• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.313-323
• /
• 2021

The purpose of this study is to propose rules that can identify the speaker referred by the speaker directive in the text for the realization of a machine learning-based virtual character using a literary text. Through previous studies, we found that when applying literary texts to machine learning, the machine did not properly discriminate the speaker without any specific rules for the analysis of speaker directives such as other names, nicknames, pronouns, and so on. As a way to solve this problem, this study proposes 'nine rules for finding a speaker indicated by speaker directives (including pronouns)': location, distance, pronouns, preparatory subject/preparatory object, quotations, number of speakers, non-characters directives, word compound form, dispersion of speaker names. In order to utilize characters within a literary text as virtual ones, the learning text must be presented in a machine-comprehensible way. We expect that the rules suggested in this study will reduce trial and error that may occur when using literary texts for machine learning, and enable smooth learning to produce qualitatively excellent learning results.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.1-15
• /
• 2024

The construction of smart communities is a new method and important measure to ensure the security of residential areas. In order to solve the problem of low accuracy in face recognition caused by distorting facial features due to monitoring camera angles and other external factors, this paper proposes the following optimization strategies in designing a face recognition network: firstly, a global graph convolution module is designed to encode facial features as graph nodes, and a multi-scale feature enhancement residual module is designed to extract facial keypoint features in conjunction with the global graph convolution module. Secondly, after obtaining facial keypoints, they are constructed as a directed graph structure, and graph attention mechanisms are used to enhance the representation power of graph features. Finally, tensor computations are performed on the graph features of two faces, and the aggregated features are extracted and discriminated by a fully connected layer to determine whether the individuals' identities are the same. Through various experimental tests, the network designed in this paper achieves an AUC index of 85.65% for facial keypoint localization on the 300W public dataset and 88.92% on a self-built dataset. In terms of face recognition accuracy, the proposed network achieves an accuracy of 83.41% on the IBUG public dataset and 96.74% on a self-built dataset. Experimental results demonstrate that the network designed in this paper exhibits high detection and recognition accuracy for faces in surveillance videos.

• Radiation Oncology Journal
• /
• v.8 no.1
• /
• pp.85-93
• /
• 1990

A series of 25 patients with residual, recurrent, and unresectable gastric cancer received various combination of surgery, radiotherapy (RT), chemotherapy (CT), and hyperthermia (HT). They were placed into 7 categories; 1) CT and HT-14 patients; 2) RT and HT-15 patients; 3) surgery, RT and HT-2 patients; 4) surgery, RT, HT and CT-1 patient; 5) RT, HT and CT -1 patient; 6) RT and CT-1 patient; 7) RT alone-1 patient. Three patients had curative resection. 21 patients received irradiation with tightly contoured portals to spare as much small bowel, kidney and marrow as possible. Hyperthermia was applied regionally once or twice a week for 23 patients using 8 MHz radiofrequency capacitive heating device (Thermotron RF-8). HT was given approximately 30 min after RT 7 patients were treated with CT: 4 patients received HT and concomitant Mitomycin-C; 3 patients received HT and sequential 5-FU+Adriamycin+Mitomycin-C. There was not any treatment related deaths. There was also no evidence of treatment related problems with liver, kidney, stomach, or spinal cord except only one case of transient diabetic ketoacidosis. The tumor response was evaluable in 22 patients. None achieved complete remission.11 ($50\%$) achieved partial remission. The response rate was correlated with total radiation dose and achieved maximum temperature. 9 of 14 ($64\%$) received more than 4000 cGy showed partial remission; especially, all 3 patients received more than 5500 cGy achieved partial response.8 of the 12 patients ($67\%$) who achieved maximal temperature more than $41^{\circ}C$ showed partial response in comparing with $25\%$ (2 of 8 patients, below $41^{\circ}C$). The numbers of HT, however, was not correlated with the response. 3 of the 25 patients ($12\%$) remain alive. The one who was surgically unresectable and underwent irradiation alone is in progression of the disease with distant metastases. The remaining two patients with curative resection are alive with free of disease, 24 and 35 months, respectively. The median survival by response are 11.5 months in responders and 4.6 months in non-responders.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.11 no.2
• /
• pp.282-289
• /
• 2000

This study was designed to examine the validity of HPR subscale in Korean Personality Inventory for Children(KPI-C) and Attention Problems subscale in Korean Child Behavior Checklist(K-CBCL) as diagnostic tool for Attention-Deficit/Hyperactivity Disorder(ADHD). Nineteen ADHD-1 type, twenty-three ADHD-H type, sixteen Neurosis, and fifteen normal children with the age from 6 to12 were selected based on DSM-IV, and their responses of the KPI-C and CBCL were analyzed. Omnibus F-test results showed that there were significant differences in the F scores of HPR and Attention Problems T scores(p<.05). But in Posthoc analysis, the HPR and AP scores in three clinical groups were significantly higher than in normal group, but there was no group difference among three clinical groups(p<.05). These results shows that HPR subscale and Attention Problems subscale may be useful tools for screening clinical groups(vs normal group) but there was a limit to the clinical validity of two subscales as diagnostic tools for the subtypes of ADHD.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.19-29
• /
• 2006

As the security of personal information is becoming more important in mobile phones, we are starting to apply iris recognition technology to these devices. In conventional iris recognition, magnified iris images are required. For that, it has been necessary to use large magnified zoom & focus lens camera to capture images, but due to the requirement about low size and cost of mobile phones, the zoom & focus lens are difficult to be used. However, with rapid developments and multimedia convergence trends in mobile phones, more and more companies have built mega-pixel cameras into their mobile phones. These devices make it possible to capture a magnified iris image without zoom & focus lens. Although facial images are captured far away from the user using a mega-pixel camera, the captured iris region possesses sufficient pixel information for iris recognition. However, in this case, the eye region should be detected for accurate iris recognition in facial images. So, we propose a new fast iris detection method, which is appropriate for mobile phones based on corneal specular reflection. To detect specular reflection robustly, we propose the theoretical background of estimating the size and brightness of specular reflection based on eye, camera and illuminator models. In addition, we use the successive On/Off scheme of the illuminator to detect the optical/motion blurring and sunlight effect on input image. Experimental results show that total processing time(detecting iris region) is on average 65ms on a Samsung SCH-S2300 (with 150MHz ARM 9 CPU) mobile phone. The rate of correct iris detection is 99% (about indoor images) and 98.5% (about outdoor images).

• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.249-259
• /
• 2018

This research had intended to find out regarding the present influences of the Smart Work on the intention to use continuously with the staff members working in the small- and medium-sized enterprises as the subject. And, finally, it had intended to find out about the Smart Work environments of the IT corporations and the non-IT corporations. For this research, the questionnaire survey data were collected from the staff members working at the small- and medium-sized enterprises. Through the questionnaire survey data that were collected, an empirical analysis was carried out. And, through the reliability analysis, the feasibility analysis, the discriminatory feasibility analysis, and the inspection of the degree of suitableness of the structural equation model, finally, the research model was verified and, finally, a difference analysis of the IT corporations and the non-IT corporations was carried out. Regarding the results of the analysis of the research, it appeared that the factors of the job efficiency and the job autonomy of the special characteristics of the job had the positive influences on the usefulness and the job satisfaction, which were the parameters and which were perceived. And it appeared that the time flexibility of the job form could not have any influences on the usefulness and the job satisfaction, which were the parameters and which were perceived. And it appeared that the spatial flexibility had the influences on the job satisfaction only. The perceived usefulness, which was a parameter, had the positive influences on the job satisfaction and the intention to use continuously. And, finally, the job satisfaction had the positive influences on the intention to use continuously. And it appeared that there were the differences, too, between the IT corporations and the non-IT corporations. It is thought that, through the results of this research and through the Smart Work environment, the positive influences on the workers and the organizations could be induced and that a better working environment than previously can be provided to the workers to fit the special characteristics of the corporations.

• Journal of the Korean earth science society
• /
• v.30 no.4
• /
• pp.427-443
• /
• 2009

Cretaceous intrusive and extrusive rocks in the southwestern part of the Yeongnam Massif are possibly the result of intensive magmatism which occurred in response to subduction of the Pacific plate beneath the northeast portion of the Eurasian plate. Geochemical and petrological study on the granitic rocks were carried out in order to constrain the petrogenesis of the granitic magma and to establish the paleotectonic environment of the area. Whole rock chemical data of the granitic rocks from the study area indicate that all the rocks have characteristics of calc-alkaline series in the subalkaline field. The overall geochemical features show systematic variations in each granitic body, but the source materials of each granitic body are thought to have been different in their chemical composition. The granodiorites distributed around Donggyori in the Bognae area (DGd) are different from other granitic rocks within the study area in the contents and differentiation trends of $Al_2O_3$ and MgO as well as in the contents of the trace elements such as Ba, Sr, Pb, Ni, Cr and Y DGd have geochemical features similar to slab-derived adakites such as high $Al_2O_3$, Sr contents and high Sr/Y, La/Yb ratios, but low Y and Yb contents. The major and trace element contents of the DGd fall well within the adakitic field, whereas other Cretaceous granites in the study area are plotted in the island arc ADR area in Sr/Y vs. Y diagram. On the ANK vs. A/CNK and tectonic discrimination diagrams, parental magma type of the granites corresponds to I-type and volcanic arc granite (VAG). Interpretations of the chemical characteristics of the granitic rocks favor their emplacement in a compressional tectonic regime at continental margin during the subduction of Pacific plate. The geochemical and tectonic features reveal that adakite-like signatures of the DGd were generated by the interaction of mantle peridotite and subducted slab-derived adakitic melts (caused by the thermal effect of ridge subduction), and which slightly modified by crustal contamination during emplacement.