• Journal of the Korean Institute of Landscape Architecture
• /
• v.30 no.3
• /
• pp.12-24
• /
• 2002

The purpose of this paper is to decompose the effect of resources of natural parks(NP) on user's satisfaction to answer the research question: What are the causal effects of resources of natural parks on user\ulcorner After reviewing the literature, classification of resources of NP, various approaches and analysis methods employed, we constructed the conceptual framework and have formulated the hypothesis of this research. We had obtained data through a questionnaire, which surveyed 414 visitors at 6 of the 73 NP in Korea in 2001, based on a stratified sampling method. We have analyzed the data using descriptive statistical methods, Pearson's correlation analysis, and a path analysis method. We found that 1) While the indirect effect of topographical feature and valley(TFV), socio-cultural resources(SCR), and climate, sound, and scent(CSS) turned out to be 2.75, 1.20, and 2.00 times higher than that of wild animal and plant(WAP), the direct effect of TFV, SCR, and landscape turned out to be 2.95, 2.88, and 2.64 times higher than that of CSS, 2) The magnitude of causal effects of the three exogeneous variables of TFV, WAP, and SCR and two intervening variables of CSS and landscape on User's satisfaction turned out to be 0.403, 0.048, 0.323, 0.188, and 0.243, respectively, 3) Total direct effect of the exogeneous and intervening variables on user's satisfaction is 0.871, while that of indirect effect is 0.334, and 4) Causal effect of tangible resources is 1.80 times higher than that of intangible while total effect of tangible resources are 1.36 times higher than that of intangible. The research results suggest that 1) Criteria for designation and maintenances of NP and results of previous studies on resources turned out to be unreliable and distorted, 2) In the criteria of planning and maintenance of NP, intangible resources must be included, 3) Remedial directions to increase user's satisfaction should be focused on maintenance of TFV and landscape in NP, and 4) The approach and path analysis adopted by this research is valid and highly useful for other resource based recreation area. It is recommended that more empirical study on seasonal variation of resources in NP based user's preference be performed in the future.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7C
• /
• pp.675-686
• /
• 2005

In this paper, we propose an efficient face region detection technique for the content-based video summarization. To segment video, shot changes are detected from a video sequence and key frames are selected from the shots. We select one frame that has the least difference between neighboring frames in each shot. The proposed face detection algorithm detects face region from selected key frames. And then, we provide user with summarized frames included face region that has an important meaning in dramas or movies. Using Bayes classification rule and statistical characteristic of the skin pixels, face regions are detected in the frames. After skin detection, we adopt the projection method to segment an image(frame) into face region and non-face region. The segmented regions are candidates of the face object and they include many false detected regions. So, we design a classifier to minimize false lesion using CART. From SGLD matrices, we extract the textual feature values such as Inertial, Inverse Difference, and Correlation. As a result of our experiment, proposed face detection algorithm shows a good performance for the key frames with a complex and variant background. And our system provides key frames included the face region for user as video summarized information.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.388-396
• /
• 2017

Since there are many variables such as various poses, illuminations and occlusions in a face detection problem, a high performance detection system is required. Although CNN is excellent in image classification, CNN operatioin requires high-performance hardware resources. But low cost low power environments are essential for small and mobile systems. So in this paper, the CPU-FPGA integrated system is designed based on 3-stage cascade CNN architecture using small size FPGA. Adaptive Region of Interest (ROI) is applied to reduce the number of CNN operations using face information of the previous frame. We use a Field Programmable Gate Array(FPGA) to accelerate the CNN computations. The accelerator reads multiple featuremap at once on the FPGA and performs a Multiply-Accumulate (MAC) operation in parallel for convolution operation. The system is implemented on Altera Cyclone V FPGA in which ARM Cortex A-9 and on-chip SRAM are embedded. The system runs at 30FPS with HD resolution input images. The CPU-FPGA integrated system showed 8.5 times of the power efficiency compared to systems using CPU only.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.6
• /
• pp.21-28
• /
• 2013

This paper proposes an effective fire detection approach that includes the following multiple heterogeneous algorithms: moving region detection using grey level histograms, color segmentation using fuzzy c-means clustering (FCM), feature extraction using a grey level co-occurrence matrix (GLCM), and fire classification using support vector machine (SVM). The proposed approach determines the optimal threshold values based on grey level histograms in order to detect moving regions, and then performs color segmentation in the CIE LAB color space by applying the FCM. These steps help to specify candidate regions of fire. We then extract features of fire using the GLCM and these features are used as inputs of SVM to classify fire or non-fire. We evaluate the proposed approach by comparing it with two state-of-the-art fire detection algorithms in terms of the fire detection rate (or percentages of true positive, PTP) and the false fire detection rate (or percentages of true negative, PTN). Experimental results indicated that the proposed approach outperformed conventional fire detection algorithms by yielding 97.94% for PTP and 4.63% for PTN, respectively.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.5
• /
• pp.1087-1097
• /
• 2017

As the penetration rate of smartphones increases, the number of malicious codes targeting smartphones is increasing. I 360 Security 's smartphone malware statistics show that malicious code increased 437 percent in the first quarter of 2016 compared to the fourth quarter of 2015. In particular, malicious applications, which are the main means of distributing malicious code on smartphones, are aimed at leakage of user information, data destruction, and money withdrawal. Often, it is operated by an API, which is an interface that allows you to control the functions provided by the operating system or programming language. In this paper, we propose a mechanism to detect malicious application based on the similarity of API pattern in normal application and malicious application by learning pattern of API in application derived from static analysis. In addition, we show a technique for improving the detection rate and detection rate for each label derived by using the corresponding mechanism for the sample data. In particular, in the case of the proposed mechanism, it is possible to detect when the API pattern of the new malicious application is similar to the previously learned patterns at a certain level. Future researches of various features of the application and applying them to this mechanism are expected to be able to detect new malicious applications of anti-malware system.

• Journal of Navigation and Port Research
• /
• v.37 no.6
• /
• pp.617-625
• /
• 2013

"Sale and purchase brokers" are independent contractors who act as agents for principals intending to seller or buy ships in English Maritime Law. The essential feature is that legal position of shipbroker is largely one of agency. They can be obtained by a study of the Lloyd's Register or the equivalent registers of other Classification Societies, the American Bureau of Shipping and Korean Registers. Such a broker is of valuable assistance to the prospective seller or purchaser. And the broker's liability normally arises in the context of a contract. But, expressed in general terms, those contractual obligations are, in absence of contrary agreement, to act with reasonable care and skilled to obtain the cover requested by his client not to guarantee that such will be concluded and to ensure that the scope of the policy, its essential terms and relevant exclusions are made known to the insured. Acting in this professional capacity, the broker's liability are such that the facts upon which an action for breach of contract may be based may also found an action for the trot of negligence provided that there is shown to be the necessary 'assumption of responsibility' by the broker conveyed directly or indirectly to the insured. This thesis deals with liability of S&P Brokers, the legal problems of ship broking, commission, conflicts of interest and secret commissions in English Maritime Law and the Cases.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.10
• /
• pp.447-454
• /
• 2015

This paper proposes geographical name denoising by machine learning of event detection based on twitter. Recently, the increasing number of smart phone users are leading the growing user of SNS. Especially, the functions of short message (less than 140 words) and follow service make twitter has the power of conveying and diffusing the information more quickly. These characteristics and mobile optimised feature make twitter has fast information conveying speed, which can play a role of conveying disasters or events. Related research used the individuals of twitter user as the sensor of event detection to detect events that occur in reality. This research employed geographical name as the keyword by using the characteristic that an event occurs in a specific place. However, it ignored the denoising of relationship between geographical name and homograph, it became an important factor to lower the accuracy of event detection. In this paper, we used removing and forecasting, these two method to applied denoising technique. First after processing the filtering step by using noise related database building, we have determined the existence of geographical name by using the Naive Bayesian classification. Finally by using the experimental data, we earned the probability value of machine learning. On the basis of forecast technique which is proposed in this paper, the reliability of the need for denoising technique has turned out to be 89.6%.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.861-869
• /
• 2020

We introduce the application that automatically makes several images stored in user's device into one video by using the different climax patterns appearing for each film genre. For the classification of the genre characteristics of movies, a climax pattern model style was created by analyzing the genre of domestic movie drama, action, horror and foreign movie drama, action, and horror. The climax pattern was characterized by the change in shot size, the length of the shot, and the frequency of insert use in a specific scene part of the movie, and the result was visualized. The model visualized by genre developed as a template using Firebase DB. Images stored in the user's device were selected and matched with the climax pattern model developed as a template for each genre. Although it is a short video, it is a feature of the proposed application that it can create an emotional story video that reflects the characteristics of the genre. Recently, platform operators such as YouTube and Naver are upgrading applications that automatically generate video using a picture or video taken by the user directly with a smartphone. However, applications that have genre characteristics like movies or include video-generation technology to show stories are still insufficient. It is predicted that the proposed automatic video editing has the potential to develop into a video editing application capable of transmitting emotions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.