• Ocean and Polar Research
• /
• v.44 no.1
• /
• pp.13-27
• /
• 2022

The Yeongsan River estuary was altered by a sea dike built in 1981 and the sluice gates in the dike were extended recently in 2014. The construction has caused changes in water properties and hydrodynamics and also produced disturbances including hypoxia and algal blooms. We analyzed the water quality and chlorophyll-a data (2009-2018) collected seasonally at 3 stations (Sts. 1-3) along the channel of the estuary by the Marine Environmental Monitoring System. Variations in water quality and chlorophyll-a (an index of phytoplankton biomass) were examined and their stressors were also identified by statistics including correlation and multivariate principal component analyses (PCA). The water quality was mainly affected by freshwater discharge from the dike. Salinity, nutrients and chlorophyll-a were especially affected by the discharge and the effect enhanced during summer and at the upper region near the sea dike decreasing downstream. Three factors were extracted for each station in the PCA accounting for 66.07-72.42% of the variations. The first was an external factor associated with freshwater discharge and the second and third were seasonal or biological factors. The results indicate that the water quality is more affected by short-termed and episodic events such as freshwater discharge than seasonal events and the influence of freshwater discharge on water quality is more extensive than that previously reported. This suggests that the boundary of the estuary should be extended to take into account the findings of this study and a management strategy linked to the freshwater zone is required to manage the integrity and water quality of the Yeongsan River estuary.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1729-1738
• /
• 2021

Machine learning has a close relationship with cognitive psychology and brain science and is developing together. This paper analyzes the OASIS-3 dataset using machine learning techniques and proposes a model for predicting dementia. Dimensional reduction through PCA (Principal Component Analysis) is performed on the data quantifying the volume of each area among OASIS-3 data, and only important elements (features) are extracted and then various machine learning including gradient boosting and stacking Apply the models and compare the performance of each. Unlike previous studies, the proposed technique has a great differentiation because it uses not only the brain biometric data, but also basic information data such as the participant's gender and medical information data of the participant. In addition, it was shown that the proposed technique through various performance evaluations is a model that can better predict dementia by finding features that are more related to dementia among various numerical data.

• Preventive Nutrition and Food Science
• /
• v.17 no.3
• /
• pp.184-191
• /
• 2012

The purpose of this study was to investigate the fatty acid profiles in 18 soybean cultivars grown in Korea. A total of eleven fatty acids were identified in the sample set, which was comprised of myristic (C14:0), palmitic (C16:0), palmitoleic (C16:1, ${\omega}7$), stearic (C18:0), oleic (C18:1, ${\omega}9$), linoleic (C18:2, ${\omega}6$), linolenic (C18:3, ${\omega}3$), arachidic (C20:0), gondoic (C20:1, ${\omega}9$), behenic (C22:0), and lignoceric (C24:0) acids by gas-liquid chromatography with flame ionization detector (GC-FID). Based on their color, yellow-, black-, brown-, and green-colored cultivars were denoted. Correlation coefficients (r) between the nine major fatty acids identified (two trace fatty acids, myristic and palmitoleic, were not included in the study) were generated and revealed an inverse association between oleic and linoleic acids (r=-0.94, p<0.05), while stearic acid was positively correlated to arachidic acid (r=0.72, p<0.05). Principal component analysis (PCA) of the fatty acid data yielded four significant principal components (PCs; i.e., eigenvalues>1), which together account for 81.49% of the total variance in the data set; with PC1 contributing 28.16% of the total. Eigen analysis of the correlation matrix loadings of the four significant PCs revealed that PC1 was mainly contributed to by oleic, linoleic, and gondoic acids, PC2 by stearic, linolenic and arachidic acids, PC3 by behenic and lignoceric acids, and PC4 by palmitic acid. The score plots generated between PC1-PC2 and PC3-PC4 segregated soybean cultivars based on fatty acid composition.

• ALGAE
• /
• v.23 no.2
• /
• pp.135-140
• /
• 2008

A field survey for dinoflagellate cysts was carried out from May 2000 to November 2002 for the Southwest Sea of Korea. A total dinoflagellate cysts identified were 33 species, which belonged to 17 genera, 31 species, and 2 unidentified species. A cysts density were 16-1,501 cysts-gdry$^{-1}$. The dominant species of dinoflagellate cysts in the Southwestern Sea of Korea were Spiniferites bulloideus and Scrippsiella trochoidea, which are autotrophic species. To investigate the environmental characteristics of the Southwestern Sea of Korea using the dinoflagellate cysts, a principal component analysis (PCA) was conducted using the data collected from a total of 51 stations. From the score distribution map by the PCA, the Southwestern Sea of Korea was largely divided into three regions according to the first primary component and the second primary component. In other words, Group 1 was the western sea area of Mokpo and Jindo, Group 2 was the outer sea area of the South Sea, and Group 3 was the coastal areas of the South Sea around the Archipelago. It was found that this division of sea area was influenced by effects of the sea environment of the coastal areas of Korea. The coastal areas of Mokpo and Jindo that belong to Group 1 were affected by the cold Yellow Sea water. The outer sea area of the central parts of the South Sea that belong to Group 2, which is the boundary between the Southern coastal water of Korea and the Tsushima warm water, was subject to the formation of temperature fronts throughout the year, while Group 3 was affected by the coastal waters of Korea. It was also found that this division was in close relationship with the distribution of sediment facies in the bottom layer. From the above results, the environmental factors that influence the cyst distribution in he Southwestern Sea of Korea were found to include the eutrophication status of the sea area, the physical characteristics of the sea environment such as the flow of sea current and fronts, the sediment facies in the bottom layer, and the appearance volume of motile cells.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1333-1342
• /
• 2018

Until now, Electroencephalography(: EEG) has been the most important and convenient method for the diagnosis and treatment of epilepsy. However, it is difficult to identify the wave characteristics of an epileptic EEG signals because it is very weak, non-stationary and has strong background noise. In this paper, we analyse the effect of dimensionality reduction methods on Epileptic EEG feature selection and classification. Three dimensionality reduction methods: Pincipal Component Analysis(: PCA), Kernel Principal Component Analysis(: KPCA) and Linear Discriminant Analysis(: LDA） were investigated. The performance of each method was evaluated by using Support Vector Machine SVM, Logistic Regression(: LR), K-Nearestneighbor(: K-NN), Decision Tree(: DR) and Random Forest(: RF). From the experimental result, PCA recorded 75% of highest accuracy in SVM, LR and K-NN. KPCA recorded 85% of best performance in SVM and K-KNN while LDA achieved 100% accuracy in K-NN. Thus, LDA dimensionality reduction is found to provide the best classification result for epileptic EEG signal.

• Food Science and Preservation
• /
• v.30 no.4
• /
• pp.602-616
• /
• 2023

Fifteen types of rice collected from Kurdistan region-Iraq were investigated by principal component analysis (PCA) in terms of physical properties and cooking characteristics. The dimensions of evaluated grains correspond to 5.05-8.75 mm for length, 1.54-2.47 mm for width, and 1.37-1.95 for thickness. The equivalent diameter was in the range of 5.23-10.03 mm, and the area took 13.30-28.25 mm². The sphericity analysis values varied from 0.32 to 0.56, the aspect ratio from 0.17 to 0.39, and the volume of the grain was measured in the range from 4.48 to 17.74 mm³, hectoliter weight values were 730-820 kg/m³, and true density from 0.6 to 0.96 g/cm³. The broken grain ratio was 1.5-18.3%, thousand kernel weight corresponded to 15.88 to 22.42 g. The water uptake ratios for 30 min of soaking were increased at 60℃ compared to 30 and 45℃. The PCA was used to study the correlation of the most effective factors. Results of PCA showed that the first (PC1) and second (PC2) components retained 63.4% and 34.8% of the total variance, which PC1 was mostly related to hectoliter, broken ratio, and moisture content characteristics while PC2 was mostly concerned with hardness and true density. For cooking properties, the PC1 and PC2 retained 88.5% and 9.3% of the total variance, respectively. PC1 was mostly related to viscosity, spring value, and hardness after cooking, while PC2 was mostly concerned with spring value, hardness before cooking, and hardness after cooking.

• Korean Journal of Computational Design and Engineering
• /
• v.16 no.4
• /
• pp.249-259
• /
• 2011

In this paper we present our work on the parameterized construction of virtual drivers' reach motion to seat belt, by using motion capture data. A user can generate a new reach motion by controlling a number of parameters. We approach the problem by using multiple sets of example reach motions and learning the relation between the labeling parameters and the motion data. The work is composed of three tasks. First, we construct a motion database using multiple sets of labeled motion clips obtained by using a motion capture device. This involves removing the redundancy of each motion clip by using PCA (Principal Component Analysis), and establishing temporal correspondence among different motion clips by automatic segmentation and piecewise time warping of each clip. Next, we compute motion blending functions by learning the relation between labeling parameters (age, hip base point (HBP), and height) and the motion parameters as represented by a set of PC coefficients. During runtime, on-line motion synthesis is accomplished by evaluating the motion blending function from the user-supplied control parameters.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1287-1287
• /
• 2001

The structure of water molecules in the pure liquid state has been subjected to extensive research for several decades. Questions still remain unanswered, however, and no single model has been found capable of explaining all the anomalies of water. In the present study near-infrared spectra of water in the temperature region 6-$80^{\circ}C$ have been analysed by use of principal component analysis (PCA) and two-dimensional correlation spectroscopy in order to study the dynamic behaviour of the water band centred at 1440 nm, which is due to the combination of symmetric and antisymmetric O-H stretching modes. It has been found that the wavelengths 1412 and 1491 nm account for more than 99% of the spectral variation, representing two major water species with weaker and stronger hydrogen bonds, respectively. A third species located at 1438 nm, whose concentration was relatively constant as a function of temperature, is also indicated. A somewhat distorted two-state structural model for water is suggested.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2000.04b
• /
• pp.176-179
• /
• 2000

In the recognition of the gases using the quartz crystal microbalance (QCM) coated with the film materials, it is important to obtain the recognition ability of gases, and the stability of film coated above the QCM. Especially, the thickness of film coated above the QCM is decreased according with the using circumstance and time of QCM gas sensor. Therefore, the sensing chararcteristics of film is changed with these. In this paper, we coated the lipid PC (Phosphatidyl Choline) materials varing with the blended amount of PVC(Poly Vinyl Chloride) and solution (Tetra Hydrofan:THF) above QCM to obtain the stability of lipid PC film. QCM gas sensors coated with film materials were measured the frequency change in the chamber of stationary gas sensing system injected 1-hexane, ethyl acetate, ethanol and benzene of $20{\mu}{\ell}$, respectively. We obtained the principal component analysis (PCA) from the frequency change due to the absorption of gas. Also, we measured the degradation characteristics of QCM gas sensor to show the properties of stability.

• Smart Structures and Systems
• /
• v.21 no.1
• /
• pp.1-14
• /
• 2018

A method is proposed to detect structural damages in the presence of damping using noisy data. This method uses Frequency Response Function (FRF) and Mode-Shapes as the input parameters for a system of Couple Sparse Coding (CSC) to study the healthy state of the structure. To obtain appropriate patterns of FRF for CSC training, Principal Component Analysis (PCA) technique is adopted to reduce the full-size FRF to overcome over-fitting and convergence problems in machine-learning training. To verify the proposed method, a numerical two-story frame structure is employed. A system of individual CSCs is trained with FRFs and mode-shapes, and then termed ensemble to detect the health condition of the structure. The results demonstrate that the proposed method is accurate in damage identification even in presence of up to 20% noisy data and 5% unconsidered damping ratio. Furthermore, it can be concluded that CSC ensemble is highly efficient to detect the location and the severity of damages in comparison to the individual CSC trained only with FRF data.