• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.4
• /
• pp.84-92
• /
• 1997

Among the various sources of vehicle interior noise, this paper concerns the road induced noise ; the identification of its transfer path by using experimental method. Multiple input and single output model is taken as a noise generation model. Because it is impossible to measure the road imput forces directly, the acceleration signals are measured on four axle;three directions for each point. By considering the cross correlations of input signals, four uncorrelated source groups are taken. Multiple coherence function is employed to investigate the contribution of each group. In addtion, to identify the detailed path through the suspension systems, the contributions of all possible paths are ranked by using the coherence functions between interior noise and the relative accelerations of connections such as bushings and mountings. Measurements are performed with passenger vehicle traveling on concrete and asphalt roads at 60㎞/h.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.509-514
• /
• 2006

Human action recognition is an active research area in computer vision. In this paper, we present a robust method for human action recognition by using combined information of human body shape and motion information with multiple views image sequence. The principal component analysis is used to extract the shape feature of human body and multiple block motion of the human body is used to extract the motion features of human. This combined information with multiple view sequences enhances the recognition of human action. We represent each action using a set of hidden Markov model and we model each action by multiple views. This characterizes the human action recognition from arbitrary view information. Several daily actions of elderly persons are modeled and tested by using this approach and they are correctly classified, which indicate the robustness of our method.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.55 no.4
• /
• pp.167-175
• /
• 2006

This paper presents a method to segment semiconductor wafer ID on poor quality images. The method is based on multiple templates and normalized gray-level correlation (NGC) method. If the lighting condition is not so good and hence, we can not control the image quality, target image to be inspected presents poor quality ID and it is not easy to identify and then recognize the ID characters. Conventional several method to segment the interesting ID regions fails on the bad quality images. In this paper, we propose a multiple template method, which uses combinational relation of multiple templates from model templates to match several characters of the inspection images. To find out the optimal solution of multiple template model in ID regions, we introduce newly-developed snake algorithm. Experimental results using images from real FA environment are presented.

• Journal of Power Electronics
• /
• v.16 no.4
• /
• pp.1483-1493
• /
• 2016

Multiple parallel inverters have multiple resonant frequencies that are influenced by many factors. This often results in stability and power quality problems. This paper develops a multiple input multiple output model of grid-connected inverter systems using a closed-loop transfer function. The influence factors of the resonant characteristics are analyzed with the developed model. The analysis results show that the resonant frequency is closely related to the number, type and composition ratio of the parallel inverters. To suppress resonance, a scheme based on virtual impedance is presented, where the virtual impedance is emulated in the vicinity of the resonance frequency. The proposed scheme needs one inverter with virtual impedance control, which reduces the design complexity of the other inverter controllers. Simulation and experimental tests are carried out on two single phase converter-based setups. The results validate the correctness of the model, the analytical results and the resonant suppressing scheme.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.375-380
• /
• 2010

Most of previous algorithms of object boundary extraction have been studied for extracting the boundary of single object. However, multiple objects are much common in the real image. The proposed algorithm of extracting the boundary of each of multiple objects has two steps. In the first step, we propose the fast method using the outer and inner products; the initial contour including multiple objects is split and connected and each of new contours includes only one object. In the second step, an improved active contour model is studied to extract the boundary of each object included each of contours. Experimental results with various test images have shown that our algorithm produces much better results than the previous algorithms.

• Korean Chemical Engineering Research
• /
• v.47 no.6
• /
• pp.695-699
• /
• 2009

As a rule, when develop new product in company, multiple products that have similar function are developed simultaneously. These products are subjected to a group of tests covering quality, safety and durability. If the schedule of tests is changed, the expected net presented value(NPV) of new products is changed. The tests should be scheduled with the goal of maximizing the expected NPV of the new products. A model incorporated resource constraints with the sequencing of testing tasks of multiple products is proposed in this paper. Examples show that the proposed model can handle stochastic task duration data represented by scenarios with probabilities.

• Journal of The Korean Association of Information Education
• /
• v.20 no.2
• /
• pp.197-206
• /
• 2016

A fill-in-the-blank with choices are widely used in classrooms in order to check whether students' understand what is being taught. Although there have been proposed many algorithms for generating this type of questions, most of them focus on preparing sentences with blanks rather than generating multiple choices. In this paper, we propose a novel algorithm for generating multiple choices, given a sentence with a blank. Because the algorithm is based on a statistical language model, we can generate relatively unbiased result and adjust the level of difficulty with ease. The experimental results show that our approach automatically produces similar multiple-choices to those of the exam writers.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.807-823
• /
• 2018

Speaker verification system performance depends on the utterance of each speaker. To verify the speaker, important information has to be captured from the utterance. Nowadays under the constraints of limited data, speaker verification has become a challenging task. The testing and training data are in terms of few seconds in limited data. The feature vectors extracted from single frame size and rate (SFSR) analysis is not sufficient for training and testing speakers in speaker verification. This leads to poor speaker modeling during training and may not provide good decision during testing. The problem is to be resolved by increasing feature vectors of training and testing data to the same duration. For that we are using multiple frame size (MFS), multiple frame rate (MFR), and multiple frame size and rate (MFSR) analysis techniques for speaker verification under limited data condition. These analysis techniques relatively extract more feature vector during training and testing and develop improved modeling and testing for limited data. To demonstrate this we have used mel-frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) as feature. Gaussian mixture model (GMM) and GMM-universal background model (GMM-UBM) are used for modeling the speaker. The database used is NIST-2003. The experimental results indicate that, improved performance of MFS, MFR, and MFSR analysis radically better compared with SFSR analysis. The experimental results show that LPCC based MFSR analysis perform better compared to other analysis techniques and feature extraction techniques.

• Nuclear Engineering and Technology
• /
• v.56 no.2
• /
• pp.558-567
• /
• 2024

Diagnostic support systems are being researched to assist operators in identifying and responding to abnormal events in a nuclear power plant. Most studies to date have considered single abnormal events only, for which it is relatively straightforward to obtain data to train the deep learning model of the diagnostic support system. However, cases in which multiple abnormal events occur must also be considered, for which obtaining training data becomes difficult due to the large number of combinations of possible abnormal events. This study proposes an approach to maintain diagnostic performance for multiple abnormal events by training a deep learning model with data on single abnormal events only. The proposed approach is applied to an existing algorithm that can perform feature selection and multi-label classification. We choose an extremely randomized trees classifier to select dedicated monitoring parameters for target abnormal events. In diagnosing each event occurrence independently, two-channel convolutional neural networks are employed as sub-models. The algorithm was tested in a case study with various scenarios, including single and multiple abnormal events. Results demonstrated that the proposed approach maintained diagnostic performance for 15 single abnormal events and significantly improved performance for 105 multiple abnormal events compared to the base model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.210-217
• /
• 2020

Since multiple generation technology can have various entry modes by adjusting performance, price, and entry timing, understanding of market entry mode of multiple generation technology is important. This study defined the concept of market entry mode based on multiple dimensions (technology, time, performance, or price) and developed a model for various types of market entry modes. Based on a literature review, the definition and types of market entry mode were provided, and the accuracy of the model was verified based on a case study on the semiconductor and smartphone market. Six market entry modes of multiple generation technology were modeled as moderate performance and early entry, high performance and early entry, low performance and early entry, moderate performance and late entry, high performance and late entry, and low performance and late entry. This study will be useful to understand the market entry mode of multiple generation technology by defining and developing a model for entry mode and can be applied to other markets in addition to multiple generation technology.