检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Gong, Maoguo Gao, Yuan Xie, Yu Qin, A.K. Pan, Ke Ong, Yew-Soon The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an Shaanxi Province710071 China The Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Taiyuan030006 China The Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

The performance of machine learning algorithms heavily relies on the availability of a large amount of training data. However, in reality, data usually reside in distributed parties such as different institutions and may not be directly gathered and integrated due to various data policy constraints. As a result, some parties may suffer from insufficient data available for training machine learning models. In this paper, we propose a multi-party dual learning (MPDL) framework to alleviate the problem of limited data with poor quality in an isolated party. Since the knowledge sharing processes for multiple parties always emerge in dual forms, we show that dual learning is naturally suitable to handle the challenge of missing data, and explicitly exploits the probabilistic correlation and structural relationship between dual tasks to regularize the training process. We introduce a feature-oriented differential privacy with mathematical proof, in order to avoid possible privacy leakage of raw features in the dual inference process. The approach requires minimal modifications to the existing multi-party learning structure, and each party can build flexible and powerful models separately, whose accuracy is no less than non-distributed self-learning approaches. The MPDL framework achieves significant improvement compared with state-of-the-art multi-party learning methods, as we demonstrated through simulations on real-world datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MULTI-SCALE FEATURE LEARNING BASED ON NON-CONTRST CT FOR PANCREATIC LESIONS DETECTION

MULTI-SCALE FEATURE LEARNING BASED ON NON-CONTRST CT FOR PAN...

引用

第十六届国际体视学与图像分析学术会议

作者： Tian YAN Geye TANG Lidu LIANG Jianhua MA Yi GAO Chenjie ZHOU Shulong LI School of Biomedical Engineering Guangdong Provincial Key Laboratory of Medical Image ProcessingGuangdong Province Engineering Laboratory for Medical Imaging and Diagnostic TechnologySouthern Medical University General Surgery Center Department of Hepatobiliary Surgery ⅡGuangdong Provincial Research Center for Artificial Organ and Tissue EngineeringGuangzhou Clinical Research and Transformation Center for Artificial LiverInstitute of Regenerative MedicineZhujiang HospitalSouthern Medical University State Key Laboratory of Organ Failure Research Southern Medical University

Pancreatic cancer is one of the most malignant tumors with poor prognosis and mortality also close to the morbidity,mainly because of the difficulty of early diagnosis and timely treatment in localized *** is clinically important to develop a non-contrast CT(NCCT)-based pancreatic lesion detection model,which would be expected as an intelligent tool for realizing the early ***,it poses the great challenge,because abdominal NCCT presents low contrast intensity for pancreas and its lesions and complex anatomical ***,we design a multiscale feature learning network(MSFL) with Resnet50 and feature pyramid network(FPN) as backbone,by adding multiscale atrous convolutions to expand different receptive fields,contextual attention to perceive contextual information,channel attention and spatial attention to focus on important channels and spatial *** MSFL is used as the feature extractor to propose the NCCT-based pancreatic lesion detection model based on Faster R-CNN as baseline model,to achieve accurate detection of pancreatic *** model with the new MSFL as feature extractor obtains the best performance with recall(75.40%),precision(40.84%),F1 score(51.17%),F2 score(62.86%) and Ap50(60.19%) at image level,and also the best results for recall(85.27%),precision(68.21%),F1 score(77.96%),F2 score(85.26%) and Ap50(60.19%) at patient level,which are superior to conventional object detection *** new model has achieved good performance,which implies that it has high application value,and is expected to be developed as an intelligent method for early detection of pancreatic cancer.

关键词： pancreatic cancer lesion detection atrous convolution multi-scale feature learning attention mechanism

来源：评论

学校读者我要写书评

暂无评论

In vivo imaging of mammalian embryos by NIR-I photoacoustic tomography and NIR-II optical coherence tomography using gold nanostars as multifunctional contrast agents

Research Square

引用

Research Square 2021年

作者： Zhang, Sheng Liu, Zhenyang Mao, Linlin Wu, Jian Zhang, Di Liu, Ruiyuan Qi, Li Department of Cell Biology School of Basic Medicine Southern Medical University Guangzhou510515 China School of Biomedical Engineering Southern Medical University Guangzhou510515 China Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou510515 China Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology Southern Medical University Guangzhou510515 China

Background High resolution, strong contrast and multimodality visualization of live mammalian embryo is an important requirement for studying foetal development. Photoacoustic Tomography (PAT) and Optical Coherence Tomography (OCT) are two advanced imaging modalities that has been utilized for embryonic imaging. However, high contrast, multiscale and deep tissue visualization of live embryos remains challenging. Results Here, we demonstrate the use of gold nanostars (GNS) as multimodality contrast agents for the visualization and differentiation of embryos in vivo using NIR-I PAT and NIR-II OCT. We perform NIR-I PAT imaging to confirm in vivo GNS accumulation in the foetuses, and then use a customized NIR-II OCT system to further reveal deep, contrast-enhanced micro features of freshly harvested embryos. We investigate two different GNS administration pathways, i.e. intravenous and intravaginal injection, and significant enhancement of signal, image contrast, and imaging depth are achieved for both PAT and OCT. Conclusions These findings prove that PAT-OCT bi-modal imaging with GNS enhancement provides more accurate structural characteristic of live mammalian embryos, and thus reveal its potential for embryonic development visualization and early abnormality examination. © 2021, CC BY.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Technical Analysis on Application Layer Error Control in IPTV

引用

ZTE communications 2010年第1期000卷

作者： Xia Hongfei Lü Xiaopeng Liu Feng ZTE Corporation Nanjing 210012P.R.China Image Processing and Image Communication Laboratory of Jiangsu Province Nanjing University of Posts and TelecommunicationsNanjing 210003P. R. China

When they provide Internet Protocol Television (IPTV) services, IP networks face difficulties such as reduced transmission bandwidth, delay, jitter, and packet loss. A terminal-centric solution can improve the image quality by adding control policies like congestion control and error control to the receiving terminal and source code. An end-to-end application layer reliability method is usually required to satisfy IPTV requirements in the IP network. Application Layer Forward Error Correction (AL-FEC) technology solves the problem of packet loss, and can ensure the end-to-end reliability for IPTV services.

关键词：差错控制分析应用 IPTV 技术接收终端 IP网络服务终端互联网协议

来源：评论

学校读者我要写书评

暂无评论

Smoothing Energy Transfer Enabling Efficient Large-Area Qusai-2d Perovskite Light-Emitting Diodes

SSRN

引用

SSRN 2022年

作者： Lei, Cai Zang, Jiaqing Jiangyu, Chen Jungui, Zhou Yatao, Zou Guilin, Bai Zhewei, Chen Song, Tao Chuan-Kui, Wang Sun, Baoquan Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Shandong Jinan250014 China Soochow University Jiangsu Suzhou215123 China Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices Soochow University Jiangsu Suzhou215123 China MUST-SUDA Joint Research Center for Advanced Functional Materials Macau University of Science and Technology Taipa999078 China

Electroluminescence (EL) efficiency of perovskite light-emitting diodes (PeLEDs) based on a few square millimeters has improved significantly in recent years. Nevertheless, the EL efficiency of PeLEDs would be plunged once the active area was enlarged from millimeter to even sub-centimeter due to the unsmooth energy transfer process among the edge region with numerous nonradiative recombination centers. Herein, we developed an intriguing strategy to realize high-quality quasi-two-dimensional (quasi-2D) perovskite thin film via tuning perovskite precursor rheological properties as well as modulating the substrate surface tension. The perovskite crystallization process was retarded by incorporating a strong chelating ligand into its precursor. Hydroxylamine-O-sulfonic acid (ASC), containing a sulfonic acid group and an amino group acted as a strong chelating agent with lead ions (Pb 2+ ), which exhibited a great synergistic potential in defect passivation and crystallization modulation. An atop ultrathin lithium fluoride interlayer was pre-deposited to boost the substrate surface tension resulting in full coverage on a large-area substrate. ASC-anchored quasi-2D intermediate phases delayed the crystallization due to the strong chemical interaction between ASC and perovskite and then suppressed small-nanoplatelet phase formation in quasi-2D perovskite. ASC additives can also suppress nonradiative recombination, which is ascribed to the high binding energy between high electro positivity of the amino group with negatively charged defects as well as the elimination of uncoordinated Pb 2+ by the electron-rich sulfonic acid group. As a result, a large-area (25 cm 2 ) quasi-2D PeLED achieves an external quantum efficiency of 20.7% with uniform emitting characteristics, a record value among analogous same-size PeLEDs. Our work may pave the way to realizing high-performance large-area perovskite optoelectronic devices. © 2022, The Authors. All rights reserved.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Cooperative MIMO Channel Modeling and Multi-Link Spatial Correlation Properties

引用

IEEE Journal on Selected Areas in communications 2012年第2期30卷 388-396页

作者： Xiang Cheng Cheng-Xiang Wang Haiming Wang Xiqi Gao Xiao-Hu You Dongfeng Yuan Bo Ai Qiang Huo Ling-Yang Song Bing-Li Jiao School of Electronics and Computer Science Peking University Beijing China Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University China Joint Research Institute for Signal and Image Processing School of Engineering & Physical Sciences Heriot-Watt University Edinburgh UK School of Information Science and Engineering South East University Najing China School of Information Science and Engineering Shandong University Jinan China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China

In this paper, a novel unified channel model framework is proposed for cooperative multiple-input multiple-output (MIMO) wireless channels. The proposed model framework is generic and adaptable to multiple cooperative MIMO scenarios by simply adjusting key model parameters. Based on the proposed model framework and using a typical cooperative MIMO communication environment as an example, we derive a novel geometry-based stochastic model (GBSM) applicable to multiple wireless propagation scenarios. The proposed GBSM is the first cooperative MIMO channel model that has the ability to investigate the impact of the local scattering density (LSD) on channel characteristics. From the derived GBSM, the corresponding multi-link spatial correlation functions are derived and numerically analyzed in detail.

关键词： MIMO Correlation Channel models Scattering Educational institutions Fading Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Npc Model: A Multi-Task Solution for Nasopharyngeal Carcinoma Based on Pretraining and Large Language Models

SSRN

引用

SSRN 2024年

作者： Han, Xu Wang, Zhaonian Zheng, Chundan Lu, Wantong Chen, Zihang Sun, Ying Lu, Lijun School of Biomedical Engineering Southern Medical University 1023 Shatai Road Guangzhou510515 China Guangdong Provincial Key Laboratory of Medical Image Processing Guangzhou510515 China Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology Southern Medical University 1023 Shatai Road Guangzhou510515 China State Key Laboratory of Oncology in South China Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy Guangdong Provincial Clinical Research Center for Cancer Sun Yat-sen University Cancer Center Guangzhou510060 China Hebei Key Laboratory of Nerve Injury and Repair China

We proposed a multimodal model tailored for vertical segmentation in the healthcare sector, named the NPC model. We meticulously developed and validated our model using Magnetic Resonance Imaging images from a cohort of 1910 NPC *** NPC model employs a self-supervised learning method for pretraining the feature extractor, followed by modifications to the segmentation process decoder for joint segmentation. To bridge the information dimension gap between clinical textual information and clinical image data, we incorporated a transformer-based architecture in multimodal fusion, leveraging a Large Language Model to derive results for chemotherapy sensitivity classification. The NPC model achieved outstanding Dice of 0.9012 and 0.8056 for the joint segmentation of GTV and MLN. Furthermore, the NPC model achieved AUC of 0.7250 for sensitivity *** model establishes a novel paradigm for NPC management by seamlessly integrating SSL, LLM, and multimodal fusion and sets a new benchmark for future research in NPC. © 2024, The Authors. All rights reserved.

关键词： Chemotherapy

来源：评论

学校读者我要写书评

暂无评论

1D N-type SnO2 nanofibers coexisted with P-type Co3O4 cubes for highly selective acetone sensor

引用

IOP Conference Series: Materials Science and Engineering 2019年第1期479卷

作者： W Tang D W Li X J Du J Yu Q Q Sun Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Jinan 250014 Jinan Province China

1D n-type SnO2 nanofibers coexisted with p-type Co3O4 particles were synthesized by electrospinning with subsequent hydro-thermal process. The morphology and composition of Co3O4/SnO2 were characterized by X-ray diffraction (XRD), scanning electron microscope (SEM). XRD patterns showed that the synthesized Co3O4/SnO2 were assigned to cubic Co3O4 and tetragonal rutile structure of SnO2 without any other impurity peaks. A possible growth mechanism was proposed to describe the formation of hierarchical SnO2 nanofibers coexisted with Co3O4 cubes. The Co3O4/SnO2 compound exhibited a relatively highly selective response to acetone and stable acetone sensing performance after a long period of aging. The Co3O4/SnO2 compound had a p-type response. It may be ascribed to the high coverage of p-type Co3O4 on n-type SnO2. The excellent acetone sensing properties of Co3O4/SnO2 nanostructures may be attributed to p-n junctions between Co3O4 and SnO2 nanograins as well as the unique coexistence structure of nanofibers and cubes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A stability-based multicast routing algorithm for wireless ad hoc networks

引用

Journal of Computers (Taiwan) 2017年第2期28卷 73-85页

作者： Zhang, Fan Yuan, Qi Li, Mingming Xu, Xinyan Xing, Jian Technical Department of Jinan Branch Shandong Cable Interactive Service LTD Jinan250014 China Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Jinan250014 China Department of Substation Maintenance State Grid Weifang Power Supply Company Weifang261021 China Department of Computer Science and Technology Shandong College of Electronic Technology Jinan250200 China

The research on wireless mobile Ad hoc networks has attracted much attention over the past few years, and IP multicast technology supports data transmission from one or several sources to a certain group of receivers. PUMA, as a mesh-based multicast routing algorithm for Ad hoc networks, has been demonstrated to perform better compared with other protocols under high-speed situation. Moreover, node mobility has been one of the dominant factors causing loss of system performance so that the stability is necessary to be taken into account when designing routing protocols. In this paper, a novel stability-based multicast routing algorithm (SMRA) is developed on the basis of PUMA, where the robustness and the congestion are jointly considered. In order to determine the forwarding path and the mesh member status of each node, SMRA utilizes the power information and is implemented across physical layer and network layer. We compare SMRA with PUMA and another well-known tree-based multicast protocol MAODV. Simulation results show that the performance of the proposed algorithm is better than that of PUMA and MAODV in terms of packet delivery ratio and throughput with limited control overhead.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Multi-materials beam hardening artifacts correction for computed tomography (CT) based on X-ray spectrum estimation

arXiv

引用

arXiv 2018年

作者： Zhao, Wei Li, Dengwang Niu, Kai Qin, Wenjian Peng, Hao Niu, Tianye Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Jinan250014 China Department of Medical Physics University of Wisconsin-Madison MadisonWI53705 United States Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Department of Physics Wuhan University Institute of Translational Medicine

Due to the energy dependent nature of the attenuation coefficient and the polychromaticity of X-ray source, beam hardening effect occurs when X-ray photons penetrate through an object, causing a nonlinear projection data. When a linear reconstruction algorithm, such as filtered backprojection, is applied to reconstruct the projection data, beam hardening artifacts which show as cupping and streaks, are present in the CT image. The aim of this study was to develop a fast and accurate beam hardening correction method which can deal with beam hardening artifacts induced by multi-materials objects. Based on spectrum estimation, the nonlinear attenuation process of the X-ray projection was modeled by reprojecting a template image with the estimated polychromatic spectrum. The template images were obtained by segmenting the uncorrected into different components using a simple segmentation algorithm. By adding the scaled difference of the monochromatic reprojection data and the polychromatic reprojection to the raw projection data, the raw projection data was mapped into the corresponding monochromatic projection data, which was used to reconstruct the beam hardening artifacts corrected images. The algorithm can also be implemented in image-domain which takes the uncorrected image volume as input. In this case, the scaled mapping term was reconstructed to yield a set of artifacts images which can be added directly to the uncorrected images. Numerical simulations, experimental phantom data and animal data which were acquired on a modern diagnostic CT scanner (Discovery CT750 HD, GE Healthcare, WI, USA) and a modern C-Arm CT scanner (Artis Zee, Siemens Healthcare, Forchheim, Germany), respectively, were used to evaluate the proposed method. The results show the proposed method significantly Copyright © 2018, The Authors. All rights reserved.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：