• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.1
• /
• pp.84-89
• /
• 2004

The machine cell formation problem is the problem to group machines into machine families and parts into part families so as to minimize bottleneck machines, exceptional parts, and inter-cell part movements in cellular manufacturing systems and flexible manufacturing systems. This paper proposes a new machine cell formation method based on the adaptive Hamming net which is a kind of neural network model. To show the applicability of the proposed method, it presents some experiment results and compares the method with other cell formation methods. From the experiments, we observed that the proposed method could produce good cells for the machine cell formation problem.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.2
• /
• pp.125-128
• /
• 2004

Using the theory of Generalized Nets we have modelled the information exchange within the electronic archives of an idealized univerity Intranet.

• Journal of Korea Multimedia Society
• /
• v.4 no.4
• /
• pp.333-338
• /
• 2001

In this paper, fuzzy-ARTMAP equalizer is developed mainly for overcoming the obstacles, such as complexity and long training, in implementing the previously developed neural-basis equalizers. The proposed fuzzy-ARTMAP equalizer is fast and easy to train and includes capabilities not found in other neural network approaches a small number of parameters, no requirements for the choice of initial weights, no risk of getting trapped in local minima, and capability of adding new data without retraining previously trained data. In simulation studies, binary signals were generated at random from linear channel with Gaussian noise. The performance of the proposed equalizer is compared with other neural net basis equalizers, such as MLP and RBF equalizers. The fuzzy ARTMAP equalizer combines relatively simple structure and fast processing speed; it gives accurate results for nonlinear problems that cannot be solved with a linear equalizer.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.5
• /
• pp.797-804
• /
• 2017

A social network is a typical social science environment with both network and iteration characteristics. This research presents a reaction analysis model of how each node responds to social networks when given input such as promotions or incentives. In addition, the setting value of a specific node is changed while examining the response of each node. And we try to understand the reactions of the nodes involved. The reaction analysis model is constructed by applying various techniques such as unidirectional, fuzzy set, weighting, and cyclic feedback, so it can accommodate the complicated environment of practice. Finally, the implementation model is implemented using Vensim rather than NetLogo because it requires repetitive input, change of setting value in real time, and analysis of association between nodes.

• Nuclear Engineering and Technology
• /
• v.54 no.3
• /
• pp.948-958
• /
• 2022

Since reliability and security of man-machine system increasingly depend on reliability of human, human reliability analysis (HRA) has attracted a lot of attention in many fields especially in nuclear engineering. Dependence assessment among human tasks is a important part in HRA which contributes to an appropriate evaluation result. Most of methods in HRA are based on experts' opinions which are subjective and uncertain. Also, the dependence influencing factors are usually considered to be constant, which is unrealistic. In this paper, a new model based on Dempster-Shafer evidence theory (DSET) and fuzzy number is proposed to handle the dependence between two tasks in HRA under uncertain and dynamic situations. First, the dependence influencing factors are identified and the judgments on the factors are represented as basic belief assignments (BBAs). Second, the BBAs of the factors that varying with time are reconstructed based on the correction BBA derived from time value. Then, BBAs of all factors are combined to gain the fused BBA. Finally, conditional human error probability (CHEP) is derived based on the fused BBA. The proposed method can deal with uncertainties in the judgments and dynamics of the dependence influencing factors. A case study is illustrated to show the effectiveness and the flexibility of the proposed method.

• Nuclear Engineering and Technology
• /
• v.54 no.11
• /
• pp.4095-4101
• /
• 2022

Following the climate-related disasters considered by several efforts, the nuclear capacity needs to double by 2050 compared to 2015. So, it is reasonable to investigate global warming incorporated with the fuzzy set theory for nuclear energy consumption in the aspect of fuzziness and nonlinearity of temperature variations. The complex modeling is proposed for the enhanced assessment of climate change where simulations indicate the degree of influence with the Boolean values between 0.0 and 1.0 in the designed variables. In the case of OIL, there are many 1.0 values between 20^th and 60^th months in the simulations where there are 10 times more for a 1.0 value in influence. Hence, the temperature variable can give the effective time using this study for 100 months. In the analysis, the 1.0 value in NUCLEAR means the highest influence of the modeling as the temperature increases resulting in global warming. In detail, the first influence happens near the 8th month and then there are four times more influences than effects in the early part of the temperature mitigation. Eventually, in the GLOBAL WARMING, the highest peak is around the 20^th month, and then it is stabilized.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.773-779
• /
• 1996

Dried oak mushroom have complex and various visual features. Grading and sorting of dried oak mushrooms has been done by the human expert. Though actions involved in human grading looked simple, a decision making underneath the simple action comes from the result of the complex neural processing of the visual image. Through processing details involved in human visual recognition has not been fully investigated yet, it might say human can recognize objects via one of three ways such as extracting specific features or just image itself without extracting those features or in a combined manner. In most cases, extracting some special quantitative features from the camera image requires complex algorithms and processing of the gray level image requires the heavy computing load. This fact can be worse especially in dealing with nonuniform, irregular and fuzzy shaped agricultural products, resulting in poor performance because of the sensitiveness to the crisp criteria or specific ules set up by algorithms. Also restriction of the real time processing often forces to use binary segmentation but in that case some important information of the object can be lost. In this paper, the neuro net based real time recognition algorithm was proposed without extracting any visual feature but using only the directly captured raw gray images. Specially formated adaptable size of grids was proposed for the network input. The compensation of illumination was also done to accomodate the variable lighting environment. The proposed grading scheme showed very successful results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.11
• /
• pp.7971-7977
• /
• 2015

This paper attempts to select the attributes of job creation and to rank them for evaluation of companies' job creation. And the results of this paper are expected to provide the information for the polices of job creation. In doing so, this paper applies fuzzy decision making analysis that reflects ambiguity and uncertainty in decision-making process. According to the results, the weight of quality of employment is similar with that of quantity of employment. In addition, annual employment growth rate, annual net employment are ranked as first and the percentage of irregular employment, the average length of employment of all workers, average monthly wages of all workers, and employment growth over sales growth rate are next ranked.

• IE interfaces
• /
• v.13 no.1
• /
• pp.92-99
• /
• 2000

Conflicts and interruptions caused by resource failures and rush orders require a nonlinear dynamic production management. Generally the PP&C systems used in industry presently do not meet these requirements because of their rigid concepts. Starting with the grasp of the disadvantages of current approaches, this paper presents a control structure that enables system to react to various malfunctions using a planning tolerance concept. Also, production processes are modeled by using Fuzzy-Petri-Net modeling tool in other to handle the complexity of job allocation and the existence of many disparities. On the basis of this model the developed system support the short-term shop control by rule based decision.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.4
• /
• pp.314-318
• /
• 2010

Predicting Alpha-helicies, Beta-sheets and Turns of a proteins secondary structure is a complex non-linear task that has been approached by several techniques such as Neural Networks, Genetic Algorithms, Decision Trees and other statistical or heuristic methods. This project introduces a new machine learning method by combining Bayesian Inference with offline trained Multilayered Perceptron (MLP) models as the likelihood for secondary structure prediction of proteins. With varying window sizes of neighboring amino acid information, the information is extracted and passed back and forth between the Neural Net and the Bayesian Inference process until the posterior probability of the secondary structure converges.