• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.24 no.4
• /
• pp.495-508
• /
• 2019

Tidal datums are key and basic information used in fields of navigation, coastal structures' design, maritime boundary delimitation and inundation warning. In Korea, the Approximate Lowest Low Water (ALLW) and the Approximate Highest High Water (AHHW) have been used as levels of tidal datums for depth, coastline and vertical clearances in hydrography and coastal engineering fields. However, recently the major maritime countries including USA, Australia and UK have adopted the Lowest Astronomical Tide (LAT) and the Highest Astronomical Tide (HAT) as the tidal datums. In this study, 1-hr interval 19-year sea level records (1999-2017) observed at 9 tidal observation stations along the west and south coasts of Korea were used to calculate LAT and HAT for each station using 1-minute interval 19-year tidal prediction data yielded through three tidal harmonic methods: 19 year vector average of tidal harmonic constants (Vector Average Method, VA), tidal harmonic analysis on 19 years of continuous data (19-year Method, 19Y) and tidal harmonic analysis on one year of data (1-year Method, 1Y). The calculated LAT and HAT values were quantitatively compared with the ALLW and AHHW values, respectively. The main causes of the difference between them were explored. In this study, we used the UTide, which is capable of conducting 19-year record tidal harmonic analysis and 19 year tidal prediction. Application of the three harmonic methods showed that there were relatively small differences (mostly less than ±1 cm) of the values of LAT and HAT calculated from the VA and 19Y methods, revealing that each method can be mutually and effectively used. In contrast, the standard deviations between LATs and HATs calculated from the 1Y and 19Y methods were 3~7 cm. The LAT (HAT) differences between the 1Y and 19Y methods range from -16.4 to 10.7 cm (-8.2 to 14.3 cm), which are relatively large compared to the LAT and HAT differences between the VA and 19Y methods. The LAT (HAT) values are, on average, 33.6 (46.2) cm lower (higher) than those of ALLW (AHHW) along the west and south coast of Korea. It was found that the S_a and N₂ tides significantly contribute to these differences. In the shallow water constituents dominated area, the M₄ and MS₄ tides also remarkably contribute to them. Differences between the LAT and the ALLW are larger than those between the HAT and the AHHW. The asymmetry occurs because the LAT and HAT are calculated from the amplitudes and phase-lags of 67 harmonic constituents whereas the ALLW and AHHW are based only on the amplitudes of the 4 major harmonic constituents.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Science of Emotion and Sensibility
• /
• v.11 no.4
• /
• pp.461-480
• /
• 2008

There are innumerable studies on technology adoption and usage continuance; most examine cognitive factors while affective factors or the feelings of users are left relatively unexplored. Although attitude and user satisfaction are factors commonly considered in Information Systems(IS) research, they represent only some aspects of feelings. In contrast, researchers in diverse fields have begun to note the importance of feelings in understanding and predicting human behavior. Feelings are anticipated to be essential particularly in the context of modern applications, such as mobile internet(M-internet) services, where users are not simply technology users but also service consumers. Drawing on the support of consumer research, social psychology and computer science, this study proposes a balanced cognition-affect model of IS continuance. Prior works in relation to IS research have already considered the emotional factors. The common factors are enjoyment, anxiety, affect and satisfaction. The main difference in our study is that the factors that we used are the primary dimensions of affect according to Circumplex Model of Affect. The horizontal axis of the model represents the pleasure dimension and the vertical represents the arousal dimension. Other emotional factors such as enjoyment and anxiety can be viewed as a combination of these two dimensions, and they can be placed in the vector space formed by these two primary dimensions. Affect has been defined as the enjoyment a person derives from using computers. Satisfaction has different conceptualizations. It has been conceptualized as judgment based on the expectation disconfirmation theory. Thus, while prior works considered the direct and indirect effects of "feeling-related constructs"(enjoyment and anxiety) on usage behavior, our study proposes effects of "feeling-based constructs"(pleasure and arousal). The balanced cognition-affect model is tested in a survey of, M-internet service users. The results establish the validity of the model.

• Research in Plant Disease
• /
• v.18 no.4
• /
• pp.402-405
• /
• 2012

We surveyed the occurrence of Rice stripe virus (RSV) disease in 672 fields from 29 rice representative area in July 2012 as nationwide survey for RSV occurrence since 2008. We confirmed occurrence of virus disease in 18 areas, in west coast region including Secheon, Taean, Buwan and Cheorwon. RSV incidence rates of plant in Sacheon and Buan were less than 0.01% and 0.15%, respectively, showing similar rate with the nationwide survey carried out in 2008, whereas incidence rate of field declined from 19.9% in 2008 to 4.9% in 2012. Earlier, RSV occurred largely across the southern region of Korea. In 2001, RSV disease was found in Gangwha and Gyeonggi-do, the northern region of Korea. In 2007, RSV appeared in west coast; Buan in Jeollabuk-do and Seocheon in Choongnam-do. After migration of the vector, small brown plant hopper, from China in 2009, RSV is becoming a pandemic.

• Korean Journal of Agricultural Science
• /
• v.45 no.1
• /
• pp.38-42
• /
• 2018

Demand for tomatoes has been increasing every year as people desire more healthy food. In Korea, tomatoes are mainly grown in the Chungnam, Chunnam and Kyungnam provinces. Recently, reports of whitefly-transmitted viral diseases have increased due to newly emerging whitefly pressures caused by climate change in Korea. Specifically, in 2017, the main tomato growing areas, Buyeo and Nonsan in Chungnam, showed damage typical of viral infection; therefore, we investigated viral diseases in these areas. We collected samples with virus-like symptoms and found that not only whitefly transmitted Tomato yellow leaf curl virus (TYLCV) and Tomato chlorosis virus (ToCV) were detected but also Tomato mosaic virus (ToMV, for which no specific vector is known) and Tomato spotted wilt virus (TSWV, transmitted by thrips). The ToMV-infected samples were mostly co-infected with either TYLCV or ToCV. Mixed infections of different combinations of TYLCV, ToCV and ToMV were detected with the mixed infection of two whitefly-transmitted viruses (TYLCV and ToCV) causing the most severe symptoms. According to the CP sequence of each virus, the 100% identities were shown to be Mexico/ABG73017.1 (TYLCV), Greece/CDG34553.1 (ToCV), China/AKN79752 (TSWV), and Australia/NP078449.1 (ToMV). Based on the sequence data, we presumed that these tomato infecting viruses were transmitted through insects and seeds introduced from neighboring countries.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.85-92
• /
• 2017

As accessibility toward traditional cultural contents drops compared to its increase in production, the need for higher accessibility for continued management and research to exist. For this, this paper introduces an image classifier model for traditional images based on artificial neural networks, which converts the input image's features into a vector space and by utilizing a RNN based model it recognizes and compares the details of the input which enables the classification of traditional images. This enables the classifiers to classify similarly looking traditional images more precisely by focusing on the details. For the training of this model, a wide range of images were arranged and collected based on the format of the Korean information culture field, which contributes to other researches related to the fields of using traditional cultural images. Also, this research contributes to the further activation of demand, supply, and researches related to traditional culture.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.20 no.7
• /
• pp.639-647
• /
• 2009

In this work, wrapping conductors with thin magnetic materials is proposed as a magnetic shielding method. The 0.1 mm thick metal sheets of mu-metal, grain-oriented electrical steel, and non-oriented electrical steel were produced from commercial alloy sheets through cold rolling and followed high temperature annealing. In case of 3-phase electric currents, mu-metal was the best in shielding performance at a B-field magnitude of about 100 ${\mu}T$, whereas silicon steels were better than mu-metal at a B-magnitude over 500 ${\mu}T$. In addition, wrapping with silicon steel(inner) together with mu-metal(outer) resulted in a shielding factor less than 0.1 even at 500 ${\mu}T$. These results are due to changes in hierarchy of magnetic permeabilities of the materials with increasing magnetic field strength. In case of single-phase electric current, B-magnitude outside the magnetic shell was rather increased compared to the unshielded case. This result is explained by vector composition of B-fields near magnetic shielding materials.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.36 no.3
• /
• pp.257-265
• /
• 2000

Brushless DC(BLDC) motors are widely used as AC servo motors in factory automation fields because of their quick instantaneous mobility, good energy saving efficiency and easiness of design for control system comparing with induction motors. Recently, a Two-Degree-of-Freedom(2DOF) PI control law has been adopted to some application parts to accomplish an advanced speed control of BLDC motors. The method can treat the two conflicting performances, minimum tracking errors versus reference inputs without large overshoot and rejection of some disturbances including modeling errors, independently. However, the method can not design the optimal system which is able to minimize tracking errors and energy consumption simultaneously. In this paper, a 2DOF integral type optimal servo control method is investigated to promote the speed control performances of BLDC motors considering energy consumption. In order to applicate the method to the speed servo system of the BLDC motor, the motor is modeled in the state space using the vector control and decoupling technique. To verify the validity of the suggested method, some simulations and experiments are performed.

• The Journal of Information Technology
• /
• v.7 no.2
• /
• pp.93-104
• /
• 2004

Sports scene is characterized by large amount of global motion due to pan and zoom of camera motion, and includes many small objects moving independently. Some short period of sports games is thrilling to televiewers, and important to producers. At the same time that kinds of scenes exhibit exceptionally dynamic motions and it is very difficult to analyze the motions with conventional algorithms. In this thesis, several algorithms are proposed for global motion analysis on these dynamic scenes. It is shown that proposed algorithms worked well for motion compensation and panorama synthesis. When cascading the inter frame motions, accumulated errors are unavoidable. In order to minimize these errors, interpolation method of motion vectors is introduced. Affined transform or perspective projection transform is regarded as a square matrix, which can be factorized into small amount of motion vectors. To solve factorization problem, we preposed the adaptation of Newton Raphson method into vector and matrix form, which is also computationally efficient. Combining multi frame motion estimation and the corresponding interpolation in hierarchical manner enhancement algorithm of motion parameters is proposed, which is suitable for motion compensation and panorama synthesis. The proposed algorithms are suitable for special effect rendering for broadcast system, video indexing, tracking in complex scenes, and other fields requiring global motion estimation.