• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.140-144
• /
• 2021

The article considers aspects of improving the quality of training of specialists based on the use of modern information and communication technologies in the educational process; the use of teaching methods and, as a result, an increase in the creative and intellectual components of educational activities; integration of various types of educational activities (educational, research, etc.); adaptation of information technology training to individual the characteristics of the student; ensuring continuity and consistency in learning; development of information technologies for distance learning; improving the software and methodological support of educational process.

• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.82-89
• /
• 2023

Various machine-learning models may yield high predictive power for massive time series for time series prediction. However, these models are prone to instability in terms of computational cost because of the high dimensionality of the feature space and nonoptimized hyperparameter settings. Considering the potential risk that model training with a high-dimensional feature set can be time-consuming, we evaluate a feature-importance-based feature selection method to derive a tradeoff between predictive power and computational cost for time series prediction. We used two machine learning techniques for performance evaluation to generate prediction models from a retail sales dataset. First, we ranked the features using impurity- and Local Interpretable Model-agnostic Explanations (LIME) -based feature importance measures in the prediction models. Then, the recursive feature elimination method was applied to eliminate unimportant features sequentially. Consequently, we obtained a subset of features that could lead to reduced model training time while preserving acceptable model performance.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.595-598
• /
• 2020

IoU (Intersection over Union) is the most commonly used index in target detection. The core requirement of target detection is what is in the image and where. Based on these two problems, classification training and positional regression training are needed. However, in the process of position regression, the most commonly used method is to obtain the IoU of the predicted bounding box and ground-truth bounding box. Calculating bounding box regression losses should take into account three important geometric measures, namely the overlap area, the distance, and the aspect ratio. Although GIoU (Generalized Intersection over Union) improves the calculation function of image overlap degree, it still can't represent the distance and aspect ratio of the graph well. As a result of technological progress, Bounding-Box is no longer represented by coordinates x,y,w and h of four positions. Therefore, the IoU can be further optimized with the center point and aspect ratio of Bounding-Box.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2012년도 춘계학술대회
• /
• pp.110-112
• /
• 2012

Education and training of technical staff for the new generation technological equipment has a vital importance for developing countries in order to maintain sustainable development and keep up with new generation technologies. Mechatronics the synergistic combination of mechanical, electronic and software engineering from an engineering perspective to serve the purposes of controlling advanced hybrid systems is a product of new generation technology which can be given as a sample to this phenomenon. Recent marine engines are combination of heavy industry with high technology. Nowadays, ships are built in full automation and equipped with computer controlled mechatronics systems. However, finding qualified officer and engineers who can operate, maintain, control and repair when it is required such full automatic systems with knowledge of a new generation system became a serious issue. Due to importance of this fact STCW Manila amendment has new training and certification requirements for electro-technical officers. In this paper, Mechatronics applications on ship are introduced, importance of it highlighted and a new syllabus is proposed for the training of marine engineers to be nurtured with mechatronics knowledge as it is required.

• ETRI Journal
• /
• 제21권4호
• /
• pp.41-51
• /
• 1999

This research is an attempt to obtain more accurate land cover information from LANDSAT images. Canonical correlation analysis, which has not been widely used in the image classification community, was applied to the classification of a LANDSAT images. It was found that it is easy to select training areas on the classification using canonical correlation analysis in comparison with the maximum likelihood classifier of $ERDAS^{(R)}$ software. In other words, the selected positions of training areas hardly affect the classification results using canonical correlation analysis. when the same training areas are used, the mapping accuracy of the canonical correlation classification results compared with the ground truth data is not lower than that of the maximum likelihood classifier. The kappa analysis for the canonical correlation classifier and the maximum likelihood classifier showed that the two methods are alike in classification accuracy. However, the canonical correlation classifier has better points than the maximum likelihood classifier in classification characteristics. Therefore, the classification using canonical correlation analysis applied in this research is effective for the extraction of land cover information from LANDSAT images and will be able to be put to practical use.

• ETRI Journal
• /
• 제33권3호
• /
• pp.423-433
• /
• 2011

This paper introduces an adaptive and integrated utterance verification (UV) framework using minimum verification error (MVE) training as a new set of solutions suitable for real applications. UV is traditionally considered an add-on procedure to automatic speech recognition (ASR) and thus treated separately from the ASR system model design. This traditional two-stage approach often fails to cope with a wide range of variations, such as a new speaker or a new environment which is not matched with the original speaker population or the original acoustic environment that the ASR system is trained on. In this paper, we propose an integrated solution to enhance the overall UV system performance in such real applications. The integration is accomplished by adapting and merging the target model for UV with the acoustic model for ASR based on the common MVE principle at each iteration in the recognition stage. The proposed iterative procedure for UV model adaptation also involves revision of the data segmentation and the decoded hypotheses. Under this new framework, remarkable enhancement in not only recognition performance, but also verification performance has been obtained.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권9호
• /
• pp.912-919
• /
• 2005

문서 범주화에서 이진 분류를 다중 분류에 적용할 때 일반적으로 '한 범주에 적합-다른 모든 범주에서는 부적합(One-Against-All) 판정 방법'을 사용한다. 하지만, 이러한 '한 범주에 적합-다른 모든 범주에서는 부적합 판정 방법'은 한 가지 문제점을 가지는데, 적합(positive) 집합의 문서들은 사람이 직접범주를 할당한 것이지만 부적합(negative) 집합의 문서들은 사람이 직접 범주를 할당한 것이 아니기 때문에 오류 문서들이 많이 포함될 수 있다는 것이다. 본 논문에서는 이러한 문제점을 해결하기 위해서 슬라이딩 원도우(sliding window) 기법과 EM 알고리즘을 이진 분류 기반의 문서 범주화에 적용할 것을 제안한다. 제안된 기법은 먼저 슬라이딩 윈도우 기법을 사용하여 오류 문서들을 추출하고 이들을 EM알고리즘을 사용해서 다시 범주를 할당함으로써 이진 분류 기반의 문서 범주화 기법의 성능을 향상시킨다.

• 한국응급구조학회지
• /
• 제23권2호
• /
• pp.19-31
• /
• 2019

Purpose: This study aimed to investigate disaster preparedness competence and disaster response competence of paramedics working in emergency medical centers operating a disaster medical assistance teams. Methods: Data of 174 emergency medical technician(EMT)-paramedics were collected from July 15 to August 14, 2018 at regional and local emergency medical centers that operate disaster medical assistant team. Analysis of the data was carried out with IBM SPSS statistics 24.0 software (IBM, Armonk, NY, USA). Results: The mean disaster preparedness competence score was $3.57{\pm}0.63$ (out of five). Participants' disaster preparedness competence significantly differed according to type of emergency medical center (p<.000), disaster education experience (p<.000), and education frequency (p=.001). The mean disaster response competence score was $4.09{\pm}0.57$ (out of five). Participants' disaster response competence significantly differed according to disaster education experience (p<.000) and medical assistance experience (p=.045). Conclusion: Emergency medical technician-paramedics without disaster training should first be provided with this training. Further, it is important for EMT-paramedics to know their disaster preparedness and response capacities and strengthen their shortcomings. It is also important to develop education and training programs that properly equip EMT-paramedics with practical competencies.

• 한국정보기술학회논문지
• /
• 제17권12호
• /
• pp.29-38
• /
• 2019

라이프로그를 이용한 경로 예측 기법은 정확한 경로 예측을 위하여 많은 양의 학습 데이터를 요구하며, 학습 데이터가 부족할 경우 경로 예측 성능이 저하된다. 학습 데이터 부족은 사용자의 이동 패턴이 유사한 다른 사용자의 데이터를 이용하여 해결이 가능하다. 따라서 이 논문은 사용자 유사도 기반 경로 예측 알고리즘을 제안한다. 이를 위하여 제안 알고리즘은 경로를 3단 그리드 패턴으로 학습하고 코사인 유사도 기법을 이용하여 사용자 간 유사도를 측정한다. 이후, 측정된 유사도를 학습된 모델에 적용하여 경로를 예측한다. 평가를 위하여 기존 경로 예측 기법들과 제안 기법의 경로 예측 정확도를 측정 및 비교한다. 그 결과, 제안 기법의 정확도는 66.6%로 다른 기법들에 비해 평균 1.8% 더 높은 정확도를 가진 것으로 평가된다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권3호
• /
• pp.205-213
• /
• 2010

본 논문에서는 단어간 관계 패턴을 학습한 후 이에 기반하여 자연 언어 문장을 생성하는 방법을 소개한다. 기존의 문장 생성 방법론에서는 내재된 문법 규칙의 존재를 가정하거나 템플릿을 사용하고 있으나, 본 논문에서 소개하는 방법론에서는 태깅 등의 부가 정보 없이 단어의 동시 등장 빈도만을 활용하여 단어간 관계 패턴을 학습한다. 단어간 관계 패턴은 하이퍼네트워크 방법론에 기반하여 학습되었다. 학습이 진행됨에 따라 하이퍼네트워크의 복잡도가 높아지며, 학습 모델에 축적되는 언어 관계 패턴의 수가 증가한다. 학습된 모텔의 유효성은 학습 패턴에 기반한 자연 언어 문장 생성을 통해 확인하였다. 실험 결과 학습이 진행됨에 따라 문법적으로 성립하는 문장의 비율이 향상하였다. 파서를 이용하여 생성된 문장을 구성하는 문법 규칙을 분석한 후 문법 규칙의 분포를 학습에 사용한 코퍼스의 문법 규칙 분포와 비교한 결과 학습에 사용된 코퍼스의 문법적 특성을 학습할 수 있는 잠재력을 갖고 있음을 확인하였다.