• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.1-9
• /
• 2021

Disaster alerts are text messages sent by government to people in the area in the event of a disaster. Since the number of disaster alerts has increased, the number of people who block disaster alerts is increasing as many unnecessary disaster alerts are being received. To solve this problem, this study proposes a deep learning model that automatically classifies disaster alerts by disaster type, and allows only necessary disaster alerts to be received according to the recipient. The proposed model embeds disaster alerts via KoBERT and classifies them by disaster type with LSTM. As a result of classifying disaster alerts using 3 combinations of parts of speech: [Noun], [Noun + Adjective + Verb] and [All parts], and 4 classification models: Proposed model, Keyword classification, Word2Vec + 1D-CNN and KoBERT + FFNN, the proposed model achieved the highest performance with 0.988954 accuracy.

• The Journal of Korean Philosophical History
• /
• no.54
• /
• pp.115-151
• /
• 2017

With Seopa Ryu-Hee's Chunqiugwalyebulyu as the main research subject. this paper is to clarify characteristics in classification of the book's introductory remarks and its academic values. This book is a sort of synthetic collection of introductory remarks classification that defines standardized introductory remarks based on fundamental principles of Chunqiu introductory remarks. Seopa presented two fundamental principles for classifying Chunqiu introductory remarks. First, he clearly defined the nature and the system of the book Chunqiu, which was to present the background of classifying Chunqiu introductory remarks. Second, he declared that writing style and righteousness in Chunqiu serves as standard for classifying the introductory remarks. Seopa classified introductory remarks by type in accordance with these fundamental principles of introductory remarks in order to lay the groundwork for right interpretation of Chunqiu. Further, he was convinced that this classification of introductory remarks would block any chance of the book's wrong interpretation and at the same time, be able to remove the rationale behind distorted theories. This book can be appraised to have significant academic values in that it attempted standardization in classifying Chunqiu introductory remarks through systematic and synthetic analysis on various introductory remarks.

• Journal of the Korean Institute of Educational Facilities
• /
• v.9 no.1
• /
• pp.27-36
• /
• 2002

This paper is to evaluate the campus master plan, which is influenced by Korean educational policy and managing organization, with respect to land use and block plans of buildings. It uses a case study method to periodically know specific details to form a master plan. It is found, at first, that design method of master plan was influenced by some educational policies and managing organization of ministry of education. Secondly, design methods have been changed according to the change of the times. Any master plan was not formulated until the 1960s. Seoul National University formed a master plan adopting radiated sector pattern for land use and a block plan in the early years of the 1970s. Chungnam National University used a squared space style with a trouble of the learned from the SNU design methods in the year 1974. A concept of axis according to topography] in Andong National University and environmental preservation in Yiosu National University was used in the 1980s. Korean Athletic Educational University used a transportation model for facilitating efficiency to use university land and making pedestrian convenient by classification with fast and slow walker's way.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4502-4518
• /
• 2015

Fisher linear discriminant analysis (LDA) is one of the most popular projection techniques for feature extraction and has been widely applied in face recognition. However, it cannot be used when encountering the single sample per person problem (SSPP) because the intra-class variations cannot be evaluated. In this paper, we propose a novel method called local similarity based linear discriminant analysis (LS_LDA) to solve this problem. Motivated by the "divide-conquer" strategy, we first divide the face into local blocks, and classify each local block, and then integrate all the classification results to make final decision. To make LDA feasible for SSPP problem, we further divide each block into overlapped patches and assume that these patches are from the same class. To improve the robustness of LS_LDA to outliers, we further propose local similarity based median discriminant analysis (LS_MDA), which uses class median vector to estimate the class population mean in LDA modeling. Experimental results on three popular databases show that our methods not only generalize well SSPP problem but also have strong robustness to expression, illumination, occlusion and time variation.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.2
• /
• pp.101-109
• /
• 2006

We propose an adaptive digital watermarking algorithm using HVS(human visual system) and SOM(Self-Organizing Map) among neural networks. This method adjusts adaptively the strength of the watermark which is embedded in different blocks according to block classification in DCT(Discrete Cosine Transform) domain. All blocks in 3 classes out of 4 are selected to embed a watermark. Watermark sequences are embedded in 6 lowest frequency coefficients of each block except the DC component. The experimental results are excellent.

• Korean Journal of Remote Sensing
• /
• v.32 no.5
• /
• pp.471-482
• /
• 2016

This paper presents an extraction method for water body which uses block-based image partitioning and extension of water body boundaries to improve the performance of supervised classification for water body extraction. The Mahalanobis distance image is created by computing the spectral information of Normalized Difference Water Index (NDWI) and Near Infrared (NIR) band images over a training site within the water body in order to extract an initial water body area. To reduce the effect of noise contained in the Mahalanobis distance image, we apply mean curvature diffusion to the image, which controls diffusion coefficients based on connectivity strength between adjacent pixels and then extract the initial water body area. After partitioning the extracted water body image into the non-overlapping blocks of same size, we update the water body area using the information of water body belonging to water body boundaries. The update is performed repeatedly under the condition that the statistical distance between water body area belonging to water body boundaries and the training site is not greater than a threshold value. The accuracy assessment of the proposed algorithm was tested using KOMPSAT-2 images for the various block sizes between $11{\times}11$ and $19{\times}19$. The overall accuracy and Kappa coefficient of the algorithm varied from 99.47% to 99.53% and from 95.07% to 95.80%, respectively.

• Journal of Society of Preventive Korean Medicine
• /
• v.14 no.1
• /
• pp.111-123
• /
• 2010

Backgrounds : Stroke is characterized by loss of brain functions due to a disturbance in the blood vessels supplying blood to the brain, and classified into hemorrhage and ischemia. Stroke is known to be affected by genetic factors and other diseases such as hypertension and cardiovascular diseases. However, the distinctive association between stroke and genetic variations has not discovered yet. Objectives : This study investigated the effects of fibrinogen level and genetic variations in FGA (Fibrinogen alpha chain) gene on stroke in Korean stroke patients and controls. Methods : DNA samples from 674 stroke patients diagnosed by Oriental medical hospitals and 267 controls were used in this study. Two common single nucleotide polymorphism(SNP) with high minor allele frequency(MAF), rs2070011G/A of promoter region and nonsynonymous rs6050A/G of exon 5 in FGA gene, were targeted for Taqman genotyping. Because the TOAST classification is important to the factors and symptoms of stroke, ischemic patients were further classified into five subtypes using diagnosis and clinical data. One-way ANOVA and chi-square test were used for clinical data and genetic association, respectively. Haploview v4.1 program was used for linkage disequilibrium(LD), haplotype and haplotype block analysis. Results : The levels of red blood cells and fibrinogen from clinical data were shown to be significant factors for the sub-groups of TOAST classification. No significant associations of stroke, hemorrhage, ischemic and subtypes of TOAST with rs2070011 and rs6050 of FGA gene were found(P > 0.05). However, rs2070011 in promoter region and nonsynonymous rs6050 in exon 5 which produce the amino acid change from threonine to alanine showed a haplotype block and three haplotypes of A-G, G-A, A-A, suggesting that rs2070011 and rs6050 might be co-segregated in generic recombination. Although A-A haplotype of stroke patients showed 64-69% low frequency compared to controls, there was no significant association between stroke and haplotype(P > 0.05). Conclusion : This study showed that there was no significant association between stroke and two SNP of rs2070011G/A and nonsynonymous rs6050A/G in FGA gene. However, these two SNP compose a haplotype block and three haplotypes of A-G, G-A, A-A. This finding suggests that rs2070011 and rs6050 are so close as to be positioned as linkage disequilibrium. Nevertheless, no significant association between haplotypes and stroke was found.

• Journal of the Korean Institute of Gas
• /
• v.17 no.5
• /
• pp.42-50
• /
• 2013

With the rapid change of industry and the development of science and technology, more than 100,000 industrial chemicals are being used and 2,000 new materials are developed every year. Chemical products have had favorable influence on our daily life and contributed very much to the prosper of human culture. But some materials are inherently poisonous and dangerous. Korea ranks as the number 7 in world's chemical products market and the chemical sector is contributing to the economic revival through importing and exporting of the products. With the increasing domestic as well as international interests about REACH and GHS, the need for the effective and efficient chemical material management system is getting bigger and bigger. In this research, we compare the criteria in UN GHS and Safety Control of Dangerous Substances Act of Korea for the development of global standard test methods and the classification and labelling for the chemicals, and suggest an advancement plan for the introduction of the GHS in a building block approach. In addition, providing the harmonized information about chemical hazards is suggested for the elimination of international trade barriers for chemical industries.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.79-85
• /
• 2022

Anomaly detection is a method to detect and block abnormal data flows in general users' data sets. The previously known method is a method of detecting and defending an attack based on a signature using the signature of an already known attack. This has the advantage of a low false positive rate, but the problem is that it is very vulnerable to a zero-day vulnerability attack or a modified attack. However, in the case of anomaly detection, there is a disadvantage that the false positive rate is high, but it has the advantage of being able to identify, detect, and block zero-day vulnerability attacks or modified attacks, so related studies are being actively conducted. In this study, we want to deal with these anomaly detection mechanisms, and we propose a new mechanism that performs both anomaly detection and classification while supplementing the high false positive rate mentioned above. In this study, the experiment was conducted with five configurations considering the characteristics of various algorithms. As a result, the model showing the best accuracy was proposed as the result of this study. After detecting an attack by applying the Extra Tree and Three-layer ANN at the same time, the attack type is classified using the Extra Tree for the classified attack data. In this study, verification was performed on the NSL-KDD data set, and the accuracy was 99.8%, 99.1%, 98.9%, 98.7%, and 97.9% for Normal, Dos, Probe, U2R, and R2L, respectively. This configuration showed superior performance compared to other models.

• Journal of Korean Neurosurgical Society
• /
• v.51 no.5
• /
• pp.281-285
• /
• 2012

Objective : Occipital neuralgia is characterized by paroxysmal jabbing pain in the dermatomes of the greater or lesser occipital nerves caused by irritation of these nerves. Although several therapies have been reported, they have only temporary therapeutic effects. We report the results of pulsed radiofrequency treatment of the occipital nerve, which was used to treat occipital neuralgia. Methods : Patients were diagnosed with occipital neuralgia according to the International Classification of Headache Disorders classification criteria. We performed pulsed radiofrequency neuromodulation when patients presented with clinical findings suggestive occipital neuralgia with positive diagnostic block of the occipital nerves with local anesthetics. Patients were analyzed according to age, duration of symptoms, surgical results, complications and recurrence. Pain was measured every month after the procedure using the visual analog and total pain indexes. Results : From 2010, ten patients were included in the study. The mean age was 52 years (34-70 years). The mean follow-up period was 7.5 months (6-10 months). Mean Visual Analog Scale and mean total pain index scores declined by 6.1 units and 192.1 units, respectively, during the follow-up period. No complications were reported. Conclusion : Pulsed radiofrequency neuromodulation of the occipital nerve is an effective treatment for occipital neuralgia. Further controlled prospective studies are necessary to evaluate the exact effects and long-term outcomes of this treatment method.