• Title/Summary/Keyword: Domain Adaptation

Search Result 154, Processing Time 0.019 seconds

Domain Adaptation Method for LHMM-based English Part-of-Speech Tagger (LHMM기반 영어 형태소 품사 태거의 도메인 적응 방법)

  • Kwon, Oh-Woog;Kim, Young-Gil
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.16 no.10
    • /
    • pp.1000-1004
    • /
    • 2010
  • A large number of current language processing systems use a part-of-speech tagger for preprocessing. Most language processing systems required a tagger with the highest possible accuracy. Specially, the use of domain-specific advantages has become a hot issue in machine translation community to improve the translation quality. This paper addresses a method for customizing an HMM or LHMM based English tagger from general domain to specific domain. The proposed method is to semi-automatically customize the output and transition probabilities of HMM or LHMM using domain-specific raw corpus. Through the experiments customizing to Patent domain, our LHMM tagger adapted by the proposed method shows the word tagging accuracy of 98.87% and the sentence tagging accuracy of 78.5%. Also, compared with the general tagger, our tagger improved the word tagging accuracy of 2.24% (ERR: 66.4%) and the sentence tagging accuracy of 41.0% (ERR: 65.6%).

Comparison of structure, function and regulation of plant cold shock domain proteins to bacterial and animal cold shock domain proteins

  • Chaikam, Vijay;Karlson, Dale T.
    • BMB Reports
    • /
    • v.43 no.1
    • /
    • pp.1-8
    • /
    • 2010
  • The cold shock domain (CSD) is among the most ancient and well conserved nucleic acid binding domains from bacteria to higher animals and plants. The CSD facilitates binding to RNA, ssDNA and dsDNA and most functions attributed to cold shock domain proteins are mediated by this nucleic acid binding activity. In prokaryotes, cold shock domain proteins only contain a single CSD and are termed cold shock proteins (Csps). In animal model systems, various auxiliary domains are present in addition to the CSD and are commonly named Y-box proteins. Similar to animal CSPs, plant CSPs contain auxiliary C-terminal domains in addition to their N-terminal CSD. Cold shock domain proteins have been shown to play important roles in development and stress adaptation in wide variety of organisms. In this review, the structure, function and regulation of plant CSPs are compared and contrasted to the characteristics of bacterial and animal CSPs.

Stereoscopic 3D Video Editing Method for Visual Comfort (시각적 편안함을 위한 입체적 삼차원 영상 편집 방법)

  • Kim, Jung-Un;Kang, Hang-Bong
    • Journal of Korea Multimedia Society
    • /
    • v.19 no.4
    • /
    • pp.706-716
    • /
    • 2016
  • Each year, significant amounts of Stereoscopic 3D(S3D) contents have been introduced. However, viewers who enjoy the contents readily experience a sense of fatigue on account of various factors. Consequently, many improvement studies have been conducted with the domain of disparity by, for example, simply controlling the disparity or optimizing the reaction speed of viewers' eyes to vergence. However, such studies are limited to the disparity domain and therefore are restricted to a limited number of applications. In this study, we attempted to transcend this limitation and analyzed how a reconstruction in color and brightness, as well as disparity and other important features, affects eyes in terms of vergence adaptation. As a result, we found that, the higher the color similarity is, the better it positively affects vergence adaptation during viewing. Based on this analysis, we propose in this paper a similar color extraction method between takes that are applicable to real-life situations. In an evaluation, the algorithm was applied to publicly available S3D contents and produced a converted color optimized image. The vergence adaptation time of this applied contents was significantly decreased. Also it was minimized through color reconstruction, thereby, being resulted in enhancing viewer concentration.

The Korean language version of Stroke Impact Scale 3.0: Cross-cultural adaptation and translation

  • Lee, Hae-jung;Song, Ju-min
    • Journal of the Korean Society of Physical Medicine
    • /
    • v.10 no.3
    • /
    • pp.47-55
    • /
    • 2015
  • PURPOSE: Stoke is one of most common disabling conditions and it is still lacking of measuring patient's functioning level. The aim of the study was to develop Korean language version of stroke impact scale 3.0. METHODS: Korean version of stroke impact scale 3.0 was developed in idiomatic modern Korean with a standard protocol of multiple forward and backward translations and an expert reviews to achieve equivalence with the original English version. Interviews with clinicians who were currently managing patients with stroke were also conducted for language evaluation. A reliability test was performed to make final adaptation using a pre-final version. To assess the reliability of the translated questionnaire, the intraclass correlation coefficient (ICC) was calculated for each domain of the scale. RESULTS: Thirty subjects (16 male, 14 female) aged from 20 to 75 years old participated to review the translated questionnaire. Reliability of each domain of the questionnaire was found to be good in strength (ICC=0.74), ADL (ICC=0.81), mobility (ICC=0.90), hand function (ICC=0.80) and social participation (ICC=0.79), communication (ICC=0.77) with total (ICC=0.76). However, domains of memory and thinking (ICC=0.66), and emotion (ICC=0.27) and showed poor reliability. CONCLUSION: This study indicates that the Korean version of SIS 3.0 was successfully developed. Future study needed for obtaining the validity of the Korean version of SIS 3.0.

Frequency Analysis of Adaptive Behavior of NEAT based Control for Snake Modular Robot (뱀형 모듈라 로봇을 위한 NEAT 기반 제어의 적응성에 대한 주파수 분석)

  • Lee, Jaemin;Seo, Kisung
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.64 no.9
    • /
    • pp.1356-1362
    • /
    • 2015
  • Modular snake-like robots are robust for failure and have flexible locomotions for obstacle environment than of walking robot. This requires an adaptation capability which is obtained from a learning approach, but has not been analysed as well. In order to investigate the property of adaptation of locomotion for different terrains, NEAT controllers are trained for a flat terrain and tested for obstacle terrains. The input and output characteristics of the adaptation for the neural network controller are analyzed for different terrains in frequency domain.

Evidence-based Clinical Practice Protocol of Physical Restraints by Adaptation Process for Patients in a Geriatric Hospital (요양병원 입원 노인을 위한 신체 억제대 프로토콜의 수용개작)

  • Park, Mi Hwa;Sohng, Kyeong-Yae
    • The Korean Journal of Rehabilitation Nursing
    • /
    • v.19 no.2
    • /
    • pp.118-127
    • /
    • 2016
  • Purpose: This study was to develop an evidence-based clinical practice protocol of physical restraints by adaptation process for patients with a geriatric hospital. Methods: Protocol adaptation process was conducted in accordance with manual for guideline adaptation version 1.0 by ADAPTE collaboration. Results: The adapted physical restraint protocol was consisted of 3 domains and 37 recommendations. The number of recommendations in each domain were: 7 nursing assessment, 19 nursing intervention, and 11 nursing evaluation. More than half (56.8%) of the recommendations were rated as grade B, 37.8% as grade C, and 5.4% were rated as grade D. Conclusion: The adapted physical restraint protocol is expected to contribute as an evidence-based clinical practice protocol for healthcare workers in geriatric hospitals for reducing and improving efficiency of appropriate physical restraints use.

Spontaneous Speech Language Modeling using N-gram based Similarity (N-gram 기반의 유사도를 이용한 대화체 연속 음성 언어 모델링)

  • Park Young-Hee;Chung Minhwa
    • MALSORI
    • /
    • no.46
    • /
    • pp.117-126
    • /
    • 2003
  • This paper presents our language model adaptation for Korean spontaneous speech recognition. Korean spontaneous speech is observed various characteristics of content and style such as filled pauses, word omission, and contraction as compared with the written text corpus. Our approaches focus on improving the estimation of domain-dependent n-gram models by relevance weighting out-of-domain text data, where style is represented by n-gram based tf/sup */idf similarity. In addition to relevance weighting, we use disfluencies as Predictor to the neighboring words. The best result reduces 9.7% word error rate relatively and shows that n-gram based relevance weighting reflects style difference greatly and disfluencies are good predictor also.

  • PDF

Regulation and Function of the Peg3 Imprinted Domain

  • He, Hongzhi;Kim, Joomyeong
    • Genomics & Informatics
    • /
    • v.12 no.3
    • /
    • pp.105-113
    • /
    • 2014
  • A subset of mammalian genes differ functionally between two alleles due to genomic imprinting, and seven such genes (Peg3, Usp29, APeg3, Zfp264, Zim1, Zim2, Zim3) are localized within the 500-kb genomic interval of the human and mouse genomes, constituting the Peg3 imprinted domain. This Peg3 domain shares several features with the other imprinted domains, including an evolutionarily conserved domain structure, along with transcriptional co-regulation through shared cis regulatory elements, as well as functional roles in controlling fetal growth rates and maternal-caring behaviors. The Peg3 domain also displays some unique features, including YY1-mediated regulation of transcription and imprinting; conversion and adaptation of several protein-coding members as ncRNA genes during evolution; and its close connection to human cancers through the potential tumor suppressor functions of Peg3 and Usp29. In this review, we summarize and discuss these features of the Peg3 domain.

SINGLE PANORAMA DEPTH ESTIMATION USING DOMAIN ADAPTATION (도메인 적응을 이용한 단일 파노라마 깊이 추정)

  • Lee, Jonghyeop;Son, Hyeongseok;Lee, Junyong;Yoon, Haeun;Cho, Sunghyun;Lee, Seungyong
    • Journal of the Korea Computer Graphics Society
    • /
    • v.26 no.3
    • /
    • pp.61-68
    • /
    • 2020
  • In this paper, we propose a deep learning framework for predicting a depth map of a 360° panorama image. Previous works use synthetic 360° panorama datasets to train networks due to the lack of realistic datasets. However, the synthetic nature of the datasets induces features extracted by the networks to differ from those of real 360° panorama images, which inevitably leads previous methods to fail in depth prediction of real 360° panorama images. To address this gap, we use domain adaptation to learn features shared by real and synthetic panorama images. Experimental results show that our approach can greatly improve the accuracy of depth estimation on real panorama images while achieving the state-of-the-art performance on synthetic images.