• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.487-496
• /
• 2000

In this paper, the Multi-FNN(Fuzzy-Neural Networks) model is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNN is based on Yamakawa's FNN and uses simplified inference as fuzzy inference method and error back propagation algorithm as learning rules. We use a HCM clustering and Genetic Algorithms(GAs) to identify both the structure and the parameters of a Multi-FNN model. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNN according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNN model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. A aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. The aggregate performance index stands for an aggregate objective function with a weighting factor to consider a mutual balance and dependency between approximation and predictive abilities. According to the selection and adjustment of a weighting factor of this aggregate abjective function which depends on the number of data and a certain degree of nonlinearity, we show that it is available and effective to design an optimal Multi-FNN model. To evaluate the performance of the proposed model, we use the time series data for gas furnace and the numerical data of nonlinear function.

• Korean journal of communication and information
• /
• v.22
• /
• pp.77-106
• /
• 2003

As globalization of communication is going on and as the media have become increasingly central to the world economy, media policy matters have become the province of world economic organizations like the IMF and the WTO. The WTO service negotiation is focused primarily on the discriminatory and quantitative barriers associated with the trade of audiovisual services. Domestic measures such as subsidization, content regulation including quotas, and licensing requirements and restrictions on foreign ownership and control are at issues here. These measures have been successfully implemented by countries wishing to withstand competition from the American audiovisual industry. The debate about trade in audiovisual services is permeated by the unstated assumption that these programs are pure commodities whose production, distribution, exhibition and in turn, values are solely determined by the market forces. It is therefore presumed that liberalization of trade in audiovisual services will benefit all, serving cultural pluralism and diversity as well as economic efficiency. However, this assumption is not shared by developing countries, the recipients of U.S. television material. They argue audiovisual sector requires a social and cultural approach, since it plays a key role in the preservation of people's identity and social bonds. They claim that it is the each state's right to define its media policy and to implement it through the means it considers fit. These clashing views over the nature of the audiovisual material and the ways in which protect cultural pluralism and diversity do not confine to be the realm of theoretical debate. Each state's interest and motivation to protect its local industry and to have a competitive advantage in the international market is working in this battle. Consolidation with the countries like Australia, Canada, and EU nations, in favour of cultural exemption, seems to be the best policy for us. However, we are not entirely free from the WTO pressures, considering relation to the U. S. This study analyzes Korean Broadcasting Law compared with those of other OECD countries and tries to propose some strategical guidelines facing WTO service negotiation in the area of broadcasting.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.563-568
• /
• 2007

This paper presents a methodology for predicting nonlinear time series based on the neural network with weighted fuzzy membership functions (NEWFM). The degree of classification intensity is obtained by bounded sum of weighted fuzzy membership functions extracted by NEWFM, then weighted average defuzzification is used for predicting nonlinear time series. The experimental results demonstrate that NEWFM has the classification capability of 92.22% against the target class of GDP. The time series created by NEWFM model has a relatively close approximation to the GDP which is a typical business cycle indicator, and has been proved to be a useful indicator which has the turning point forecasting capability of average 12 months in the peak point and average 6 months in the trough point during 5th to 8th cyclical period. In addition, NEWFM measures the efficiency of the economic indexes by the feature selection and enables the users to forecast with reduced numbers of 7 among 10 leading indexes while improving the classification rate from 90% to 92.22%.

• Korean Journal of Ecology and Environment
• /
• v.56 no.3
• /
• pp.218-228
• /
• 2023

Invasive predators are one of the most damaging species groups to biodiversity. In the Nakdong River, the lake skygazer Chanodichthys erythropterus is a dominant species that is fiercely carnivorous and a concern for commercial fish. Although it is important to understand the ecological characteristics related to the feeding habit, studies on the diets of lake skygazer in Nakdong River have been limited to studies of gut contents. In this study, the trophic position (TP) and feeding habits of C. erythropterus were studied by calculating TPs using samples collected from 13 sites throughout the Nakdong River. Compound-specific isotopic analysis of amino acids provided reliable TPs from the muscle of Lake skygazer C. erythropterus without any isotope baseline. The results were approximately 3 to 3.6 and suggesting a carnivorous but size-dependent prey variation. In particular, the TP variability of C. erythropterus observed in the Nakdong River showed that it had a selective feeding habit compared to carnivorous fish species of relatively similar trophic levels.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.3
• /
• pp.293-304
• /
• 2024

In this paper, efficient and reliable methodologies for conducting sea trials to evaluate the performance of hull-mounted sonar systems is discussed. These systems undergo performance verification during ship construction via sea trials. However, the evaluation procedures often lack detailed consideration of variabilities in detection performance due to seabed topography, seasonal factors. To resolve this issue, temperature and salinity structure data were collected from 1967 to 2022 using ARGO floats and ocean observers data. The paper proposes an efficient and reliable sea trial method incorporating Bellhop modeling. Furthermore, a machine learning model applying a Physics-Informed Neural Networks was developed using the acquired data. This model predicts the sound speed profile at specific points within the sea trial area, reflecting seasonal elements of performance evaluation. In this study, we predicted the seasonal variations in sound speed structure during sea trial operations at a specific location within the trial area. We then proposed a strategy to account for the variability in detection performance caused by seasonal factors, using results from Bellhop modeling.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.15 no.1
• /
• pp.25-35
• /
• 2010

The biodiversity of eukaryotic plankton has commonly been used to evaluate the status of aquatic ecosystems. Therefore, an accurate and rapid method for species identification is needed to reveal the biodiversity of environmental water samples. To date, molecular methods have provided a great deal of information that has enabled identification of the hidden biodiversity in environmental samples. In this study, we utilized environmental polymerase chain reaction (PCR) and constructed the 18S nuclear ribosomal RNA clone library from environmental water samples in order to develop more efficient methods for species identification. For the molecular analysis, water samples were collected from the Seonakdong River (Gimhae Bridge) and the coast of Namhae，(Namhaedo). Colony PCR and restriction fragment length polymorphism of PCR (PCR-RFLP) were then adopted to isolate unique clones from the 18S rDNA clone library. Restriction fragment length polymorphism pattern analysis of the Gimhae Bridge sample revealed 44 unique clones from a total of 60 randomly selected clones, while analysis of the Namhae sample revealed 27 unique clones from 150 clones selected at random. A BLAST search and subsequent phylogenetic analysis conducted using the sequences of these clones revealed hidden biodiversity containing a wide range of taxonomic groups (Heterokontophyta (7), Ciliophora (23), Dinophyta (1), Chytridiomycota (1), Rotifera (1) and Arthropoda (11) in the Gimhae Bridge samples Ciliophora (4), Dinophyta (3), Cryptophyta (1), Arthropoda (19) in the Namhae samples). Therefore, the molecular monitoring method developed here can provide additional information regarding the biodiversity and community structure of eukaryotic plankton in environmental samples and helps construct a useful database of biodiversity for aquatic ecosystems.

• Korean Journal of Environment and Ecology
• /
• v.22 no.5
• /
• pp.471-480
• /
• 2008

This study was conducted to investigate the characteristics of breeding bird community in relation to altitude and vegetation in Jirisan National Park. The survey was carried over 4 study sites by point counts method to figure out habitat environment and breeding bird community from March to August in 2006. The study results are summarized as follows: Total 32 species were recorded, and 27 species and density of 37.31 ea/ha in low altitude mixed forest, 23 species and 34.99 ea/ha in low altitude deciduous forest, 18 species and 23.95 ea/ha in high altitude mixed forest, 19 species and 20.21 ea/ha in high altitude deciduous forest, respectively. Eleven species were observed only in the low altitude sites, 4 species were observed only in the high altitude sites. Number of species and density were high in the low altitude sites, and they were high in the mixed forests. In nesting guild analysis, the low altitude sites are similarly found species number of three types but canopy nesting species in the high altitude sites are advent less. In foraging guild analysis, the species number of canopy foraging appeared most highly in all study sites. In the difference analysis of each species density. Four species which are showed the difference in the low altitude sites, owing to vegetation. Long-tailed Tit(Aegithalos caudatus) and Great tit(Parus major) are difference because of difference in volume of canopy layer, and Coal Tit(Parus ater) was difference because of coniferous forest preference quality. Four species(Hazel Grouse, Winter Wren, Pale Thrush, Yellow-throated Bunting) which are showed the difference of the density in the high altitude sites because of thick growth of the bush layer. Ten species which are showed the difference in study sites, owing to altitude. Oriental Cuckoo(Cuculus saturatus), Winter Wren(Troglodytes troglodytes), Siberian Blue Robin(Luscinia cyane), Arctic Warbler(Phylloscopus borealis), Coal Tit(Parus ater), and Yellow-throated Bunting(Emberiza elegans) appeared highly in the high altitude sites, Pale Thrush(Turdus pallidus), Long-taild Tit(Aegithalos caudatus), Varied Tit(Parus varius), and Eurasian Nuthatch(Sitta europaea) appeared highly in the low altitude sites. It seems that bush layer coverage volume and canopy layer total coverage volume do influences on the breeding bird community, because the bush layer was thick growth, and canopy layer coverage volume was difference. It would be needed the management and maintenance of bush layer coverage volume and canopy layer with multi-layer structure to increase foliage height diversity and total coverage volume for the protection and management of bird community in Jirisan National Park.