• Journal of Biomedical Engineering Research
• /
• v.30 no.5
• /
• pp.428-437
• /
• 2009

The Performance research about EEG-BCI algorithm in BCI-naive subjects is very important for evaluating the applicability to the public. We analyzed the result of the performance evaluation experiment about the EEG-BCI algorithm in BCI-naive subjects on three different aspects. The EEG-BCI algorithm used in this paper is composed of the common spatial pattern(CSP) and the least square linear classifier. CSP is used for obtaining the characteristic of event related desynchronization, and the least square linear classifier classifies the motor imagery EEG data of the left hand or right hand. The performance evaluation experiments about EEG-BCI algorithm is conducted for 40 men and women whose age are 23.87${\pm}$2.47. The performance evaluation about EEG-BCI algorithm in BCI-naive subjects is analyzed in terms of the accuracy, the relation between the information transfer rate and the accuracy, and the performance changes when the different types of cue were used in the training session and testing session. On the result of experiment, BCI-naive group has about 20% subjects whose accuracy exceed 0.7. And this results of the accuracy were not effected significantly by the types of cue. The Information transfer rate is in the inverse proportion to the accuracy. And the accuracy shows the severe deterioration when the motor imagery is less then 2 seconds.

• Proceedings of the Safety Management and Science Conference
• /
• 2002.05a
• /
• pp.91-97
• /
• 2002

In this thesis presents line balancing problems of two-sided and mixed model assembly line widely used in practical fields using genetic algorithm for reducing throughput time, cost of tools and fixtures and improving flexibility of assembly lines. Two-sided and mixed model assembly line is a special type of production line where variety of product similar in product characteristics are assembled in both sides. This thesis proposes the genetic algorithm adequate to each step in tow-sided and mixed model assembly line with suitable presentation, individual, evaluation function, selection and genetic parameter. To confirm proposed genetic algorithm, we apply to increase the number of tasks in case study. And for evaluation the performance of proposed genetic algorithm, we compare to existing algorithm of one-sided and mixed model assembly line. The results show that the algorithm is outstanding in the problems with a larger number of stations or larger number of tasks.

• Journal of the Korea Safety Management & Science
• /
• v.4 no.2
• /
• pp.83-101
• /
• 2002

In this thesis presents line balancing problems of two-sided and mixed model assembly line widely used in practical fields using genetic algorithm for reducing throughput time, cost of tools and fixtures and improving flexibility of assembly lines. Two-sided and mixed model assembly line is a special type of production line where variety of product similar in product characteristics are assembled in both sides. This thesis proposes the genetic algorithm adequate to each step in tow-sided and mixed model assembly line with suitable presentation, individual, evaluation function, selection and genetic parameter. To confirm proposed genetic algorithm, we apply to increase the number of tasks in case study. And for evaluation the performance of proposed genetic algorithm, we compare to existing algorithm of one-sided and mixed model assembly line. The results show that the algorithm is outstanding in the problems with a larger number of stations or larger number of tasks.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.233-237
• /
• 2006

This study proposes an innovative measure for evaluating the performance of text clustering. In using K-means algorithm and Kohonen Networks for text clustering, the number clusters is fixed initially by configuring it as their parameter, while in using single pass algorithm for text clustering, the number of clusters is not predictable. Using labeled documents, the result of text clustering using K-means algorithm or Kohonen Network is able to be evaluated by setting the number of clusters as the number of the given target categories, mapping each cluster to a target category, and using the evaluation measures of text. But in using single pass algorithm, if the number of clusters is different from the number of target categories, such measures are useless for evaluating the result of text clustering. This study proposes an evaluation measure of text clustering based on intra-cluster similarity and inter-cluster similarity, what is called CI (Clustering Index) in this article.

• Phonetics and Speech Sciences
• /
• v.6 no.2
• /
• pp.9-20
• /
• 2014

In this paper, we propose an automatic fluency evaluation algorithm for English speaking tests. In the proposed algorithm, acoustic features are extracted from an input spoken utterance and then fluency score is computed by using support vector regression (SVR). We estimate the parameters of feature modeling and SVR using the speech signals and the corresponding scores by human raters. From the correlation analysis results, it is shown that speech rate, articulation rate, and mean length of runs are best for fluency evaluation. Experimental results show that the correlation between the human score and the SVR score is 0.87 for 3 speaking tests, which suggests the possibility of the proposed algorithm as a secondary fluency evaluation tool.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1226-1229
• /
• 1993

This paper proposes a new on-line fuzzy model identification(ONFID) algorithm in which the fuzzy model evaluation stage is incorporated. The fuzzy model evaluation is performed by the fuzzy equality index which is known to be a useful tool to evaluate the performance of the identified fuzzy model. Then the fuzzy model is updated according to the result of the evaluation. Proposed ONFID algorithm can sensibly identify to the system changes. To show the usefulness of the proposed algorithm, it is applied to the fuzzy model identification problem of the gas furnace and the output prediction problem of the flexible joint manipulator which is a nonlinear system.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.9
• /
• pp.896-902
• /
• 2012

For most applications of the vibration energy harvesting technology as in wireless sensor networks for smart buildings and plants, the evaluation of DC output performance of vibration energy harvesters is typically required. However, there is no dedicated algorithm for the evaluation. The lack of a dedicated algorithm results from difficulties in the direct incorporation of nonlinear rectifying and regulating circuitry into finite element models of piezoelectric vibration energy harvesters. In this study, we develop a dedicated algorithm and present software based on it for the evaluation of not only AC but also DC electrical quantities. Here, an equivalent electrical circuit model is employed. The COMSOL multiphysics simulation tool is adopted for extracting equivalent electrical circuit parameters of a piezoelectric vibration energy harvester and MATLAB is used to make a graphical user interface. The AC voltage and power outputs calculated by the proposed algorithm under various conditions are compared with those by a traditional finite element analysis. The DC output voltage and power through a rectifier are obtained for varying values of smoothing capacitance and external resistance.

• Smart Structures and Systems
• /
• v.4 no.4
• /
• pp.449-464
• /
• 2008

An array based, outward monitoring, ultrasonic guided wave based SHM technique using a single transmitter and multiple receivers (STMR), with a small footprint is discussed here. The previous implementation of such SHM arrays used a phase-reconstruction algorithm (that is similar to the beam-steering algorithm) for the imaging of reflectors. These algorithms were found to have a limitation during the imaging of defects/reflectors that are present in the "near-field" of the array. Here, the "near-field" is defined to be approximately 3-4 times the diameter of the compact array. This limitation is caused by approximations in the beam-steering reconstruction algorithm. In this paper, a migration-based reconstruction algorithm, with dispersion correction in the frequency domain, is discussed. Simulation and experimental studies are used to demonstrate that this algorithm improves the reconstruction in the "near-field" without decreasing the ability to reconstruct defects in the "far-field" in both isotropic and anisotropic plates.

• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.623-628
• /
• 2019

The aim of this study was to design fast non local means (FNLM) noise reduction algorithm and to confirm its application feasibility in light microscopic image. For that aim, we acquired mouse first molar image and compared between previous widely used noise reduction algorithm and our proposed FNLM algorithm in acquired light microscopic image. Contrast to noise ratio, coefficient of variation, and no reference-based evaluation parameter such as natural image quality evaluator (NIQE) and blind/referenceless image spatial quality evaluator (BRISQUE) were used in this study. According to the result, our proposed FNLM noise reduction algorithm can achieve excellent result in all evaluation parameters. In particular, it was confirmed that the NIQE and BRISQUE evaluation parameters for analyzing the overall morphologcal image of the tooth were 1.14 and 1.12 times better than the original image, respectively. In conclusion, we demonstrated the usefulness and feasibility of FNLM noise reduction algorithm in light microscopic image of small animal tooth.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.6
• /
• pp.658-663
• /
• 2018

In this paper, a performance evaluation algorithm of contents curation platform is proposed. The evaluation starts with setting the initial-final conditions, and measures four performance evaluation parameters. These parameters are response rate of service, accuracy of response result, precision of analysis result, and recall rate of analysis result. To verify the effectiveness of the proposed algorithm, a database of 118,738 cases was constructed and the contents was opened on the Internet. In this experiment, 6,975,365 pageviews were applied to analysis user behavior. Through the measurement of four parameters, it was confirmed that the integrated and unit evaluation of content curation platform can be performed objectively.