• Journal of Advanced Navigation Technology
• /
• v.26 no.2
• /
• pp.113-118
• /
• 2022

Motivated by people highlighting important phrases while reading or taking notes we propose a neural network training method by highlighting defective pixel areas to classify effectively defect types of images with complex background textures. To verify our proposed method we apply it to the problem of classifying the defect types of tire band fabric images that are too difficult to classify. In addition we propose a backlight highlighting technique which is tailored to the tire band fabric images. Backlight highlighting images can be generated by using both the GradCAM and simple image processing. In our experiment we demonstrated that the proposed highlighting method outperforms the traditional method in the view points of both classification accuracy and training speed. It achieved up to 13.4% accuracy improvement compared to the conventional method. We also showed that the backlight highlighting technique tailored for highlighting tire band fabric images is superior to a contour highlighting technique in terms of accuracy.

• The Journal of the Korea Contents Association
• /
• v.18 no.6
• /
• pp.374-384
• /
• 2018

This study examined the effects of clarification training on conversational breakdowns and repair strategies of 3 school aged children with ASD. Clarification training provided to the participants during playing the barrier games. The results found that the occurrence of conversational breakdown was decreased in terms of overall and types. The occurrence and appropriateness rates of repair strategies were increased among all participants. Based on the results, 'clarification training' used in this study can be an effective method to train children with ASD for appropriate repair strategies in conversation.

• Journal of Korean Ophthalmic Optics Society
• /
• v.19 no.4
• /
• pp.539-550
• /
• 2014

Purpose: This research was designed to figure out if there are changes based on types of vergence fixation disparity curve after optical correction and vision training to for people with steep slope of forced vergence fixation disparity curve and symptoms. Methods: For 30 subjects out of 91 subjects, who have steep slopes of fixation disparity curve examined with Wesson Fixation Disparity Card and symptoms about steep slope of fixation disparity curve, proper vision training was offered for 5 weeks. Results: After Vision training for 30 people with the symptoms of type I, II, III, IV for 5 weeks, slope of fixation disparity curve was significantly changed (p=0.013), and the results of binocular vision test and subjective symptoms were also significantly improved. Conclusions: Vision training can not only affect the change of fixation disparity curve, but also relieve the symptoms. Fixation disparity curve has lots of visual function information of the subject and can be suggested as a guideline for prescribing.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.191-203
• /
• 2022

In this paper, we developed a system that intelligently identifies skin image data from big data collected from social media Instagram and extracts standardized skin sample data for skin condition diagnosis and management. The system proposed in this paper consists of big data collection and analysis stage, skin image analysis stage, training data preparation stage, artificial neural network training stage, and skin image identification stage. In the big data collection and analysis stage, big data is collected from Instagram and image information for skin condition diagnosis and management is stored as an analysis result. In the skin image analysis stage, the evaluation and analysis results of the skin image are obtained using a traditional image processing technique. In the training data preparation stage, the training data were prepared by extracting the skin sample data from the skin image analysis result. And in the artificial neural network training stage, an artificial neural network AnnSampleSkin that intelligently predicts the skin image type using this training data was built up, and the model was completed through training. In the skin image identification step, skin samples are extracted from images collected from social media, and the image type prediction results of the trained artificial neural network AnnSampleSkin are integrated to intelligently identify the final skin image type. The skin image identification method proposed in this paper shows explain high skin image identification accuracy of about 92% or more, and can provide standardized skin sample image big data. The extracted skin sample set is expected to be used as standardized skin image data that is very efficient and useful for diagnosing and managing skin conditions.

• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.399-406
• /
• 2018

Much research has been done using the KDDCup99 data set to study intrusion detection using artificial intelligence. Previous studies have shown that the performance of the SMO (SVM) algorithm is superior. However, intrusion detection studies of new intrusion types not used in training are insufficient. In this paper, a model was created using the instances of weka's SMO and KDDCup99 training data set, kddcup.data.gz. We tested existing instances(292,300) of the corrected.gz file and new intrusions(18,729). In general, intrusion labels not used in training are not tested, so new intrusion labels were changed to normal. Of the 18,729 new intrusions, 1,827 were classified as intrusions. 1,827 instances classified as new intrusions are buffer_overflow. Three, neptune. 392, portsweep. 164, ipsweep. 9, back. 511, imap. 1, satan. Dogs, 645, nmap. 102.

• Korean Security Journal
• /
• no.13
• /
• pp.471-485
• /
• 2007

This study is performed to find out what type instructions are produced to players by coaches and what effects are resulted in cooperative spirit of the concerned group. Furthermore the study has its aims at advancing instructors' skills by using finding of it. The study used 'SPSS 11.0 FOR WINDOW - Statistical Package' to analyze the collected samples and dealt with data of 174 individuals. Statistical analysis of the research for hypothesis verification was about frequency, trust level, mutual relationship, variables, and T-verification. The meaningful level for any result was ranged within 95%(p< .05), 99%(p<.01). The finding are as follows. Effects on pleasure, one of elements of team spirits taken by instructor's training style are analyzed as follows. It was proved to be meaningful in relation with a series of activities like training, democratic, social, compensatory aspects and showed also considerable relation with power based behaviors. That says, players are found to enjoy high pleasure when social and bureaucratic behaviors of instructors are very energetic. In addition to that, training, democratic, and compensatory activities didn't show any meaningful effect. Team spirit was found to play a main role between instructor's behaviors and training, democratic, social rewarding activities. Democratic and social acts influence on team spirit. Looking into the detailed aspects, team spirit was resulted very high in the individuals with low democratic mind and was shown high group spirit by groups with high sociable activities. Teamworks was found to be affected by relation between instructor's acts and training, democratic, social and compensatory aspects and it showed meaningful relations with training, social, bureaucratic behaviors. Low degree of training and bureaucratic activities are found to prefer for power team spirit, and high social activities led a strong teamworks. Group binding spirit was influenced by training, democratic, social compensatory, bureaucratic behaviors and it showed to give effects on democratic, social, and bureaucratic activities of instructors. Low degree of democratic and bureaucratic behaviors are found to produce strong team spirit. In contrast with that, strong social activities was found to be motive of powerful team spirit. Value of team spirit was found to play a main role between instructor's behaviors and training, democratic, social, rewarding activities. It didn't show any meaningful effect on behavior of instructors.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.569-572
• /
• 2002

한글을 인식하기 위한 전처리 방법으로 흔히 모음의 종류 및 자음과의 결합 정도에 따라 6가지 유형으로 분류하는 방법을 많이 사용하고 있다. 간 논문에서는 이러한 한글 문자를 인식하기 위한 전처리 과정으로써 한글의 유형을 분류하는 방법에 대한 연구로 계층적인 신경회로망을 도입하여 빠르고 신뢰성 있는 분류 방법을 제안한다. 실험에 사용된 글자는 KS X 1001(KS C 5601) 완성형 글자 2,350개에 대한 굴림, 바탕, 돋움, 궁서 글꼴로 총 9400개의 이미지 파일을 사용하였으며. 이 중 일부는 훈련에 사용하고 나머지는 분류를 위한 테스트 데이터로 사용한 결과 약 94%의 유형 분류율과 개별 패턴을 5.67ms에 분류하는 빠른 분류 속도를 나타내었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.345-352
• /
• 2021

The Republic of Korea Army (ROK Army) is trying to improve the effectiveness of education and training. On the other hand, there are many restrictions in actual training, limiting their practical education and training. Virtual reality technology is being used to overcome these limitations. Virtual reality technology is developing in various types, and the ROK Army needs to introduce a virtual reality training system for cost-effective education. The ROK Army mainly uses high-cost simulator-types that are similar to real equipment. Recently, a low-cost immersive-type virtual reality training system wearing an HMD is also being used. This study analyzed the cost education effectiveness of simulator-type and immersive-type virtual reality training systems in operation at the ROK Army air defense school. First, the research method used AHP to analyze the educational effects. Second, the cost was applied to the production cost of the virtual reality training system to analyze the cost-effectiveness of the education. The immersion-type was 3.4 times higher than the simulator-type in terms of cost effectiveness. These results can be used as basic data for analyzing the cost-effectiveness of a virtual reality training system.

• Therapeutic Science for Rehabilitation
• /
• v.9 no.1
• /
• pp.91-99
• /
• 2020

Objective : The purpose of this study was to investigate the effects of the IOPI articulator strength training program on articulator(tongue and lip) muscle strength, numbers of /l, s, ʨ/ articulation accuracy, articulatory numbers, articulation regularity and accuracy in the alternate motion rates, and sequential motion rate changes in patients with spastic dysarthria. Methods : Three cases of patients with spastic dysarthria living in Jeju, Korea, were included in this study. A single subject design was selected to study changes in articulator(tongue and lip) muscle strength, numbers of /ㄹ, ㅅ, ㅈ/ articulation accuracy, articulatory numbers, articulation regularity and accuracy in the alternate motion rates and sequential motion rates. Results : After the articulator strength training program was conducted on patients with spastic dysarthria, there were positive changes in articulator(tongue and lip) muscle strength, numbers of /ㄹ, ㅅ, ㅈ/ articulation accuracy, articulatory numbers, articulation regularity and accuracy on the alternate motion rates and sequential motion rates. Conclusion : Our findings suggest that IOPI articulator strength training program could be very useful for the most representative childeren with cerebral palsy if conducted in various subtypes of dysarthric patients and linked with articulatory function training with IOPI at home.

• Journal of the Society of Disaster Information
• /
• v.15 no.4
• /
• pp.617-625
• /
• 2019

Purpose: The fields manuals which is managed by the each disaster types are the integrated guideline. When the disaster occurred, all kinds of SOPs which are described in the manual does not need. Therefore, the person in charge is confused which SOP is executed. In this study, we propose the disaster response process model based on the specific disaster situation case. Method: Firstly, we define the disaster situation cases which is mentioned in the field manual, and then, we develop the disaster response process model including indispensible SOPs for the specific disaster situation case. As a verification and feedback process, we apply the model to Safety Korea Exercise scenario. Result: We developed SOP model and disaster response process model reflecting the concept of the disaster situation case. Conclusion: Safety Kore Exercise scenario reflecting the developed model may continuously upgrade the field manual.