• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.635-642
• /
• 2003

Reinforcement learning got successful results in a lot of applications such as control and scheduling. Various function approximation methods have been studied in order to improve the learning speed and to solve the shortage of storage in the standard reinforcement learning algorithm of Q-Learning. Most function approximation methods remove some special quality of reinforcement learning and need prior knowledge and preprocessing. Fuzzy Q-Learning needs preprocessing to define fuzzy variables and Local Weighted Regression uses training examples. In this paper, we propose a function approximation method, Fuzzy Q-Map that is based on on-line fuzzy clustering. Fuzzy Q-Map classifies a query state and predicts a suitable action according to the membership degree. We applied the Fuzzy Q-Map, CMAC and LWR to the mountain car problem. Fuzzy Q-Map reached the optimal prediction rate faster than CMAC and the lower prediction rate was seen than LWR that uses training example.

• Journal of Microbiology and Biotechnology
• /
• v.30 no.9
• /
• pp.1355-1366
• /
• 2020

Sediment bacterial communities are critical to the biogeochemical cycle in river ecosystems, but our understanding of the relationship between sediment bacterial communities and their specific input streams in rivers remains insufficient. In this study, we analyzed the sediment bacterial community structure in a local river receiving discharge of urban domestic sewage by applying Illumina MiSeq high-throughput sequencing. The results showed that the bacterial communities of sediments samples of different pollution types had similar dominant phyla, mainly Proteobacteria, Actinobacteria, Chloroflexi and Firmicutes, but their relative abundances were different. Moreover, there were great differences at the genus level. For example, the genus Bacillus showed statistically significant differences in the hotel site. The clustering of bacterial communities at various sites and the dominant families (i.e., Nocardioidaceae, and Sphingomonadaceae) observed in the residential quarter differed from other sites. This result suggested that environmentally induced species sorting greatly influenced the sediment bacterial community composition. The bacterial co-occurrence patterns showed that the river bacteria had a nonrandom modular structure. Microbial taxonomy from the same module had strong ecological links (such as the nitrogenium cycle and degradation of organic pollutants). Additionally, PICRUSt metabolic inference analysis showed the most important function of river bacterial communities under the influence of different types of domestic sewage was metabolism (e.g., genes related to xenobiotic degradation predominated in residential quarter samples). In general, our results emphasize that the adaptive changes and interactions in the bacterial community structure of river sediment represent responses to different exogenous pollution sources.

• Proceedings of the KIEE Conference
• /
• 2004.11b
• /
• pp.190-193
• /
• 2004

Optimal Power Flow (OPF) is becoming more and more important in the deregulation environment of power pool and there is an urgent need of faster solution technique for on-line application. So this paper presents parallel genetic algorithm-tap search for the solution of the OPF. The control variables modeled unit active power outputs, generator-bus voltage magnitudes and transformer-tap settings. A number of functional operating constraints, such as branch flow limits, load bus boltage magnitude limits and generator reactive capabilities are included as penalties in the fitness function. In parallel GA-TS, GA operators are executed for each process. If best fitness of the GA is not changed for several generations, TS operators are executed for the upper three populations to enhance the local searching capabilities. With migration operation, best string of each node is transferred to the neighboring node after predetermined iterations are executed. For parallel computing, we developed a PC-cluster system consisting of 8 PCs. Each PC employs the 2 GHz Pentium IV CPU and is connected with others through ethernet switch based fast ethernet. To show the usefulness of the proposed method, developed algorithm has been tested and compared on an IEEE 30-bus system in the reference paper. From the simulation results, we can find that the proposed algorithm is efficient for the OPF.

• Journal of Wetlands Research
• /
• v.15 no.3
• /
• pp.397-406
• /
• 2013

Wetland conservation plan has been established to protect ecologically important wetlands based on vegetation integrity, spatial distribution of endangered species, but recently more demands are concentrated on the landscape ecological approaches such as topological relationship, neighboring area, spatial arrangements between wetlands at the broad scale. Landscape ecological analysis and graph theory are conducted to identify spatial characteristics related to core nodes and weak links of wetland networks in Nakdong basin. Regular planar model, which is selected for wetland networks, is applied in the Nakdong basin. The analysis indicates that 5 regional groups and 4 core wetlands are extracted with 15km threshold distance. The IIC and PC values based on the binary and probability models suggest that the wetland group C composed of main stream of Nakdong river and Geumho river is the most important area for wetland network. Wetland conservation plan, restoration projected of damaged and weak links between wetlands should be proposed through evaluating the node, links, and networks from wetlands at the local to the regional scale in Nakdong basin.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.777-784
• /
• 2006

This paper proposes a c-fuzzy model tree using partial least square method to predict the Chlorophyll-a concentration in each zone. First, cluster centers are calculated by fuzzy clustering method using all input and output attributes. And then, each internal node is produced according to fuzzy membership values between centers and input attributes. Linear models are constructed by partial least square method considering input-output pairs remained in each internal node. The expansion of internal node is determined by comparing errors calculated in parent node with ones in child node, respectively. On the other hands, prediction is performed with a linear model haying the highest fuzzy membership value between input attributes and cluster centers in leaf nodes. To show the effectiveness of the proposed method, we have applied our method to water quality data set measured at several stations. Under various experiments, our proposed method shows better performance than conventional least square based model tree method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2179-2184
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. This paper described appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• pp.57-81
• /
• 2019

Satellite images can be integrated into a crop model to strengthen the advantages of each technique for crop monitoring and to compensate for weaknesses of each other, which can be systematically applied for monitoring inaccessible croplands. The objective of this study was to outline the productivity of paddy rice based on simulation of the yield of all paddy fields in North Korea, using a grid crop model combined with optical satellite imagery. The grid GRAMI-rice model was used to simulate paddy rice yields for inaccessible North Korea based on the bidirectional reflectance distribution function-adjusted vegetation indices (VIs) and the solar insolation. VIs and solar insolation for the model simulation were obtained from the Geostationary Ocean Color Imager (GOCI) and the Meteorological Imager (MI) sensors of the Communication Ocean and Meteorological Satellite (COMS). Reanalysis data of air temperature were achieved from the Korea Local Analysis and Prediction System (KLAPS). Study results showed that the yields of paddy rice were reproduced with a statistically significant range of accuracy. The regional characteristics of crops for all of the sites in North Korea were successfully defined into four clusters through a spatial analysis using the K-means clustering approach. The current study has demonstrated the potential effectiveness of characterization of crop productivity based on incorporation of a crop model with satellite images, which is a proven consistent technique for monitoring of crop productivity in inaccessible regions.

• Health Policy and Management
• /
• v.32 no.2
• /
• pp.205-215
• /
• 2022

Background: The purpose of this study is to identify the factors infecting the medical care utilization from a new perspective by newly classifying the categories of administrative districts using the urban decline index and medical vulnerability index as indicators. Methods: This study targeted 150,940 people who used medical services using the 2015 cohort database (DB), 2010-2015 urban regeneration analysis index DB, and 2014-2015 public health and medical statistics DB. The decline of the region was classified using the urban decline index typed using k-means clustering and the medical vulnerability index typed using the quantile score calculation. Regression analysis was performed 3 times with medical expenditure, length of stay, and the number of outpatient visits as dependent variables. Results: There were 37 stable region (47.4%), 29 health vulnerable region (37.2%), and 12 decline region (15.4%). The health vulnerable region had lower medical expenditure, fewer outpatient visits, and a higher length of stay than the stable region. The decline region was all higher than the stable region but had no significant effect. Conclusion: The factors that cause the health disparity between regions are not only factors related to individual health behavior but also environmental factors of the local community. Therefore, there is a need for a systematic alternative that properly considers the resources within the community and reflects the characteristics of the population.

• Environmental and Resource Economics Review
• /
• v.33 no.1
• /
• pp.59-86
• /
• 2024

Recently, research on city gas demand is increasing by reflecting the characteristics of each region. The similarity of the social structure of the adjacent region and the density of the supply infrastructure induce spatial correlation with the clustering that has a microscopic relationship between regions. Accordingly, as a result of analyzing the spatial correlation after dividing the demand for city gas for civilian use into a total of 54 regions based on the jurisdiction of 34 city gas companies, it was confirmed that there was a positive spatial correlation from a global and local perspective. In this study, the demand for city gas for civilian use for 54 regions from January 2014 to December 2022 was composed of panel data, and the spatial panel regression analysis and the general panel regression analysis were compared, and it was found that the spatial error model (SEM) was the most suitable model. This presents policy and practical implications by confirming that the demand for city gas for civilian use in one region has a significant relationship with the adjacent region.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.2
• /
• pp.177-187
• /
• 2000

In the past several years, many systems which adopted ring topology with high-speed unidirectional point-to-point links have emerged to overcome the limit of bus for interconnection network of clustered multiprocessor system. However, rapid increase of processor speed and performance improvement of local bus and memory system limit scalability of system with point-to-point link of standard bandwidth. Therefore, necessity to extend bandwidth is emphasized. In this paper, we adopt PANDA system as base model, which is clustering-based multiprocessor system. By simulating a model adopting commercial processor and local bus specification, we show that point-to-point link is bottleneck of system performance, and bandwidth expansion by more than 200% is needed. To expand bandwidth of interconnection network, it needs excessive design cost and time to develop new point-to-point link with doubled bandwidth. As an alternative to double bandwidth, we propose several ways to implement dual ring -simple dual ring, transaction-separated dual ring, direction-separated dual ring- by using off-the-shelf point-to-point links with IEEE standard bandwidth. We analyze pros. and cons. of each model compared with doubled-bandwidth single ring by simulation.