• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.11 s.353
• /
• pp.26-36
• /
• 2006

In this paper, we propose a cost-effective color filter may (CFA) demosaicing method for digital still cameras in which a single CCD or CMOS image sensor is used. Since a CFA is adopted, we must interpolate missing color values in the red, green and blue channels at each pixel location. While most state-of-the-art algorithms invest a great deal of computational effort in the enhancement of the reconstructed image to overcome the color artifacts, we focus on eliminating the color artifacts with low computational complexity. Using spatial correlation of the adjacent pixels, the edge-directional information of the neighbor pixels is used for determining the edge direction of the current pixel. We apply our method to the state-of-the-art algorithms which use edge-directed methods to interpolate the missing color channels. The experiment results show that the proposed method enhances the demosaiced image qualify from $0.09{\sim}0.47dB$ in PSNR depending on the basis algorithm by removing most of the color artifacts. The proposed method was implemented and verified successfully using verilog HDL and FPGA. It was synthesized to gate-level circuits using 0.25um CMOS standard cell library. The total logic gate count is 12K, and five line memories are used.

• Journal of the Microelectronics and Packaging Society
• /
• v.19 no.1
• /
• pp.81-87
• /
• 2012

This paper focuses on three-dimensional measurement system of micro balls on micro Ball-Grid-Array(BGA) packages in-line. Most of visual inspection system still suffers from sophisticate reflection characteristics of micro balls. For accurate shape measurement of them, a specially designed visual sensor system is proposed under the sensing principle of phase shifting moire interferometry. The system consists of a pattern projection system with four projection subsystems and an imaging system. In the projection system, four subsystems have spatially different projection directions to make target objects experience the pattern illuminations with different incident directions. For the phase shifting, each grating pattern of subsystem is regularly moved by PZT actuator. To remove specular noise and shadow area of BGA balls efficiently, a compact multiple-pattern projection and imaging system is implemented and tested. Especially, a sensor fusion algorithm to integrate four information sets, acquired from multiple projections, into one is proposed with the basis of Bayesian sensor fusion theory. To see how the proposed system works, a series of experiments is performed and the results are analyzed in detail.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.3
• /
• pp.359-364
• /
• 2011

The study uses department of the sensitivity and fuzzy reasoning, one of artificial intelligence algorithms, so that develop LED lighting system based on fuzzy reasoning for systematical control of the LED color temperature. In the area of sensitivity engineering, by considering the relation between color and emotion expressed as an adjective word, the corresponding sensitivity word can be determined, By taking into consideration the relation between the brain wave measured from the human brain and the color temperature, the preferred lesson subject can be determined. From the decision of the sensitivity word and the lesson subject, we adjust the color temperature of RGB (Red, Green, Blue) LED. In addition, by using the information of the latitude and the longitude from GPS(Global Positioning System), we can calculate the on-line moving altitude of sun. By using the sensor information of both temperature and humidity, we can calculate the discomfort index. By considering the altitude of sun as well as the value of the discomfort index, the illumination of W(white) LED and the color temperature of RGB LED can be determined. The (LED) sensitivity lighting control system is bulit up by considering the sensitivity word, the lesson subject, the altitude of sun, and the discomfort index The developed sensitivity lighting control system leads to more suitable atmosphere and also the enhancement of the efficiency of lesson subjects as well as business affairs.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.43-53
• /
• 2009

Knowledge retrieval service that uses collective intelligence which has special quality of open structure and can share the accumulative data is gaining popularity. However, acquiring the right needs for users from massive public knowledge is getting harder. Recently, search results from Google which is known for it's exquisite algorism, shows results for collective intelligence such as Wikipedia, Yahoo Q/A at the highest rank. Objective of this paper is to show that most answers come from human and to find the most influential people in on-line knowledge retrieval service. Hereupon, this paper suggest the influence value calculation algorism by analyzing user relation as centrality which social network is based on user activeness and reliance in Naver 지식iN. The influence value calculated by the suggested algorism will be an important index in distinguishing reliable and the right user for the question by ranking users with troubleshooting solutions in the knowledge retrieval service. This will contribute in search satisfaction by acquiring the right information and knowledge for the users which is the most important objective for knowledge retrieval service.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.

• Journal of Radiation Protection and Research
• /
• v.23 no.3
• /
• pp.139-147
• /
• 1998

Purpose: Tissue inhomogeneity such as lung affects tumor dose as well as transmission dose in new concept of on-line dosimetry which estimates tumor dose from transmission dose using the new algorithm. This study was carried out to confirm accuracy of correction by tissue density in tumor dose estimation utilizing transmission dose. Methods: Cork phantom (CP, density $0.202\;gm/cm^3$) having similar density with lung parenchyme and polystyrene phantom (PP, density $1.040\;gm/cm^3$) having similar density with soft tissue were used. Dose measurement was carried out under condition simulating human chest. On simulating AP-PA irradiation, PPs with 3 cm thickness were placed above and below CP, which had thickness of 5, 10, and 20 cm. On simulating lateral irradiation, 6 cm thickness of PP was placed between two 10 cm thickness CPs additional 3 cm thick PP was placed to both lateral sides. 4, 6, and 10 MV x-ray were used. Field size was in the range of $3{\times}3$ cm through $20{\times}20$ cm, and phantom-chamber distance (PCD) was 10 to 50 cm. Above result was compared with another sets of data with equivalent thickness of PP which was corrected by density. Result: When transmission dose of PP was compared with equivalent thickness of CP which was corrected with density, the average error was 0.18 (${\pm}0.27$) % for 4 MV, 0.10 (${\pm}0.43$) % for 6 MV, and 0.33 (${\pm}0.30$) % for 10 MV with CP having thickness of 5 cm. When CP was 10 cm thick, the error was 0.23 (${\pm}0.73$) %, 0.05 (${\pm}0.57$) %, and 0.04 (${\pm}0.40$) %, while for 20 cm, error was 0.55 (${\pm}0.36$) %, 0.34 (${\pm}0.27$) %, and 0.34 (${\pm}0.18$) % for corresponding energy. With lateral irradiation model, difference was 1.15 (${\pm}1.86$) %, 0.90 (${\pm}1.43$) %, and 0.86 (${\pm}1.01$) % for corresponding energy. Relatively large difference was found in case of PCD having value of 10 cm. Omitting PCD with 10 cm, the difference was reduced to 0.47 (${\pm}$1.17) %, 0.42 (${\pm}$0.96) %, and 0.55 (${\pm}$0.77) % for corresponding energy. Conclusion When tissue inhomogeneity such as lung is in tract of x-ray beam, tumor dose could be calculated from transmission dose after correction utilizing tissue density.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.2
• /
• pp.225-236
• /
• 1994

Many research result conducted by neural network researchers claimed that the degree of generalization of the neural network system is higher or at least equal to that of statistical methods. However, those successful results could be brought only if the neural network was trained by appropriately sound data, having a little of noisy data and being large enough to control noisy data. Real data used in a lot of fields, especially business fields, were not so sound that the network have frequently failed to obtain satisfactory prediction accuracy, the degree of generalization. Enhancing the degree of generalization with noisy data is discussed in this study. The suggestion, which was obtained through a series of experiments, to enhance the degree of generalization is to remove inconsistent data by checking overlapping and inconsistencies. Furthermore, the previous conclusion by other reports is also confirmed that the learning mechanism of neural network takes average value of two inconsistent data included in training set［2］. The interim results of on-going research project are reported in this paper These are ann architecture of the neural network adopted in this project and the whole idea of developing on-line credit evaluation system,being intergration of the expert(resoning)system and the neural network(learning system.Another definite result is corroborated through this study that quickprop,being agopted as a learing algorithm, also has more speedy learning process than does back propagation even in very noisy environment.

• The KIPS Transactions:PartC
• /
• v.14C no.3 s.113
• /
• pp.209-220
• /
• 2007

IPS(Intrusion Prevention Systems), which is installed in inline mode in a network, protects network from outside attacks by inspecting the incoming/outgoing packets and sessions, and dropping the packet or closing the sessions if an attack is detected in the packet. In the signature based filtering, the payload of a packet passing through IPS is matched with some attack patterns called signatures and dropped if matched. As the number of signatures increases, the time required for the pattern matching for a packet increases accordingly so that it becomes difficult to develop a high performance US working without packet delay. In this paper, we propose a high performance IPS based on signature hashing to make the pattern matching time independent of the number of signatures. We implemented the proposed scheme in a Linux kernel module in a PC and tested it using worm generator, packet generator and network performance measure instrument called smart bit. Experimental results show that the performance of existing method is degraded as the number of signatures increases whereas the performance of the proposed scheme is not degraded.

• The KIPS Transactions:PartA
• /
• v.13A no.1 s.98
• /
• pp.45-52
• /
• 2006

To perform on-line maintenance for Distributed Information System, it is indispensable to disseminate files to participant nodes in the network. When users' requests for file deployment occur simultaneously in a short period a deployment server falls into overload phase, which is often called Flash Crowds. h common solution to avoid Flash Crowds is to increase hardware capacity. In this paper, we propose a software solution based on P2P, which does not cost any additional expense. In the proposed solution, nodes in the network are grouped into subnetworks one of which is composed of only neighboring nodes. In each subnetwork, copies of deployment files can be transferred to each other. Consequently, it brings about the effect of load balancing in deployment server. To raise the effectiveness, target files for deployment are packed into one package. Before being transferred, each package is divided into multiple equal-sized segments. A deployment server in a normal phase transmits a package requested from nodes in segment units. However a deployment server is overloaded, if segments already exist in the subnetwork participant nodes in the subnetwork receive necessary segments from neighboring nodes. In this paper, we propose data structures and algorithm for this approach and show performance improvement through simulation.

• Journal of Astronomy and Space Sciences
• /
• v.26 no.4
• /
• pp.567-588
• /
• 2009

Korea-Japan Joint VLBI Correlator (KJJVC) is being developed by collaborating KASI (Korea Astronomy and Space Science Institute), Korea, and NAOJ(National Observatory of Japan), Japan. In early 2010, KJJVC will work in normal operation. In this study, we developed the software correlator which is based on VCS (VLBI Correlation Subsystem) hardware specification as the core component of KJJVC. The main specification of software correlator is 8 Gbps, 8192 output channels, and 262,144-points FFT (Fast Fourier Transform) function same as VCS. And the functional algorithm which is same as specification of VCS and arithmetic register are adopted in this software correlator. To verify the performance of developed software correlator, the correlation experiments were carried out using the spectral line and continuum sources which were observed by VERA (VLBI Exploration of Radio Astrometry), NAOJ. And the experimental results were compared to the output of Mitaka FX correlator by referring spectrum shape, phase rate, and fringe detection and so on. Through the experimental results, we confirmed that the correlation results of software correlator are the same as Mitaka FX correlator and verified the effectiveness of it. In future, we expect that the developed software correlator will be the possible software correlator of KVN (Korean VLBI Network) with KJJVC by introducing the correlation post-processing and modifying the user interface as like GUI (Graphic User Interface).