• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2010년도 춘계학술대회 논문집
• /
• pp.445-446
• /
• 2010

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2006년도 춘계학술대회 논문집
• /
• pp.258-264
• /
• 2006

• ETRI Journal
• /
• 제36권5호
• /
• pp.696-703
• /
• 2014

In this paper, we present a walking guidance system for the visually impaired for use at subway stations. This system, which is based on environmental knowledge, automatically detects and recognizes both exit numbers and arrow signs from natural outdoor scenes. The visually impaired can, therefore, utilize the system to find their own way (for example, using exit numbers and the directions provided) through a subway station. The proposed walking guidance system consists mainly of three stages: (a) sign detection using the MCT-based AdaBoost technique, (b) sign recognition using support vector machines and hidden Markov models, and (c) three verification techniques to discriminate between signs and non-signs. The experimental results indicate that our sign recognition system has a high performance with a detection rate of 98%, a recognition rate of 99.5%, and a false-positive error rate of 0.152.

• 한국안전학회지
• /
• 제25권3호
• /
• pp.83-90
• /
• 2010

In this study, it is conducted that the performance verification of the ambient load carrying capacity algorithm using long-term measurement systems of bridges. For this purpose, a steel-box type model bridge is fabricated and the public load carrying capacity of a steel-box model bridge is estimated by conducting the numerical analysis and load test. In addition, we compare the public load carrying capacity with the estimated result of a steel-box model bridge using the ambient load carrying capacity algorithm. By the assessment result, it is shown that the estimated ambient load carrying capacity is the difference of approximately 6.0 percentages as compared with the public load carrying capacity.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.464-467
• /
• 1999

Usually, more reference signatures result in better performance in signature verification. However, registering .many signatures may be a tedious work for users, so algorithms that use less signatures for the registration without increasing error rate is needed. In this paper, we find the features such as pen-down duration, the number of locally minimum velocity points, and the number of locally maximum curvature points. Then we find the relationship between these features and the optimal decision boundary. We apply this relationship in deciding threshold for signature verification. Experimental results show that the method using three reference signatures has almost same error rate as algorithms with many references.

• 대한기계학회논문집
• /
• 제19권7호
• /
• pp.1555-1562
• /
• 1995

This study represents the non-dimensional cutting force model. With the non-dimensional cutting force model it is possible to estimate efficiently the maximum cutting force during one revolution of cutter. Using the non-dimensional cutting force model, the feed rate and spindle speed are adjusted so as to satisfy the maximum cutting force and maximum machining error. To verify the accuracy and efficiency of the non-dimensional cutting force model, a series of experiments were conducted, and experimental results proved and verified the non-dimensional cutting force model. The NC toolpath verification system developed in this paper uses the non-dimensional cutting force model, so that it is effective for calculating the cutting force and adjusting the cutting conditions.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권1호
• /
• pp.27-31
• /
• 2003

This paper proposes a robust on-line signature verification system based on a new segmentation method and fusion scheme. The proposed segmentation method resolves the problem of segment-to-segment comparison where the variation between reference signature and input signature causes the errors in the location and the number of segments. In addition, the fusion scheme is adopted, which discriminates genuineness by calculating each feature vector's fuzzy membership degree yielded from the proposed segmentation method. Experimental results show that the proposed signature verification system has lower False Reject Rate(FRR) for genuine signature and False Accept Rate(FAR) for forgery signature.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2007년도 동계학술발표대회 논문집
• /
• pp.453-458
• /
• 2007

The importance of the evaluation and verification of small-size cogeneration system has been emphasized because there is no KS-code related to the small-size cogeneration system. The evaluation method of small-size engine cogeneration system was investigated by the reference of Japan evaluation code, JIS B-8122 and international standard organization, ISO-8528. Evaluation method was introduced such as start-test, rapid-load-up and rapid-load-down, etc. The evaluation method was applied to the 300kW small-size gas engine cogeneration system newly developed. The precise and strict evaluation and verification of the system will help the developing cogeneration system to optimum condition. It will also be a base document of KS-Code.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.472-474
• /
• 2019

Because of the difference in network structure and loss function, Verification and identification models have their respective advantages and limitations for person reidentification (re-ID). In this work, we propose a multi-task network simultaneously computes the identification loss and verification loss for person reidentification. Given a pair of images as network input, the multi-task network simultaneously outputs the identities of the two images and whether the images belong to the same identity. In experiments, we analyze the major factors affect the accuracy of person reidentification. To address the occlusion problem and improve the generalization ability of reID models, we use the Random Erasing Augmentation (REA) method to preprocess the images. The method can be easily applied to different pre-trained networks, such as ResNet and VGG. The experimental results on the Market1501 datasets show significant and consistent improvements over the state-of-the-art methods.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.865-867
• /
• 2009

본 논문에서는 서명에서 생성되는 속도 성분(방향 정보, 거리 정보)에서 방향 정보만을 특징 정보로 하여 오류율에 영향을 주지 않으면서 처리속도를 개선하였으며, 특징 정보 크기도 크게 줄일 수 있었다. 이를 위해 실험결과를 토대로 하여 통계적 방법 T-test를 이용하여 분석하였다.