• Proceedings of the IEEK Conference
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.583-586
• /
• 1999

In this paper, the wavelet transform is performed in the input 256$\times$256 color image and decomposes a image into low-pass and high-pass components. Since the high-pass band contains the components of three directions, edges are detected by combining three parts. After finding the position of face using the histogram of the edge component, a face region in low-pass band is cut off. Since RGB color image is sensitively affected by luminances, the image of low pass component is normalized, and a facial region is detected using face color informations. As the wavelet transform decomposes the detected face region into three layer, the dimension of input image is reduced. In this paper, we use the 3000 images of 10 persons, and KL transform is applied in order to classify face vectors effectively. FCM(Fuzzy C-Means) algorithm classifies face vectors with similar features into the same cluster. In this case, the number of cluster is equal to that of person, and the mean vector of each cluster is used as a codebook. We verify the system performance of the proposed algorithm by the experiments. The recognition rates of learning images and testing image is computed using correlation coefficient and Euclidean distance.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 한국작물학회 2017년도 9th Asian Crop Science Association conference
• /
• pp.22-22
• /
• 2017

Genetic diversity is one of fundamental parameters for rice cultivar improvement. Rice mutants are also a new source for rice breeding innovation. In this study, ninety-three SSR markers were applied to evaluate the genetic variation among nineteen rice mutant lines. The results showed that a total of 169 alleles from 56 polymorphism markers was recorded with an average of 3.02 alleles per locus. The values of polymorphism information content (PIC) varied from 0.09 to 0.79. The maximum number of alleles was 7, whereas the minimum number of alleles was 2. The heterozygosity values ranged from 0.10 to 0.81. Four clusters were generated using the unweighted pair group method with arithmetic mean (UPGMA) clustering. Fourteen phenotype characteristics were also evaluated. The correlation coefficient values among these phenotye characteristics were obtained in this study. Genetic diversity information of rice mutant lines can support rice breeders in releasing new rice varieties with elite characterisitics.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• 제56권4호
• /
• pp.384-394
• /
• 2020

This paper proposes an outlier detection model based on machine learning that can diagnose the presence or absence of major engine parts through unsupervised learning analysis of main engine big data of a ship. Engine big data of the ship was collected for more than seven months, and expert knowledge and correlation analysis were performed to select features that are closely related to the operation of the main engine. For unsupervised learning analysis, ensemble model wherein many predictive models are strategically combined to increase the model performance, is used for anomaly detection. As a result, the proposed model successfully detected the anomalous engine status from the normal status. To validate our approach, clustering analysis was conducted to find out the different patterns of anomalies the anomalous point. By examining distribution of each cluster, we could successfully find the patterns of anomalies.

• Journal of Microbiology and Biotechnology
• /
• 제20권3호
• /
• pp.587-593
• /
• 2010

Three hundred and seventy-four rhizobacteria were isolated from the rhizosphere soil (RS) or rhizoplane (RP) of Echinochloa crus-galli, Carex leiorhyncha, Commelina communis, Persicaria lapathifolia, Carex kobomugi, and Equisetum arvense, grown in contaminated soil with petroleum and heavy metals. The isolates were screened for plant growth-promoting trait (PGPT), including indole acetic acid (IAA) productivity, 1-aminocyclopropane-1-carboxylic acid (ACC) deaminase activity, and siderophore(s) synthesis ability. IAA production was detected in 86 isolates (23.0%), ACC deaminase activity in 168 isolates (44.9%), and siderophore(s) synthesis in 213 isolates (57.0%). Among the rhizobacteria showing PGPT, 162 isolates had multiple traits showing more than two types of PGPT. The PGPT-possesing rhizobacteria were more abundant in the RP (82%) samples than the RS (75%). There was a negative correlation (-0.656, p<0.05) between the IAA producers and the ACC deaminase producers. Clustering analysis by principal component analysis showed that RP was the most important factor influencing the ecological distribution and physiological characterization of PGPT-possesing rhizobacteria.

• Journal of Astronomy and Space Sciences
• /
• 제29권4호
• /
• pp.389-395
• /
• 2012

The problem of spacecraft attitude control is solved using an adaptive neuro-fuzzy inference system (ANFIS). An ANFIS produces a control signal for one of the three axes of a spacecraft's body frame, so in total three ANFISs are constructed for 3-axis attitude control. The fuzzy inference system of the ANFIS is initialized using a subtractive clustering method. The ANFIS is trained by a hybrid learning algorithm using the data obtained from attitude control simulations using state-dependent Riccati equation controller. The training data set for each axis is composed of state errors for 3 axes (roll, pitch, and yaw) and a control signal for one of the 3 axes. The stability region of the ANFIS controller is estimated numerically based on Lyapunov stability theory using a numerical method to calculate Jacobian matrix. To measure the performance of the ANFIS controller, root mean square error and correlation factor are used as performance indicators. The performance is tested on two ANFIS controllers trained in different conditions. The test results show that the performance indicators are proper in the sense that the ANFIS controller with the larger stability region provides better performance according to the performance indicators.

• The Plant Pathology Journal
• /
• 제27권2호
• /
• pp.128-137
• /
• 2011

Fifty two Macrophomina phaseolina isolates were recovered from 24 host plant species through the 14 Iranian provinces. All isolates were confirmed to species using species-specific primers. The colony characteristics of each isolate were recorded, including chlorate phenotype, relative growth rate at $30^{\circ}C$ and $37^{\circ}C$, average size of microsclerotia, and time to microsclerotia formation. The feathery colony phenotype was the most common (63.7%) on the chlorate selective medium and represented the chlorate sensitive phenotype of the Iranian Macrophomina phaseolina population. Meantime, inter simple sequence repeats (ISSR) Markers were used to assess the genetic diversity of the fungus. Unweighted pair-group method using arithmetic means (UPGMA) clustering of data showed that isolates did not clearly differentiate to the specific group according to the host or geographical origins, however, usually the isolates from the same host or the same geographic origin tend to group nearly. Our results did not show a correlation between the genetic diversity based on the ISSR and phenotypic characteristics. Similar to the M. phaseolina populations in the other countries, the Iranian isolates were highly diverse based on the phenotypic and the genotypic characteristics investigated and needs more studies using neutral molecular tools to get a deeper insight into this complex species.

• Journal of Industrial Technology
• /
• 제30권A호
• /
• pp.111-117
• /
• 2010

To improve the performance of the prediction system, the system should reflect well the uncertainty of nonlinear data. Thus, this paper presents multiple prediction systems based on Type-2 fuzzy sets. To construct each prediction system, an Interval Type-2 TSK Fuzzy Logic System and difference data were used, because, in general, it has been known that the Type-2 Fuzzy Logic System can deal with the uncertainty of nonlinear data better than the Type-1 Fuzzy Logic System, and the difference data can provide more steady information than that of original data. Also, to improve each rule base of the fuzzy prediction systems, the HCBKA (Hierarchical Correlation Based K-means clustering Algorithm) was applied because it can consider correlationship and statistical characteristics between data at a time. Subsequently, to alleviate complexity of the proposed prediction system, a system selection method was used. Finally, this paper analyzed and compared the performances between the Type-1 prediction system and the Interval Type-2 prediction system using simulations of three typical time series examples.

• Journal of Korean Society for Quality Management
• /
• 제39권2호
• /
• pp.244-255
• /
• 2011

In this study, we try to evaluate the efficiency of the photonics industry using a data envelopment analysis(DEA) model. We first develope four stage procedures for selecting proper input and output variables which consist of selecting the first candidate variables from literature survey, selecting the second candidate variables through experts' discussion, measuring the partial efficiency of the selected variables based on Tofallis' profiling, and clustering some variables through the rank correlation analysis of partial efficiency proposed by Min and Kim(l998). With this procedure, we select 4 input variables(capital, number of employee, R&D cost, operating cost) and 2 output variables(sales, growth of sales) and then utilize CCR and BCC model to measure efficiencies of 26 photonics companies in Gwangju. Moreover, we perform the reference group analysis to figure out what causes inefficiencies and to provide the desirable values for input and output variables at which inefficient photonics companies become efficient. Finally, we classify 26 photonics companies into three groups such as optical communications, optical applications, and optical sources, and perform the Kruskal-Wallis test to check if there exist some differences between efficiencies of three groups.

• Journal of the Korea Convergence Society
• /
• 제10권11호
• /
• pp.159-164
• /
• 2019

Recent developments in ICT technology have increased interest in the care and health of pets such as dogs and cats. In this paper, cluster analysis was performed based on the component data of pet food to be used in various fields of the pet industry. For cluster analysis, the similarity was analyzed by analyzing the correlation between components of 300 dogs and cats in the market. In this paper, clustering techniques such as Hierarchical, K-Means, Partitioning around medoids (PAM), Density-based, Mean-Shift are clustered and analyzed. We also propose a personalized recommendation system for pets. The results of this paper can be used for personalized services such as feed recommendation system for pets.

• New & Renewable Energy
• /
• 제16권4호
• /
• pp.33-40
• /
• 2020

The research topics of more than 1,900 wind energy papers registered in the Korean Journal Citation Index (KCI) were modeled into 25 topics using latent directory allocation (LDA), and their consistency was cross-validated through principal component analysis (PCA) of the document word matrix. Key research topics in the wind energy field were identified as "offshore, wind farm," "blade, design," "generator, voltage, control," 'dynamic, load, noise," and "performance test." As a new method to determine the similarity between research topics in journals, a systematic evaluation method was proposed to analyze the correlation between topics by constructing a journal-topic matrix (JTM) and clustering them based on topic similarity between journals. By evaluating 24 journals that published more than 20 wind energy papers, it was confirmed that they were classified into meaningful clusters of mechanical engineering, electrical engineering, marine engineering, and renewable energy. It is expected that the proposed systematic method can be applied to the evaluation of the specificity of subsequent journals.