• ETRI Journal
• /
• 제46권1호
• /
• pp.22-34
• /
• 2024

Exposure to varied noisy environments impairs the recognition performance of artificial intelligence-based speech recognition technologies. Degraded-performance services can be utilized as limited systems that assure good performance in certain environments, but impair the general quality of speech recognition services. This study introduces an audiovisual speech recognition (AVSR) model robust to various noise settings, mimicking human dialogue recognition elements. The model converts word embeddings and log-Mel spectrograms into feature vectors for audio recognition. A dense spatial-temporal convolutional neural network model extracts features from log-Mel spectrograms, transformed for visual-based recognition. This approach exhibits improved aural and visual recognition capabilities. We assess the signal-to-noise ratio in nine synthesized noise environments, with the proposed model exhibiting lower average error rates. The error rate for the AVSR model using a three-feature multi-fusion method is 1.711%, compared to the general 3.939% rate. This model is applicable in noise-affected environments owing to its enhanced stability and recognition rate.

• 폴리머
• /
• 제32권3호
• /
• pp.193-198
• /
• 2008

시부트라민은 비만을 치료하기 위한 식욕억제제로서 높은 결정성을 갖는 난용성 약물이다. 이러한 난용성 약물의 용해도를 증가시키기 위하여 고체분산법을 바탕으로 한 분무건조기를 이용하여 미립구를 제조할 수 있었다. 제조된 미립구는 주사전자현미경을 이용하여 제조시 사용한 용매에 따른 미립구 형태차이를 확인할 수 있었으며 용매증발 속도가 빠를수록 구형을 이루는 것을 확인할 수 있었다. X선 회절기를 이용하여 제조된 미립구에서 시부트라민의 결정성이 10%이하로 감소되었음을 확인하였다. 제조된 미립구는 pH 1.2와 pH 6.8에서 방출을 실시하였으며 시부트라민이 pH에 따라서 용해도 차이가 크다는 것을 확인하였다. 또한, 경필 캡슐을 이용한 것이 정제형태보다 방출이 약 4배 정도 빠르다는 것을 확인할 수 있었다. 이러한 결과를 바탕으로 제형의 형태에 따라 방출거동이 조절될 수 있음을 확인하였다.

• 한국해양공학회지
• /
• 제24권3호
• /
• pp.46-51
• /
• 2010

This paper describes the implementation of a precise underwater navigation solution using a multi-sensor fusion technique based on USBL, DVL, and IMU measurements. To implement this precise underwater navigation solution, three strategies are chosen. The first involves heading alignment angle identification to enhance the performance of a standalone dead-reckoning algorithm. In the second, the absolute position is found quickly to prevent the accumulation of integration error. The third one is the introduction of an effective outlier rejection algorithm. The performance of the developed algorithm was verified with experimental data acquired by the deep-sea ROV, Hemire, in the East-sea during a survey of a methane gas seepage area at a 1,500 m depth.

• 한국환경과학회:학술대회논문집
• /
• 한국환경과학회 2020년도 정기학술대회 발표논문집
• /
• pp.214-214
• /
• 2020

• 한국산학기술학회논문지
• /
• 제19권3호
• /
• pp.601-613
• /
• 2018

본 연구는 스마트시티 공간에 적용된 디바이스/기술과 아티팩트의 융합유형을 도출 하는데 목적을 두고 있다. 주요연구 내용은 스마트시티에 적용된 환경기술(ET), 정보기술(IT), 환경 정보기술(ET+IT)의 융합 변화에 관한 심층 분석 이다. 연구결과는 다음과 같다. 첫째, 31개의 사례분석을 통해 디바이스/기술과 아티팩트를 아래와 같이 도출 하였다. 아티팩트는 총 92개, 디바이스/기술은 환경기술 중심에서 83개, 정보기술 중심에서 51개, 총 134개 디바이스/기술 이다. 둘째, 디바이스/기술과 아티팩트 간의 융합 변화는 7개 유형에 의해 진화하고 있다. 유형1, 'ET중심의 진화형' 은 1기(분리융합), 2기(ET중심융합), 3기(ET중심으로 IT성장과 ET+IT융합) 이다. 유형2, 'ET+IT중심의 ET고도화형'은 1기(초기 ET+IT융합), 2기(ET 고도화, IT보조융합), 3기(ET 초고도화, IT보조융합) 이다. 유형3, 'ET+IT 일체화형'은 1기(ET, IT 개별융합), 2기(ET+IT 혼합융합), 3기(ET+IT 일체화 융합) 이다. 유형4, 'IT중심의 진화형'은 1기(IT중심으로 개발), 2기(IT중심의 고도화), 3기(IT중심의 초고도화) 이다. 유형5 6, 'ET+IT 동반 고도화형'은 1기(ET+IT중심의 IT개발), 2기(ET+IT중심의 IT고도화), 3기(ET+IT중심의 IT 초고도화) 이다. 유형7, 'ET+IT중심의 IT고도화형'은 1기(초기 ET+IT융합), 2기(ET보조융합, IT고도화), 3기(ET 보조융합, IT 초고도화) 이다. 본 결과는 향후 다양한 새로운 융합유형이 도출될 것이라 예상 된다.

• 전자공학회논문지SC
• /
• 제49권2호
• /
• pp.55-62
• /
• 2012

정보기술과 의료기기의 융합에 의해 혈당을 집에서 측정하거나 운동 시에 심박수를 측정하는 것과 같이 건강관련 정보를 언제 어디서나 측정할 수 있게 되었고, 이에 따라 의료를 장소에 구애받지 않고 쉽게 접근할 수 있게 되었다. 최근에 유헬스케어 의료기기 시장이 빠르게 성장하고 있으나 이러한 기기의 안전성과 유효성을 평가하는 가이드라인이 아직 마련되지 않은 실정이다. 이를 위해 식약청, ISO/IEEE, CE 등 국내외의 유헬스케어 관련 규정을 조사하고, 이 중 유헬스케어 의료기기에 관련된 안정성 및 성능 평가에 대한 시험 방법과 항목을 제안하였다. 유헬스케어 의료기기의 가장 큰 특성인 무선 데이터 통신에 있어 데이터 무결성과 기기 사용환경이 다양하기 때문에 환경 요인이 기기에 미치는 영향을 평가하였다. 이를 바탕으로 휴대형 유헬스케어 의료기기의 평가 가이드라인을 제안하였다. 제안하는 지침을 기반으로 휴대형 유헬스케어 기기를 개발한다면 사용자들에게 보다 안전성과 신뢰도 높은 기기를 제공할 수 있을 것으로 기대된다.

• 한국자동차공학회논문집
• /
• 제22권6호
• /
• pp.14-22
• /
• 2014

An autonomous vehicle requires a technology of generating maps by recognizing surrounding environment. The recognition of the vehicle's environment can be achieved by using distance information from a 2D laser scanner and color information from a camera. Such sensor information is used to generate 2D or 3D maps. A 2D map is used mostly for generating routs, because it contains information only about a section. In contrast, a 3D map involves height values also, and therefore can be used not only for generating routs but also for finding out vehicle accessible space. Nevertheless, an autonomous vehicle using 3D maps has difficulty in recognizing environment in real time. Accordingly, this paper proposes the technology for generating 2D maps that guarantee real-time recognition. The proposed technology uses only the color information obtained by removing height values from 3D maps generated based on the fusion of 2D laser scanner and camera data.

• 패션비즈니스
• /
• 제14권6호
• /
• pp.70-83
• /
• 2010

With the rapid development of science and technology and the increased preference by consumers for high-function products, many products are being developed through the fusion of technologies in different industries. Among such fusion technologies, digital clothing which combines clothing with computer functions is being examined as a new growth item. The objectives of this study are to examine the concept, history, development, and market of intelligent clothing, in order to discuss future directions for the development of digital clothing technology. intelligent clothing (wearable computers) originated in the 1960s from the concept of separating computing equipment and attaching it to the body. This technology was studied intensively from the early 1980s and to the early 1990s. In the late 1990s, studies on wearable computers began to develop intelligent/digital clothing that was more comfortable and beneficial to users. Depending on the user and purpose, intelligent/digital clothing is now being developed and used in diverse industrial areas that include sports, medicine, military, entertainment, daily life, and business. Many experts forecast a huge growth potential for the digital textile/clothing market, and predict the fastest market growth in the field of healthcare/medicine. There exists a need to find solutions for many related technological, economic, and social issues for the steady dissemination and advancement of intelligent/digital clothing in various industries. Further, research should be continued on effective fusion technologies that reflect human sensitivity and that increase user convenience and benefits.

• 한국분말재료학회지
• /
• 제26권1호
• /
• pp.11-15
• /
• 2019

In this study, a method to remove residual powder on a multi-layered graphene and a new approach to transfer multi-layered graphene at once are studied. A graphene one-step transfer (GOST) method is conducted to minimize the residual powder comparison with a layer-by-layer transfer. Furthermore, a residual powder removing process is investigated to remove residual powder at the top of a multi-layered graphene. After residual powder is removed, the sheet resistance of graphene is decreased from 393 to 340 Ohm/sq in a four-layered graphene. In addition, transmittance slightly increases after residual powder is removed from the top of the multi-layered graphene. Optical and atomic-force microscopy images are used to analyze the graphene surface, and the Ra value is reduced from 5.2 to 3.7 nm following residual powder removal. Therefore, GOST and residual powder removal resolve the limited application of graphene electrodes due to residual powder.

• BMB Reports
• /
• 제32권5호
• /
• pp.486-491
• /
• 1999

An engineered cDNA from Phanerochaete chrysosporium encoding both the mature and propeptide-sequence regions of lignin peroxidase H2 (Lip H2) was overexpressed in Escherichia coli BL21 (DE3) to evaluate its catalytic characteristics and potential application as a pollution scavenger. All expressed proteins were aggregated in an inactive inclusion body, which might be due to inherent disulfide bonds. Active enzyme was obtained by refolding with glutathione-mediated oxidation in refolding solution containing $Ca^{2+}$, heme, and urea. Propeptide-sequence region was not processed as evidenced by N-terminal sequence analysis. Recombinant Lip H2 (rLip H2) had the same physical properties of the native protein but differed in the $K_{cat}$. Catalytic efficiency ($k_{cat}/K_m$) of rLip H2 was slightly higher than that of the native enzyme. In order to express an active protein, fusion systems with thioredoxin or Dsb A, which have disulfide isomerase activity, were used. The fused proteins expressed by the Dsb A fusion vector were aggregated, whereas half of the thioredoxin fusion proteins were recovered as a soluble form but still catalytically inactive. These results suggest that Lip H2 may not be expressed as an active enzyme in Escherichia coli although the activity can be recovered by in vitro refolding.