• Journal of the Korean GEO-environmental Society
• /
• v.23 no.8
• /
• pp.5-10
• /
• 2022

Ground Subsidence has been continuously occurring in densely populated downtown. The main cause of ground subsidence is the damaged underground facility like sewer. Currently, ground subsidence is being dealt with by discovering cavities in ground using GPR. However, this consumes large amount of manpower and cost, so it is necessary to predict hazardous area for efficient operation of GPR. In this study, ◯◯city is divided into 500 m×500 m grids. Then, data set was constructed using the characteristics of the underground facility and ground subsidence in grids. Data set used to machine learning model for ground subsidence risk grade prediction. The purposed model would be used to present a ground subsidence risk map of target area.

• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.364-373
• /
• 2022

Purpose: The purpose of this paper is to develope smoke detection using AI model for detecting the initial fire in underground utility tunnels using CCTV Method: To improve detection performance of smoke which is high irregular, a deep learning model for fire detection was trained to optimize smoke detection. Also, several approaches such as dataset cleansing and gradient exploding release were applied to enhance model, and compared with results of those. Result: Results show the proposed approaches can improve the model performance, and the final model has good prediction capability according to several indexes such as mAP. However, the final model has low false negative but high false positive capacities. Conclusion: The present model can apply to smoke detection in underground utility tunnel, fixing the defect by linking between the model and the utility tunnel control system.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.621-635
• /
• 2023

The assessment of structural condition is a crucial process for evaluating its usability and determining the diagnostic cycle. The currently employed manpower-based methods suffer from issues related to safety, efficiency, and objectivity. To address these concerns, research based on deep learning using images is being conducted. However, acquiring structural damage data is challenging, making it difficult to construct a substantial amount of training data, thus limiting the effectiveness of deep learning-based condition assessment. In this study, we propose a foundation model-based 2-step structural damage analysis to overcome the lack of training data in image-based structural condition assessments. We subdivided the elements of structural condition assessment into instantiation and quantification. In the quantification step, we applied a foundation model for image segmentation. Our method demonstrated a 10%-point increase in mean intersection over union compared to conventional image segmentation techniques, with a notable 40%-point improvement in the case of rebar exposure. We anticipate that our proposed approach will enhance performance in domains where acquiring training data is challenging.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.174-180
• /
• 2024

In this paper, we explore an emotion classification method through multimodal learning utilizing wav2vec 2.0 and KcELECTRA models. It is known that multimodal learning, which leverages both speech and text data, can significantly enhance emotion classification performance compared to methods that solely rely on speech data. Our study conducts a comparative analysis of BERT and its derivative models, known for their superior performance in the field of natural language processing, to select the optimal model for effective feature extraction from text data for use as the text processing model. The results confirm that the KcELECTRA model exhibits outstanding performance in emotion classification tasks. Furthermore, experiments using datasets made available by AI-Hub demonstrate that the inclusion of text data enables achieving superior performance with less data than when using speech data alone. The experiments show that the use of the KcELECTRA model achieved the highest accuracy of 96.57%. This indicates that multimodal learning can offer meaningful performance improvements in complex natural language processing tasks such as emotion classification.

• Journal of The Korean Association For Science Education
• /
• v.26 no.1
• /
• pp.16-24
• /
• 2006

The purpose of this study was to compare student-student verbal interaction from two type's experiments; problem-solving and task-solving. For this study, five 3rd grade middle school students were selected and their verbal interactions recorded via voice and video; and later transcribed. The student-student verbal interactions were classified as questions, explanations, thoughts, or metacognition fields, which were separated into deep versus surface learning approaches. For the problem-solving experiment, findings revealed that the number of verbal interactions is more than doubled and in particular, the number of verbal interactions using deep-approach is more than quadrupled from the point of problem-recognition to problem-solution. As for the task-solving experiment, findings showed that verbal interactions remained evenly distributed throughout the entire experiment. Finally, it was also discovered that students relied upon a more deep learning approach during the problem-solving experiment than the task-solving experiment.

• Journal of Preventive Medicine and Public Health
• /
• v.26 no.4 s.44
• /
• pp.628-649
• /
• 1993

This study was conducted to investigate the factors related to the poor school performance of the elementary school children. Two schools in Taegu, one in the affluent area and the other in the poor area, were selected and a total of 175 children whose school performance was within low 10 percentile (poor performers) and 97 children whose school performance were within high 5 percentile (good performers) in each class of 2nd, 4th and 6th grades were tested for the physical health, behavioral problem and family background. Each child had gone through a battery of tests including visual and hearing acuity, anthropometry (body weight, height, head circumference), intelligence (Kodae Stanford-Binet test), test anxiety (TAI-K), neurologic examination by a developmental pediatrician and heavy metal content (Pb, Cd, Zn) in hair by atomic absorption spectrophotometry. A questionnaire was administered to the mothers for prenatal and prenatal courses of the child, family environment, child's developmental history, and child's behavioral and learning problems. Another questionnaire was administered to the teachers of the children for the child's family background, arithmatic & language abilities and behavioral problem. The poor school performance had a significant correlation with male gender, high birth order, broken home, low educational and occupational levels of parents, visual problem, high test anxiety score, attention deficit hyperactivity disorder (ADHD), poor physical growth (weight, height, head circumference) and low I.Q. score. The factors that had a significant correlation with the poor school performance in multiple logistic regression analysis were child's birth order (odds ratio=2.06), male gender(odds ratio=5.91), broken home(odds ratio=9.29), test anxiety score(odds ratio=1.07), ADHD (odds ratio=9.67), I.Q. score (odds ratio=0.85) and height less than Korean standard mean-1S.D.(odds ratio=11.12). The heavy metal contents in hair did not show any significant correlation with poor school performance. However the lead and cadmium contents were high in males than in females. The lead content was negatively correlated with child's grade(P<0.05) and zinc was positively correlated with grade (P<0.05). among the factors that showed a significant correlation with the poor school performance, high birth order, short stature and ADHD may be modified by a good family planning, good feeding practice for infant and child, and early detection and treatment of ADHD. Also, teacher and parents should restrain themselves from inducing excessive test anxiety by forcing the child to study and over-expecting beyond the child's intellectual capability.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.12 no.1
• /
• pp.125-137
• /
• 2001

We investigated the self-concept, subjective depression, and state-trait anxiety of the school boys with learning disabilities(abbr. LD, n=86) and compared them with normal boys(n=52) using Piers-Harris Self-Concept Inventory, Child Depression Inventory(abbr. CDI), and State-Trait Anxiety Inventory(abbr. STAI). With regard to Piers-Harris Self-Concept Inventory total scores, there was no significant difference between two groups, but normal boys showed higher scores in intellectual and school status, physical appearance, and happiness-satisfaction subscales than patients with LD. The male patients with LD showed significantly higher ratings in CDI total scores, and CDI subscales - ineffectiveness, anhedonia, negative self-esteem than normal children. The patients with LD reported significantly higher state anxiety, but not trait anxiety. Correlation analyses revealed that self-concept decreased over time, and depression-anxiety increased across grades in the patients with LD, but not in normal children. Especially, negative mood, anhedonia, negative self-esteem subscales of CDI, and state-trait anxiety showed significant positive correlation with grades. In both groups, CDI scores were inversely correlated with Piers-Harris Self-Concept and positively with State-Trait anxiety. In conclusion, self-concept problems which were related with school achievement and self-esteem were more abundant in the patients with LD than normal children, self-image problem, depression and anxiety increased across grades. According to regression analysis, age, behavior subscale, intellectual-school status, anxiety, popularity, happiness-satisfaction, CDI-ineffectiveness, interpersonal problem, negative self-esteem, and state anxiety could explain the self-concept in the patients with LD, not in normal children. So, the self-concept of the patients with LD were found to be related to the school achievement and stress when comparing with peers. In conclusion, elementary school boys with LD showed lower self-concept, higher depression and anxiety, and these differences increased across grades. Since the patients with LD have concomitant depression and anxiety disorders, it is important that comorbidity with emotional problems should be explored and managed properly.

• Journal of Engineering Education Research
• /
• v.2 no.1
• /
• pp.24-28
• /
• 1999

The information technology is becoming very essential in our daily lives. Internet environment, especially, has been seriously affecting the area of education. The cost-effectiveness analysis is required as universities are investing quite much in the development of internet infrastructure. This study shows a simple statistical result on the utilization of internet equipments. It is found that the enough availability is not provided to the students who are going to use equipments for the purpose of study as a big portion of them are occupied by the users for the purpose of amusement.

• School Mathematics
• /
• v.19 no.1
• /
• pp.1-18
• /
• 2017

In this study we analyse the features of process of problem posing and explore the development of mathematical knowledge of primary preservice teachers as result of their engagement in problem posing activity. Data was collected through the preservice teachers' class discussions. Analysis of the data shows that preservice teachers developed their ability to understand connections among mathematical concepts.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04a
• /
• pp.847-849
• /
• 2002

인공면역시스템에서 중요한 특징중의 하나는 지속적으로 변화하는 환경에서 자기(self)의 유동적인 패턴을 동적으로 학습하고 비자기(non-self)에 대한 새로운 패턴을 예측하는데 있다. 본 논문은 자기적 용(self-adaptation)의 인공면역체계 특성을 기반으로하여 설계된 dynamics(동적 클론선택 알고리즘, dynamic clonal selection algorithm)의 역할을 논한다. 시스템의 세가지 중요한 변수인 자기내성 기간(Tolerisation Period). 연역 반응 임계값(activation threshold). 수명(life span)에 따라 변화하는 dynamics의 성능을 네트워크 침입에서 흔히 발견되는 시나리오를 모의실험하여 평가한다