检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, Pengfei Jiang, Zhengyuan Wang, Yixuan Li, Yu Department of Computer Science and Engineering CUHK Hong Kong University of Science and Technology of China Anhui Hefei China The CUHK Shenzhen Research Institute Hi-Tech Park Nanshan Shenzhen518057 China Department of Mathematics HIT Weihai264209 China

The reconstruction of microbial genomes from large metagenomic datasets is a critical procedure for finding uncultivated microbial populations and defining their microbial functional roles. To achieve that, we need to perform metagenomic binning, clustering the assembled contigs into draft genomes. Despite the existing computational tools, most of them neglect one important property of the metagenomic data, that is, the noise. To further improve the metagenomic binning step and reconstruct better metagenomes, we propose a deep Contrastive Learning framework for Metagenome Binning (CLMB), which can efficiently eliminate the disturbance of noise and produce more stable and robust results. Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data. Consequently, the trained model will be robust to noise and handle it implicitly during usage. CLMB outperforms the previous state-of-the-art binning methods significantly, recovering the most near-complete genomes on almost all the benchmarking datasets (up to 17% more reconstructed genomes compared to the second-best method). It also improves the performance of bin refinement, reconstructing 8-22 more high-quality genomes and 15-32 more middle-quality genomes than the second-best result. Impressively, in addition to being compatible with the binning refiner, single CLMB even recovers on average 15 more HQ genomes than the refiner of VAMB and Maxbin on the benchmarking datasets. On a real mother-infant microbiome dataset with 110 samples, CLMB is scalable and practical to recover 365 high-quality and middle-quality genomes (including 21 new ones), providing insights into the microbiome transmission. CLMB is open-source and available at https://***/zpf0117b/CLMB/. © 2021, CC BY-NC-ND.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Design innovation and study on pot bearings for highway bridges 6

Design innovation and study on pot bearings for highway brid...

引用

6th Chinese-European Workshop on Functional Pavement Design, CEW 2020

作者： Li, M. Zhang, C. Yin, P. Ban, X.Y. Rong, J.G. Wang, C. Research Institute of Highway Ministry of Transportation Beijing China China Transportation Inspection and Verification Hi-Tech Co. Ltd Beijing China National Engineering Research Center of Road Maintenance Technologies RoadMainT Co. Ltd. Beijing China Highway Monitoring and Response Center Ministry of Transport of the P.R.C Beijing China National Routes Network Beijing Transportaion Technology Co. Ltd. Beijing China

ISBN: (纸本)9780367726102

All the time, the main elements of pot bearings including pots, steel pistons and anchoring bolts are designed respectively for the three types including fixed, bilateral, and unilateral types. The optimal design idea of mechanical engineering which is to obtain the optimal design with the minimum numbers of elements is introduced in the innovative design of pot bearings for highway bridges. By the application of innovative design of elements including pots, steel pistons as well as anchoring bolts, the steel pistons can be employed universally for the two types of unilateral and bilateral pot bearings, meanwhile, pots are also interchangeable for the three types of unilateral, bilateral and fixed pot bearings, and the related elements like elastomeric discs, anchoring bolts can be employed universally, which provides great convenience for factory production and assembly. The 3D finite element analyses results indicate the pot bearings for highway bridges with innovative design can meets the design requirements. © 2021 Taylor & Francis Group, London,

关键词： Optimal systems

来源：评论

学校读者我要写书评

暂无评论

The cyclic strain evolution and the fatigue prediction in non-proportional multiaxial loadings of NiTi SMAs

引用

Procedia Structural Integrity 2022年 38卷 546-553页

作者： Di Song Chao Yu School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China No.2006 Xiyuan Ave West Hi-Tech Zone 611731 Chengdu P.R. China Materials Mechanics Group Department of Civil and Environmental Sciences Technical University of Darmstadt Franziska-Braun-Straße 3 64285 Darmstadt Germany Institute of Electronic and Information Engineering of UESTC in Guangdong No. 17 Headquarters 2nd Road Songshan Lake High-tech Industrial Development Zone 523808 Dongguan P.R. China School of Mechanics and Engineering Southwest Jiaotong University No. 111 North Section 1 Second Ring Road 610031 Chengdu P.R. China

NiTi shape memory alloy is a kind of smart material which present unique properties of superelasticity, shape memory and excellent biocompatibility. The applications of such alloys are generally the connectors and fasteners, vibration-dampers, and endovascular stents, etc.. The cyclic deformation and fatigue failure of NiTi SMAs are key issues that need to be investigated since they usually endure complex cyclic loadings during the using process. In this paper, the evolutions of the peak/valley strains in non-proportional multiaxial fatigue loadings of NiTi SMAs are considered, and the fatigue failure mechanism is investigated. The results show that the martensite transformation and martensite re-orientation process greatly influence the transformation ratcheting and fatigue life of NiTi SMAs, and a life-prediction model that considers these deformation mechanisms particular for NiTi SMAs is also proposed to give reasonable predictions.

关键词： NiTi shape memory alloys fatigue failure superelasticity cyclic deformation

来源：评论

学校读者我要写书评

暂无评论

Nanoporous Titanate Nanosheet-Based Membranes for Water Treatment and Molecular Separations

SSRN

引用

SSRN 2022年

作者： Yao, Fangyi Zhang, Wenxiong Hu, Dengwei Li, Sen Kong, Xingang Uemura, Shinobu Kusunose, Takafumi Feng, Qi Department of Advanced Materials Science Faculty of Engineering and Design Kagawa University 2217-20 Hayashi-cho Takamatsu-shi 761-0396 Japan Institute for Solid State Physics The University of Tokyo Sayo Hyogo 679-5148 Japan College of Chemistry and Chemical Engineering Baoji University of Arts and Science 1-Hi-Tech Avenue Shaanxi Baoji721013 China Materials Science and Engineering Southern University of Science and Technology Nanshan 1088 Xueyuan Avenue Guangdong Shenzhen518055 China School of Materials Science and Engineering Shaanxi University of Science and Technology Weiyang Shaanxi Xi’an710021 China

Nanoporous layered titanate (HTO) nanosheet membranes were fabricated via restacking nanoporous HTO nanosheets on a hydrophilic polytetrafluoroethylene (PTFE) filter substrate. Nanoporous HTO nanosheets were prepared by exfoliating a nanoporous HTO that was obtained by selectively dissolving BaTiO 3 (BT) nanoparticles in a mesocrystalline BT/HTO nanocomposite in an HCl solution. The BT/HTO nanocomposites were synthesized by the solvothermal treatment of HTO platelike particles in a Ba(OH) 2 solution. The pore size of the nanoporous HTO nanosheet membrane was controlled by the BT nanoparticle size in the BT/HTO nanocomposite. Meanwhile, the size of the BT nanoparticle was controllable by the solvothermal synthesis conditions of the BT/HTO nanocomposite, including the reaction temperature, Ba/Ti mole ratio, and solvent in the reaction system. Furthermore, we designed a self-adjusting membrane thickness process (SAMTP) to efficiently fabricate nanoporous HTO nanosheet membranes on the PTFE substrate. The rejection of solutes with different sizes and water permeance capacities demonstrated that the nanoporous HTO nanosheet membranes fabricated by the SAMTP possessed size-controlled nanopores with uniform size in the range of 1.5–100 nm, uniform nanometer-scale thicknesses, excellent hydrophilicity, high water permeance, and good durability. Thus, the fabricated nanoporous HTO nanosheet membranes would be excellent candidates for water treatment and molecule separation. © 2022, The Authors. All rights reserved.

关键词： Water treatment

来源：评论

学校读者我要写书评

暂无评论

Ultra-Hydrophilic Layered Titanate Nanosheet-Based Nanofiltration Membrane with Ultrafast Water Transport for Low Energy Consumption Desalination

SSRN

引用

SSRN 2022年

作者： Yao, Fangyi Zhang, Wenxiong Hu, Dengwei Li, Sen Kong, Xingang Uemura, Shinobu Kusunose, Takafumi Feng, Qi Department of Advanced Materials Science Faculty of Engineering and Design Kagawa University 2217-20 Hayashi-cho Takamatsu-shi761-0396 Japan Institute for Solid State Physics The University of Tokyo Hyogo Sayo679-5148 Japan College of Chemistry and Chemical Engineering Baoji University of Arts and Sciences 1-Hi-Tech Avenue Shaanxi Baoji721013 China Materials Science and Engineering Southern University of Science and Technology Nanshan 1088 Xueyuan Avenue Guangdong Shenzhen518055 China School of Materials Science and Engineering Shaanxi University of Science and Technology Weiyang Shaanxi Xi’an710021 China

Nanofiltration (NF) membranes have significant applications to solve global water scarcity issues. An ultra-hydrophilic inorganic NF membrane was fabricated using ultra-hydrophilic layered titanate H 1.07 Ti 1.73 O 4 · n H 2 O nanosheets (HTO-ns), which exhibits high selectivity for desalination and small molecule separations while maintained an ultrafast water transport at low operating pressure. This membrane would be a low-energy consumption NF membrane. To fabricate the HTO-ns membrane, a straightforward technique, namely, the self-adjusting membrane thickness process (SAMTP), was developed by the restacking process of negatively charged HTO-ns with cations on a porous polytetrafluoroethylene (PTFE) substrate. A large-scaled high-quality HTO-ns membrane can be fabricated on a PTFE substrate surface-modified with a silane coupling agent of N -(2-aminoethyl)-3-aminopropyltrimethoxysilane and Cu 2+ adsorption. There are two kinds of nanochannels for water transport through the membrane, namely, interlayer nanochannels and nanosheet edges chink nanochannels. The excellent separation performances were contributed by the interlayer nanochannels and Donnan exclusion effect of the negatively charged HTO-ns. The SAMTP technique developed in this study could also be applied simply to fabricate other metal oxide nanosheet membranes, which would open a new avenue to the high-performance ultra-hydrophilic inorganic nanosheet-based membranes for low energy consumption separation processes. © 2022, The Authors. All rights reserved.

关键词： Desalination

来源：评论

学校读者我要写书评

暂无评论

Machine learning based model for risk prediction after ST-Elevation myocardial infarction: Insights from the North India ST elevation myocardial infarction (NORIN-STEMI) registry

引用

International Journal of Cardiology 2022年 362卷 6-13页

作者： Shetty, Manu Kumar Kunal, Shekhar Girish, M.P. Qamar, Arman Arora, Sameer Hendrickson, Michael Mohanan, Padhinhare P. Gupta, Puneet Ramakrishnan, S. Yadav, Rakesh Bansal, Ankit Zachariah, Geevar Batra, Vishal Bhatt, Deepak L. Gupta, Anubha Gupta, Mohit Department of Clinical Pharmacology Maulana Azad Medical College Delhi India Department of Cardiology GB Pant Institute of Postgraduate Medical Education and Research New Delhi India Section of Interventional Cardiology and Vascular Medicine NorthShore University Health System University of Chicago Pritzker School of Medicine Evanston IL United States Division of Cardiology University of North Carolina School of Medicine Chapel Hill NC United States University of North Carolina School of Medicine Chapel Hill NC United States Department of Cardiology Westfort Hi-Tech Hospital Punkunnam Kerala Thrissur India Department of Cardiology Janakpuri Superspeciality Hospital New Delhi India Department of Cardiology All India Institute of Medical Sciences Delhi India Mother Heart Care Kerala Thrissur India Heart and Vascular Institute Brigham and Women's Hospital Harvard Medical School Boston MA United States SBILab Department of Electronics and Communications Engineering Indraprastha Institute of Information Technology- Delhi IIIT-D India

Background: Risk prediction following ST-Elevation Myocardial Infarction (STEMI) in resource limited countries is critical to identify patients at an increased risk of mortality who might benefit from intensive management. Methods: North India ST-Elevation Myocardial Infarction (NORIN-STEMI) is an ongoing registry that has prospectively enrolled 3,635 STEMI patients. Of these, 3191 patients with first STEMI were included. Patients were divided into two groups: development (n=2668) and validation (unseen) dataset (n=523). Various ML strategies were used to train and tune the model based on validation dataset results that included 31 clinical characteristics. These models were compared in sensitivity, specificity, F1-score, receiver operating characteristic area under the curve (AUC), and overall accuracy to predict mortality at 30 days. ML model decision making was analyzed using the Shapley Additive exPlanations (ShAP) summary plot. Results: At 30 days, the mortality was 7.7%. On the validation dataset, Extra Tree ML model had the best predictive ability with sensitivity: 85%, AUC: 79.7%, and Accuracy: 75%. ShAP interpretable summary plot determined delay in time to revascularization, baseline cardiogenic shock, left ventricular ejection fraction <30%, age, serum creatinine, heart failure on presentation, female sex, and moderate-severe mitral regurgitation to be major predictors of all-cause mortality at 30 days (P<0.001 for all). Conclusion: ML models lead to an improved mortality prediction following STEMI. ShAP summary plot for the interpretability of the AI model helps to understand the model's decision in identifying high-risk individuals who may benefit from intensified follow-up and close monitoring. © 2022 Elsevier B.V.

关键词： Artificial intelligence Machine learning Risk prediction STEMI

来源：评论

学校读者我要写书评

暂无评论

Multi-target Positioning Method of Passive MIMO Radar based on DBSCAN 2020

Multi-target Positioning Method of Passive MIMO Radar based ...

引用

3rd International Conference on Signal Processing and Machine Learning, SPML 2020

作者： Wang, Lijun Han, Yu Wang, Li Chen, Yiqi Li, Wanchun Science and Technology on Communication Information Security Control Laboratory. No. 36 Research Institute of Cetc No.387 hongxing road Jiaxing Zhejiang314033 China School of Information and Communication Engineering University of Electronic Science and Technology of China No.2006 Xiyuan Ave West Hi-Tech Zone Chengdu Sichuan611731 China

ISBN: (纸本)9781450375733

In this paper, we propose a passive Multiple Input Multiple Output (MIMO) radar multi-target positioning method based on DBSCAN (Density-Based Spatial Clustering of Applications with Noise). MIMO radar has received extensive attention and researches since it has been introduced. Applying MIMO radar theory to passive radar technology can combine the advantages of the two technologies and get better detection performance. In this paper, the multi-target data association algorithm is mainly used, and the time delay information measured by multiple receiving stations is converted into distance information and associated with the cost matrix. First, data preprocessing is performed by eliminating data in the cost matrix which is greater than the threshold. Then DBSCAN clustering algorithm is used to divide the data into clusters. Finally, different clusters are weighted and fused to obtain multi-target position estimates. Simulation results prove that the algorithm performs well. © 2020 ACM.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Fast distance measurement with a long ambiguity range using a free-running dual-comb fiber laser

Fast distance measurement with a long ambiguity range using ...

引用

2020 Frontiers in Optics Conference, FiO 2020

作者： Liu, Ya Zhu, Zhigao Yang, Jie Hu, Guoqing Yunnan Key Laboratory of Opto-Electronic Information Technology School of Physics and Electronic Information Technology Yunnan Normal University Kunming650500 China School of Electronic and Information Engineering Beihang University Beijing100191 China School of Mechanical Engineering and Automation Beihang University Beijing100191 China Hefei Innovation Research Institute of Beihang University Xinzhan Hi-tech District Anhui230012 China

A distance measurement scheme based on a free-running dual-comb mode-locked fiber laser is demonstrated. With alternately sampling based on Vernier effect, it can realize long ambiguity range for fast real-time measur... 详细信息

ISBN: (纸本)9781943580804

关键词： Fiber lasers

来源：评论

学校读者我要写书评

暂无评论

Correction to: Deep convolutional spiking neural network fostered automatic detection and classification of breast cancer from mammography images

引用

Research on Biomedical engineering 2023年第4期39卷 1033-1033页

作者： Prakash, T. Senthil Kannan, G. Prabhakaran, Salini Prajapati, Bhagirath Parshuram Department of Computer Science and Engineering Shree Venkateshwara Hi-Tech Engineering College Gobichettipalayam India Department of Electronics and Communication Engineering Amrita College of Engineering and Technology Nagercoil India Department of Computer Science and Engineering Puducherry Technological University Puducherry India Department of Computer Engineering A. D. Patel Institute of Technology New Vallabh Vidyanagar India

来源：评论

学校读者我要写书评

暂无评论

An Efficient Attention-Based Meta Normalcy Learner for Video Anomaly Detection

SSRN

引用

SSRN 2022年

作者： Huang, Li Zeng, Yuqing Xie, Xiurui Yin, Shibai Liu, Guisong School of Computing and Artificial Intelligence Southwestern University of Finance and Economics 555 Liutai Avenue Wenjiang District Sichuan Chengdu611130 China School of Computer Science and Engineering University of Electronic Science and Technology of China Qingshuihe Campus No.2006 Xiyuan Avenue West Hi-Tech Zone Sichuan Chengdu611731 China Kashi Institute of Electronics and Information Industry Xinjiang Kashgar844000 China

Video Anomaly Detection (VAD) is a challenging pattern recognition task which asks automated detection abnormal behavior of human beings from videos. Unfortunately, VAD models are known to be computationally expensive and poor robustness – anomalies in different scenes can not be exhaustive, which hinders the VAD model to apply in the real-world although this is a particularly realistic task. Previous methods formulated this task as a reconstructed task under unsupervised learning. The main drawback is that might cause the "over-generalization" problem due to the powerful representation capacity of deep neural networks. To address this issue, we present ABNL, an attention-based Normalcy Learner for VAD. It records diverse normal patterns by taking advantage of different group parameters in the attention network, without any extra storage. Furthermore, we incorporate the Meta-Learning to enable the ABNL with powers of scene-adaptive by a few frames adjustment. Experimental results on three standard benchmarks show the impressive running time of our model and demonstrate the effectiveness and efficiency. © 2022, The Authors. All rights reserved.

关键词： Anomaly detection

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：