• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.30 no.3
• /
• pp.142-149
• /
• 1994

In order to investigate the environmental properties of set net grounds located in the coastal waters of Yeosu. The current in the vicinity of set net grounds was observed by drogue and current meter in 1990 and 1992. The results obtained are summarized as follows: The direction of tidal current at the north enterance of Yeosu bay was southerly in ebb and northwesterly in flood without the distiction of the neap tide and the spring tide. In spring tide the maximum Velocity of the tidal current was 68 cm/sec in ebb and 66 cm/sec in flood. In neap tide the maximum velocity of the tidal current was 37 cm/sec in ebb and 35 cm/sec in flood. And so the direction of residual current was the south ward mainly and 21 cm/sec. The direction of tidal current at set net fishing grounds was southwesterly in ebb and westerly or northwesterly in flood. Regardless of the distinction of neap and spring. The maximum velocity of the current in spring tide was 50 cm/sec in ebb and 40 cm/sec in flood and that in neap was 28 cm/sec in ebb and 25 cm/sec in flood. In spring tide the speed vector along the major axis of semidiurnal tide component was three times as large as diurnal tide. In neap tide, however, the speed vector was about 50% less then that in spring tide, and the semidiurnal tide and diurnal tide were equal in the size of current ellipse and the direction of major axis. The sea area had a southwesterly residual current. 11 cm/sec in spring tide and 7 cm/sec in neap tide. According to the result of drogue tracking, the vicinity of set net fishing ground had a southerly residual current which formed in Yeosu Bay and a weak westerly residual current toward Dolsando from Namhedo. Therefore, set net fishing ground in coastal water of Yeosu was distributed in boundary of inner water which formed from Seamjin river and offshore water supplied from the vicinity of Sorido and Yochido.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.131-138
• /
• 2013

In this paper, I propose and evaluate the method that classifies emotional type of characters with their emotional words. Emotional types are classified as three types such as positive, negative and neutral. They are selected by classification of emotional words that characters speak. I propose the method to extract emotional words based on WordNet, and to represent as emotional vector. WordNet is thesaurus of network structure connected by hypernym, hyponym, synonym, antonym, and so on. Emotion word is extracted by calculating its emotional distance to each emotional category. The number of emotional category is 30. Therefore, emotional vector has 30 levels. When all emotional vectors of some character are accumulated, her/his emotion of a movie can be represented as a emotional vector. Also, thirty emotional categories can be classified as three elements of positive, negative, and neutral. As a result, emotion of some character can be represented by values of three elements. The proposed method was evaluated for 12 characters of four movies. Result of evaluation showed the accuracy of 75%.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.10 no.3
• /
• pp.133-146
• /
• 2015

This study is to investigate the causal relationship between exchange hedge and the net income of the shipbuilder through the unit root test and co-integration and vector autoregressive model(Vector Autoregressive Model: VAR). First, quarter net income of shipbuilders to order a unit root tests from 2000 to 2013 was used as a value after the Johnson transformation. In the same period, the return on bond futures(KTBF), three years bond yield(KTB3Y), America-Korea exchange differences are weekly data for each quarterly difference in value was converted by utilization, shipbuilding shares after log transformation which it was used. Also, structural change point investigation analysis to verify that looked to take advantage of the structural changes occur in the exchange hedge strategies affecting net income in the shipbuilding industry. Between the exchange hedge and net income of shipbuilders in structural change points detection and analysis showed that structural changes occur starting in 2004. In other words, strategy of shipbuilders about exchange hedge has occurred from "passive exchange hedge" to "active exchange hedge". The exchange hedge of the Korea shipbuilders through the estimation of the VAR was able to grasp that affect the profitability of mutual shipbuilders. Macroeconomic variables and stock prices could also check to see that affected the net income of the shipbuilding industry.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.2C
• /
• pp.141-146
• /
• 2003

In this paper, we propose an adaptive search range decision algorithm for motion vector estimation in video coding. The performance of general motion estimation method in video coding mechanism is evaluated with respect to the motion vector accuracy and the complexity, which is trade-off. The proposed algorithm that plays as a role of pre-processing for motion vector estimation determines the motion search range by the local statistics of motion vector of neighboring blocks, resulting in more than 60(%) reduction of the computational cost without the loss of visual quality. Experimental results show the capability of the proposed algorithm.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.307-322
• /
• 2024

Most object detection methods use a horizontal bounding box that causes problems between adjacent objects with arbitrary directions, resulting in misaligned detection. Hence, the horizontal anchor should be replaced by a rotating anchor to determine oriented bounding boxes. A two-stage process of delineating a horizontal bounding box and then converting it into an oriented bounding box is inefficient. To improve detection, a box-boundary-aware vector can be estimated based on a convolutional neural network. Specifically, we propose a ResNeXt101 encoder to overcome the weaknesses of the conventional ResNet, which is less effective as the network depth and complexity increase. Owing to the cardinality of using a homogeneous design and multi-branch architecture with few hyperparameters, ResNeXt captures better information than ResNet. Experimental results demonstrate more accurate and faster oriented object detection of our proposal compared with a baseline, achieving a mean average precision of 89.41% and inference rate of 23.67 fps.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.142-148
• /
• 2003

Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By ap-plying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic net-work for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• pp.539-550
• /
• 2021

Purpose: The purpose of this study is to propose a multivariate CUSUM control chart that can detect the out-of-control state fast while monitoring the cross- and auto- correlated multivariate time series data. Methods: We first build models to estimate the observation data and calculate the corresponding residuals. After then, a multivariate CUSUM chart is applied to monitor the residuals instead of the original raw observation data. Vector Autoregression and Artificial Neural Net are selected for the modelling, and Separated-MCUSUM chart is selected for the monitoring. The suggested methods are tested under a number of experimental settings and the performances are compared with those of other existing methods. Results: We find that Artificial Neural Net is more appropriate than Vector Autoregression for the modelling and show the combination of Separated-MCUSUM with Artificial Neural Net outperforms the other alternatives considered in this paper. Conclusion: The suggested chart has many advantages. It can monitor the complicated multivariate data with cross- and auto- correlation, and detects the out-of-control state fast. Unlike other CUSUM charts finding their control limits by trial and error simulation, the suggested chart saves lots of time and effort by approximating its control limit mathematically. We expect that the suggested chart performs not only effectively but also efficiently for monitoring the process with complicated correlations and frequently-changed parameters.

• Ocean Science Journal
• /
• v.42 no.1
• /
• pp.19-30
• /
• 2007

This study analyzed the current meter records along with wind records for over 500 days obtained in the Kangjin Bay, South Sea, Korea spanning from March, 2003 to Nov. 2005. Various analyses include descriptive statistics, harmonic analysis of tidal constituents, spectra and coherence, the principal axis, progressive vector diagrams. These analyses can illustrate the response of residual current to the local wind resulting in the net drift with rotational motion. Current speed ranges from -28 to 33 (cm/sec), with standard deviations from 6.5 to 12.9 (cm/sec). The harmonic analyses of the tidal current show the average form number, 0.12 with semi-diurnal type and the rectilinear orientation of the major axis toward northeast. The magnitudes of the semi-major range from 12.7 to 17.7 (cm/sec) for M2 harmonics, while for S2 harmonics, they range from 6.3 to 10.4 (cm/sec), respectively. In the spectral and coherency analysis of residual current and wind, a periodicity of 13.6 (day) is found to be most important in both records and plays an important role in the net drift of residual current. The progressive vector diagrams of residual current and wind show two types of behaviors such as unidirectional drift and rotational motion. It was also found that 3 % rule holds approximately to drive 1 (cm/sec) drift current by 30 (cm/sec) wind speed based on the correlation of the semi-major axis of wind and residual current.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.600-602
• /
• 1997

In this study, a hybrid neural net consisting of an Adaptive LVQ(ALVQ) algorithm and MLP is proposed to perform speaker identification task. ALVQ is a new learning procedure using adaptively feature vector sequence instead of only one feature vector in training codebooks initialized by LBG algorithm and the optimization criterion of this method is consistent with the speaker classification decision rule. ALVQ aims at providing a compressed, geometrically consistent data representation. It is fit to cover irregular data distributions and computes the distance of the input vector sequence from its nodes. On the other hand, MLP aim at a data representation to fit to discriminate patterns belonging to different classes. It has been shown that MLP nets can approximate Bayesian "optimal" classifiers with high precision, and their output values can be related a-posteriori class probabilities. The different characteristics of these neural models make it possible to devise hybrid neural net systems, consisting of classification modules based on these two different philosophies. The proposed method is compared with LBG algorithm, LVQ algorithm and MLP for performance.