http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Fabrication of polymer microlens for cell detection by light scattering
박세완(Sewan Park),정용원(Yongwon Jeong),김진석(Jinseok Kim),최기환(Kihwan Choi),김현철(Hyeon Cheol Kim),정두수(Doo Soo Chung),전국진(Kukjin Chun) 대한전자공학회 2006 대한전자공학회 학술대회 Vol.2006 No.11
In laser light scattering detection and laser-induced fluorescence detection, the focusing of the excitation laser beam into a focal point of the channel in a microfluidic chip is important to obtain the largest intensity, and consequently to obtain the light collected to the photodetector with a high efficiency. In this paper, we present a polydimethylsiloxane (PDMS) microfluidic chip consisting of an integrated PDMS microlens for cell detection based on laser light scattering. The PDMS micro lens was fabricated by the photoresist reflow and PDMS replica molding method. This fabrication technique is simple and has a good property in terms of the microlens and a high-dimensional accuracy. The PDMS microlens integrated on the PDMS microfluidic channel was verified to improve the laser light intensity, and consequently signal to noise ratio and sensitivity of laser light scattering detection using red blood cells (RBCs).
잔향 환경 음성인식을 위한 다중 해상도 DenseNet 기반 음향 모델
박순찬(Park, Sunchan),정용원(Jeong, Yongwon),김형순(Kim, Hyung Soon) 한국음성학회 2018 말소리와 음성과학 Vol.10 No.1
Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.