• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.16 no.4
• /
• pp.341-348
• /
• 1983

The Relationship between the distribution of the fishing grounds of anchovy and the oceanographic conditions in the Korean Waters are investigated by using the data of the catch of anchovy by the gill net fishery (Fisheries Research and Development Agency, 1969-1982) and the oceanographic observation data (Fisheries Research and Development Agency, 1979). The main fishing ground of anchovy by the gill net fishery was five fishing areas located in the adjacent seas of Sockcho, Kuryong-po, Kijang, Keoje island and Chungmu, the area of which occupies no more than $20\%$ of all fishing grounds, and it appeared that about $80\%$ of mean catches of fourteen years was concentrated in this area. The main fishing periods were from April to June and October to November. The coefficient of variation of the catch for the main fishing ground were from 0.3 to 0.6 and the condition of all fishing ground was generally stable. The mean CPUE was 81.2 kg/set at the main fishing ground. The annual mean catch of anchovy by the gill net was the smallest in February and the largest in May through a year. It was found that the fluctuation is related to the expansion and reduction of the isothermal line of $10^{\circ}C$.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.31-38
• /
• 2017

In this paper, we propose a system which estimates Manhattan coordinate systems for urban scene images using a convolutional neural network (CNN). Estimating the Manhattan coordinate system from an image under the Manhattan world assumption is the basis for solving computer graphics and vision problems such as image adjustment and 3D scene reconstruction. We construct a CNN that estimates Manhattan coordinate systems based on GoogLeNet [1]. To train the CNN, we collect about 155,000 images under the Manhattan world assumption by using the Google Street View APIs and calculate Manhattan coordinate systems using existing calibration methods to generate dataset. In contrast to PoseNet [2] that trains per-scene CNNs, our method learns from images under the Manhattan world assumption and thus estimates Manhattan coordinate systems for new images that have not been learned. Experimental results show that our method estimates Manhattan coordinate systems with the median error of $3.157^{\circ}$ for the Google Street View images of non-trained scenes, as test set. In addition, compared to an existing calibration method [3], the proposed method shows lower intermediate errors for the test set.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.5 no.2
• /
• pp.63-67
• /
• 1972

Preliminary creel-holding test of live anchovies which are to be used as bait for the skipjact fishery, was conducted on the fish caught by set net and lift net. They were held in the creels constructed with bamboo frame and minnow netting, during the period of Oct. 24-Nov. 28 in 1972. If was found that the survival rate of the creel-held anchovies varied by the size of fish, the towed distance and speed of fish-carrying creel in which the fish were accomodated after catchi. 1. The survival rate of the medium size anchovies, 7.8-9.6cm in length and 4.6-4.8 g in weight, was $70-92\%$ during the holding period of 20-35 days. Whereas, only $16\%$ of juvenile anchovies, 5.3cm in length and 1.0 g in weight, were survived for 19 hours after catch. 2. During the time of transport, the farther and faster the creel containing fish were towed, the less fish were survived in the subsequent holding period. 3. Though both the set net and lift net could be fairly used to catch live anchovy, no decision between these two gears could be made in this experiment to determine the superiorness for the subsequent survival rate.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.1
• /
• pp.23-33
• /
• 2020

Recently, high-resolution images can be easily acquired using UAV (Unmanned Aerial Vehicle), so that it is possible to produce small area observation and spatial information at low cost. In particular, research on the generation of cover maps in crop production areas is being actively conducted for monitoring the agricultural environment. As a result of comparing classification performance by applying RF(Random Forest), SVM(Support Vector Machine) and CNN(Convolutional Neural Network), deep learning classification method has many advantages in image classification. In particular, land cover classification using satellite images has the advantage of accuracy and time of classification using satellite image data set and pre-trained parameters. However, UAV images have different characteristics such as satellite images and spatial resolution, which makes it difficult to apply them. In order to solve this problem, we conducted a study on the application of deep learning algorithms that can be used for analyzing agricultural lands where UAV data sets and small-scale composite cover exist in Korea. In this study, we applied DeepLab V3 +, FC-DenseNet (Fully Convolutional DenseNets) and FRRN-B (Full-Resolution Residual Networks), the semantic image classification of the state-of-art algorithm, to UAV data set. As a result, DeepLab V3 + and FC-DenseNet have an overall accuracy of 97% and a Kappa coefficient of 0.92, which is higher than the conventional classification. The applicability of the cover classification using UAV images of small areas is shown.

• Proceedings of the KIEE Conference
• /
• 1990.07a
• /
• pp.535-538
• /
• 1990

The main problem in speech recognition is the enormous variability in acoustic signals due to complex but predictable contextual effects. Especially in plosive consonants it is very difficult to find invariant cue due to various contextual effects, but humans use these contextual effects as helpful information in plosive consonant recognition. In this paper we experimented on three artificial neural net models for the recognition of plosive consonants. Neural Net Model I used "Multi-layer Perceptron ". Model II used a variation of the "Self-organizing Feature Map Model". And Model III used "Interactive and Competitive Model" to experiment contextual effects. The recognition experiment was performed on 9 Korean plosive consonants. We used VCV speech chains for the experiment on contextual effects. The speech chain consists of Korean plosive consonants /g, d, b, K, T, P, k, t, p/ (/ㄱ, ㄷ, ㅂ, ㄲ, ㄸ, ㅃ, ㅋ, ㅌ, ㅍ/) and eight Korean monothongs. The inputs to Neural Net Models were several temporal cues - duration of the silence, transition and vot -, and the extent of the VC formant transitions to the presence of voicing energy during closure, burst intensity, presence of asperation, amount of low frequency energy present at voicing onset, and CV formant transition extent from the acoustic signals. Model I showed about 55 - 67 %, Model II showed about 60%, and Model III showed about 67% recognition rate.

• Journal of Korean Society for Quality Management
• /
• v.44 no.4
• /
• pp.869-881
• /
• 2016

Purpose: The objective of this study is to verify the economic validation of quality management integrated train freight car by analyzing economic evaluation indicators such as benefit and cost, net present value, and inter rate of return. Methods: First, we itemize benefit and cost field by reviewing literatures; Benefit consists of 1)Safety, 2)Operation, and 3)Maintenance; Cost consists of 1)Set-up fee, 2)Wireless internet fee, and 3)Cloud storage using fee. Second, based on these estimated values, we conduct an economic evaluation analysis. Among them, benefit and cost, net present value, and internal rate of return are selected. Results: As a result, all estimated values are highly over criterion of economic validity($$B/C{\geq}_-1$$, $$NPV{\geq}_-0$$, $$IRR{\geq}_-R$$); 1)benefit over cost ratio is 28.22, 2)Net present value is 8,121.66million KRW, and 3)Internal rate of return value is 2272%. Conclusion: The findings of this study will help making a decision when train industry adopts IoT technology for improving the effectiveness.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.235-243
• /
• 2011

The most widely used data mining technique is to explore association rules. This technique has been used to find the relationship between each set of items based on the association thresholds such as support, confidence, lift, etc. There are many interestingness measures as the criteria for evaluating association rules. Among them, confidence is the most frequently used, but it has the drawback that it can not determine the direction of the association. The net confidence measure was developed to compensate for this drawback, but it is useless in the case that the value of positive confidence is the same as that of negative confidence. This paper propose a attributably pure confidence to evaluate association rules and then describe some properties for a proposed measure. The comparative studies with confidence, net confidence, and attributably pure confidence are shown by numerical example. The results show that the attributably pure confidence is better than confidence or net confidence.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.135-145
• /
• 2017

Principal component analysis (PCA) describes the variation of multivariate data in terms of a set of uncorrelated variables. Since each principal component is a linear combination of all variables and the loadings are typically non-zero, it is difficult to interpret the derived principal components. Sparse principal component analysis (SPCA) is a specialized technique using the elastic net penalty function to produce sparse loadings in principal component analysis. When data are structured by groups of variables, it is desirable to select variables in a grouped manner. In this paper, we propose a new PCA method to improve variable selection performance when variables are grouped, which not only selects important groups but also removes unimportant variables within identified groups. To incorporate group information into model fitting, we consider a hierarchical lasso penalty instead of the elastic net penalty in SPCA. Real data analyses demonstrate the performance and usefulness of the proposed method.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1591-1604
• /
• 2020

This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.

• Journal of radiological science and technology
• /
• v.45 no.1
• /
• pp.41-47
• /
• 2022

The purpose of this study is to apply a deep learning model that can distinguish lung perfusion and lung ventilation images in nuclear medicine, and to evaluate the image classification ability. Image data pre-processing was performed in the following order: image matrix size adjustment, min-max normalization, image center position adjustment, train/validation/test data set classification, and data augmentation. The convolutional neural network(CNN) structures of VGG-16, ResNet-18, Inception-ResNet-v2, and SE-ResNeXt-101 were used. For classification model evaluation, performance evaluation index of classification model, class activation map(CAM), and statistical image evaluation method were applied. As for the performance evaluation index of the classification model, SE-ResNeXt-101 and Inception-ResNet-v2 showed the highest performance with the same results. As a result of CAM, cardiac and right lung regions were highly activated in lung perfusion, and upper lung and neck regions were highly activated in lung ventilation. Statistical image evaluation showed a meaningful difference between SE-ResNeXt-101 and Inception-ResNet-v2. As a result of the study, the applicability of the CNN model for lung scintigraphy classification was confirmed. In the future, it is expected that it will be used as basic data for research on new artificial intelligence models and will help stable image management in clinical practice.