• MALSORI
• /
• no.49
• /
• pp.107-121
• /
• 2004

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon to improve the performance of a Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished phonological rules that can be applied to phonemes in within-morpheme and cross-morpheme. The results of 33K-morpheme Korean CSR experiments show that an absolute reduction of 1.45% in WER from the baseline performance of 18.42% WER was achieved by modeling proposed pronunciation variations with a possible multiple context-dependent pronunciation lexicon.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.75-78
• /
• 2003

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon for Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished pronunciation variation rules according to the locations such as within a morpheme, across a morpheme boundary in a compound noun, across a morpheme boundary in an eojeol, and across an eojeol boundary. In 33K-morpheme Korean CSR experiment, an absolute improvement of 1.16％ in WER from the baseline performance of 23.17％ WER is achieved by modeling cross-morpheme pronunciation variations with a context-dependent multiple pronunciation lexicon.

• Korean Institute of Interior Design Journal
• /
• v.20 no.5
• /
• pp.68-77
• /
• 2011

In this research it is concentrated first of all on the attempts to reconstruct the historical context of the idea for the space design based on the natural construction and to re-appropriate il critically to the present context. Sequentially in the areas of philosophy, biology, neuroscience, and architecture it has been variously discussed on the problems about the synthesis of biology and techniques. In the context of the consilience of biology and technique Werner Nachtigall, who has intended to shed light on the morphological principles in the natural construction, founded the 'Bionik', which is different from the bionics or the biomechanics that are oriented to the imitation of natural forms. The space design that is on the basis of the Bionik treats organisms as a functional whole. Therefore the Bionik space design follows two kinds of principle such as the principle of analogy and the principle of optimization. After all the understanding of the consilience of nature and technique for Nachtigall and Bionik designers tends toward the explication of the complex process in which the human perceptions, the environment, and the phenomenal techniques are united together, and this complex process is associated with the space design based on the Bionik.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.10
• /
• pp.1317-1328
• /
• 2001

The existing swearing remover programs could not have blocked even slightly transformed swearings because of their input blocking properties. To overcome these defects, this paper implemented a supervising program which analysize and remove/replace swearings on web board. For this purpose this paper first classified the patterns of swearings on web board and then implemented a tokenizer which can analysize those patterns. The module tokenizing and removing/replacing swearings on each web board was implemented as a thread so that it could be parallely controlled. As a result of running this Program on some web boards , we found out it had detected almost of the swearings as 91.9% of recall but it could not meet our purpose sufficiently on morphological transformed swearings and swearings in context. So the studies will be continued about processing on morphological ambiguous words, ambiguous words in meaning and sweaings in context by extracting this program's manual mode. We expect this program could induce the users to proper usage of words and replace the manual works of web board managers in schools, public bodies, broadcasting stations etc.

• International Journal of High-Rise Buildings
• /
• v.6 no.2
• /
• pp.139-147
• /
• 2017

Analyzing morphological evolution over a long period of time is deemed an effective way to identify problems occurring in the process of urban development, in addition to achieving a fundamental understanding of socio-cultural changes and growth rooted from the context. As far as the urban morphology is concerned, Hong Kong is characterized by its unique high-density and compact layout patterns, which have aroused the interest of a number of authors in the urban design domain. Whilst an increasing number of redevelopment projects in Hong Kong were criticized for ignoring and destroying the old urban fabric, there is a need for research to investigate the origins and changes of various urban patterns and their implications for society. By employing the theories and techniques of space syntax, this paper accordingly provides a morphological analysis based on the Wanchai District - a 'Segment-line' city, which particularly epitomizes various urban grids of Hong Kong and may have different implications for functional aspects. By axial-mapping the urban layouts of five stages of growth since 1842 and subsequently investigating their spatial and functional transformation over the past 170 years, this paper identifies a series of spatial characteristics underlying different grid patterns, as well as achieves a precise understanding of their ever changing relationship. Based on these understandings, this paper intends to provide valuable reference and guidance for upcoming spatial development in Hong Kong and other regions.

• Journal of KIISE:Software and Applications
• /
• v.26 no.1
• /
• pp.178-178
• /
• 1999

Most stochastic taggers can not resolve some morphological ambiguities that can be resolved only by referring to lexical contexts because they use only contextual probabilities based ontag n-grams and lexical probabilities. Existing lexical rules are effective for resolving such ambiguitiesbecause they can refer to lexical contexts. However, they have two limitations. One is that humanexperts tend to make erroneous rules because they are deterministic rules. Another is that it is hardand time-consuming to acquire rules because they should be manually acquired. In this paper, wepropose context-dependent lexical rules, which are lexical rules based on the statistics of a taggedcorpus, and an ambiguity-driven teaming method, which is the method of automatically acquiring theproposed rules from a tagged corpus. By using the proposed rules, the proposed tagger can partiallyannotate an unseen corpus with high accuracy because it is a kind of memorizing tagger that canannotate a training corpus with 100% accuracy. So, the proposed tagger is useful to improve theaccuracy of a stochastic tagger. And also, it is effectively used for detecting and correcting taggingerrors in a manually tagged corpus. Moreover, the experimental results show that the proposed methodis also effective for English part-of-speech tagging.

• Journal of Species Research
• /
• v.4 no.2
• /
• pp.159-168
• /
• 2015

Although airborne pollen is invisible to the eye, it has been known as a major source to respiratory allergic reactions. For this reason, airborne pollen is monitoring in many countries to predict pollen concentration based on locality and season. However, the morphological characteristics of airborne pollen and their potential tendency as an allergen are still obscure. In the present study, we selected 52 airborne pollen samples based on previously reported data and investigated their detail pollen characteristics using LM and SEM. Major airborne pollen in Korea has sorted in 19 families (most angiosperms except four gymnosperm families), and all pollen grains are small to medium in size ($P=17.34-49.86{\mu}m$) apart from the bisaccate pollen grains of Pinaceae ($P=46.49-106.20{\mu}m$). The aperture number and shape vary from sulcate to polyporate. While the inaperture pollen has found only in gymnosperm (Cupressaceae and Taxaceae), triporate or polyporate is common pollen type in angiosperm. The sexine ornamentations could divide into several types, but the most sculpturing types are inconspicuous like psilate, rugulate and granulate. Reticulate pollen grains as a semitectum have occurred the species of genera Platanus and Fraxinus only. To estimate the possible relationships between pollen features and allergen, the results are discussed in botanical context.

• Molecules and Cells
• /
• v.19 no.3
• /
• pp.428-435
• /
• 2005

This study was carried out to assess the potential of SSR markers for variety identification by comparing SSR markers and morphological traits in tests of distinctiveness, uniformity, and stability (DUS) of pepper (Capsicum annuum L.) varieties. Twenty-seven SSR markers were polymorphic in 66 pepper varieties, revealing a total of 89 alleles. Average polymorphism information content (PIC) value was 0.529, ranging from 0.03 to 0.877. Cluster analysis of the band patterns separated the varieties into three groups corresponding to varietal types. Morphological trait-based clustering showed some degree of similarity to dendrogram topologies based on the SSR index. However, no significance correlation was found between the SSR and morphological data. SSR markers could be used to complement a DUS test of a candidate variety and to select complimentary varieties by pre-screening existing varieties in the context of protecting new varieties of pepper.

• Journal of Korea Entertainment Industry Association
• /
• v.5 no.1
• /
• pp.127-133
• /
• 2011

Characters in natural image are an important information with various context. Previous work of character region detection algorithms is not detect of character region in case of image complexity and the surrounding lighting, similar background to character, so this paper propose an method of character region detection in natural image using edge and connected component by morphological reconstructions. Firstly, we detect edge using Canny-edge detector and connected component with local min/max value by morphological reconstructed-operation in gray-scale image, and labeling each of detected connected component elements. lastly, detected candidate of text regions was merged for generation for one candidate text region, Final text region detected by checking the similarity and adjacency of neighbor of text candidate individual character. As the results of experiments, proposed algorithm improved the correctness of character regions detection using edge and connected components.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.121-126
• /
• 2004

An efficient multi face detection technique is proposed based on hierarchical context-free attention operators in which multiple faces are efficiently detected from a noisy and complex background. A noise-tolerant generalized symmetry transform (NTSGT) is applied hierarchically, as a context free attention operator, to the input pyramidal image for the high speed global location of the regions of face candidates (ROFCs) with a single mask. For the face verification, local NTGST is applied within each ROFC to confirm the existence of the detailed facial features. First, by globally applying NTGST which introduces the average pyramid method and focusing to the input image with complex background, ROFCs with recognizable resolution are detected robustly. Morphological operations are applied only to the each detected ROFCs to emphasize the facial features like eyes and lips. Then, eyes are detected by locally appling NTGST to the ROFCs and only faces are detected by verifying the existence of the geometrical features of the faces relatively to the location of eyes. The experimental results show that the proposed method can efficiently detect multiple faces from a noisy or complex background with 93.5% detection rate.