http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Modern Achalasia: Diagnosis, Classification, and Treatment
Marcella Pesce,Marta Pagliaro,Giovanni Sarnelli,Rami Sweis 대한소화기 기능성질환∙운동학회 2023 Journal of Neurogastroenterology and Motility (JNM Vol.29 No.4
Achalasia is a major esophageal motor disorder featured by the altered relaxation of the esophagogastric junction in the absence of effective peristaltic activity. As a consequence of the esophageal outflow obstruction, achalasia patients present with clinical symptoms of dysphagia, chest pain, weight loss, and regurgitation of indigested food. Other less specific symptoms can also present including heartburn, chronic cough, and aspiration pneumonia. The delay in diagnosis, particularly when the presenting symptoms mimic those of gastroesophageal reflux disease, may be as long as several years. The widespread use of high-resolution manometry has permitted earlier detection and uncovered achalasia phenotypes which can have prognostic and therapeutic implications. Other tools have also emerged to help define achalasia severity and which can be used as objective measures of response to therapy including the timed barium esophagogram and the functional lumen imaging probe. Such diagnostic innovations, along with the increased awareness by clinicians and patients due to the availability of alternative therapeutic approaches (laparoscopic and robotic Heller myotomy, and peroral endoscopic myotomy) have radically changed the natural history of the disorder. Herein, we report the most recent advances in the diagnosis, classification, and management of esophageal achalasia and underline the still-grey areas that needs to be addressed by future research to reach the goal of personalizing treatment.
What Do Pedestrians See?: Visualizing Pedestrian-View Intersection Classification
Marcella Astrid,Muhammad Zaigham Zaheer,Jin-Ha Lee,Jae-Yeong Lee,Seung-Ik Lee 제어로봇시스템학회 2020 제어로봇시스템학회 국제학술대회 논문집 Vol.2020 No.10
Extensive research has been carried out on intersection classification to assist the navigation in autonomous maneuvering of aerial, road, and cave mining vehicles. In contrast, our work tackles intersection classification at pedestrian-view level to support navigation of the slower and smaller robots for which it is too dangerous to steer on a normal road along with the usual vehicles. Particularly, we focus on investigating the kind of features a network may exploit in order to classify intersection at pedestrian-view. To this end, two sets of experiments have been conducted using an ImageNet-pretrained ResNet-18 architecture fine-tuned on our image-level pedestrian-view intersection classification dataset. First, ablation study is performed on layer depth to evaluate the importance of high-level feature, which demonstrated superiority in using all of the layers by yielding 77.56% accuracy. Second, to further clarify the need of such high level features, Class Activation Map (CAM) is applied to visualize the parts of an image that affect the most on a given prediction. The visualization justifies the high accuracy of an all-layers network.
Deep compression of convolutional neural networks with low‐rank approximation
Marcella Astrid,이승익 한국전자통신연구원 2018 ETRI Journal Vol.40 No.4
The application of deep neural networks (DNNs) to connect the world with cyber physical systems (CPSs) has attracted much attention. However, DNNs require a large amount of memory and computational cost, which hinders their use in the relatively low‐end smart devices that are widely used in CPSs. In this paper, we aim to determine whether DNNs can be efficiently deployed and operated in lowend smart devices. To do this, we develop a method to reduce the memory requirement of DNNs and increase the inference speed, while maintaining the performance (for example, accuracy) close to the original level. The parameters of DNNs are decomposed using a hybrid of canonical polyadic–singular value decomposition, approximated using a tensor power method, and fine‐tuned by performing iterative one‐shot hybrid fine‐tuning to recover from a decreased accuracy. In this study, we evaluate our method on frequently used networks. We also present results from extensive experiments on the effects of several fine‐tuning methods, the importance of iterative fine‐tuning, and decomposition techniques. We demonstrate the effectiveness of the proposed method by deploying compressed networks in smartphones.
Intra-Batch Features Separation for Indoor and Outdoor Pedestrian-View Intersection Classification
Marcella Astrid,Muhammad Zaigham Zaheer,Seung-Ik Lee 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10
Pedestrian-view intersection classification is an important component to assist robots to navigate in the pedestrian path. To solve this problem, previous approaches simply fine-tune an ImageNet-pretrained network with intersection classification dataset using cross-entropy loss as classification loss in an end-to-end manner. In this work, we propose a novel additional loss to further improve the model’s capability to discriminate intersection and non-intersection class. This loss is directly calculated on the features in a given mini-batch without requiring any additional inference. Furthermore, previous works cover only outdoor domain while we also propose indoor domain in addition to the outdoor intersection classification dataset. Extensive experiments show that the models trained using the proposed loss yields better performance compared to the models trained without it on both indoor and outdoor datasets. This demonstrates the potential of the proposed loss in improving the discrimination capability of our models.