• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 춘계학술발표대회
• /
• pp.352-353
• /
• 2018

Many deep learning approaches are studied for face detection in these days. However, there is still a performance problem to run efficiently on devices with limited resources. Our method can enhance the detection speed by decreasing the number of scaling for detection methods that use many different scaling per image to detect the different size of faces. Also, we keep our deep learning model easy to implement and small as possible. Moreover, it can be used for other special object detection problems but not only for face detection.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제22권2호
• /
• pp.83-97
• /
• 2019

Science, Technology, Engineering, and Mathematics (STEM) education has been at the forefront of K-12 curricula in the technology-rich 21st century, with emphasis on how these fields reinforce each other in preparing students for a dynamic future. However, there is a need for greater attention to STEM education research in the mathematics education community, in particular to pedagogical approaches that facilitate integrating the mathematics component of STEM education. Toward this end, the authors report the outcomes of a Project-based Learning (PBL) unit in which upper elementary students integrated STEM elements by researching, crafting, testing, and evaluating kites they created by applying scientific knowledge of aerodynamics and mathematical knowledge of polygons, surface area, graphs, and data analysis. This unit, which the authors developed, implemented, and assessed, demonstrates how STEM subjects and in particular mathematics can be effectively integrated in upper elementary school classrooms through PBL.

• Steel and Composite Structures
• /
• 제45권6호
• /
• pp.877-894
• /
• 2022

Geopolymer concrete (GPC) has emerged as a feasible choice for construction materials as a result of the environmental issues associated with the production of cement. The findings of this study contribute to the development of machine learning methods for estimating the properties of eco-friendly concrete to help reduce CO₂ emissions in the construction industry. The compressive strength (f_c) of GPC is predicted using artificial intelligence approaches in the present study when ground granulated blast-furnace slag (GGBS) is substituted with natural zeolite (NZ), silica fume (SF), and varying NaOH concentrations. For this purpose, two machine learning methods multi-layer perceptron (MLP) and radial basis function (RBF) were considered and hybridized with arithmetic optimization algorithm (AOA), and grey wolf optimization algorithm (GWO). According to the results, all methods performed very well in predicting the f_c of GPC. The proposed AOA - MLP might be identified as the outperformed framework, although other methodologies (AOA - RBF, GWO - RBF, and GWO - MLP) were also reliable in the fc of GPC forecasting process.

• Journal of Information Processing Systems
• /
• 제20권1호
• /
• pp.13-23
• /
• 2024

Music brings pleasure and relaxation to people. Therefore, it is necessary to classify musical genres based on scenes. Identifying favorite musical genres from massive music data is a time-consuming and laborious task. Recent studies have suggested that machine learning algorithms are effective in distinguishing between various musical genres. However, meeting the actual requirements in terms of accuracy or timeliness is challenging. In this study, a hybrid machine learning model that combines a deep residual auto-encoder (DRAE) and support vector machine (SVM) for musical genre recognition was proposed. Eight manually extracted features from the Mel-frequency cepstral coefficients (MFCC) were employed in the preprocessing stage as the hybrid music data source. During the training stage, DRAE was employed to extract feature maps, which were then used as input for the SVM classifier. The experimental results indicated that this method achieved a 91.54% F1-score and 91.58% top-1 accuracy, outperforming existing approaches. This novel approach leverages deep architecture and conventional machine learning algorithms and provides a new horizon for musical genre classification tasks.

• 한국과학교육학회지
• /
• 제31권3호
• /
• pp.475-489
• /
• 2011

The purposes of this study were to inform the exemplary models of integrated science and mathematics and to analyze and discuss their similarities and differences of the models. There were two steps to select the exemplary models of integrated science and mathematics. First, the second volume (Berlin & Lee, 2003) of the bibliography of integrated science and mathematics was analyzed to identify the models. As a second step, we selected the models that are dealt with in the School Science Mathematics journal and were cited more than three times. The findings showed that the following four exemplary theoretical models were identified and published in the SSM journal: the Berlin-White Integrated Science and Mathematics (BWISM) Model, the Mathematics/Science Continuum Model, the Continuum Model of Integration, and the Five Types of Science and Mathematics Integration. The Berlin-White Integrated Science and Mathematics (BWISM) Model focused an interpretive or framework theory for integrated science and mathematics teaching and learning. BWISM focused on a conceptual base and a common language for integrated science and mathematics teaching and learning. The Mathematics/Science Continuum Model provided five categories and ways to clarify the extent of overlap or coordination between science and mathematics during instructional practice. The Continuum Model of Integration included five categories and clarified the nature of the relationship between the mathematics and science being taught and the curricular goals for the disciplines. These five types of science and mathematics integrations described the method, type, and instructional implications of five different approaches to integration. The five categories focused on clarifying various forms of integrated science and mathematics education. Several differences and similarities among the models were identified on the basis of the analysis of the content and characteristics of the models. Theoretically, there is strong support for the integration of science and mathematics education as a way to enhance science and mathematics learning experiences. It is expected that these instructional models for integration of science and mathematics could be used to develop and evaluate integration programs and to disseminate integration approaches to curriculum and instruction.

• 비교교육연구
• /
• 제19권1호
• /
• pp.25-58
• /
• 2009

대학의 기능 수행에 대한 사회적인 관심이 증대되어 대학의 질 제고와 대학의 질 평가가 중요한 과제로 인식되고 있다. 이에 이 연구는 대학의 질 개념을 정립하고, 정립된 질 개념에 터하여 대학의 질적 수준을 종합적으로 진단할 수 있는 지표를 개발하는 데 연구의 주된 목적을 두었다. 종합적인 문헌분석과 연구진 검토를 통해 목표/목적 달성, 고객요구충족, 가치부가 측면을 강조한 투입-과정-산출 체제로서의 대학의 질 개념을 설정하였다. 설정된 대학의 질 개념을 바탕으로 하여 미국, 영국, 호주, 일본 등 주요국에서 사용되고 있는 대학기관인증평가, 대학순위평가, 학생설문조사, 학습성과평가 등 4가지 유형의 질적 수준 분석 도구에 포함된 지표들(6개국 13개 평가도구)을 분석한 뒤 대학의 질적 수준 평가 지표 초안을 마련하였고, 전문가 검증과 연구진 검토를 통해 최종 지표들을 개발하였다. 이러한 지표들은 투입-과정-산출 차원에서 기관목표, 인적자원, 물적자원, 교육과정, 학습활동, 교육산출, 연구산출의 영역으로 구성되었다. 개발된 지표가 대학의 질 제고를 유도하는 순기능 역할을 발휘하는 데 필요한 사항들이 제안되었다.

• 한국융합학회논문지
• /
• 제10권2호
• /
• pp.13-20
• /
• 2019

맞춤형 교육을 위해 학습자에 맞는 학습 경로를 탐색하는 것은 필수적이다. 유전 알고리즘은 해공간이 매우 커서 결정적 방법으로 해를 구하기 어려울 때 타당한 시간 내에 최적해를 찾게 해준다. 본 연구는 유전 알고리즘을 이용하여 200개 코드를 가진 악보 27개를 대상으로 학습자 부담을 최소화하고 단계별 학습량을 균등하게 분산함으로써 학습 효과를 최대화 할 수 있도록 학습 경로를 최적화하였다. 학습 컨텐츠가 27개만 되어도 학습 경로의 순열 크기는 $10^{28}$을 넘지만, 본 연구에서 구현한 도구로 평균 20분 이내에 최적해를 구할 수 있었다. 실험 결과는 유전 알고리즘이 다양한 목적의 맞춤형 교육을 위한 복잡한 학습 경로 설계에 효과적임을 보여주었다. 제안한 방법은 다른 교육 도메인에도 활용할 수 있을 것으로 기대된다.

• 한국환경보건학회지
• /
• 제50권2호
• /
• pp.113-124
• /
• 2024

Background: The increasing need to minimize animal testing has sparked interest in alternative methods with more humane, cost-effective, and time-saving attributes. In particular, in silico-based computational toxicology is gaining prominence. Adverse outcome pathway (AOP) is a biological map depicting toxicological mechanisms, composed of molecular initiating events (MIEs), key events (KEs), and adverse outcomes (AOs). To understand toxicological mechanisms, predictive models are essential for AOP components in computational toxicology, including molecular structures. Objectives: This study reviewed the literature and investigated previous research cases related to AOP and in silico methodologies. We describe the results obtained from the analysis, including predictive techniques and approaches that can be used for future in silico-based alternative methods to animal testing using AOP. Methods: We analyzed in silico methods and databases used in the literature to identify trends in research on in silico prediction models. Results: We reviewed 26 studies related to AOP and in silico methodologies. The ToxCast/Tox21 database was commonly used for toxicity studies, and MIE was the most frequently used predictive factor among the AOP components. Machine learning was most widely used among prediction techniques, and various in silico methods, such as deep learning, molecular docking, and molecular dynamics, were also utilized. Conclusions: We analyzed the current research trends regarding in silico-based alternative methods for animal testing using AOPs. Developing predictive techniques that reflect toxicological mechanisms will be essential to replace animal testing with in silico methods. In the future, since the applicability of various predictive techniques is increasing, it will be necessary to continue monitoring the trend of predictive techniques and in silico-based approaches.

• 정보처리학회논문지B
• /
• 제13B권2호
• /
• pp.171-178
• /
• 2006

기계가독형사전(Machine Readable Dictionary)에서 단어의 정의문에 나타나는 항목 단어의 상위개념을 추출하는 대부분의 연구들은 전문가에 의해 작성된 어휘패턴을 사용하였다. 이 방법은 사람이 직접 패턴을 수집하므로 시간과 비용이 많이 소모될 뿐만 아니라, 자연언어에는 같은 의미를 가진 다앙한 표현들이 존재하므로 넓은 커버리지를 갖는 어휘패턴들을 수집하는 것이 매우 어렵다는 단점이 있다. 이런 문제점들을 해결하기 위하여, 본 논문에서는 구문적 특징만을 이용한 상위어 판별 규칙을 기계학습함으로써 기존에 사용되었던 어휘패턴의 지나친 어휘 의존성으로 인한 낮은 커버리지 및 패턴 수집의 문제를 해결하는 방법을 제안한다. 제안한 방법으로 기계학습된 규칙들을 상위어 자동추출과정에적용한 결과 정확도 92.37% 성능을 보였다. 이는 기존 연구들보다 향상된 성능으로 기계학습에 의해 수집된 판별규칙이 상위어 판별에 있어서 어휘패턴의 문제를 해결할 수 있다는 것을 입증하였다.

• 대한물리치료과학회지
• /
• 제9권3호
• /
• pp.179-186
• /
• 2002

This study addresses the need to adopt teaching-learning approaches in physical therapy education that develop links between theory and clinical practice in a meaningful way. Problem-based learning (PBL) is presented as a useful way to educate physical therapy for the future. The essential characteristics of problem-based learning include: curricular organization around problems rather than disciplines; an integrated curriculum rather than one separated into clinical and theoretical components; and an inherent emphasis on cognitive skills as well as on knowledge. PBL as implemented in the health sciences, is an educational method in which the focus of learning is a small-group tutorial in which students work through health care scenarios. The goals of the health care scenarios are to provide a context for learning, to activate prior knowledge, to motivate students, and to stimulate discussion. Learning is student-centered rather than faculty-centered, and self-directed learning is emphasized. Whereas the former focuses on critical thinking and clinical judgement, the latter's emphasis is on clinical competency. The physical therapist (PT) program at Cheju Halla college is a partial integrated problem-based curriculum. The history and process of PBL in general and in the PT program are reviewed. Long-term advocates of PBL stress that it is the only known method for preparing future professionals to be able to adapt to change, learning how to reason critically, enabling a holistic approach to health.