• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.55-63
• /
• 2017

One of the purposes of Information Technology (IT) is to support human response to natural and social problems such as natural disasters and spread of disease, and to improve the quality of human life. Recent climate change has happened worldwide, natural disasters threaten the quality of life, and human safety is no longer guaranteed. IT must be able to support tasks related to disaster response, and more importantly, it should be used to predict and minimize future damage. In South Korea, the data related to the damage is checked out by each local government and then federal government aggregates it. This data is included in disaster reports that the federal government discloses by disaster case, but it is difficult to obtain raw data of the damage even for research purposes. In order to obtain data, information extraction may be applied to disaster reports. In the field of information extraction, most of the extraction targets are web documents, commercial reports, SNS text, and so on. There is little research on information extraction for government disaster reports. They are mostly text, but the structure of each sentence is very different from that of news articles and commercial reports. The features of the government disaster report should be carefully considered. In this paper, information extraction method for South Korea government reports in the word format is presented. This method is based on patterns and dictionaries and provides some additional ideas for tokenizing the damage representation of the text. The experiment result is F1 score of 80.2 on the test set. This is close to cutting-edge information extraction performance before applying the recent deep learning algorithms.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.159-170
• /
• 2008

Nowadays, one of the important functionalities required from robot task planners is to generate plans to compose existing component services into a new service. In this paper, we introduce the design and implementation of a heuristic search planner, JPLAN, as a kernel module for component service composition. JPLAN uses a local search algorithm and planning graph heuristics. The local search algorithm, EHC+, is an extended version of the Enforced Hill-Climbing(EHC) which have shown high efficiency applied in state-space planners including FF. It requires some amount of additional local search, but it is expected to reduce overall amount of search to arrive at a goal state and get shorter plans. We also present some effective heuristic extraction methods which are necessarily needed for search on a large state-space. The heuristic extraction methods utilize planning graphs that have been first used for plan generation in Graphplan. We introduce some planning graph heuristics and then analyze their effects on plan generation through experiments.

• Journal of The Korean Dental Society of Anesthesiology
• /
• v.10 no.1
• /
• pp.1-6
• /
• 2010

Background: Articaine, commercially available in South Korea from 2004, is widely being used for dental treatments. In the surgical extraction of impacted mandibular third molars, one of the most common procedures in oral and maxillofacial surgery, the anesthetic efficacy of 4% articaine and 2% lidocaine, both with 1：100,000 epinephrine, was compared. Methods: A randomized double-blind clinical trial was conducted of 80 patients for bilateral surgical extraction of mandibular third molars with informed consents. One operator carried out the routine surgical procedures using local anesthetic 4% articaine or 2% lidocaine with the same concentration of vasoconstrictor. Latency, duration of anesthesia and the amount of anesthetic solution were recorded. A visual analog scale (VAS) was used to evaluate the intraoperative pain. Results: The pain VAS scores reported similar anesthetic effect with both local anesthetics. Not in the latency of anesthesia and the amount of anesthetic solution, statistically significant difference was found in the mean duration of anesthesia. Conclusions: It was concluded that 4% articaine could offer better or at least the same clinical feasibility compared to 2% lidocaine, particularly in terms of the duration of the local anesthesia for common dental treatments.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

• 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.

• Journal of the Korean Institute of Educational Facilities
• /
• v.21 no.4
• /
• pp.3-10
• /
• 2014

The opportunity, provided for a direction planning mixed-use facilities for secondary schoo, is the purpose of this paper. Mixed-use facilities are an important issue in school building as it seeks to revive the facilities for local residents in school zone. The latest works of mixed-use facilities in secondary school, however, which are evaluated as well reflected the patterns of education and local community, are still deficient in that communicational elements in secondary school are inadequate. The cases of this paper, which are grown up as an educational building with mixed-use facilities opened to the local residents, are suitable to offer the design method for the future secondary school with mixed-use facilities. This paper reviews an assessment of its success in mixed-use facilities for secondary school as a public building for both of local residents and students and concludes with the establishment of design method for the future school; extraction of the factors contributing to development of mixed-use facilities in school area and proposal of design method; implementation of renewal of mixed-use facilities including educational program and spaces for the creation of identity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4126-4142
• /
• 2015

Finger vein recognition is a biometric technology using finger veins to authenticate a person, and due to its high degree of uniqueness, liveness, and safety, it is widely used. The traditional Symmetric Local Graph Structure (SLGS) method only considers the relationship between the image pixels as a dominating set, and uses the relevant theories to tap image features. In order to better extract finger vein features, taking into account location information and direction information between the pixels of the image, this paper presents a novel finger vein feature extraction method, Multi-Orientation Weighted Symmetric Local Graph Structure (MOW-SLGS), which assigns weight to each edge according to the positional relationship between the edge and the target pixel. In addition, we use the Extreme Learning Machine (ELM) classifier to train and classify the vein feature extracted by the MOW-SLGS method. Experiments show that the proposed method has better performance than traditional methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.508-510
• /
• 2000

본 논문은 의료 영상 중에서 복부 방사선 분야에서 보편적으로 사용되고 있는 CT 영상으로부터 간영역을 분할해내는 방법을 제시한다. 본 논문에서는 복부 CT영상에서 근육 부분과 척추, 늑골 부분을 제거하고, co-occurrence matrix를 이용한 국부 영상 이진화(local image thresholding) 방법을 통해 영상에서 간 영역을 분할한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.425-429
• /
• 1992

Point sets in the Euclidean and digital planes are discussed. The local necessary and sufficient conditions are suggested for pointed lattice extraction from these sets are presented. A number of theorems and corollaries are given. The regular and "almost" regular point sets are studied. The results can be used in automatic control of textured textile images by both general and multiprocessing systems.g systems.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.6
• /
• pp.2468-2478
• /
• 2018

We propose the Sparse Feature Convolutional Neural Network (SFCNN) to reduce the volume of convolutional neural networks (CNNs). Despite the superior classification performance of CNNs, their enormous network volume requires high computational cost and long processing time, making real-time applications such as online-training difficult. We propose an advanced network that reduces the volume of conventional CNNs by producing a region-based sparse feature map. To produce the sparse feature map, two complementary region-based value extraction methods, cluster max extraction and local value extraction, are proposed. Cluster max is selected as the main function based on experimental results. To evaluate SFCNN, we conduct an experiment with two conventional CNNs. The network trains 59 times faster and tests 81 times faster than the VGG network, with a 1.2% loss of accuracy in multi-class classification using the Caltech101 dataset. In vehicle classification using the GTI Vehicle Image Database, the network trains 88 times faster and tests 94 times faster than the conventional CNNs, with a 0.1% loss of accuracy.