Maomao Chen

Linkai Zhu, Maoyi Huang, Maomao Chen et al.

A lot of manual work goes into identifying a topic for an article. With a large volume of articles, the manual process can be exhausting. Our approach aims to address this issue by automatically extracting topics from the text of large Numbers of articles. This approach takes into account the efficiency of the process. Based on existing N-gram analysis, our research examines how often certain words appear in documents in order to support automatic topic extraction. In order to improve efficiency, we apply custom filtering standards to our research. Additionally, delete as many noncritical or irrelevant phrases as possible. In this way, we can ensure we are selecting unique keyphrases for each article, which capture its core idea. For our research, we chose to center on the autonomous vehicle domain, since the research is relevant to our daily lives. We have to convert the PDF versions of most of the research papers into editable types of files such as TXT. This is because most of the research papers are only in PDF format. To test our proposed idea of automating, numerous articles on robotics have been selected. Next, we evaluate our approach by comparing the result with that obtained manually.

Tri Vu, Anthony DiSpirito, Daiwei Li et al.

Photoacoustic microscopy (PAM) is an emerging imaging method combining light and sound. However, limited by the laser's repetition rate, state-of-the-art high-speed PAM technology often sacrifices spatial sampling density (i.e., undersampling) for increased imaging speed over a large field-of-view. Deep learning (DL) methods have recently been used to improve sparsely sampled PAM images; however, these methods often require time-consuming pre-training and large training dataset with ground truth. Here, we propose the use of deep image prior (DIP) to improve the image quality of undersampled PAM images. Unlike other DL approaches, DIP requires neither pre-training nor fully-sampled ground truth, enabling its flexible and fast implementation on various imaging targets. Our results have demonstrated substantial improvement in PAM images with as few as 1.4$\%$ of the fully sampled pixels on high-speed PAM. Our approach outperforms interpolation, is competitive with pre-trained supervised DL method, and is readily translated to other high-speed, undersampling imaging modalities.

Anthony DiSpirito, Daiwei Li, Tri Vu et al.

One primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed. In this study, we propose a novel application of deep learning principles to reconstruct undersampled PAM images and transcend the trade-off between spatial resolution and imaging speed. We compared various convolutional neural network (CNN) architectures, and selected a fully dense U-net (FD U-net) model that produced the best results. To mimic various undersampling conditions in practice, we artificially downsampled fully-sampled PAM images of mouse brain vasculature at different ratios. This allowed us to not only definitively establish the ground truth, but also train and test our deep learning model at various imaging conditions. Our results and numerical analysis have collectively demonstrated the robust performance of our model to reconstruct PAM images with as few as 2% of the original pixels, which may effectively shorten the imaging time without substantially sacrificing the image quality.