检索结果-南通市图书馆

Deep learning-based lung sound analysis for intelligent stethoscope

Military Medical Research 2024年第4期11卷 567-588页

作者： Dong-Min Huang Jia Huang Kun qiao Nan-shan Zhong Hong-Zhou Lu Wen-Jin Wang Department of Biomedical Engineering Southern University of Science and TechnologyShenzhen 518055GuangdongChina The Third People’s Hospital of Shenzhen Shenzhen 518112GuangdongChina Guangzhou Institute of Respiratory Health China State Key Laboratory of Respiratory DiseaseNational Clinical Research Center for Respiratory Diseasethe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhou 510120China

Auscultation is crucial for the diagnosis of respiratory system ***,traditional stethoscopes have inherent limitations,such as inter-listener variability and subjectivity,and they cannot record respiratory sounds for offline/retrospective diagnosis or remote prescriptions in *** emergence of digital stethoscopes has overcome these limitations by allowing physicians to store and share respiratory sounds for consultation and *** this basis,machine learning,particularly deep learning,enables the fully-automatic analysis of lung sounds that may pave the way for intelligent *** review thus aims to provide a comprehensive overview of deep learning algorithms used for lung sound analysis to emphasize the significance of artificial intelligence(AI)in this *** focus on each component of deep learning-based lung sound analysis systems,including the task categories,public datasets,denoising methods,and,most importantly,existing deep learning methods,i.e.,the state-of-the-art approaches to convert lung sounds into two-dimensional(2D)spectrograms and use convolutional neural networks for the end-to-end recognition of respiratory diseases or abnormal lung ***,this review highlights current challenges in this field,including the variety of devices,noise sensitivity,and poor interpretability of deep *** address the poor reproducibility and variety of deep learning in this field,this review also provides a scalable and flexible open-source framework that aims to standardize the algorithmic workflow and provide a solid basis for replication and future extension:https://***/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis.

关键词： Deep learning Lung sound analysis Respiratory sounds

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

承认政治视角下的民族政策诠释

引用

贵州民族研究 2015年第3期36卷 10-15页

作者：乔姗姗南京大学政府管理学院江苏南京210046

各民族之间的和谐关系建立在相互平等的基础上,实现平等的核心就是对不同民族差异性给予承认而不是同化。为此,泰勒在其承认政治理论中论证了少数群体文化差异性存在的合法性。从承认政治理论视角而言,民族政策核心内容的融合并非指完... 详细信息

各民族之间的和谐关系建立在相互平等的基础上,实现平等的核心就是对不同民族差异性给予承认而不是同化。为此,泰勒在其承认政治理论中论证了少数群体文化差异性存在的合法性。从承认政治理论视角而言,民族政策核心内容的融合并非指完全一样,而是指在承认差异的基础上文化间的互动,从而构建和谐的民族关系。由于民族地区相对较为落后,国家承认差异后仅靠少数民族一己之力难以提高当地经济。为此,国家应民族地区所需制定帮扶性民族政策,引导少数民族地区发展。实践证明,我国民族政策建立在承认政治基础之上,又对其实现了创新性的超越,从而取得了民族团结和共同繁荣的预期目标。

关键词：民族政策承认政治民族关系民族发展

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

论行政行为规范的自律性人格之维——基于乔治·H.米德的“自我”理论视角

引用

华中科技大学学报（社会科学版） 2015年第3期29卷 23-30页

作者：乔姗姗南京大学政府管理学院江苏南京210046

从形式上看,行政行为异化是由于制度的不完善所引发的。而现实中制度只能对行政行为做出模糊的原则性要求,至于行政人员的具体行动则受他的自我价值观支配。米德认为由"主我"与"客我"的辩证统一关系组成了自我,当"主我"的私利追求与"客... 详细信息

从形式上看,行政行为异化是由于制度的不完善所引发的。而现实中制度只能对行政行为做出模糊的原则性要求,至于行政人员的具体行动则受他的自我价值观支配。米德认为由"主我"与"客我"的辩证统一关系组成了自我,当"主我"的私利追求与"客我"的公利实现共同组成行政人员的自我时,他就生成了混合性人格。对于社会其他职业而言,混合性人格中"主我"与"客我"的对立对职责的实现影响不大,但是,由于行政人员职业的特殊性,"主我"与"客我"的冲突则是导致行政行为失范的本质原因。因此,统一行政人员的"主我"与"客我"认知,把道德价值的内容充分吸纳到制度中,在德制中重塑行政人员的自律性人格,才能从根本上规避行政行为异化的问题。

关键词：行政人员自我混合性人格自律性人格

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

尹昌衡:一个保守主义者的革命与归隐

引用

社会科学研究 2020年第5期 187-196页

作者：谯珊四川大学历史文化学院四川成都610064

保守主义与激进主义是近代中国两股重要的社会思潮,分别代表了变革中国的两种政治取向。保守相对于激进而言,非“保守派”或“旧派”之意。清季民初,中国未建立起一个稳定的政治秩序,保守主义如同空中楼阁,难以在现实中找到立足点。反之... 详细信息

保守主义与激进主义是近代中国两股重要的社会思潮,分别代表了变革中国的两种政治取向。保守相对于激进而言,非“保守派”或“旧派”之意。清季民初,中国未建立起一个稳定的政治秩序,保守主义如同空中楼阁,难以在现实中找到立足点。反之,激进主义不断扩大政治舞台,以致保守者的命运不得不同革命联系在一起,革命有时竟成为保守主义者的安身立命之处。政治与文化思想保守的尹昌衡,从“忠清”到“反清”,最后被迫“归隐”的人生经历,恰是一位保守主义者在不断激进的革命潮流中难以立足的写照。

关键词：尹昌衡四川保路运动保守主义革命高潮归隐

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Predictive value of tumor markers in patients with recurrent hepatocellular carcinoma in different vascular invasion pattern

引用

Hepatobiliary & Pancreatic Diseases International 2016年第4期15卷 371-377页

作者： Feng Gao Heng-Kai Zhu Yang-Bo Zhu qiao-Nan shan Qi Ling Xu-Yong Wei Hai-Yang Xie Lin Zhou Xiao Xu Shu-Sen Zheng Division of Hepatobiliary and Pancreatic Surgery Department of Surgery First Affiliated Hospital Zhejiang University School of Medicine Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases Zhejiang University Key Lab of Combined Multi-Organ Transplantation Ministry of Public Health First Affiliated Hospital Zhejiang University School of Medicine

BACKGROUND： Four tumor markers for hepatocellular carcinoma（HCC）, alpha-fetoprotein（AFP）, glypican-3（GPC3）, vascular endothelial growth factor（VEGF） and des-gammacarboxy prothrombin（DCP）, are closely associated with tumor invasion and patient＇s survival. This study estimated the predictability of preoperative tumor marker levels along with pathological parameters on HCC recurrence after ***： A total of 140 patients with HCC who underwent hepatectomy between January 2012 and August 2012 were enrolled. The demographics, clinical and follow-up data were collected and analyzed. The patients were divided into two groups： patients with macroscopic vascular invasion（Ma VI ＋） and those without Ma VI（Ma VI-）. The predictive value of tumor markers and clinical parameters were evaluated by univariate and multivariate ***： In all patients, tumor size（〉8 cm） and Ma VI were closely related to HCC recurrence after hepatectomy. For Ma VI＋ patients, VEGF（〉900 pg/m L） was a significant predictor for recurrence（RR=2.421; 95% CI： 1.272-4.606; P=0.007）. The 1- and 2-year tumor-free survival rates for Ma VI＋ patients with VEGF ≤900 pg/m L versus for those with VEGF 〉900 pg/m L were 51.5% and 17.6% versus 19.0% and 4.8%（P〈0.001）. For Ma VI- patients, DCP 〉445 m Au/m L and tumor size 〉8 cm were two independent risk factors for tumor recurrence（RR=2.307, 95% CI： 1.132-4.703, P=0.021; RR=3.150, 95% CI： 1.392-7.127, P=0.006; respectively）. The 1- and 2-year tumor-free survival rates for the patients with DCP ≤445 m Au/m L and those with DCP 〉445 m Au/m L were 90.4% and 70.7% versus 73.2% and 50.5% respectively（P=0.048）. The 1-and 2-year tumor-free survival rates for the patients with tumor size ≤8 cm and 〉8 cm were 83.2% and 62.1% versus 50.0% and 30.0%, respectively（P=0.003）.CONCLUSIONS： The Ma VI＋ patients with VEGF ≤900 pg/m L had a relatively high tumor-free survival than those with VEGF 〉900 pg/m L. In the Ma VI- patients, DCP 〉445 m Au/m L and tumor size 〉8

关键词： tumor markers hepatocellular carcinoma recurrence vascular invasion prediction

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于深度图的水下图像复原

引用

吉林大学学报（工学版） 2021年第2期51卷 677-684页

作者：郭继昌乔珊珊天津大学电气自动化与信息工程学院天津300072

水下图像深度图估计的准确性影响复原后的图像质量,为得到更加准确的深度图,提出了一种基于衰减通道结合亮度图的深度图求解算法,并利用该深度图复原水下图像。首先,根据图像像素值与场景深度的关系估计水下图像的深度图,并使用图像的... 详细信息

水下图像深度图估计的准确性影响复原后的图像质量,为得到更加准确的深度图,提出了一种基于衰减通道结合亮度图的深度图求解算法,并利用该深度图复原水下图像。首先,根据图像像素值与场景深度的关系估计水下图像的深度图,并使用图像的亮度图对深度图进行修正和细化;然后,利用深度图计算图像的大气光值和透射率图;最后,通过逆求解水下成像模型复原退化的图像。实验证明:与现有算法相比,利用该深度图得到的模型参数更加准确,复原后的图像不仅拥有更好的对比度,而且能保持自然真实的颜色。

关键词：信息处理技术水下图像复原水下成像模型深度图

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Clinical applications of neurolinguistics in neurosurgery

引用

Frontiers of Medicine 2021年第4期15卷 562-574页

作者： Peng Wang Zehao Zhao Linghao Bu Nijiati Kudulaiti qiao shan Yuyao Zhou N.U.Farrukh Hameed Yangming Zhu Lei Jin Jie Zhang Junfeng Lu Jinsong Wu Glioma Surgery Division Neurologic Surgery DepartmentHuashan HospitalFudan UniversityShanghai 200040China Brain Function Laboratory Neurosurgical Institute ofFudan UniversityShanghai 201100China Institute of Brain-Intelligence Technology Zhangjiang LabShanghai 200135China

The protection of language function is one of the major challenges of brain *** the past century,neurosurgeons have attempted to seek the optimal strategy for the preoperative and intraoperative identification of language-related brain *** have investigated the neural mechanism of language,developed neurolinguistics theory,and provided unique evidence to further understand the neural basis of language functions by using intraoperative cortical and subcortical electrical *** the emergence of modern neuroscience techniques and dramatic advances in language models over the last 25 years,novel language mapping methods have been applied in the neurosurgical practice to help neurosurgeons protect the brain and reduce *** rapid advancements in brain-computer interface have provided the perfect platform for the combination of neurosurgery and *** this review,the history of neurolinguistics models,advancements in modern technology,role of neurosurgery in language mapping,and modern language mapping methods(including noninvasive neuroimaging techniques and invasive cortical electroencephalogram)are presented.

关键词： neurolinguistics language mapping dual pathway model neurosurgery

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Two-Step Regularization Framework for Non-Local Means

引用

Journal of Computer Science & Technology 2014年第6期29卷 1026-1037页

作者：孙忠贵陈松灿乔立山 Department of Mathematics Science Liaocheng University College of Computer Science and Technology Nanjing University of Aeronautics & Astronautics

As an effective patch-based denoising method, non-local means （NLM） method achieves favorable denoising performance over its local counterparts and has drawn wide attention in image processing community. The in, plementation of NLM can formally be decomposed into two sequential steps, i.e., computing the weights and using the weights to compute the weighted means. In the first step, the weights can be obtained by solving a regularized optimization. And in the second step, the means can be obtained by solving a weighted least squares problem. Motivated by such observations, we establish a two-step regularization framework for NLM in this paper. Meanwhile, using the fl-amework, we reinterpret several non-local filters in the unified view. Further, taking the framework as a design platform, we develop a novel non-local median filter for removing salt-pepper noise with encouraging experimental results.

关键词： non-local means non-local median framework image denoising regularization

来源：

维普期刊数据库

同方期刊数据库评论