• Journal of the Korean Chemical Society
• /
• v.56 no.1
• /
• pp.144-158
• /
• 2012

In this study, science teachers' and students' perceptions were searched on lectures and experiment of law of definite proportion in middle school science classes. For this study, the three teachers' lessons were observed and recorded, following interviews related to teachers' perceptions on the lessons and experiments. Also, We analyzed students' science scores, cognitive levels, science attitude, experimental reports, etc. According to the results, the three teachers had different focuses in the lectures. Chemistry teachers accentuated calculation of proportions and application rather than basic conceptions. But the students could not understand basic conceptions properly. The teachers spend long time to explain experimental procedures by assuming a low performance level of students in experimental classes. And the teachers had negative perceptions about error of results. The students could not understand the experiment results well, tried to manipulate data artificially, and had negative perceptions about error of results like the teachers. We suggested that these problems might be solved by changing teachers' perceptions on school science lectures and experiments.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.4
• /
• pp.1-7
• /
• 2012

This paper proposes a new indoor location recognition system using a ZigBee network and a global positioning system(GPS). The proposed location recognition system applies GPS values that are mainly used for outdoor location recognition, to indoor location recognition; hence the techniques conventionally separated for the indoor and outdoor location recognition are integrated into one location recognition technique. The proposed system recognizes a location using the distance between nodes. Although the distance between nodes can be calculated by measuring the strength of the received ZigBee signals, generally the measured distance is not accurate and has high error rates since the strength of the ZigBee signals is different depending on the distance. In order to reduce the error rate, we have subdivided the output power of the received ZigBee signals into five levels. When a moving node generates a signal, each fixed node transmits the received signal strength and its own GPS information to other nodes, so the moving node can find its own accurate location in terms of the received signals.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.655-660
• /
• 2005

This paper studied the feature parameters less affected by the emotional variation for the development of the robust speech recognition technologies. For this purpose, the effect of emotional variation on the speech recognition system and robust feature parameters of speech recognition system were studied using speech database containing various emotions. In this study, LPC cepstral coefficient, met-cepstral coefficient, root-cepstral coefficient, PLP coefficient, RASTA met-cepstral coefficient were used as a feature parameters. And CMS and SBR method were used as a signal bias removal techniques. Experimental results showed that the HMM based speaker independent word recognizer using RASTA met-cepstral coefficient :md its derivatives and CMS as a signal bias removal showed the best performance of $7.05\%$ word error rate. This corresponds to about a $52\%$ word error reduction as compare to the performance of baseline system using met - cepstral coefficient.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.109-116
• /
• 2019

This study proposed a robust detection algorithm. It detects face more stably with respect to changes in light and rotation for the identification of a face shape. Also it satisfies both efficiency of calculation and the function of detection. The algorithm proposed segmented the face area through pre-processing using a face shape as input information in an environment with a single camera and then identified the shape using a Self Organized Feature Map(SOFM). However, as it is not easy to exactly recognize a face area which is sensitive to light, it has a large degree of freedom, and there is a large error bound, to enhance the identification rate, rotation information on the face shape was made into a database and then a principal component analysis was conducted. Also, as there were fewer calculations due to the fewer dimensions, the time for real-time identification could be decreased.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.458-460
• /
• 1998

본 논문은 주성분 분석으로 시점 기반 고유얼굴(view-based eigenface)을 생성하고, 그에 기반한 얼굴 인식을 수행하고자 한다. 주성분 분석을 통한 고유얼굴 생성은 얼굴 인식의 어려운 문제 중 하나인 특징 선택과 추출이라는 문제를 해결해 준다. 또한 얼굴 표정이나 방향의 변화에도 인식률이 저하되는 것을 방지할 수 있다. 얼굴 영상을 특징공간(고유공간)으로 변환할 때, 원 얼굴영상의 정보를 최대한으로 나타낼 수 있는 최적의 고유치 개수 선택은 얼굴 데이터베이스의 크기와 인식 속도에 영향을 끼친다. 따라서 본 논문에서는 고유치 개수를 고유치의 누적기여율을 이용해서 구한다. 이는 64$\times$64(=4096)차원의 원 얼굴 영상을 5~7차원으로 표현 가능하게 하였다. 그리고, 각 얼굴 방향에 따라 특징공간을 분리해서 생성함으로써 얼굴 방향의 변화에 따라 오인식률을 줄였다. 축소된 차원과 분리된 특징공간은 메모리 사용과 인식속도의 향상에 기여한다. 본 논문에서 얼굴의 인식은 Mahalanobis distance와 재구성 오차율을 고려해서 이루어졌다. 실험은 개인당 세가지 다른 방향을 가지는 얼굴 영상을 이용하여 이루어졌고, 실험결과, 약 93%의 인식률을 보여주었다.

• Journal of Korea Entertainment Industry Association
• /
• v.5 no.2
• /
• pp.166-172
• /
• 2011

This paper presents a sensor system which recognizes the location of a magnet using cheap hall sensor. The proposed methods measure magnetic field from a magnet using model equation, analyze the property of horizontal and vertical magnetic field, and decide the method of sensor arrangement. And, this paper proposes the algorithm which infers the location of a magnet from the measured magnetic field that relates the position between the magnet and the hall sensor, and calculate theoretical error, which is found to be no more than 0.0025cm. The results actually measured show that the measured error no more than 0.07cm and confirm that proposed systems are highly applicable to the various situations.

• The korean journal of orthodontics
• /
• v.28 no.1 s.66
• /
• pp.75-83
• /
• 1998

This study was done to recognize the importance of errors in measurements of cephalometric radiograph and to find the anatomical structures those need special care to select as a reference points through the detection of the systematic errors and estimation of random errors. For this purose, 100 cephalometric radiographs were prepared by usual manner and 61 reference points, and 130 measurement variables were established. Measurement errors were detected and estimated by the comparison of the 25 randomly-selected samples for repeated measurements with the main sample. The following results were obtained : 1. In comparison of the repeated measurements, there were statistical significant differences in 24 variables which were 18.4% of 130 total variables. 2. The frequency of the difference in identification of the reference points between the repeated measurements was very high in the root apex of upper incisor(as), the most posterior wall of maxilla(tu), soft tissue nasion(n'), soft tissue frontal eminence(ft), and ad3 in airway. 3. After correction of reference points marking until the level of below 5% significance, the range of random errors were from 0.67 to 1.71 degree or mm. 4. The variable shown the largest random error was the interincisal angle(ILs-ILi). 5. Measurement errors were mainly caused by the lack of precision in anatomic definitions and obscure radiographic image. From the above results, the author could find the high possibility of errors in cephalometric measurements and from this point, we should include error analysis in all the studies concerning measurments. In is essential to have a concept of error analysis not only for the investigator but also for a reader of other articles.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2006.06a
• /
• pp.5-8
• /
• 2006

본 논문에서는 3차원 좌표를 얻을 수 있는 카메라 Calibration 알고리듬을 확립하고, View Frustum(V.F.) 모델을 이용하여 도로의 영상을 모델화하였다. 그리고 주행하는 차선 내에 존재하는 선행차량의 위치측정 및 차량까지의 거리를 정확히 인식하기 위해 피칭오차를 보정하며 실시간으로 계측하는 알고리듬을 제안하였다. 기존의 많은 추돌 경보시스템(CWS)들은 도로가 평면이라 가정하여 도로와 차량사이의 기하적인 변화에 따른 오차 특성을 고려하지 않았다. 이를 보완하고자 본 논문에서는 카메라 Calibration 알고리듬을 적용하여 실세계 좌표계와 영상좌표계 사이의 기하해석으로 사영행렬을 추출하였고, V.F. 모델을 이용하여 소실점의 기하적인 해석을 통하여 차량의 피칭변화에 따른 오차특성을 실시간으로 보정하였다. 실험결과 거리의 오차를 2%이하로 줄일 수 있어 피칭변화에 강인함을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.735-738
• /
• 2005

기존의 주성분 분석을 이용한 물체 인식 기술은 모델 영상내의 각각의 물체의 대표 값을 만든 후에 실험 영상을 물체 공간에 투영 시켜서 나온 성분과 대표 값의 거리를 비교하여 인식하게 된다. 그러나 단순히 기존의 방법인 point to point 방식인 단순 거리 계산은 오차가 많기 때문에 본 논문에서는 개선된 Class to Class방식인 k-Nearest Neighbor을 이용하여 몇 개의 연속적인 입력영상에 대해 각 각의 모델영상들을 인식의 단위로 이용하였다. 또한, 물체 인식을 하는데 있어 본 논문에서 제안한 주성분 분석법을 물체 영상 자체를 계산하여 인식하는 게 아니라 물체 영상 공간이라는 고유 공간을 구성한 후에 단지 기여도가 큰 8개의 벡터로만 인식을 수행하기 때문에 자원 축소의 효과까지 얻을 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.787-789
• /
• 2004

본 논문에서는 별도의 센서를 부착하지 않고 영상만을 이용하여 실시간으로 손 형상을 인식하는 알고리즘에 대해 기술한다. 손은 형상이 매우 복잡하기 때문에 2차원 형상의 불변량에 해당하는 에지의 방향성 히스토그램을 이용하여 인식을 행한다. 이 방법은 복잡한 배경에서 색상정보를 이용하여 손 영역이 정확히 추출되면 계산량이 적고 조명변화에 덜 민감하기 때문에 실시간 손 형상 인식에 적합하다. 본 논문에서는 손의 형상제시 방향이 변하는 경우에도 인식을 가능하게 하기 위해 주성분 분석법을 사용하여 인식오차를 줄이는 방법을 기술한다. 이 방법을 사용함으로써 손 형상이 3차원적으로 회전에 의해 변하는 경우도 인식가능하게 되었다. 실험부분에서 제안하는 방법을 이용하여 가정용 가전제품이나 게임을 제어하는 실시간 휴먼 인터페이스 시스템 제작기술로 활용될 수 있음을 보인다.