http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
실시간 감정인식을 위한 파형 단위 PPG 신호 Labeling 기법
이하늘,강동현,김덕환 한국차세대컴퓨팅학회 2021 한국차세대컴퓨팅학회 학술대회 Vol.2021 No.05
Real-time emotion recognition technology is required for human-robot interaction. There is a method using the Somatic Nervous System (SNS). The PPG signal, which is easy to acquire data and can be used by dividing it into pulse units, is easy for real-time emotion recognition. However, each pulse label is the most important factor in segmenting and using the short-term 1-second to 3-second PPG signal. However, DEAP and MAHNOB-HCI are public bio-signal data, but DEAP Dataset only provides Self-Assessment Labeling for emotion-inducing videos of 60 seconds. The MAHNOB-HCI Database provides Annotation Labeling in which the observer sees the frontal image of the subject's face and measures emotion in real-time. Annotation labeling is effective to split the labels of PPG signals by pulse units. As a result of the experiment, Arousalbased positives 2415/neutral 3884/negative 4201, Valence-based positives 3570/neutral 2835/negative 4095.labels were drived. Annotation labeling allows us to check the emotions of participants in various distributions for 60 seconds. Analyzing the label setting and data preprocessing process contributes to improving short-term real-time emotion recognition.
우주 이미지 시뮬레이터 및 인공지능 기반의 합성 우주 이미지 생성기법 연구
이하늘,이현재 한국항공우주학회 2023 韓國航空宇宙學會誌 Vol.51 No.5
With the arrival of the New Space era, techniques that using artificial intelligence (AI) for various space missions, such as on-orbit servicing (OOS) and space debris removal, are being proposed. However, since artificial intelligence technology is learning-based, it requires a large amount of image data. Currently, acquiring data related to space missions is not easy in terms of cost and time, and there is a limit to relying on simulator-based technology. In this paper, we propose a technique for generating space images using simulators and artificial intelligence. The synthetic space image generation technology and proposed technique described are expected to be used for various space missions in the future. 뉴스페이스(New Space) 시대가 도래함에 따라 우주 쓰레기 제거, 우주 파편 분석 및 제거 등 다양한 우주 임무에 인공지능(AI)을 활용하는 기법들이 제안되고 있다. 하지만 인공지능 기술은 학습 기반이기 때문에 방대한 이미지 데이터가 필요한데, 현재 우주 임무 관련 데이터를 얻는 것은 비용 및 시간적 측면에서 쉽지 않고 시뮬레이터 기반 기술에 의존한다는 한계가 있다. 이에 본 논문에서는 시뮬레이터 및 인공지능을 활용해 우주 소천체 이미지를 생성하는 기법에 대해 제안한다. 본 논문에서 기술하는 합성 우주 이미지 생성 관련 기술 및 제안 기법은 향후 다양한 우주 임무에 활용될 수 있을 것으로 기대된다.
이하늘,이주희,Yoo Kyung Kang,이주훈,양승주,정현정 한국바이오칩학회 2022 BioChip Journal Vol.16 No.4
We introduce a lateral flow assay (LFA) integrated with a modified isothermal nucleic acid amplification procedure for rapid and simple genetic testing. Padlock probes specific for the target DNA were designed for ligation, followed by rolling circle amplification (RCA) using capture ligand-modified oligonucleotides as primers. After hybridization with detection linker probes, the amplified target DNA is flowed through an LFA membrane strip for binding of gold nanoparticles as the substrate for colorimetric detection. We established and validated the “RCA-LFA” method for detection of mecA, the antibiotic resistance gene for methicillin-resistant Staphylococcus aureus (MRSA). The assay was optimized using various concentrations of primers and probes for RCA and LFA, respectively. The sensitivity was determined by performing RCA-LFA using various amounts of mecA target DNA, showing a detection limit of ~ 1.3 fmol. The specificity of the assay was examined using target DNAs for other resistance genes as the controls, which demonstrated positive detection signals only for mecA DNA, when added either individually or in combinations with the control targets. Furthermore, applying the RCA-LFA method using specifically designed probes for RNA-dependent RNA polymerase (RdRp) and receptor binding domain (RBD) gene for SARS-CoV-2, which demonstrated feasibility of the method for viral gene targets. The current method suggests a useful platform which can be universally applied for various nucleic acid targets, allowing rapid and sensitive diagnosis at point-of-care.
1P-257 Nanoparticle-based isothermal sensing of bacterial nucleic acids
이하늘,정현정 한국공업화학회 2017 한국공업화학회 연구논문 초록집 Vol.2017 No.1
Nucleic acid amplification techniques are used for molecular biology research and medical diagnostics to specifically detect and analyze small amounts of genetic targets. Isothermal amplification has a great advantage over conventional PCR, since the procedure can be performed in simple, miniaturized settings more suitable for point-of-care testing. Herein, we designed a simple, easy and rapid assay based on loopmediated isothermal amplification (LAMP) of nucleic acid targets and their subsequent hybridization with nanoparticle probes that induce a color change that can be observed with the naked eye. We performed the LAMP reaction for the antibiotic resistance gene KPC, followed by addition with gold nanoparticle probes specific to the loop region of the amplified DNA products. Color changes of the final products were characterized by visualization as well as spectral quantitative analyses.