• East Asian mathematical journal
• /
• 제30권2호
• /
• pp.223-248
• /
• 2014

Although a figure expression has a role of mediator in the geometry proof, it is not admitted to prove based on a vision-dependent feature. This study starts from the problem that although a figure expression has an important role in the geometry proof, a lot of students don't understand the limit of vision-dependent feature in the figure expression. We will investigate this problem to understand cognitive characteristic of students. Moreover, we try to get the didactical implications. To do this, we investigate the cognitive ability for a limit of vision-dependent feature, targeting a class of middle school seniors And we will have a personal interview with four students who show a lack of sense of limit of vision-dependent feature in the figure expression and two students for who it is difficult to judge that they don't understand the limit of vision-dependent feature in the figure expression. We will observe and analyzed the cognitive characteristic of six students. Based on the analysis, we will finally discuss on the didactical implications to help students understand the limit of vision-dependent feature in the figure expression.

• 한국콘텐츠학회논문지
• /
• 제10권6호
• /
• pp.27-34
• /
• 2010

본 논문은 가중 퍼지소속함수 기반 신경망(neural network with weighted fuzzy membership functions, NEWFM)과 웨이블릿 기반의 특징 추출기법을 사용하여 왼쪽 또는 오른쪽의 운동 형상을 분류하는 방안을 제안하고 있다. 초기 특징을 추출하기 위해서 첫 번째 단계에서 웨이블릿 변환(wavelet transforms)을 이용하여 뇌파(electroencephalogram, EEG) 신호로부터 웨이블릿 계수들을 추출하였다. 두 번째 단계에서는 첫 번째 단계에서 추출한 웨이블릿 계수들을 통계적인 방법인 주파수 분포와 주파수 변동량을 이용하여 60개의 초기 특징을 추출하였다. 이들 60개의 초기 특징은 NEWFM에서 제공하는 비중복면적 분산 측정법에 의해 중요도가 가장 낮은 특징을 하나씩 제거되면서 정확도가 가장 높은 6개의 최소 특징을 선택되었다. 이들 6개의 최소 특징을 NEWFM의 입력으로 사용하여 86.43%의 정확도를 구하였다.

• Journal of Information Science Theory and Practice
• /
• 제9권4호
• /
• pp.15-34
• /
• 2021

Text clustering is one of the most commonly used methods for detecting themes or types of documents. Text clustering is used in many fields, but its effectiveness is still not sufficient to be used for the understanding of Arabic text, especially with respect to terms extraction, unsupervised feature selection, and clustering algorithms. In most cases, terms extraction focuses on nouns. Clustering simplifies the understanding of an Arabic text like the text of the Quran; it is important not only for Muslims but for all people who want to know more about Islam. This paper discusses the complexity and limitations of Arabic text clustering in the Quran based on their themes. Unsupervised feature selection does not consider the relationships between the selected features. One weakness of clustering algorithms is that the selection of the optimal initial centroid still depends on chances and manual settings. Consequently, this paper reviews literature about the three major stages of Arabic clustering: terms extraction, unsupervised feature selection, and clustering. Six experiments were conducted to demonstrate previously un-discussed problems related to the metrics used for feature selection and clustering. Suggestions to improve clustering of the Quran based on themes are presented and discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• 제어로봇시스템학회논문지
• /
• 제16권6호
• /
• pp.517-523
• /
• 2010

In this paper, we proposed an algorithm to detect aggressive driving status by analysing six kinds of driving patterns, which was achieved by comparing for the feature vectors using mahalanobis distance. The first step is to construct feature matrix of $6{\times}2$ size using frequency response of the time-series accelerometer data. Singular value decomposition makes it possible to find the dominant eigenvalue and its corresponding eigenvector. We use the eigenvector as the feature vector of the driving pattern. We conducted real experiments using three drivers to see the effects of recognition. Although there exists differences from individual drivers, we showed that driving patterns can be recognized with about 80% accuracy. Further research topics will include the development of aggressive driving warning system by improving the proposed technique and combining with post-processing of accelerometer signals.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.639-642
• /
• 1999

There exist geometrically invariant relations in single-view images under a specific geometrical structure. This invariance may be utilized for 3D object recognition. Two types of invariants are compared in terms of the robustness to the variation of the feature points. Deviation of the invariant relations are measured by adding random noise to the feature point location. Zhu’s invariant requires six points on adjacent planes having two sets of four coplanar points, whereas the Kaist method requires four coplanar points and two non-coplanar points. Experimental results show that the latter method has the advantage in choosing feature points while suffering from weak robustness to the noise.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권10호
• /
• pp.1751-1768
• /
• 2011

Falls are one of the most concerned accidents for elderly people and often result in serious physical and psychological consequences. Many researchers have studied fall detection techniques in various domain, however none released to a commercial product satisfying user requirements. We present a systematic modeling and evaluating procedure for best classification performance and then do experiments for comparing the performance of six procedures to get a statistical classifier based wrist-type fall detector to prevent dangerous consequences from falls. Even though the wrist may be the most difficult measurement location on the body to discern a fall event, the proposed feature deduction process and fall classification procedures shows positive results by using data sets of fall and general activity as two classes.

• 교육시설 논문지
• /
• 제21권1호
• /
• pp.33-42
• /
• 2014

The purpose of this study is to suggest a basis for exterior space improving in university campus in terms of upgrading the quality of university education environment by analysing user's cognition and physical feature about campus exterior space. For this, this study was survey six major university students in Busan city about perception of campus exterior space, and analyzes the user's cognition by using natural-language vocabulary analysis for qualitative approach. Next, this study analyzes the physical feature of campus exterior space by investigating user's intensive using spaces and preferred, non-preferred spaces in their universities, then propose the improved direction of campus exterior space by comparing the analyzed data of user's cognition and physical feature. A SPSS20 program is used for the data analysis and the sample sizes are 171 college students.

• 한국통신학회논문지
• /
• 제19권10호
• /
• pp.1991-2000
• /
• 1994

본 논문에서는 필기체 문자 인식 시스템을 위하여 6형식 분류 알고리즘을 제안하였다. 입력 영상은 세선화 과정을 거친 후 잡음을 제거하는 절단화 과정을 거친 후 $64\times64$ 크기로 정규화하여 이용하였다. 6형식 분류는 신경회로망의 모델 중 다층 퍼셉트론의 학습알고리즘을 이용하여 대분류와 상세분류 과정에서 이루어진다. 특징값 추출은 부분적인 특정값으로는 Subblock Hough transform을 이용하였으며 전체적인 특징값으로는 표본화 Hough transfrom을 이용하였다. 실험은 10사람이 한 형식당 30번씩 쓴 1800자를 대상으로 하였으며 받침의 유무로 대분류한 후 각기 종모음과 횡모음의 유무로 상세분류하여 90%의 분류 성공율을 얻었다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.1334-1337
• /
• 2007

A steel pallet to carry lighter logistic articles is developed based on the DFSS(design for Six Sigma) methodology. Combining the conventional DFSS(Design For Six Sigma) methodology with that of VE(Value Engineering) is the novel feature of this paper to achieve maximum cost reduction. In this paper, systematical steps to achieve the required structural spec's are presented by conventional DMEDI(Define-Measure-Explore-Develop-Implement) process. To imply the target costing, evaluation of functions consisting of the pallet has been performed by value methodology. Then best design concept is selected in the Explore step, following structural optimization utilizing FEM. Finally the performance of prototype is investigated by pilot test in the Implement step. The developed steel pallet is being commercialized in the fields of automated ware house.