• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 학술대회지
• /
• pp.671-674
• /
• 2004

We propose accurate classification method of EEG signals during mental tasks. In the experimental task, the tasks of subjects show 3 major measurements; there are mathematical tasks, color decision tasks, and Chinese phrase tasks. The classifier implemented for this work is a feed-forward neural network that trained with the error back-propagation algorithm. The new BCI system is proposed by using neural network. In this system, tr e architecture of the neural network is composed of three layers with a feed-forward network, which implements the error back propagation-learning algorithm. By applying this algorithm to 4 subjects, we achieved $95{\%}$ classification rates. The results for BCI mathematical task experiments show performance better than those of the Chinese phrase tasks. The selection time of each task depends on the mental task of subjects. We expect that the proposed detection method can be a basic technology for brain-computer interface by combining with left/right hand movement or yes/no discrimination methods.

• 품질경영학회지
• /
• 제42권4호
• /
• pp.607-616
• /
• 2014

Purpose: This paper reviews popular measurement system indices and proposes a procedure for assessing a measurement system using two parameters with intraclass correlation and a factor for process capability. Methods: Gage Repeatability and Reproducibility(GR&R), precision-to-tolerance ratio(PTR), number of distinct categories, producer's and consumer's risks are employed to assess the measurement capabilities and discuss the relationships between measurement system metrics. Results: Two-dimensional plot by two parameters is presented to assess adequacy of the measurement system and process capability. A numerical example and previously studied case study are provided for illustration. Conclusion: The procedure proposed in this paper using two-dimension parameters provides a valuable procedure and helpful guidelines to quality and production managers in assessing the capabilities of a measurement system and choosing the needed actions to be the most benefit.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 추계학술대회 논문집
• /
• pp.490-495
• /
• 1996

Though the increment of using computer vision system in modern industry, there are lots of difficulties to measure precisely because of measurement error distortion phenomenon. Among these reasons, the distortion of edge is dominant reason which is occurred by the blurred image. The blurred image is happened when camera can not discriminate its precise focus. To calibrate and generalize distortion phenomenon is important. Thus, we must fix the discrimination criteria which is collected by image recognition of precise focus. Also, radial distortion causes an inward or outward displacement of a given image point from its ideal location. This type of distortion is mainly caused by flawed radial curvature curve of the elements. Thus, we were analyzed the distortion in terms of the changed with lens magnification.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.997-1002
• /
• 1994

Predictive neural network models are powerful speech recognition models based on a nonlinear pattern prediction. Those models can effectively normalize the temporal and spatial variability of speech signals. But those models suffer from poor discrimination between acoustically similar words. In this paper, we propose a discriminative training algorithm for predictive neural network models based on a generalized probabilistic descent (GPD) algorithm and minimum classification error formulation (MCEF). The Evaluation of our training algorithm on ten Korean digits shows its effectiveness by 40% reduction of recognition error.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1994년도 춘계학술대회논문집
• /
• pp.19-31
• /
• 1994

The accurate error size and discrimination region in the perception of depth amount from 3- dimensional images by the human visual system will be the basic data for the utilization and application of the binocular 3 - Dimensional image system. This paper is focused on studying the accuracy of the depth amount perceived from 3-dimensional images by the human visual system. From the performed experiment, the following results have been obtained: (1) The depth amount perceived from the binocular 3-dimensional images has been displayed by a proper scale of distance, and found to be imprecise and also have a large variance. (2) In utilizing the binocular 3-dimensional image system, it seems more appropriate to make the images viewed outward rather than inward from the screen in the regard of error and variance. (3) The binocular 3- dimensional image system can be effectively applied to displaying unreal space, for example, the layout of room in design, from the viewpoint of perception characteristics of depth amount.

• 대한한의학원전학회지
• /
• 제30권1호
• /
• pp.87-110
• /
• 2017

Objectives : The purpose of this paper is to study the form, contents and special features found in Qianhuang's life, books, his relationship with his disciples and Shanghansuyuanji's edition and its pass-ons. Methods : The best version among Shanghansuyuanji's copies was selected. Based on this, Qianhuang's life, books and his relationship with his disciples were studied, and Shanghansuyuanji's edition and its pass-ons, form and contents were analyzed. Results & Conclusions: Through study, first I see that Qianhuang was born in the early period of Qing Dynasty and died after the publication of Shanghansuyuanji, Suwen's annotation book probably had not been published yet, his mentor were Fangyouzhi and Yujiayan. Second, I see that he organized Shanghanlun sentences from his own perspective of cause of a disease and cure method. Third, I see that he viewed the diseases of six meridians with the perspective of yinyang and explained the concept of three yins and three yangs in relation to yinyang's ups and downs, and his Yuggyeongjasu theory made possible various interpretations of disease mechanism. Fourth, I see that he held critical views towards the Shanghanlun sentences through the Error Discrimination. Fifth, I see that he viewed disease mechaniam in interdependent relationships or from the point of view of the School of Warming and Tonifying through the Meaning of Herbal Formula. Sixth, I see that he sometimes quoted Neijing in proper ways that fit the disease mechanism in Shanghanlun. On the other hand, he quoted Neijing solely for the reason that identical words are used, but some of these were not proper. Additionally, he criticized the aforementioned annotators for improper quoting Neijing. Consequentially, for reasons mentioned above Qianhuang's Shanghansuyuanji has great importance as a Shanghanlun annotation book.

• 한국작물학회지
• /
• 제57권3호
• /
• pp.296-300
• /
• 2012

국내산 콩과 수입콩의 판별에 NIRS를 도입함으로써 보다 빠르고 정확한 식별분석을 하고자 실험을 수행하였다. NIRS를 사용하여 400~2,500 nm 범위에서 콩 분말의 파장을 측정하였으며, 측정된 spectrum은 WINISI II program 을 이용하여 수처리와 회귀분석을 하였다. 검량식 작성을 위한 수처리는 spectrum을 1차미분 및 4 nm gap으로 조정한 것이 가장 적합하였으며, 회귀식은 변형부분최소자승회귀법(Modified partial least squares regression)이 우수하였다. MPLS 회귀분석시 원산지 판별을 위해 loading value를 국내산 콩은 '100', 수입콩은 '1'로 처리하여 검량식을 작성하고 그 적합성을 검증한 결과 factor가 10일 때 도출된 calibration equation의 상관값이 0.98, 교차검증의 상관값이 0.94를 나타내어 상관도가 높음을 알 수 있었다. 따라서 NIRS를 이용한 국내산 콩과 수입콩의 판별분석이 가능할 것으로 판단되었다.

• 대한전자공학회논문지
• /
• 제27권11호
• /
• pp.111-118
• /
• 1990

본 논문에서는 pSDF(projection synthetic discriminant function)공간 불변 필터 개념을 적용하여 기준 이미지를 구현하고, 공간 평면 상관기인 이진 결합 변환 상관기를 이용하여 동일 클래스 인식 및 클래스 판별을 위한 광 패턴 인식을 수행하였다. 컴퓨터 시뮬레이션 결과, 이진 결합 변환 상관기가 기존의 결합 변환 상관기보다 상관 첨두치 세기, 상관 첨두치 세기대 부로브비, 신호대 잡음비, 상관폭 부분에서 뛰어난 상관 특성을 보였다. 이진 결합 변환 상관기를 이용한 광 패턴 인식 실험을 한 결과, 동일 클래스 인식인 경우 $4.1~9.6{\%}$ 오차 범위 내에서 상관 첨두지 세기가 일정하게 나타났으며, 클래스 판별인 경우 두 클래스간의 상관 첨두지 세기가 2배 차이가 나서 판별 능력이 우수함을 알 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제2권6호
• /
• pp.333-351
• /
• 2008

Transmission control protocols have to overcome common problems in wireless networks. TCP employing both packet loss discrimination mechanism and available bandwidth estimation algorithm, known as the good existing solution, shows significant performance enhancement in wireless networks. For instance, TCP New Jersey which exhibits high throughput in wireless networks intends to improve TCP performance by using available bandwidth estimation and congestion warning. Even though it achieves 17% and 85% improvements in terms of goodput over TCP Westwood and TCP Reno, respectively, we further improve it by exploring maximized available bandwidth estimation, handling bit-error-rate error recovery, and effective adjustment of sending rate for retransmission timeout. Hence, we propose TCP NJ+, showing that for up to 5% packet loss rate, it outperforms other TCP variants by 19% to 104% in terms of goodput when the network is in bi-directional background traffic.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.527-539
• /
• 2023

In the positioning algorithm of two-dimensional planar sensor array, the estimation error of time difference-ofarrival (TDOA) algorithm is difficult to avoid. Thus, how to achieve accurate positioning is a key problem of the positioning technology based on planar array. In this paper, a method of sensor reliability discrimination is proposed, which is the foundation for selecting positioning sensors with small error and excellent performance, simplifying algorithm, and improving positioning accuracy. Then, a positioning model is established. The estimation characteristics of the least square method are fully utilized to calculate and fuse the positioning results, and the non-uniform weighting method is used to correct the weighting factors. It effectively handles the decreased positioning accuracy due to measurement errors, and ensures that the algorithm performance is improved significantly. Finally, the characteristics of the improved algorithm are compared with those of other algorithms. The experiment data demonstrate that the algorithm is better than the standard least square method and can improve the positioning accuracy effectively, which is suitable for vibration detection with large noise interference.