• Journal of Korea Port Economic Association
• /
• v.37 no.2
• /
• pp.73-89
• /
• 2021

The handysize bulk carriers are capable of transporting a variety of cargo that cannot be transported by mid-large size ship, and the spot chartering market is active, and it is a market that is independent of mid-large size market, and is more risky due to market conditions and charterage variability. In this study, Granger causality test, the Impulse Response Function(IRF) and Forecast Error Variance Decomposition(FEVD) were performed using monthly time series data. As a result of Granger causality test, coal price for coke making, Japan steel plate commodity price, hot rolled steel sheet price, fleet volume and bunker price have causality to Baltic Handysize Index(BHSI) and charterage. After confirming the appropriate lag and stability of the Vector Autoregressive model(VAR), IRF and FEVD were analyzed. As a result of IRF, the three variables of coal price for coke making, hot rolled steel sheet price and bunker price were found to have significant at both upper and lower limit of the confidence interval. Among them, the impulse of hot rolled steel sheet price was found to have the most significant effect. As a result of FEVD, the explanatory power that affects BHSI and charterage is the same in the order of hot rolled steel sheet price, coal price for coke making, bunker price, Japan steel plate price, and fleet volume. It was found that it gradually increased, affecting BHSI by 30% and charterage by 26%. In order to differentiate from previous studies and to find out the effect of short term lag, analysis was performed using monthly price data of major cargoes for Handysize bulk carriers, and meaningful results were derived that can predict monthly market conditions. This study can be helpful in predicting the short term market conditions for shipping companies that operate Handysize bulk carriers and concerned parties in the handysize chartering market.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Applied Chemistry for Engineering
• /
• v.22 no.5
• /
• pp.532-539
• /
• 2011

The physical and chemical properties of the dried low rank coals (LRCs) before and after the surface treatment using ozone and ammonia were characterized in this study. The contents of moisture, volatiles, fixed carbon and ash consisting of dried LRCs before the surface treatment were about 2.0, 44.8, 44.9 and 8.9%, respectively. Also, it was composed of carbon of 62.66%, hydrogen of 4.33%, nitrogen of 0.94%, oxygen of 27.01% and sulfur of 0.09%. The dried LRCs was surface-treated with the various dry methods using gases such as ozone at room temperature, ammonia at $200^{\circ}C$ and then the dried LRCs before and after the surface treatment were characterized by the various analysis methods such as FT-IR, TGA, proximate and elemental analysis, caloric value, ignition test, adsorption of $H_2O$ and $NH_3-TPD$. As a result, the oxygen content increased and the calorific value, ignition temperature and the contents of carbon and hydrogen relatively decreased because the oxygen-contained functional groups were additionally generated by the surface oxidation with ozone which plays a role as an oxidant. Also, its $H_2O$ adsorption ability got higher because the hydrophilic oxygen-contained functional groups were additionally generated by the surface oxidation with ozone. On the other hand, it was confirmed that the dried LRCs after the surface treatment with $NH_3$ at $200^{\circ}C$ have the decreased oxygen content, but the increased calorific value, ignition temperature and contents of carbon and hydrogen because of the decomposition of oxygen-contained functional groups the on the surface. In addition, the $H_2O$ adsorption ability was lowered bucause the surface of the dried LRCs might be hydrophobicized by the loss of the hydrophilic oxygen-contained functional groups. It was concluded that the various physico-chemical properties of the dried LRCs can be changed by the surface treatment.

• Journal of Life Science
• /
• v.33 no.10
• /
• pp.808-819
• /
• 2023

This study was conducted to develop a selection marker for the identification of the Bacillus licheniformis K12 strain in microbial communities. The strain not only demonstrates good growth at moderate temperatures but also contains enzymes that catalyze the decomposition of various polymer materials, such as proteases, amylases, cellulases, lipases, and xylanases. To identify molecular markers appropriate for use in a microbial community, a search was conducted to identify variable gene regions that show considerable genetic mutations, such as recombinase, integration, and transposase sites, as well as phase-related genes. As a result, five areas were identified that have potential as selection markers. The candidate markers were two recombinase sites (BLK1 and BLK2), two integration sites (BLK3 and BLK4), and one phase-related site (BLK5). A PCR analysis performed with different Bacillus species (e.g., B. licheniformis, Bacillus velezensis, Bacillus subtilis, and Bacillus cereus) confirmed that PCR products appeared at specific locations in B. licheniformis: BLK1 in recombinase, BLK2 in recombinase family protein, and BLK3 and BLK4 as site-specific integrations. In addition, BLK1 and BLK3 were identified as good candidate markers via a PCR analysis performed on subspecies of standard B. licheniformis strains. Therefore, the findings suggest that BLK1 can be used as a selection marker for B. licheniformis species and subspecies in the microbiome.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

• Korean Journal of Poultry Science
• /
• v.45 no.1
• /
• pp.53-62
• /
• 2018

This study was performed to evaluate the effect of lemon and cranberry juice on meat quality of chicken thighs during cold storage. Experimental groups were chicken thigh meat dipped into distilled water (CON), 1% lemon juice (LJ), 1% cranberry juice (CJ), and a mixture of 0.5% lemon juice and 0.5% cranberry juice (LCJ). The meat quality traits were determined at day 0, 3, 6, and 9 during cold storage at $4^{\circ}C$. The pH value of all treatments was lower than that of the control (P<0.05). Total microorganisms of CJ and LCJ at day 9 was 6.94 and 6.76 log CFU/g, respectively, whereas that of the control was 7.51 log CFU/g. The $a^*$ value of CJ and LCJ was higher than that of CON and LJ during storage (P<0.05), whereas the $b^*$ value of LJ, CL, and LCJ was lower than that of CON at day 6 and 9 (P<0.05). Overall acceptability of all treatments was significantly higher than that of CON after day 3. Thiobarbituric acid reactive substances and volatile basic nitrogen values were lower than those of the CON after day 3 (P<0.05). Principle component analysis (PCA) of the aroma pattern of all treatments was closer together, whereas PCA of the CON was scattered with the increase in storage days. This result suggests that dipping the chicken thigh meat into the lemon and cranberry juice could be beneficial to enhance chicken thigh meat quality by retardation of total microbes, lipid oxidation, and protein decomposition.

• Korean Journal of Environmental Agriculture
• /
• v.18 no.4
• /
• pp.372-377
• /
• 1999

Objective of this research was to draw the basic criteria of the compost maturity evaluation, by assessing the stability of chemical and physical properties of the bark and piggery manure byproduct composts during the composting. Colors of the mature composts were black and dark brown for the bark and piggery manure by-product composts, respectively. Good earthy odor was detected for both by-product composts after approximately 40 days composting, by which odors of the original raw materials were disappeared. pH and EC of the mature bark: compost were stabilized at 6.5 and 1dS/m, respectively. The respective values for the piggery compost were stabilized at 7.2 and 6dS/m. Organic matter contents were decreased with time to be stabilized at about 60% at the end of composting. During composting, total N contents of the bark and piggery composts were maintained at $1.1{\sim}1.5%$, and $1.5{\sim}2.2%$, respectively. For both fertilizers, $NH_4-N$ contents were increased at the initial stage bur. decreased after the middle stages of decomposition, resulting in the increase of $NO_3-N$ contents. Total inorganic N contents were increased with time. C/N ratios of both mature composts were stabilized at $25{\sim}27$. CEC of the bark compost was increased logarithmically with time and that of mature compost was 87cmol(+)/㎏. CEC of the piggery manure compost was hyperbolic function with rime and reached at 70cmol(+)/㎏ at the mature stage. Crude fiber analysis indicated that relative contents of lignin were increased with composting by compensating for the decreases of cellulose and hemicellulose contents.

• Proceedings of the KSRS Conference
• /
• 2001.03a
• /
• pp.140-148
• /
• 2001

The satellite sensor model is typically established using ground control points acquired by ground survey Of existing topographic maps. In some cases where the targeted area can't be accessed and the topographic maps are not available, it is difficult to obtain ground control points so that geospatial information could not be obtained from satellite image. The paper presents several satellite sensor models and satellite image decomposition methods for non-accessible area where ground control points can hardly acquired in conventional ways. First, 10 different satellite sensor models, which were extended from collinearity condition equations, were developed and then the behavior of each sensor model was investigated. Secondly, satellite images were decomposed and also pseudo images were generated. The satellite sensor model extended from collinearity equations was represented by the six exterior orientation parameters in 1$^{st}$, 2$^{nd}$ and 3$^{rd}$ order function of satellite image row. Among them, the rotational angle parameters such as $\omega$(omega) and $\phi$(phi) correlated highly with positional parameters could be assigned to constant values. For non-accessible area, satellite images were decomposed, which means that two consecutive images were combined as one image. The combined image consists of one satellite image with ground control points and the other without ground control points. In addition, a pseudo image which is an imaginary image, was prepared from one satellite image with ground control points and the other without ground control points. In other words, the pseudo image is an arbitrary image bridging two consecutive images. For the experiments, SPOT satellite images exposed to the similar area in different pass were used. Conclusively, it was found that 10 different satellite sensor models and 5 different decomposed methods delivered different levels of accuracy. Among them, the satellite camera model with 1$^{st}$ order function of image row for positional orientation parameters and rotational angle parameter of kappa, and constant rotational angle parameter omega and phi provided the best 60m maximum error at check point with pseudo images arrangement.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.5
• /
• pp.822-828
• /
• 2012

Organic fruit production has increased due to consumer's interest and government's political support for environmentally-friendly agriculture. The aim of this study was to investigate the effects of cover plants on soil microbial community and establish the fruit cultivation method by organic farming techniques. Cover plants used as an organic nutrient source in an apple orchard were rye and barley, the Gramineae and red clover and hairy vetch, the Leguminosae. In the effects of cover plants on the soil chemical characteristics, the soil pH values were higher than that of conventional organic pear orchard. The content of P showed no significant difference between control and cover plant plots. Organic matter level was similar in control and Gramineae cover plant plots, while organic matter content in cover plants belong to Leguminosae was lower than that of control plot. K content was lower in the plots treated with rye and red clover than control plot, while K content in hairy vetch treated plot was higher than control plot. Ca content was lower in control plot than in cover plant treated plots. Concentrations of Mg in the plots treated with barley and hairy vetch was lower than control plot. In August rye and red clover covered soil showed higher bacterial community density than that of control soil and barley treated soil showed highest Actinomycetes community density among treatments. Barley and hairy vetch soils showed higher level of fungi community density than that of control soil in August. In pyrosequencing analysis barley treated soil showed highest distribution ratio of Actinomycetes among treatment. Our findings might be used as basic data for choosing cover plant with effective organic matter decomposition and nutrition supply capacity.

• Journal of Aquaculture
• /
• v.17 no.2
• /
• pp.144-150
• /
• 2004

This experiment was conducted to evaluate the parameters such as nutrient requirements, POY, AnV, Totox, VBN, total plate count, dietary fatty acids and amino acids composition, that are not included in the registered standard composition items required by the Ministry of Agriculture and Forestry, of a moist pellet (MP), three domestic extruded pellets (DEP-1, DEP-2, DEP-3), and two foreign extruded pellets (FEP-1, FEP-2) that are utilized by domestic flounder farms at present. The crude protein was added in excess of the dietary protein requirement in 6 kinds of feeds. When considering the proper PH ratio, it is obvious that protein was added in excess, especially in MP and FEP-2. Crude fat was also added in excess, especially in FEP-1. MP contained a higher dietary phosphorus content than formulated feeds, surpassing the dietary phosphorus requirement and greatly increasing the possibility for causing water pollution. The oxidation of fatty acid and decomposition of protein in MP were higher than in formulated feeds, and may also cause problems on fish farms. Also, it is difficult to store and manage MP, Among the fatty acids, EPA and DHA contents in MP were higher than those in formulated feeds. It is necessary to conduct further studies of EPA and DHA contents in formulated feeds. Lysine content in MP and FEP-2 could meet the dietary lysine requirement of flounder, however, the possibility of insufficient lysine content in the other formulated feeds was high and we considered that extra supplementation was necessary. Therefore, it is necessary to set up quality control standards according to fish species and sizes while considering the specific character of aquatic formulated feeds to restore the confidence of feed companies and aquaculturists to these feeds. This may be an opportunity to make an earlier change from MP to formulated feeds.