experiments. The proposed dynamic perceptron architectures are called as Polynomial Neural Networks(PNN). PNN is a flexible neural architecture whose topology is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated on the fly. In this sense, PNN is a self-organizing network. PNN has two kinds of networks, Polynomial Neuron(FPN)-based and Fuzzy Polynomial Neuron(FPN)-based networks, according to a polynomial structure. The essence of the design procedure of PN-based Self-organizing Polynomial Neural Networks(SOPNN) dwells on the Group Method of Data Handling (GMDH) [1]. Each node of the SOPNN exhibits a high level of flexibility and realizes a polynomial type of mapping (linear, quadratic, and cubic) between input and output variables. FPN-based SOPNN dwells on the ideas of fuzzy rule-based computing and neural networks. Simulations involve a series of synthetic as well as experimental data used across various neurofuzzy systems. A detailed comparative analysis is included as well.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2005년도 추계학술대회 학술발표 논문집 제15권 제2호
• /
• pp.483-487
• /
• 2005

We introduce a new architecture of hetero-hybridized feed-forward neural networks composed of fuzzy set-based polynomial neural networks (FSPNN) and polynomial neural networks (PM) that are based on a genetically optimized multi-layer perceptron and develop their comprehensive design methodology involving mechanisms of genetic optimization and Information Granulation. The construction of Information Granulation based HFSPNN (IG-HFSPNN) exploits fundamental technologies of Computational Intelligence(Cl), namely fuzzy sets, neural networks, and genetic algorithms(GAs) and Information Granulation. The architecture of the resulting genetically optimized Information Granulation based HFSPNN (namely IG-gHFSPNN) results from a synergistic usage of the hybrid system generated by combining new fuzzy set based polynomial neurons (FPNs)-based Fuzzy Neural Networks(PM) with polynomial neurons (PNs)-based Polynomial Neural Networks(PM). The design of the conventional genetically optimized HFPNN exploits the extended Group Method of Data Handling(GMDH) with some essential parameters of the network being tuned by using Genetie Algorithms throughout the overall development process. However, the new proposed IG-HFSPNN adopts a new method called as Information Granulation to deal with Information Granules which are included in the real system, and a new type of fuzzy polynomial neuron called as fuzzy set based polynomial neuron. The performance of the IG-gHFPNN is quantified through experimentation.

• Journal of Biosystems Engineering
• /
• 제26권5호
• /
• pp.461-468
• /
• 2001

Impact between fruits and other materials is a major cause of product damage in harvesting and handling systems. The oriental pears are more susceptible to bruising than other fruits such as European pears and apples, and are required more careful handling. The interest in the handling of the pears for the processing systems has raised the question of the allowable drop height to which pears can be dropped without causing objectionable damage. Drop tests on pears were conducted using an impact device developed by authors to estimate the allowable drop height without bruising. The impact device was constructed to hold in a selected orientation and to release a fruit by vacuum for dropping on to a force transducer. The drop height was adjustable for zero to 60 cm to achieve the desired distance between the bottom of the fruits and the top of the impact force transducer. The transducer was secured to 150 kg$\sub$f/ concrete block. The transducer signal was sampled every 0.17 ms with a strain gage measurement board in the micro computer where it was digitaly stored for later analysis. The selected sample fruit was Niitaka cultivar of pears which is one of the most promising fruit for export in Korea. The pears were harvested during the 1998 harvest season from an orchard in Daejeon. The sample fruit was selected from two groups which were stored for 3 months and 5 months respectively by the method of current commercial practice. The pears were allowed to stabilize at environmental condition(18$^{\circ}C$, 65% rh) of the experimental room. One hundred fifty six pears were tested from the heights of 5, 7.5. 10 and 12.5 cm while measurement were made of impact peak force, contact time, time to peak force, dwell time, pear diameter and mass. The bioyield strength and modulus of elasticity were measured using UTM immediately after each drop test. The allowable drop height was estimated on the base of bioyield strength of the pears in two ways. One was assumed the peak force during impact test increasing linearly with time, and the other was based on the actual drop test results. The computer program was developed for measuring the impact characteristics of the pears and analyzing the data obtained in the study. The peak force increased while contact times decreased with increasing drop height and contact times of the sample from the hard tissue group. The allowable drop height increased with increasing bioyield strength and contact times, and also varied with Poisson\`s ratio, mass and equilibrium radius of the pears. The allowable drop height calculated by a theoretical method was in the range from 1 to 4 cm, meanwhile, the estimated drop height considering the result of the impact test was in the range from 1 to 6 cm. Since the physical properties of fruits affected significantly the allowable drop height, the physical properties of the fruits should be considered when estimating the allowable drop height.

• 한국태양에너지학회:학술대회논문집
• /
• 한국태양에너지학회 2009년도 추계학술발표대회 논문집
• /
• pp.394-399
• /
• 2009

Since some decades ago, there has been a concern for resource depletion and environmental pollution associated with building properties. In addressing such impact of the built environment, there is a recognition of the existence of alternative building materials, fuels for energy supply as well as technologies for waste handling and disposal. Nevertheless, for long time, the choice between such alternatives was dictated by factors such as differences in prices and aesthetic values. A new important dimension in discriminating between different options is the environmental dimension. This aspect is important since buildings are one of the spatially big new additions to the natural environment that consume a lot of materials and energy during their long lifetime. Thus, with the environmental dimension kept in mind, a existing cost estimation needs to be changed. A new cost assessment method, Life Cycle Cost, should calculate overall costs with dimensional factors: investment and utility costs as well as maintenance costs over the lifetime of the building. Aiming to give an overview of the present status of Building Life Cycle Assessment(LCA) tools as a basis for further research and development including economic performance, this paper describes and compares 3 different tools for Life Cycle Assessment(LCA) and economic analysis of the green buildings. This paper compared these approaches based on various aspects. These include economic analysis method, evaluation duration, data of results(index). Use of the comparison analysis is to produce a better picture and indicate profits and shortcomings for the tools as a group; thus providing important direction improvement of LCA tool as well as further research and development of this group of tools.