• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.145-152
• /
• 2007

In this paper, we propose an automatic extraction model for unknown translations and implement an unknown translation extraction system using the proposed model. The proposed model as a phrase-alignment model is incorporated with three models: a phrase-boundary model, a language model, and a translation model. Using the proposed model we implement the system for extracting unknown translations, which consists of three parts: construction of parallel corpora, alignment of Korean and English words, extraction of unknown translations. To evaluate the performance of the proposed system, we have established the reference corpus for extracting unknown translation, which comprises of 2,220 parallel sentences including about 1,500 unknown translations. Through several experiments, we have observed that the proposed model is very useful for extracting unknown translations. In the future, researches on objective evaluation and establishment of parallel corpora with good quality should be performed and studies on improving the performance of unknown translation extraction should be kept up.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.911-921
• /
• 2004

Accurate minutiae extraction from input fingerprint images is one of the critical modules in robust automatic fingerprint identification system. However, the performance of a minutiae extraction is heavily dependent on the quality of the input fingerprint images. If the preprocessing is performed according to the fingerprint image characteristics in the image enhancement step, the system performance will be more robust. In this paper, we propose a knowledge-based preprocessing method, which extracts S features (the mean and variance of gray values, block directional difference, orientation change level, and ridge-valley thickness ratio) from the fingerprint images and analyzes image quality with Ward's clustering algorithm, and enhances the images with respect to oily/neutral/dry characteristics. Experimental results using NIST DB 4 and Inha University DB show that clustering algorithm distinguishes the image Quality characteristics well. In addition, the performance of the proposed method is assessed using quality index and block directional difference. The results indicate that the proposed method improves both the quality index and block directional difference.

• 한국신재생에너지학회:학술대회논문집
• /
• 2008.05a
• /
• pp.479-482
• /
• 2008

Since late of 2000, KIER has developed a novel pyrolysis process for production of fuel oils from polymer wastes. It could have been possible due to large-scale funding of the Resource Recycling R&D Center. The target was to develop an uncatalyzed, continuous and automatic process producing oils that can be used as a fuel for small-scale industrial boilers. The process development has proceeded in three stages bench-scale unit, pilot plant and demonstration plant. As a result, the demonstration plant having capacity of 3,000 tons/year has been constructed and is currently under test operation for optimization of operation conditions. The process consisted of four parts ; feeding system, cracking reactor, refining system and others. Raw materials were pretreated via shredding and classifying to remove minerals, water, etc. There were 3 kind of products, oils(80%), gas(15%), carbonic residue(5%). The main products i.e. oils were gasoline and diesel. The calorific value of gas has been found to be about 18,000kcal/$m^3$ which is similar to petroleum gas and shows that it could be used as a process fuel. Key technologies adopted in the process are 1) Recirculation of feed for rapid melting and enhancement of fluidity for automatic control of system, 2) Tubular reactor specially-designed for heavy heat flux and prevention of coking, 3)Recirculation of heavy fraction for prevention of wax formation, and 4) continuous removal & re-reaction of sludge for high yield of main product (oil) and minimization of residue. The advantages of the process are full automation, continuous operation, no requirement of catalyst, minimization of coking and sludge problems, maximizing the product(fuel oil) yield and purity, low initial investment and operation costs and environment- friendly process. In this presentation, background of pyrolysis technology development, the details of KIER pyrolysis process flow, key technologies and the performances of the process will be discussed in detail.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.7
• /
• pp.484-490
• /
• 2018

This paper describes an algorithm for calculating load impedance by measuring voltage and current components using a VI sensor in a 13.56 MHz impedance automatic matching system. We propose an algorithm that improves the error rate by using an arbitrary complex calibration load instead of the conventional $50{\Omega}$ calibration load. The error rate is targeted to attain average values of $R_{IN}$ and $X_{IN}$ at 1% and 20% or less, respectively. First, the IF frequency is calculated using a mixer to reduce the error rate. Second, when the arbitrary complex load is used as the calibration load, the error rate $R_{IN}$ decreased from 4.7 % to 0.3 % on average, and $X_{IN}$ decreased from 102 % to 18.3 % on average.

• The Journal of the Korea Contents Association
• /
• v.7 no.12
• /
• pp.333-345
• /
• 2007

In the recent years, the companies have manually recorded a production status in a work diary or have mainly used a bar code in order to collect each process's progress status, production performance and quality information in the production and logistics process in real time. But, it requires an additional work because the worker's record must be daily checked or the worker must read it with the bar code scanner. At this time, data's accuracy is decreased owing to the worker's intention or mistake, and it causes the problem of the system's reliability. Accordingly, in order to solve such problem, the companies have introduced RFID which comes into the spotlight in the latest automatic identification field. RFID is an automatic identification technology by radio communication technology that allows us to identify or record information without contacting the corresponding object, and as Gen2 and EPCIS, EPCglobal's standard tag for RFID, have recently been established, it will be introduced to the whole computation industry. This study suggests RFID type Modeling Notation for analyzing logistics flow to improve MES focusing on extended model of EPCIS, and EPCISEvent Template in manufacturing industry.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.6C
• /
• pp.471-479
• /
• 2008

In this paper, we propose a novel algorithm to automatically generate an RTP timestamp value that is required for the RTP packetization in order to transmit SVC video over various If networks such as Internet. Unlike the conventional single layer coding algorithms such as H.263, MPEG-4 and H.264, SVC generates a multi-layered single bitstream which is composed of a base layer and one or more enhancement layers in order to simultaneously provide temporal, spatial, and SNR scalability. Especially, in order to provide temporal scalability based on hierarchical B-picture prediction structure, the encoding (or transmission) and display order of pictures in SVC coding is completely decoupled. Thus, the timestamp value to be specified at the header of each RTP packet in video transmission does not increase monotonically according to the display time instant of each picture. Until now, no method for automatically generating an RTP timestamp when SVC video is loaded in a RTP packet has teen introduced. In this paper, a novel automatic RTP timestamp generation method exploiting the TID (temporal ID) field of the SVC NAL unit header is proposed to accommodate the SVC video transmission.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.3
• /
• pp.265-276
• /
• 2019

In our previous study, the LeNet3 model successfully classified images from the transverse surfaces of five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch). However, a practical limitation exists in our system stemming from the nature of the training images obtained from the transverse plane of the wood species. In real-world applications, it is necessary to utilize images from the longitudinal surfaces of lumber. Thus, we improved our model by training it with images from the longitudinal and transverse surfaces of lumber. Because the longitudinal surface has complex but less distinguishable features than the transverse surface, the classification performance of the LeNet3 model decreases when we include images from the longitudinal surfaces of the five Korean softwood species. To remedy this situation, we adopt ensemble methods that can enhance the classification performance. Herein, we investigated the use of ensemble models from the LeNet and MiniVGGNet models to automatically classify the transverse and longitudinal surfaces of the five Korean softwoods. Experimentally, the best classification performance was achieved via an ensemble model comprising the LeNet2, LeNet3, and MiniVGGNet4 models trained using input images of $128{\times}128{\times}3pixels$ via the averaging method. The ensemble model showed an F1 score greater than 0.98. The classification performance for the longitudinal surfaces of Korean pine and Korean red pine was significantly improved by the ensemble model compared to individual convolutional neural network models such as LeNet3.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.183-188
• /
• 2022

Recently, more and more researches aimed at the development of automated and autonomous ships are appearing in the scientific environment. One of the main reason is the need to solve the problems of safe navigation and reducing accidents due to human factor, as well as the ever-increasing problem associated with the lack of qualified maritime personnel. Development of technologies based on application of artificial intelligence also plays important role, after all for realization of autonomous navigation concept and enhancement of ship automatic maneuvering processes, advancement of maneuvering functions and elaboration of specific algorithms on prevention of close quarter situations and dangerous approach of ships will be required. The purpose of this work is the review of preconditions of occurrence of the autonomous ship navigation conception, overview of introduction stages and prospects for ship remote control based on unmanned technologies, analysis of technical and intellectual decisions of autonomous surface ships, main research tendencies. The research revealed that the technology of autonomous ship navigation requires further development and improvement, especially in terms of the data transmission protocols upgrading, sensors of navigation information and automatic control systems modernization, which allows to perform monitoring of equipment with the aim of improving the functions of control over the autonomous surface ship operation.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.476-483
• /
• 2021

In order to maintain the safety of the airspace with ever increasing traffic volume, it is necessary to thoroughly analyze the collision risk with the current data. In this study, collision risk analysis was conducted using Detect and Avoid (DAA) Well-Clear (DWC) metrics, risk induces developed for the DAA systems of unmanned aerial vehicles. All flights in year 2019 that flew within the Incheon Flight Information Region (FIR) boundary were analyzed using the recorded Automatic Dependent Surveillance-Broadcast(ADS-B) data. High risk regions as well as trends by airports and seasons were identified. The results indicate that the risk is higher around the congested area near Incheon International Airport and Gimpo International Airport. Seasonally, the risk was highest in August that coincides with the Summer vacation period. The result will be useful for the baseline data for various aviation safety enhancement activities such as revision of routes and procedures and training of the field specialists.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.38 no.8
• /
• pp.62-71
• /
• 2001

This paper presents a design of the real-time digital image enhancement preprocessor for CMOS image sensor. CMOS image sensor offers various advantages while it provides lower-quality images than CCD does. In order to compensate for the physical limitation of CMOS sensor, the spatially adaptive contrast enhancement algorithm was incorporated into the preprocessor with color interpolation, gamma correction, and automatic exposure control. The efficient hardware architecture for the preprocessor is proposed and was simulated in VHDL. It is composed of about 19K logic gates, which is suitable for low-cost one-chip PC camera. The test system was implemented on Altera Flex EPF10KGC503-3 FPGA chip in real-time mode, and performed successfully.