• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.33-50
• /
• 1990

Recently, neural networks have been proposed as computaional models for hard prlblems that the brain appears to solve easily. This paper proposes a hierarchical network which practically recognizes printed Hangul characters based on the various psychological stueies. This system is composed of a type classification netwotk and six recognition networks. The former clessifier input character images into one of the six thper by their overall sturcture, and the latter further classify them into character code. Extperiments with most frequently used 990 printed hangul characters conform the superiority of the propsed system. After all, neural nework approach turns out to be very reasonable through a comparison with statistical classifier and an analysis of mis-classification and generalization capability.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.4
• /
• pp.753-760
• /
• 2012

This paper is to show the character coding rule in computer and information equipment etc to improve the transmission efficiency in telecommunications. In the transmission system, the transmission efficiency can be increased by applying the proper character coding method. In datalink layer, HDSL ptotocol use FLAG byte to identify the frame to frame which consists of data bit stream and other control bytes. FLAG byte constits of "01111110". When data bit stream consist of the consecutive 5-bit "1" after "0", the decoder can not distinguish whether the data bit sequence is flag bit stream or data bit stream. To solve the problem, when the line coder in transmitter detects the consecutive 5-bits "1" after "0" in the input data stream, inserts violently the "0" after 5th "1" of the consecutive 5-bit "1" after "0". As a result, when the characters are decoded with the above procedure, the efficiency of system should be decreased. This paper shows the character code rule to minimize the consecutive 5-bits "1" after "0" when the code is given to each characters.

• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.11-20
• /
• 2014

This paper finds that the ultimate source of problems facing Korean mobile telecommunications such as excessive subsidies of handsets, waste of resources, and a vicious circle of expensive handsets and high prices for services, is bundling of handset and subscription. The analysis suggests that bundling causes consumers to confuse about prices of handsets and services, and firms focus on handset subsidy competition rather than on upgrading service qualities and lowering prices due to anti-competitive effects of bundling. Because most of the cost of bundling is passed on to consumers, the welfare of consumers decline. In particular, equality among consumers worsens due to price discriminations. To resolve these problems, unbundling of handset and subscription is a necessity. Mixed bundling allowing separate selling of handsets under bundling does not seem to work as a cure because bundling tends to be a dominant strategy. The best regulatory policy is a complete separation of handset and subscription.

• Phonetics and Speech Sciences
• /
• v.12 no.1
• /
• pp.11-17
• /
• 2020

Non-tonal language speakers may have difficulty learning second language lexical tones. In the present study, we explored this issue with Korean-speaking learners of Mandarin Chinese (i.e., non-tonal first language speakers) by examining their perception and production of Mandarin lexical tones. In the perception experiment, the Korean learners were asked to listen to the tone of each stimulus and assign it to one of four Mandarin lexical tones using the response keys; in the production experiment, the learners provided speech production data for the lexical tones and then their productions were identified by native listeners of Mandarin Chinese. Our results showed that the Korean learners of Mandarin Chinese had difficulty in perceptually distinguishing Tone 2 and Tone 3, with the most frequent production error being the mispronunciation of Tone 3 as Tone 2. We also investigated whether unfamiliar non-native phonemes (i.e., Chinese phonemes) that do not exist in the native language phonemic inventory (i.e., Korean) may hinder the processing of the non-native lexical tones. We found no evidence for such effects, neither for the perception nor for the production of the tones.

• Journal of Navigation and Port Research
• /
• v.38 no.2
• /
• pp.105-110
• /
• 2014

Korean government sets up a goal that jumps up to the third ranked powerful nation of offshore wind in the world until 2020 and announced "The plan for 2.5-gigawatt wind farm off the south-west coast by 2019". Such above, according to green energy policy, offshore wind farms(OWF) will be increased continuously. The development of OWF should be taken account of wind volume as well as marine traffic environment. Specially aids to navigation of OWF play a significant role in preventing collision between vessels navigating near waters and structures. For purpose of distinguishing OWF, IALA recommendations define installation of lights on SPS and IPS. However, there is no mention of light character that plays important role in identification of lights as marking offshore wind farm. Also the research on selection of proper light character has been insufficient state. Therefore in this paper, we analyzed internal and external regulations concerned marking with light on SPS and IPS in OWF. And suggested patterns and rhythms of light having not only easily recognized feature but also no confusion with other light of aids to navigation. The proposed light characters were verified by simulation, and the results were analysed that synchronism flickering of "Fl Y(4) 12s(SPS)" and "Fl Y 6s(IPS)" would be useful in combination of both lights.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.405-414
• /
• 2011

Korean grammar checkers typically detect context-dependent errors by employing heuristic rules that are manually formulated by a language expert. These rules are appended each time a new error pattern is detected. However, such grammar checkers are not consistent. In order to resolve this shortcoming, we propose new method for generalizing error decision rules to detect the above errors. For this purpose, we use an existing thesaurus KorLex, which is the Korean version of Princeton WordNet. KorLex has hierarchical word senses for nouns, but does not contain any information about the relationships between cases in a sentence. Through the Tree Cut Model and the MDL(minimum description length) model based on information theory, we extract noun classes from KorLex and generalize error decision rules from these noun classes. In order to verify the accuracy of the new method in an experiment, we extracted nouns used as an object of the four predicates usually confused from a large corpus, and subsequently extracted noun classes from these nouns. We found that the number of error decision rules generalized from these noun classes has decreased to about 64.8%. In conclusion, the precision of our grammar checker exceeds that of conventional ones by 6.2%.

• Journal of the Korean Society for Library and Information Science
• /
• v.46 no.4
• /
• pp.169-188
• /
• 2012

This study aimed to analyze the characteristics of the bibliographic description of ISBD Consolidated edition published in 2011 and to grasp the considerations in applying the rules of ISBD consolidated edition to KCR4. For achieving this, the four aspects were analyzed such as the description area and data elements, the resource types, the punctuation, and the order of the elements of ISBD Consolidated edition(2011). The characteristics of ISBD Consolidated edition are as follows. First, the content form and the media type area are added in new 0 area and elements are designated by mandatory to confirm to FRBR. Second, content form, content qualification and media type replaced GMD in title and statement of responsibility area. Third, the prescribed punctuations were retained even when this results in double punctuation, and individual square brackets were preferred than entire square brackets when using square brackets to all elements in same area. Fourth, the order of elements in description was set out by patterns of data elements in areas, therefore could reduce the confusion of the order of elements. ISBD Consolidated edition as an international standard would make various rules to maintain the uniformity, but also respects the bibliographic practices of individual countries. Therefore, each country must revise its own rule to conform the ISBD Consolidated edition as well as reflect its unique situation. In Korea, since KCR4 was developed based on the previous edition of ISBD, it should be revised to confirm to the ISBD Consolidated edition. Therefore, this study is expected to contribute to the revision of KCR4.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.3
• /
• pp.182-196
• /
• 2023

Accurate and timely estimation of crop yields is crucial for various purposes, including global food security planning and agricultural policy development. Remote sensing techniques, particularly using vegetation indices (VIs), have show n promise in monitoring and predicting crop conditions. However, traditional VIs such as the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) have limitations in capturing rapid changes in vegetation photosynthesis and may not accurately represent crop productivity. An alternative vegetation index, the near-infrared reflectance of vegetation (NIRv), has been proposed as a better predictor of crop yield due to its strong correlation with gross primary productivity (GPP) and its ability to untangle confounding effects in canopies. In this study, we investigated the potential of NIRv in estimating crop yield, specifically for corn and soybean crops in major crop-producing regions in 14 states of the United States. Our results demonstrated a significant correlation between the peak value of NIRv and crop yield/area for both corn and soybean. The correlation w as slightly stronger for soybean than for corn. Moreover, most of the target states exhibited a notable relationship between NIRv peak and yield, with consistent slopes across different states. Furthermore, we observed a distinct pattern in the yearly data, where most values were closely clustered together. However, the year 2012 stood out as an outlier in several states, suggesting unique crop conditions during that period. Based on the established relationships between NIRv peak and yield, we predicted crop yield data for 2022 and evaluated the accuracy of the predictions using the Root Mean Square Percentage Error (RMSPE). Our findings indicate the potential of NIRv peak in estimating crop yield at the county level, with varying accuracy across different counties.

• Economic and Environmental Geology
• /
• v.49 no.1
• /
• pp.1-11
• /
• 2016

Chrysotile is well known as a fibrous mineral in serpentinite by the previous studies in S. Korea. Previous studies in other countries showed that antigorite also occurred as asbestiform and harmful to humans. Therefore, the objective of this study was to investigate types and characteristics of fibrous serpentine minerals occurred in serpentinite in Hongseong, Chungnam and Gapyeong, Gyeonggi in S. Korea. XRD, SEM-EDS, PLM and EPMA mapping analyses were used to examine the occurrence and formation mechanism of serpentine minerals. Serpentinization partially occurred in amphibole-schist and calc-schist at two study sites, Hongseong, Chungnam and Gapyeong, Gyeonggi, respectively. Both chrysotile and antigorite occurred as a fibrous mineral at Hongseong site, but chrysotile occurred as a fibrous mineral at Gapyeong site. Based on PLM analysis with dispersion staining, the chrysotile was observed horizontally magenta and vertically blue colors. The antigorite appeared as horizontally gold to golden magenta and vertically blue magenta colors under central stop dispersion staining objective(DSO). PLM and SEM analyses showed the fibrous minerals were formed from plate form of serpentine minerals or by hydrothermal alternation of primary minerals. The EPMA mapping showed that Mg contents in chrysotile is relatively higher than that in antigorite while Si and O contents in antigorite is higher than them in chrysotile. However, more studies are necessary to know the exact variation in chemical composition of chrysotile and antigorite. These results indicate that even though asbestiform antigorite found associated with asbestos chrysotile in serpentinites, the fibrous antigorite can be distinguished from chrysotile by different dispersion staining colors.