• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.3
• /
• pp.230-245
• /
• 2005

In this paper, we develop a gesture-based input device equipped with accelerometers and gyroscopes. The sensors measure the inertial measurements, i.e., accelerations and angular velocities produced by the movement of the system when a user is inputting gestures on a plane surface or in a 3D space. The gyroscope measurements are integrated to give orientation of the device and consequently used to compensate the accelerations. The compensated accelerations are doubly integrated to yield the position of the device. With this approach, a user's gesture input trajectories can be recovered without any external sensors. Three versions of motion tracking algorithms are provided to cope with wide spectrum of applications. Then, a Bayesian network based recognition system processes the recovered trajectories to identify the gesture class. Experimental results convincingly show the feasibility and effectiveness of the proposed gesture input device. In order to show practical use of the proposed input method, we implemented a prototype system, which is a gesture-based remote controller (Magic Wand).

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.59 no.3
• /
• pp.279-287
• /
• 2010

Interior permanent magnet synchronous motor(IPMSM) adjustable speed drives offer significant advantages over induction motor drives in a wide variety of industrial applications such as high power density, high efficiency, improved dynamic performance and reliability. This paper proposes efficiency optimization control of IPMSM drive using adaptive fuzzy learning controller(AFLC). In order to optimize the efficiency the loss minimization algorithm is developed based on motor model and operating condition. The d-axis armature current is utilized to minimize the losses of the IPMSM in a closed loop vector control environment. The design of the current based on adaptive fuzzy control using model reference and the estimation of the speed based on neural network using ANN controller. The controllable electrical loss which consists of the copper loss and the iron loss can be minimized by the optimal control of the armature current. The minimization of loss is possible to realize efficiency optimization control for the proposed IPMSM. The optimal current can be decided according to the operating speed and the load conditions. This paper considers the design and implementation of novel technique of high performance speed control for IPMSM using AFLC. Also, this paper proposes speed control of IPMSM using AFLC1, current control of AFLC2 and AFLC3, and estimation of speed using ANN controller. The proposed control algorithm is applied to IPMSM drive system controlled AFLC, the operating characteristics controlled by efficiency optimization control are examined in detail.

• Journal of The Korean Astronomical Society
• /
• v.53 no.6
• /
• pp.161-168
• /
• 2020

We report the discovery of a giant exoplanet in the microlensing event OGLE-2017-BLG-1049, with a planet-host star mass ratio of q = 9.53 ± 0.39 × 10-3 and a caustic crossing feature in Korea Microlensing Telescope Network (KMTNet) observations. The caustic crossing feature yields an angular Einstein radius of θE = 0.52 ± 0.11 mas. However, the microlens parallax is not measured because the time scale of the event, tE ≃ 29 days, is too short. Thus, we perform a Bayesian analysis to estimate physical quantities of the lens system. We find that the lens system has a star with mass Mh = 0.55+0.36-0.29 M⊙ hosting a giant planet with Mp = 5.53+3.62-2.87 MJup, at a distance of DL = 5.67+1.11-1.52 kpc. The projected star-planet separation is a⊥ = 3.92+1.10-1.32 au. This means that the planet is located beyond the snow line of the host. The relative lens-source proper motion is μrel ~ 7 mas yr-1, thus the lens and source will be separated from each other within 10 years. After this, it will be possible to measure the flux of the host star with 30 meter class telescopes and to determine its mass.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Korean small business review
• /
• v.32 no.1
• /
• pp.65-87
• /
• 2010

With the advent of knowledge-based society, the revitalization of technological innovation type SMEs, termed "inno-biz" hereafter, has been globally recognized as a government policymakers' primary concern in strengthening national competitiveness, and much effort is being put into establishing polices of boosting the start-ups and innovation capability of SMEs. Especially, in that the inno-biz enables national economy to get vitalized by widening world markets with its superior technology, and thus, taking the initiative of extremely competitive world markets, its growth and development has greater significance. In the case of Korea, the government has been maintaining the policies since the late 1990s of stimulating the growth of SMEs as well as building various infrastructures to foster the start-ups of the SMEs such as venture businesses with high technology. In addition, since the enactment of "Innovation Promotion Law for SMEs" in 2001, the government has been accelerating the policies of prioritizing the growth and development of inno-biz. So, for the sound growth and development of Korean inno-biz, this paper intends to offer effective management strategies for SMEs and suggest proper policies for the government, by researching into the effect of technological innovation capability and technology commercialization capability as the primary business resources on business performance in Korean SMEs in the light of market information orientation. The research is carried out on Korean companies characterized as inno-biz. On the basis of OSLO manual and prior studies, the research categorizes their status. R&D capability, technology accumulation capability and technological innovation system are categorized into technological innovation capability; product development capability, manufacturing capability and marketing capability into technology commercialization capability; and increase in product competitiveness and merits for new technology and/or product development into business performance. Then the effect of each component on business performance is substantially analyzed. In addition, the mediation effect of technological innovation and technology commercialization capability on business performance is observed by the use of the market information orientation as a parameter. The following hypotheses are proposed. H1 : Technology innovation capability will positively influence business performance. H1-1 : R&D capability will positively influence product competitiveness. H1-2 : R&D capability will positively influence merits for new technology and/or product development into business performance. H1-3 : Technology accumulation capability will positively influence product competitiveness. H1-4 : Technology accumulation capability will positively influence merits for new technology and/or product development into business performance. H1-5 : Technological innovation system will positively influence product competitiveness. H1-6 : Technological innovation system will positively influence merits for new technology and/or product development into business performance. H2 : Technology commercializing capability will positively influence business performance. H2-1 : Product development capability will positively influence product competitiveness. H2-2 : Product development capability will positively influence merits for new technology and/or product development into business performance. H2-3 : Manufacturing capability will positively influence product competitiveness. H2-4 : Manufacturing capability will positively influence merits for new technology and/or product development into business performance. H2-5 : Marketing capability will positively influence product competitiveness. H2-6 : Marketing capability will positively influence merits for new technology and/or product development into business performance. H3 : Technology innovation capability will positively influence market information orientation. H3-1 : R&D capability will positively influence information generation. H3-2 : R&D capability will positively influence information diffusion. H3-3 : R&D capability will positively influence information response. H3-4 : Technology accumulation capability will positively influence information generation. H3-5 : Technology accumulation capability will positively influence information diffusion. H3-6 : Technology accumulation capability will positively influence information response. H3-7 : Technological innovation system will positively influence information generation. H3-8 : Technological innovation system will positively influence information diffusion. H3-9 : Technological innovation system will positively influence information response. H4 : Technology commercialization capability will positively influence market information orientation. H4-1 : Product development capability will positively influence information generation. H4-2 : Product development capability will positively influence information diffusion. H4-3 : Product development capability will positively influence information response. H4-4 : Manufacturing capability will positively influence information generation. H4-5 : Manufacturing capability will positively influence information diffusion. H4-6 : Manufacturing capability will positively influence information response. H4-7 : Marketing capability will positively influence information generation. H4-8 : Marketing capability will positively influence information diffusion. H4-9 : Marketing capability will positively influence information response. H5 : Market information orientation will positively influence business performance. H5-1 : Information generation will positively influence product competitiveness. H5-2 : Information generation will positively influence merits for new technology and/or product development into business performance. H5-3 : Information diffusion will positively influence product competitiveness. H5-4 : Information diffusion will positively influence merits for new technology and/or product development into business performance. H5-5 : Information response will positively influence product competitiveness. H5-6 : Information response will positively influence merits for new technology and/or product development into business performance. H6 : Market information orientation will mediate the relationship between technology innovation capability and business performance. H7 : Market information orientation will mediate the relationship between technology commercializing capability and business performance. The followings are the research results : First, as for the effect of technological innovation on business performance, the technology accumulation capability and technological innovating system have a positive effect on increase in product competitiveness and merits for new technology and/or product development, while R&D capability has little effect on business performance. Second, as for the effect of technology commercialization capability on business performance, the effect of manufacturing capability is relatively greater than that of merits for new technology and/or product development. Third, the mediation effect of market information orientation is identified to exist partially in information generation, information diffusion and information response. Judging from these results, the following analysis can be made : On Increase in product competitiveness, directly related to successful technology commercialization of technology, management capability including technological innovation system, manufacturing capability and marketing capability has a relatively strong effect. On merits for new technology and/or product development, on the other hand, capability in technological aspect including R&D capability, technology accumulation capability and product development capability has relatively strong effect. Besides, in the cast of market information orientation, the level of information diffusion within an organization plays and important role in new technology and/or product development. Also, for commercial success like increase in product competitiveness, the level of information response is primarily required. Accordingly, the following policies are suggested : First, as the effect of technological innovation capability and technology commercialization capability on business performance differs among SMEs; in order for SMEs to secure competitiveness, the government has to establish microscopic policies for SMEs which meet their needs and characteristics. Especially, the SMEs lacking in capital and labor are required to map out management strategies of focusing their resources primarily on their strengths. And the government needs to set up policies for SMEs, not from its macro-scaled standpoint, but from the selective and concentrative one that meets the needs and characteristics of respective SMEs. Second, systematic infrastructures are urgently required which lead technological success to commercial success. Namely, as technological merits at respective SME levels do not always guarantee commercial success, the government should make and effort to build systematic infrastructures including encouragement of M&A or technology trade, systematic support for protecting intellectual property, furtherance of business incubating and industrial clusters for strengthening academic-industrial network, and revitalization of technology financing, in order to make successful commercialization from technological success. Finally, the effort to innovate technology, R&D, for example, is essential to future national competitiveness, but its result is often prolonged. So the government needs continuous concern and funding for basic science, in order to maximize technological innovation capability. Indeed the government needs to examine continuously whether technological innovation capability or technological success leads satisfactorily to commercial success in market economic system. It is because, when the transition fails, it should be left to the government.

• IMMUNE NETWORK
• /
• v.5 no.2
• /
• pp.78-88
• /
• 2005

Background: Collagen-induced arthritis (CIA) in mice is animal model of autoimmune disease known as rheumatic arthritis in human. We investigated CII-specific CD4+ T cell receptor usage in CIA mice. Methods: In CIA model, draining lymph node (dLN) CD4+ T cells and splenocytes at $3^{rd},\;5^{th},\;8^{th}$ week, we investigated CII-specific T cell proliferation, production of IL-17, IFN-${\gamma}$, TNF-${\alpha}$, IL-4 and IL-10. And we also performed anti-CII IgG Ab measurements in serum level, TCRV ${\beta}$ usage and T cell clonality with RT-PCR-SSCP analysis. Also, we performed proliferative response against CII when CII-specific T cell subset is deleted. Results: CIA mice showed more increase in the serum level of anti-CII IgG than normal mice after induction of arthritis. And the level of anti-CII IgG2a in CIA mice was increased after $3^{rd}$ week after primary immunization, while anti-CII IgG1 was decreased. Draining LN CD4+ T cells have proliferated against CII stimulation at $3^{rd}$ week after $1^{st}$immunization. CD4+T cells derived from dLN of CIA mice produced proinflammatory cytokine IFN-${\gamma}$, IL-17 etc. Draining LN CD4 T cells of CIA presented higher proportion of CD4+V ${\beta}3$+subset compared to those of normal mice at $3^{rd}$ week after $1^{st}$ immunization, and they were increased in proportion by CII stimulation. Draining LN CD4+ T cells without TCRV ${\beta}3+/V{\beta}8.1/8.2+/V{\beta}$10b+cells were not responsive against CII stimulation. But, CII-reactive response of TCRV ${\beta}3-/V{\beta}8.1/8.2-/V{\beta}$10b- T cells was recovered when $V{\beta}3+$ T cells were added in culture. Conclusion: Our results indicate that CD4+$V{\beta}3+$ T cells are selectively expanded in dLN of CIA mice, and their recovery upon CII re-stimulation in vitro, as well as the production Th1-type cytokines, may play pivotal role in CIA pathogenesis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.285-291
• /
• 2020

In manufacturing, humans are being replaced with robots, but expert skills remain difficult to convert to data, making them difficult to apply to industrial robots. One method is by visual motion recognition, but physical features may be judged differently depending on the image data. This study aimed to improve the accuracy of vision methods for estimating the posture of humans. Three OpenPose vision models were applied: MPII, COCO, and COCO+foot. To identify the effects of face-covering accessories and image preprocessing on the Convolutional Neural Network (CNN) structure, the presence/non-presence of accessories, image size, and filtering were set as the parameters affecting the identification of a human's posture. For each parameter, image data were applied to the three models, and the errors between the actual and predicted values, as well as the percentage correct keypoints (PCK), were calculated. The COCO+foot model showed the lowest sensitivity to all three parameters. A <50% (from 3024×4032 to 1512×2016 pixels) reduction in image size was considered acceptable. Emboss filtering, in combination with MPII, provided the best results (reduced error of <60 pixels).

• Journal of the Korean Society of Earth Science Education
• /
• v.16 no.1
• /
• pp.153-165
• /
• 2023

This study investigates learners' environmental literacy, classifies the results by factors of environmental literacy, and then investigates the differences in the students' environmental behavior practice experiences according to the classification by factor. The study was conducted with 47 6th grade students from D elementary school located in P metropolitan city as the subject of final analysis, and environmental literacy questionnaires and environmental behavior practice experience questionnaires were used as the main data. As a result of the study, the learners were classified into three groups according to the factors of environmental literacy, and they were respectively named as the "High environmental literacy group", "low environmental literacy group", and "Low Function and Affectif group". A Word network was formed using the descriptions of environmental behavior practice experiences for each cluster, and a Degree Centrality Analysis was performed to visualize and then analyze. As a result of the analysis, "High environmental literacy group" was confirmed, 1) recognized the subjects of environmental action practice as individuals and families, 2) described his experience of environmental action practice in relation to all elements of environmental literacy, and had a relatively pessimistic view. "low environmental literacy group", and "Low Function and Affectif group" were confirmed 1) perceive the subject of environmental behavior practice as a relatively social problem, 2) the description of the experience of environmental behavior practice is relatively biased specific factors, and the "Low Function and Affectif group" is particularly focused on the knowledge element. And 3) it was confirmed that they were aware of climate change from a relatively optimistic perspective. Based on this conclusion, suggestions were made from the perspective of environmental education.

• Composites Research
• /
• v.19 no.5
• /
• pp.28-33
• /
• 2006

In this paper, we have studied the complex permittivities and their influence on the design of microwave absorbers of E-glass fabric/epoxy composite laminates containing three different types of carbon-based nano conductive fillers such as carbon black (CB), carbon nano fiber (CNF) and multi-wall nano tube (MWNT). The measurements were performed fur permittivities at the frequency band of 0.5 GHz$\sim$18.0 GHz using a vector network analyzer with a 7 mm coaxial air line. The experimental results show that the complex permittivities of the composites depend strongly on the natures and concentrations of the conductive fillers. The real and imaginary parts of the complex permittivities of the composites were proportional to the filler concentrations. But, depending on the types of fillers and frequency band, the increasing rates of the real and imaginary parts with respect to the filler concentrations were all different. These different rates can have an effect on the thickness in designing the single layer microwave absorbers. The effect of the different rates at 10 GHz was examined by using Cole-Cole plot; the plot is composed of a single layer absorber solution line and measured permittivities from these three types of composites. Single layer absorbers of 3 different thicknesses using carbon nano materials were fabricated and the -10 dB band of absorbing performances were all about 3 GHz.