• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.279-286
• /
• 2006

One of the widely used methods for product recommendation in Internet storefronts is matching product features against target customer profiles. When using this method, it's very important to choose a suitable subset of features for recommendation efficiency and performance, which, however, has not been rigorously researched so far. In this paper, we utilize a dataset collected from a virtual shopping experiment in a Korean Internet book shopping mall to compare several popular methods from other disciplines for selecting features for product recommendation: the vector-space model, TFIDF(Term Frequency-Inverse Document Frequency), the mutual information method, and the singular value decomposition(SVD). The application of SVD showed the best performance in the analysis results.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.881-886
• /
• 2005

This paper presents intelligent digital redesign method of global approach for hybrid state space fuzzy-model-based controllers. For effectiveness and stabilization of continuous-time uncertain nonlinear systems under discrete-time controller, Takagi-Sugeno(TS) fuzzy model is used to represent tile complex system. And global approach design problems viewed as a convex optimization problem that we minimize the error of the norm bounds between nonlinearly interpolated linear operators to be matched. Also, by using the power series, we analyzed nonlinear system's uncertain parts more precisely. When a sampling period is sufficiently small, the conversion of a continuous-time structured uncertain nonlinear system to an equivalent discrete-time system have proper reason. Sufficiently conditions for the global state-matching of tile digitally controlled system are formulated in terms of linear matrix inequalities (LMIs). Finally, a TS fuzzy model for the chaotic Lorentz system is used as an example to guarantee the stability and effectiveness of the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.532-537
• /
• 2009

The necessity of intelligent surveillance system is gradually considered seriously from the space where the security is important. In this paper, we embodied unmanned intelligent system by developing embedded mobile robot based on images and sounds tracking. For objects tracking, we used block-matching algorithm and for sound source tracking, we calculated time differences and magnitude dissimilarities of sound. And we demonstrated the superiority of intruder tracking algorithm through the embodiment of Pan-Tilt camera and sound source tracking module using system, Network camera and mobile robot using system and mobile robot using system. By linking security system, the suggested system can provide some interfacing functions for the security service of the public facilities as well as that of home.

• The Journal of the Korea Contents Association
• /
• v.7 no.6
• /
• pp.44-51
• /
• 2007

For real-time recognizing of model objects in remote position a new Neural Networks algorithm is proposed. The proposed neural networks technique is the real time computation methods through the inter-node diffusion. In the networks, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. The most reliable algorithm derived for real time recognition of objects, is a dynamic programming based algorithm based on sequence matching techniques that would process the data as it arrives and could therefore provide continuously updated neighbor information estimates. Through several simulation experiments, real time reconstruction of the nonlinear image information is processed. 1-D LIPN hardware has been composed and various experiments with static and dynamic signals have been implemented.

• Tunnel and Underground Space
• /
• v.25 no.6
• /
• pp.527-533
• /
• 2015

This study performed an on-site demonstration of the topographic surveying technique at a large-scale open-pit limestone mine in Korea using a fixed-wing unmanned aerial vehicle (UAV, Drone, SenseFly eBee). 288 sheets of aerial photos were taken by an automatic flight for 30 minutes under conditions of 300 m altitude and 12 m/s speed. Except for 37 aerial photos in which no keypoint was detected, 251 aerial photos were utilized for data processing including correction and matching, then an orthomosaic image and digital surface model with 7 cm grid spacing could be generated. A comparison of the X, Y, Z-coordinates of 4 ground control points measured by differential global positioning system and those determined by fixed-wing UAV photogrammetry revealed that the root mean squared errors were around 15 cm. Because the fixed-wing UAV has relatively longer flight time and larger coverage area than rotary-wing UAVs, it can be effectively utilized in large-scale open-pit mines as a topographic surveying tool.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.4A
• /
• pp.364-370
• /
• 2002

In this paper, we propose a VLSI array architecture for high speed processing of FBMA. First of all, the sequential FBMA is transformed into a single assignment code by using the index space expansion, and then the dependance graph is obtained from it. The two dimensional VLSI array is derived by projecting the dependance graph along the optimal direction. Since the candidate blocks in the search range are overlapped with columns as well as rows, the processing elements of the VLSI array are designed to reuse the overlapped data. As the results, the number of data inputs is reduced so that the processing performance is improved. The proposed VLSI array has (N$^2$+1)${\times}$(2p+1) processing elements and (N+2p) input ports where N is the block size and p is the maximum search range. The computation time of the rat reference block is (N$^2$+2(p+1)N+6p), and the block pipeline period is (3N+4p-1).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.5
• /
• pp.2325-2331
• /
• 2012

Planar square-spiral antenna using a strip conductor is proposed and analyzed for RFID system in UHF band operating from 860MHz to 960MHz. By varying the length of common line, detached distance, strip line-space, strip line-width and the number of spiral turn, the optimized antenna are designed and fabricated in compact size without a matching-stub between the input port of the proposed antenna and RFID tag chip. From the optimized results, the frequency bandwidth in VSWR<2 has covered 100MHz in the RFID UHF band. The antenna gain has obtained 3.5dBi at the center frequency of 910MHz and the desired beam pattern has shown directional pattern on elevation and azimuth angle. Therefore, the proposed antenna is suitable for practical RFID applications requiring various tag chips with the specific input impedance.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.86-91
• /
• 2020

The current trend of the education market is the development of the fourth industrial revolution and the development of ICT, and various technologies are developing into edu-tech technology that is integrated into the education system. In particular, the market for edu-tech systems capable of lifelike immersive learning effects in virtual space is expanding. However, education in Korean medicine is not objective because of the absence of educational simulators and systems to train and evaluate acupuncture. In this paper, we propose an acupuncture controller and a human body model to increase the effectiveness of acupuncture point training as a follow-up study of "Design of Acupuncture Contents and Dummy for Acupuncture Point Training System". Through the proposed acupuncture controller and Dummy, the accuracy of acupuncture points for the acupuncture point data matching and content motion recognition rate is presented. In addition, the results of temperature and humidity and temperature change tests for evaluating the environmental reliability of the controller are presented.

• Journal of The Korean Astronomical Society
• /
• v.31 no.2
• /
• pp.161-171
• /
• 1998

We have mapped about 1.5 square degree regions of Lynds 1299, a well isolated dark cloud in the Outer Galaxy (l = $122^{\circ}$, b = $-7^{\circ}$), in the J = 1- 0 transition of $^{12}CO$ and $^{13}CO$ with the 13.7 m radio telescope at Taeduk Radio Astronomy Observatory (TRAO). We found that there are two velocity components in the molecular emission, at $V_{LSR} = -52 km S^{-1}$ (Cloud A) and -8.8 km $s^{-1}$ (Cloud B), respectively. We have derived physical parameters of two molecular clouds and discussed three different mass estimate techniques. We found that there are large discrepancies between the virial and LTE mass estimates for both clouds. The large virial mass estimate reflects the fact that both are not gravitationally bound. We adopt the mass of $5.6 {\times}10^3 \;M{\bigodot}$ for Cloud A and $1.2{\times}10^3 \;M{\bigodot}$) for Cloud B using conversion factor. Cloud A is found to be associated with a localized star forming site, and its morphology is well matching with that of far-infrared (FIR) dust emission. It shows a clear ring structure with an obvious velocity gradient. We suggest that it may be a remnant cloud from a past episode of massive star formation. Cloud B is found to be unrelated to Cloud A (d = 800 pc) and has no specific velocity structure. The average dust color temperature of the uncontaminated portion of Cloud A is estimated to be 24$\~$27.4 K. The low dust temperature may imply that there is no additional internal heating source within the cloud. The heating of the cloud is probably dominated by the interstellar radiation field except the region directly associated with the new-born B5 star. Overall, the dust properties of Cloud A are similar to those of normal dark cloud even though it does have star forming activity.

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.1034-1042
• /
• 2016

Together with machine-learning frameworks, area-based imagery registration techniques can be easily applied to diverse types of image pairs without predefined features and feature descriptors. However, feature detectors are often used to quickly identify candidate image patch pairs, limiting the applicability of these registration techniques. In this paper, we propose a ConvNet (Convolutional Network) "Dart" that provides not only the matching metric between patches, but also information about their distance, which are helpful in reducing the search space of the corresponding patch pairs. In addition, we propose a ConvNet "Fad" to identify the patches that are difficult for Dart to improve the accuracy of registration. These two networks were successfully implemented using Deep Learning with the help of a number of training instances generated from a few registered image pairs, and were successfully applied to solve a simple image registration problem, suggesting that this line of research is promising.