• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.278-284
• /
• 2003

Speech act is the speaker's intentions indicated through utterances. It is important for understanding natural language dialogues and generating responses. This paper proposes the method of two stage that increases the performance of the korean speech act decision. The first stage is to select features from the part of speech results in sentence and from the context that uses previous speech acts. We use x$^2$ statistics(CHI) for selecting features that have showed high performance in text categorization. The second stage is to determine speech act with selected features and Neural Network. The proposed method shows the possibility of automatic speech act decision using only POS results, makes good performance by using the higher informative features and speed up by decreasing the number of features. We tested the system using our proposed method in Korean dialogue corpus transcribed from recording in real fields, and this corpus consists of 10,285 utterances and 17 speech acts. We trained it with 8,349 utterances and have test it with 1,936 utterances, obtained the correct speech act for 1,709 utterances(88.3%). This result is about 8% higher accuracy than without selecting features.

• Proceedings of KOSOMES biannual meeting
• /
• 2004.11a
• /
• pp.43-47
• /
• 2004

Two different sensors (here, KOMPSAT and RADARSAT) are considered for ship detection, and are used to delineate the detection performance for their data The experiments are set for coastal regions of Mokpo Port and Ulsan Port and field experiments on board pilot boat are conducted to collect in situ ship validation information such as ship type and length This paper introduce mainly the experiment result of ship detection by both RADARSAT SAR imagery and land-based RADAR data, operated by the local Authority of South Korean, so called vessel traffic system (VTS) radar. Fine imagery of Ulsan Port was acquired on June 19, 2004 and in-situ data such as wind speed and direction, taking pictures of ships and natural features were obtained aboard a pilot ship. North winds, with a maximum speed of 3.1 m/s were recorded Ship's position, size and shape and natural features of breakwaters, oil pipeline and alongside ship were compared using SAR and VTS. It is shown that KOMPSAT/EOC has a good performance in the detection of a moving ship at a speed of kts or more an hour that ship and its wake can be imaged. The detection capability of RADARSAT doesn't matter how fast ship is running and depends on a ship itself, e.g. its material, length and type. Our results indicate that SAR can be applicable to automated ship detection for a VTS and SAR combination service.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.117-124
• /
• 2013

In this paper, we present a new method which efficiently estimates a face direction from a sequences of input video images in real time fashion. For this work, the proposed method performs detecting the facial region and major facial features such as both eyes, nose and mouth by using the Haar-like feature, which is relatively not sensitive against light variation, from the detected facial area. Then, it becomes able to track the feature points from every frame using optical flow in real time fashion, and determine the direction of the face based on the feature points tracked. Further, in order to prevent the erroneously recognizing the false positions of the facial features when if the coordinates of the features are lost during the tracking by using optical flow, the proposed method determines the validity of locations of the facial features using the template matching of detected facial features in real time. Depending on the correlation rate of re-considering the detection of the features by the template matching, the face direction estimation process is divided into detecting the facial features again or tracking features while determining the direction of the face. The template matching initially saves the location information of 4 facial features such as the left and right eye, the end of nose and mouse in facial feature detection phase and reevaluated these information when the similarity measure between the stored information and the traced facial information by optical flow is exceed a certain level of threshold by detecting the new facial features from the input image. The proposed approach automatically combines the phase of detecting facial features and the phase of tracking features reciprocally and enables to estimate face pose stably in a real-time fashion. From the experiment, we can prove that the proposed method efficiently estimates face direction.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.473-478
• /
• 2005

The gastric cancer takes the great part of the cancer occurrence and the mortality from cancer in Korea, and the early detection of gastric cancer is very important in the treatment and convalescence. This paper. for the early detection of gastric cancer, Proposes the analysis system of endoscopic image of the stomach that detects the abnormal region by using the change of color in the image and provides the surface tissue information to the detector. While the advanced inflammation and the cancer may be easily detected, the early inflammation and the cancer have a difficulty in detection and require the more attention lot detection. This paper, at first, converts the endoscopic image to the Image of IHb(Index of Hemoglobin) model and removes noises incurred by illumination, and next, automatically detects the regions suspected as cancer and provides the related information to the detector, or provides the surface tissue information for the regions appointed by the detector. This paper does not intend to provide the final diagnosis of the detected abnormal regions as gastric cancer, but provides the supplementary mean that reduces the load and mistaken diagnosis of the detector by automatically detecting the abnormal regions being not easily detected by human eyes and providing the additional information for the diagnosis. The experiments using practical endoscopic images for performance evaluation showed that the proposed system is effective in the analysis of endoscopic image of the stomach.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.329-334
• /
• 2014

In this study, a new method that automatically segments trabecular bone for its morphological analysis using micro-computed tomography imaging was proposed. In the proposed method, the bone region was extracted using a threshold value, and the outer boundary of the bone was detected. The sphere of maximum size with the corresponding voxel as the center was obtained by applying the sphere-fitting method to each voxel of the bone region. If this sphere includes the outer boundary of the bone, the voxels included in the sphere are classified as cortical bone; otherwise, they are classified as trabecular bone. The proposed method was applied to images of the distal femurs of 15 mice, and comparative experiments, with results manually divided by a person, were performed. Four morphological parameters-BV/TV, Tb.Th, Tb.Sp, and Tb.N-for the segmented trabecular bone were measured. The results were compared by regression analysis and the Bland-Altman method; BV/TV, Tb.Th, Tb.Sp, and Tb.N were all in the credible range. In addition, not only can the sphere-fitting method be simply implemented, but trabecular bone can also be divided precisely by using the three-dimensional information.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.2
• /
• pp.99-105
• /
• 2013

In rapidly developing urban areas that include high-rise, large, and complex buildings, indoor and outdoor maps in GIS become a basis for utilizing and sharing information pertaining to various aspects of the real world. Although an indoor mapping has gained much attentions, research efforts are mostly in 2D and 3D modeling of terrain and buildings. Therefore, to facilitate fast and accurate construction of indoor GIS, this paper proposes a semi-automatic method consisting of preprocessing, 2D mapping, and 3D mapping stages. The preprocessing is designed to estimate heights of building interiors and to identify noise data from point clouds. In the 2D mapping, a floor map is extracted with a tracing grid and a refinement method. In the 3D mapping, a 3D wireframe model is created with heights from the preprocessing stage. 3D mesh data converted from noise data is combined with the 3D wireframe model for detail modeling. The proposed method was applied to point clouds depicting a hallway in a building. Experiment results indicate that the proposed method can be utilized to construct 2D and 3D maps for indoor GIS.

• The KIPS Transactions:PartA
• /
• v.12A no.6 s.96
• /
• pp.539-546
• /
• 2005

Recently, as the number of Internet users are growing explosively, e-learning has been applied spread, as well as remote evaluation of intellectual capacity However, only the multiple choice and/or the objective tests have been applied to the e-learning, because of difficulty of natural language processing. For the intelligent marking of short-essay typed answer papers with rapidness and fairness, this work utilize heterogenous linguistic knowledges. Firstly, we construct the semantic kernel from un tagged corpus. Then the answer papers of students and instructors are transformed into the vector form. Finally, we evaluate the similarity between the papers by using the semantic kernel and decide whether the answer paper is correct or not, based on the similarity values. For the construction of the semantic kernel, we used latent semantic analysis based on the vector space model. Further we try to reduce the problem of information shortage, by integrating Korean Word Net. For the construction of the semantic kernel we collected 38,727 newspaper articles and extracted 75,175 indexed terms. In the experiment, about 0.894 correlation coefficient value, between the marking results from this system and the human instructors, was acquired.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.4
• /
• pp.106-117
• /
• 2016

Recently, solar power plants have spread widely as part of the transition to greater environmental protection and renewable energy. Therefore, regular solar plant inspection is necessary to efficiently manage solar-light modules. This study implemented a test that can detect solar-light module faults using an UAV based thermal infrared camera and GIS spatial analysis. First, images were taken using fixed UAV and an RGB camera, then orthomosaic images were created using Pix4D SW. We constructed solar-light module layers from the orthomosaic images and inputted the module layer code. Rubber covers were installed in the solar-light module to detect solar-light module faults. The mean temperature of each solar-light module can be calculated using the Zonalmean function based on temperature information from the UAV thermal camera and solar-light module layer. Finally, locations of solar-light modules of more than $37^{\circ}C$ and those with rubber covers can be extracted automatically using GIS spatial analysis and analyzed specifically using the solar-light module's identifying code.

• Journal of The Korean Association of Information Education
• /
• v.9 no.1
• /
• pp.113-124
• /
• 2005

In this study, we designed and developed a tool to help teachers select and develop effective performance assessment criteria considering characteristics of individual learners. Using this tool, we can analyze preferences of teachers and characteristics of students for each rubric by exploring the classification and association rules through data mining. Those findings can give us guidelines and insights for the development and the selection of performance assessment criteria. The classification rules found are used for the learner-centered evaluation reflecting learners' interests, capabilities, and circumstances. Association rules found are utilized for analyzing teachers' preference, which enable to reduce time and efforts for the development and selection of rubric. Also, this tool supports creation, change, and selection of teachers' rubric linked with the performance assessment of NEIS(National Education Information System).

• The KIPS Transactions:PartB
• /
• v.17B no.2
• /
• pp.139-148
• /
• 2010

This paper shows a reinforcement post-processing method and feedback algorithm for improvement of assigning method in classification. Especially, we focused on complex documents that are generally considered to be hard to classify. A basis factors in traditional classification system are training methodology, classification models and features of documents. The classification problem of the documents containing shared features and multiple meanings, should be deeply mined or analyzed than general formatted data. To address the problems of these document, we proposed a method to expand classification scheme using decision boundary detected automatically in our previous studies. The assigning method that a document simply decides to the top ranked category, is a main factor that we focus on. In this paper, we propose a post-processing method and feedback algorithm to analyze the relevance of ranked list. In experiments, we applied our post-processing method and one time feedback algorithm to complex documents. The experimental results show that our system does not need to change the classification algorithm itself to improve the accuracy and flexibility.