• 한국산학기술학회논문지
• /
• 제8권5호
• /
• pp.1007-1012
• /
• 2007

되먹임 회로로 제어하는 새로운 Michelson형 레이저 간섭계를 제작하여 특성을 평가하였다. 새로운 Michelson형 레이저 간섭계는 압전 특성이 잘 알려진 PZT에 인가된 되먹임 회로의 인가전압을 직접적으로 측정함으로써 미세변위를 측정할 수 있는 간편한 측정 장치이다. 본 연구에서 제작한 Michelson형 레이저 간섭계의 신뢰성과 정밀도를 평가하기 위하여 실리콘 membrane의 단차를 측정한 결과 SEM으로 관찰한 값과 잘 일치함을 알 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제22권8호
• /
• pp.852-859
• /
• 2019

With the development of IT technology and smart devices, various applications utilizing image information are being developed. In order to provide an intuitive interface for pronunciation recognition, there is a growing need for research on pronunciation recognition using mouth feature values. In this paper, we propose a system to distinguish Korean vowel pronunciations by detecting feature points of lips region in images and applying Bayesian based learning model. The proposed system implements the recognition system based on Bayes' theorem, so that it is possible to improve the accuracy of speech recognition by accumulating input data regardless of whether it is speaker independent or dependent on small amount of learning data. Experimental results show that it is possible to effectively distinguish Korean vowels as a result of applying probability based Bayesian classification using only visual information such as mouth shape features.

• 전자통신동향분석
• /
• 제34권5호
• /
• pp.113-126
• /
• 2019

Based on the accumulation of medical big data, advances in medical artificial intelligence technology facilitate the timely treatment of disease through the reading the medical images and the increase of prediction speed and accuracy of diagnoses. In addition, these advances are expected to spark significant innovations in reducing medical costs and improving care quality. There are already approximately 40 FDA approved products in the US, and more than 10 products with K-FDA approval in Korea. Medical applications and services based on artificial intelligence are expected to spread rapidly in the future. Furthermore, the evolution of medical artificial intelligence technology is expanding the boundaries or limits of various related issues such as reference standards and specifications, ethical and clinical validation issues, and the harmonization of international regulatory systems.

• 센서학회지
• /
• 제30권1호
• /
• pp.15-19
• /
• 2021

Image processing is one of the major techniques that are used for computer vision. Nowadays, researchers are using machine learning and deep learning for the aforementioned task. In recent years, digit recognition tasks, i.e., automatic meter recognition approach using electric or water meters, have been studied several times. However, two major issues arise when we talk about previous studies: first, the use of the deep learning technique, which includes a large number of parameters that increase the computational cost and consume more power; and second, recent studies are limited to the detection of digits and not storing or providing detected digits to a database or mobile applications. This paper proposes a system that can detect the digital number of meter readings using a lightweight deep neural network (DNN) for low power consumption and send those digits to an Android mobile application in real-time to store them and make life easy. The proposed lightweight DNN is computationally inexpensive and exhibits accuracy similar to those of conventional DNNs.

• International Journal of Computer Science & Network Security
• /
• 제22권7호
• /
• pp.308-314
• /
• 2022

As a result of the global effect of infectious diseases like COVID-19, remote patient monitoring has become a vital need. Surgical ICU monitors are attached around the clock for patients in critical care. Most ICU monitor systems, on the other hand, lack an output port for transferring data to an auxiliary device for post-processing. Similarly, strapping a slew of wearables to a patient for remote monitoring creates a great deal of discomfort and limits the patient's mobility. Hence, an unique remote monitoring technique for the ICU monitor's physiologically vital readings has been presented, recognizing this need as a research gap. This mechanism has been put to the test in a variety of modes, yielding an overall accuracy of close to 90%.

• 대한의용생체공학회:의공학회지
• /
• 제33권1호
• /
• pp.15-24
• /
• 2012

Classification of human thought is an emerging research field that may allow us to understand human brain functions and further develop advanced brain-computer interface (BCI) systems. In the present study, we introduce a new approach to classify various mental states from noninvasive electrophysiological recordings of human brain activity. We utilized the full spatial and spectral information contained in the electroencephalography (EEG) signals recorded while a subject is performing a specific mental task. For this, the EEG data were converted into a 2D spatiospectral pattern map, of which each element was filled with 1, 0, and -1 reflecting the degrees of event-related synchronization (ERS) and event-related desynchronization (ERD). We evaluated the similarity between a current (input) 2D pattern map and the template pattern maps (database), by taking the inner-product of pattern matrices. Then, the current 2D pattern map was assigned to a class that demonstrated the highest similarity value. For the verification of our approach, eight participants took part in the present study; their EEG data were recorded while they performed four different cognitive imagery tasks. Consistent ERS/ERD patterns were observed more frequently between trials in the same class than those in different classes, indicating that these spatiospectral pattern maps could be used to classify different mental states. The classification accuracy was evaluated for each participant from both the proposed approach and a conventional mental state classification method based on the inter-hemispheric spectral power asymmetry, using the leave-one-out cross-validation (LOOCV). An average accuracy of 68.13% (${\pm}9.64%$) was attained for the proposed method; whereas an average accuracy of 57% (${\pm}5.68%$) was attained for the conventional method (significance was assessed by the one-tail paired $t$-test, $p$ < 0.01), showing that the proposed simple classification approach might be one of the promising methods in discriminating various mental states.

• Restorative Dentistry and Endodontics
• /
• 제41권1호
• /
• pp.6-11
• /
• 2016

Objectives: The purpose of this in vitro study was to evaluate the accuracy of working length (WL) determination of four electronic apex locators (EALs), namely, Root ZX (RZX), Elements diagnostic unit and apex locator (ELE), SybronEndo Mini Apex locator (MINI) and Propex pixi (PIXI) using Stainless steel (SS) and nickel-titanium (NiTi) hand files. The null hypothesis was that there was no difference between canal length determination by SS and NiTi files of 4 EALs. Materials and Methods: Sixty extracted, single rooted human teeth were decoronated and the canal orifice flared. The actual length (AL) was assessed visually, and the teeth were embedded in an alginate model. The electronic length (EL) measurements were recorded with all four EALs using SS and NiTi files at '0.5' reading on display. The differences between the AL and EL were compared. Results: The results obtained with each EAL with SS and NiTi files were compared with AL. A paired sample t test showed that there was a statistical significant difference between EAL readings with SS and NiTi files for RZX and MINI (p < 0.05). The accuracy of RZX, ELE, MINI and PIXI within ${\pm}0.5 mm$ of AL with SS/NiTi files were 93.3%/70%, 90%/91.7%, 95%/68.3%, and 83.3%/83.3%, respectively. Conclusions: The results of this study indicate that Root ZX was statistically more accurate with NiTi files compared to SS files, while MINI was statistically more accurate with SS files compared to NiTi files. ELE and PIXI were not affected by the alloy type of the file used to determine WL.

• 한국항행학회논문지
• /
• 제26권2호
• /
• pp.113-118
• /
• 2022

사람은 독서나 필기 중 중요 문구를 형광펜으로 칠하는 것에서 착안하여, 본 논문에서는 복잡한 배경 질감을 가진 영상에서의 불량유형을 효과적으로 분류하기 위해 불량 픽셀 영역을 하이라이팅 하여 신경망을 훈련하는 방법을 제안한다. 제안 방법의 가능성을 검증하기 위하여 불량유형 구분이 매우 어려운 타이어 밴드 직물의 불량유형 분류에 제안 방법을 적용한다. 또한, 타이어 밴드 직물 영상에 특화된 백라이트 하이라이팅 방법을 제안한다. 백라이트 하이라이트 영상은 GradCAM 기법과 간단한 영상처리를 이용하여 획득할 수 있다. 실험에서 우리는 제안하는 하이라이팅 기법이 분류 정확도뿐만 아니라 훈련속도 면에서 기존 방법보다 우수함을 보였다. 인식률 면에서는 제안 방법이 기존 방법 대비 최대 13.4%의 향상을 달성하였다. 타이어 밴드 직물 영상에 특화된 백라이트 하이라이팅 기법이 윤곽 하이라이팅 기법보다 정확도 측면에서 우수함을 보였다.

• 한국전문물리치료학회지
• /
• 제10권1호
• /
• pp.51-62
• /
• 2003

The purpose of this study was to compare the relative accuracy of a range of computer-based analysis with respect to EMG onset determined visually by an experienced examiner. Ten healthy students (6 male, 4 female) were recruited and three times randomly selected trials of isometric contraction of wrist flexion and extension were evaluated using four technique. These methods were compared which varied in terms of EMG processing, threshold value and the number of samples for which the mean must exceed the defined threshold, and beyond 7% of maximum amplitude. To identify determination of onset time, ICCs(Intraclass Correlation Coefficients) was used and inter-rater arid intra-rater reliability ranged good in visually derived onset values. The results of this study present that in wrist flexion and extension, the reliability of the inter and intra-examiner muscle contraction onset times through visual analysis showed beyond .971 with ICCs. The reliability of the muscle contraction onset time decision through visual reading, tested with computer analysis, showed a relationship of all the selected analysis methods with ICCs .859 and .871. The objective computer-based analysis comparing with visual reading at the same time is the effective and qualitative data analysis method, considering the specificity of each study method.

• 말소리와 음성과학
• /
• 제12권4호
• /
• pp.91-98
• /
• 2020

근긴장성 발성장애(cepstral peak prominence, MTD) 환자의 모음 발성과 문장읽기 과제를 켑스트럼 기반 변수를 이용하여 분석하였으며 음성장애 환자의 GRBAS청지각적 특성과 음향학적 특성의 상관관계를 살펴보고, 랜덤포레스트 머신러닝 분류 알고리듬을 이용한 MTD 감별 진단 가능성을 논의하였다. 내원 시 MTD로 진단받은 여성 36명과 정상음성을 사용하는 여성 36명이 연구에 참여했으며, 수집한 음성샘플은 ADSVTM를 사용하여 분석하였다. 연구 결과, 음향학적 측정치 중 MTD의 CSID(cepstral spectral index of dysphonia)는 대조군보다 높았으며, CPP(cepstral peak prominence), CPP_Fo 값이 대조군보다 유의하게 낮았다. 이는 모음 발성과 읽기 과제에서 모두 동일하게 나타났다. MTD 환자의 음질 특성은 전반적인 음성중증도(G)가 가장 두드러졌으며, 조조성(R), 기식성(B), 노력성(S)순으로 음성 특성을 보였다. 이 특성이 높아질수록 CPP가 감소하는 부적 상관을 보이고, CSID는 증가하는 정적 상관이 관찰되었다. 켑스트럴 변수 중 모음과 문장읽기과제 모두에서 집단간 유의한 차이를 보여준 CPP와 CPP_F0를 이용하여 MTD와 대조군의 음성분류를 시도하였다. 머신러닝 알고리듬인 랜덤포레스트로 모델링한 결과 문장읽기 과제에서 모음연장발성보다 조금 더 높은 분류 정확도(83.3%)가 나왔으며, 모음 발성과 문장 읽기 과제 모두에서 CPP변수가 더 중심적 역할을 수행하였음을 알 수 있었다.