• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.23 no.2
• /
• pp.91-108
• /
• 2018

An ecological study on subtidal macrobenthic fauna was conducted from 25 stations in the estuarine area of Wando-Doam Bay, southern coast of Korea during August 2013. A total of 186 species was collected with a mean density of $1,229ind./m^2$ and a mean biomass of $265.7g/m^2$. Polychaetes showed the richest benthic fauna comprising 43% of total fauna, whereas mollusks appeared as density- and biomass-dominant fauna accounted for 45% and 48% of the mean density and biomass, respectively. The number of species and mean faunal density were relatively higher at the stations surrounded by Sinjido, Joyakdo and Gogeumdo showing a gradual decrease toward inner bay stations. Species number and density were negatively correlated with bottom water temperature, but they were positively correlated with both the bottom salinity and DO. The most dominant species in terms of density was a semelid bivalve, Theora fragilis which showed a positive correlation with TOC content of surface sediment and its high density occurred around Gogeum-Sinji-Joyakdo area where dense aquaculture facilities exist. In the bay mouth area, an amphipod species, Eriopisella sechellensis showed its higher density at the stations with low organic content but fine grains. The combination of water temperature, salinity, pH of bottom water, water and sulfur content of the surface sediment could explain 71% of the spatial distribution of macrobenthic fauna from the Bio-Env analysis. From the cluster analysis, the study area consisted of 6 distinct station groups lineated from offshore area toward inner area. Ampharete arctica, Goniada maculata, Eriopisella sechellensis, Theora fragilis, Caprella sp. were identified as the main contributing faunas in classification by the SIMPER analysis. From the value of BPI, the benthic communities at the inner and central Wando-Doam Bay were assessed to be in a normal condition whereas those at the outer Wando harbor and Gogeum-Sinji-Joyakdo area were assessed in a poor or very poor condition due to the high concentration of particulate organic matter might be originated from the nearby dense aquaculture facilities. This study indicated that pristine inner bay has been influenced by the organic material supplied from the outer bay. Thus it is necessary to establish an ecological management plan to reduce organic enrichment of sediment from dense aquaculture facilities in the outer bay.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.40 no.2
• /
• pp.260-267
• /
• 1995

In temperate zone planting rice at different date subjects the Crop to different climatic condition. The present study aimed at comparison of the change in source-sink relationship of the Japonica(J) and that of IndicaxJaponica(I$\times$J) type rice cultivars caused by shift of heading date. Two J- and two I$\times$J-type cultivars were made to head on August 16, August 26, and September 5. Sink capacity was changed by shift of heading date in different mode between the types of cultivars. In both types major determinant of sink capacity was number of effective tillers, and the number of spikelets per panicle was the minor. In J-type earlier planting/heading was beneficial to increased panicle numbers and this was due mainly to a larger diurnal difference in temperature. I$\times$J-type cultivars favored a higher daily mean temperature to increase the sink capacity. The ability of source at heading, in terms of leaf area per panicle, chlorophyll content per spiklet, photosynthetic ability of leaves per unit area at 25$\^{\circ}C$, carbohydrate and N contents of leaves, was not so different among different heading dates in both types. However, the source activity was governed principally by temperature during grain filling. The J-type cultivars headed on Sept. 5 and I$\times$J-type cultivars headed later than August 16 could not have had sufficient source activity in grain filling due to lower temperature.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.40 no.1
• /
• pp.98-102
• /
• 1995

Popped popcorn generally have a regular popping direction and typical shape. But the reason and mechanism are not clear yet. This experiment was carried out to investigate the shape moulding factor of popped popcorn. Pericarp thickness of tip-cap section of kernels is slightly thicker than that of top section and this fact provides the important information to the reason. Popping starts when the moisture pressure of heated popcorn is increased and reaches at the critical pressure. Therefore, in the same moisture pressure conditions, top sections are bursted first because their pericarp section is thinner than that of tip-cap section. At the very moment tip-cap sections pull down the top sections of peri carp as bi-metal does. So kernels which removed tip-cap section showed the irregular popping shape because they lost the tip-cap pericarp function. How-ever, kernels which removed embryo showed the typical popping shape but their popping volume was small due to emition and shortage of critical moisture pressure. But kernels which removed the whole pericarp and top pericarp were not popped at all because moisture was entirely emitting out of kernels. These results suggest that the shape moulding factor of popped popcorn is the pericarp thickness differences between the top and tip-cap section of kernels.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.33 no.2
• /
• pp.103-111
• /
• 1988

This study was carried out with two cultivars under two levels of pH and four levels of nitrogen fertilization in a field and nutri-culture experiments to obtain the information about the effects of pH and nitrogen fertilization on the growth and yield of soybean. Acidic condition suppressed the growth of soybean plants, and thus yield and yield components of soybean decreased under acidic condition. But they increased with increased nitrogen fertilization. Especially, these respones were more remarkable under acidic condition and in the variety Jangbaegkong. Grain yield of soybean were highly correlated with the content of allantoin and total nitrogen of soybean plants in the variety Jangbaegkong, but this was not in the variety Danyeobkong. The content of protein and fat of soybean seeds decreased under acidic condition, and more nitrogen fertilization increased the protein content, but decreased the fat content.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.38 no.4
• /
• pp.350-359
• /
• 1993

The effect of gibberellic acid ($GA_3) and abscisic acid (ABA) on KCl-enhanced proteolysis of senescing leaves of rice(Oryza sativa L. cv. Chilsung) was studied. Emphasis was given to their effects on KCI-enhanced efflux of amino acids and proteinase activity. When treated singly, $GA_3 affected leaf proteolysis little, while ABA increased proteolysis, the rate of amino acid efflux, and ribulose -1,5 -bisphosphate carboxylase / oxygenase (Rubisco)-degrading endoproteinase activity. An additive increase in all three parameters mentioned above was observed when leaves were treated with ABA and KCl. No such an additive effect was found when $GA_3 was treated with KCl. Both $GA_3 and ABA helped to alleviate the KCI-suppressed activity of Rubisco-degrading exoproteinases. The additive increase in proteolysis of rice leaves in the presence of both ABA and KCl could thus be ascribed to a further increase in the efflux of protein hydrolyzates and Rubisco-degrading endoproteinase activity. An increase in proteolysis was accompanied by a decrease in water absorption, and the combined treatment of ABA with KCl resulted in a further reduction of water absorption.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.121-130
• /
• 2024

As internet and communication technology (ICT) is improved exponentially, types and amount of available data also increase. Even though data analysis including statistics is significant to utilize this large amount of data, there are inevitable limits to process various and complex data in general way. Meanwhile, there are many attempts to apply machine learning (ML) in various fields to solve the problems according to the enhancement in computational performance and increase in demands for autonomous systems. Especially, data processing for the model input and designing the model to solve the objective function are critical to achieve the model performance. Data processing methods according to the type and property have been presented through many studies and the performance of ML highly varies depending on the methods. Nevertheless, there are difficulties in deciding which data processing method for data analysis since the types and characteristics of data have become more diverse. Specifically, multi-variate data processing is essential for solving non-linear problem based on ML. In this paper, we present a multi-variate tabular data processing scheme for ML-aided data analysis by using Titanic dataset from Kaggle including various kinds of data. We present the methods like input variable filtering applying statistical analysis and normalization according to the data property. In addition, we analyze the data structure using visualization. Lastly, we design an ML model and train the model by applying the proposed multi-variate data process. After that, we analyze the passenger's survival prediction performance of the trained model. We expect that the proposed multi-variate data processing and visualization can be extended to various environments for ML based analysis.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.55-79
• /
• 2013

In this paper, we propose a hybrid genetic algorithm (HGA) approach to effectively solve the reverse logistics network with centralized centers (RLNCC). For the proposed HGA approach, genetic algorithm (GA) is used as a main algorithm. For implementing GA, a new bit-string representation scheme using 0 and 1 values is suggested, which can easily make initial population of GA. As genetic operators, the elitist strategy in enlarged sampling space developed by Gen and Chang (1997), a new two-point crossover operator, and a new random mutation operator are used for selection, crossover and mutation, respectively. For hybrid concept of GA, an iterative hill climbing method (IHCM) developed by Michalewicz (1994) is inserted into HGA search loop. The IHCM is one of local search techniques and precisely explores the space converged by GA search. The RLNCC is composed of collection centers, remanufacturing centers, redistribution centers, and secondary markets in reverse logistics networks. Of the centers and secondary markets, only one collection center, remanufacturing center, redistribution center, and secondary market should be opened in reverse logistics networks. Some assumptions are considered for effectively implementing the RLNCC The RLNCC is represented by a mixed integer programming (MIP) model using indexes, parameters and decision variables. The objective function of the MIP model is to minimize the total cost which is consisted of transportation cost, fixed cost, and handling cost. The transportation cost is obtained by transporting the returned products between each centers and secondary markets. The fixed cost is calculated by opening or closing decision at each center and secondary markets. That is, if there are three collection centers (the opening costs of collection center 1 2, and 3 are 10.5, 12.1, 8.9, respectively), and the collection center 1 is opened and the remainders are all closed, then the fixed cost is 10.5. The handling cost means the cost of treating the products returned from customers at each center and secondary markets which are opened at each RLNCC stage. The RLNCC is solved by the proposed HGA approach. In numerical experiment, the proposed HGA and a conventional competing approach is compared with each other using various measures of performance. For the conventional competing approach, the GA approach by Yun (2013) is used. The GA approach has not any local search technique such as the IHCM proposed the HGA approach. As measures of performance, CPU time, optimal solution, and optimal setting are used. Two types of the RLNCC with different numbers of customers, collection centers, remanufacturing centers, redistribution centers and secondary markets are presented for comparing the performances of the HGA and GA approaches. The MIP models using the two types of the RLNCC are programmed by Visual Basic Version 6.0, and the computer implementing environment is the IBM compatible PC with 3.06Ghz CPU speed and 1GB RAM on Windows XP. The parameters used in the HGA and GA approaches are that the total number of generations is 10,000, population size 20, crossover rate 0.5, mutation rate 0.1, and the search range for the IHCM is 2.0. Total 20 iterations are made for eliminating the randomness of the searches of the HGA and GA approaches. With performance comparisons, network representations by opening/closing decision, and convergence processes using two types of the RLNCCs, the experimental result shows that the HGA has significantly better performance in terms of the optimal solution than the GA, though the GA is slightly quicker than the HGA in terms of the CPU time. Finally, it has been proved that the proposed HGA approach is more efficient than conventional GA approach in two types of the RLNCC since the former has a GA search process as well as a local search process for additional search scheme, while the latter has a GA search process alone. For a future study, much more large-sized RLNCCs will be tested for robustness of our approach.