检索结果-内蒙古大学图书馆

Corrosion behavior of Mg-3Gd-1Zn-0.4Zr alloy with and without stacking faults

学校读者我要写书评

暂无评论

Journal of Magnesium and Alloys 2019年第2期7卷 240-248页

作者： Xiaobo Zhang Jianwei Dai Ruifeng Zhang Zhixin Ba Nick Birbilis Jiangsu Key Laboratory of Advanced Structural Materials and Application Technology School of Materials Science and EngineeringNanjing Institute of TechnologyNanjing 211167China School of Materials Science and Engineering Central South UniversityChangsha 410083China College of Engineering and Computer Science Australian National UniversityActon ACT 2000Australia

To develop biodegradable magnesium alloy with desirable corrosion properties,a low Gd-containing Mg-3Gd-1Zn-0.4Zr(wt%,GZ31K)alloy was *** as-cast ingot was solution treated and then hot *** were characterized by scanning electron microscopy(SEM).Corrosion behavior of the alloy under each condition was studied by hydrogen evolution and quasi in-situ corrosion *** has been found that the as-cast alloy is composed ofα-Mg,stacking faults(SFs)at the outer edge of the matrix grains,and eutectic phase along the grain *** solution treatment,the SFs disappear and precipitates rich in Zn and Zr elements form in the grain interior and *** microstructure is significantly refined after *** evolution tests show that the as-cast alloy exhibits the best corrosion resistance,and the solution-treated alloy has the worst corrosion *** rate of the alloy under each condition decreases first and then increases with prolonging immersion *** experiments demonstrate thatα-Mg was corroded preferentially,the eutectic phase and precipitates exhibit better corrosion *** as-extruded alloy demonstrates uniform corrosion due to fine and homogeneous microstructure.

关键词： Magnesium alloys Stacking faults Corrosion resistance Uniform corrosion

Automatic Sleep Spindle Detection and Analysis in Patients with Sleep Disorders 1

学校读者我要写书评

暂无评论

2nd International Workshop on Human Brain and Artificial Intelligence, HBAI 2020 held in Conjunction with IJCAI-PRICAI 2020

作者： Chen, Chao Zhu, Xuequan Belkacem, Abdelkader Nasreddine Lu, Lin Hao, Long You, Jia Shin, Duk Tan, Wenjun Huang, Zhaoyang Ming, Dong Academy of Medical Engineering and Translational Medicine Tianjin University Tianjin300072 China Key Laboratory of Complex System Control Theory and Application Tianjin University of Technology Tianjin300384 China Department of Computer and Network Engineering College of Information Technology UAE University Al Ain15551 United Arab Emirates Zhonghuan Information College Tianjin University of Technology Tianjin300380 China Department of Electronics and Mechatronics Tokyo Polytechnic University Atsugi243-0297 Japan School of Computer Science and Engineering Northeastern University Shenyang110189 China Department of Neurology Xuanwu Hospital Capital Medical University Beijing100088 China

ISBN: (数字)9789811612886

ISBN: (纸本)9789811612879

Nowadays, Sleep disorder is a common disease, and spindle spindles are important features of the second stage non-rapid eye movement (NREM) sleep. In this paper, we propose an improved automatic detection method of spindles based on wavelet transform. The spindles automatic detector is mainly composed of wavelet transform and clustering. We collected the electroencephalography (EEG) signals of six patients with sleep disorders all night for ten hours, and then preprocessed the data and other operations, and then used our improved method to detect the sleep EEG signals by spindles. By comparing with the previous automatic detection method not improved and another automatic detection method, the results show that the accuracy of sleep spindles detection can be effectively improved. The accuracy of the improved detector is 5.19% higher than before, and 9.7% higher than that of another method based on amplitude threshold. Finally, we made a simple comparison between people with sleep disorders and normal people. We found that there were significant differences in spindle density between people with sleep disorders and people without sleep disorders. The average spindle density in the normal population averaged 2.59 spindles per minute. People with sleep disorders had an average spindle density of 1.32 spindles per minute. In future research, our research direction is to improve the accuracy of spindles automatic detection by improving the spindles detector and study the difference of spindles between patients with sleep disorders and normal people in a large number of samples, so that the difference of spindles can be used as the basis for the diagnosis of sleep disorders. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Wavelet transforms

Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Kai Zhang, Kun Liu, Qi Huang, Zhenya Zhang, Mengdi Wu, Wei Cheng, Mingyue Chen, Enhong Anhui Province Key Lab. of Big Data Analysis and Application University of S&T of China State Key Laboratory of Cognitive Intelligence Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Meituan Beijing China Anhui Province Key Lab. of Big Data Analysis and Application University of S&T of China Hefei China

Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domain. Existing studies in this task attach more attention to the sequence modeling of sentences while largely ignoring the rich domain-invariant semantics embedded in graph structures (i.e., the part-of-speech tags and dependency relations). As an important aspect of exploring characteristics of language comprehension, adaptive graph representations have played an essential role in recent years. To this end, in the paper, we aim to explore the possibility of learning invariant semantic features from graph-like structures in CDSC. Specifically, we present Graph Adaptive Semantic Transfer (GAST) model, an adaptive syntactic graph embedding method that is able to learn domain-invariant semantics from both word sequences and syntactic graphs. More specifically, we first raise a POS-Transformer module to extract sequential semantic features from the word sequences as well as the part-of-speech tags. Then, we design a Hybrid Graph Attention (HGAT) module to generate syntax-based semantic features by considering the transferable dependency relations. Finally, we devise an Integrated aDaptive Strategy (IDS) to guide the joint learning process of both modules. Extensive experiments on four public datasets indicate that GAST achieves comparable effectiveness to a range of state-of-the-art models. © 2022, CC BY.

关键词： Sentiment analysis

Modern deep learning in bioinformatics

学校读者我要写书评

暂无评论

Journal of Molecular Cell Biology 2020年第11期12卷 823-827页

作者： Haoyang Li Shuye Tian Yu Li Qiming Fang Renbo Tan Yijie Pan Chao Huang Ying Xu Xin Gao Cancer Systems Biology Center The China-Japan Union HospitalJilin UniversityChangchun 130033China MOE Key Laboratory of Symbolic Computation and Knowledge Engineering College of Computer Science and TechnologyJilin UniversityChangchun 130012China Department of Biology Southern University of Science and TechnologyShenzhen 518055China Computational Bioscience Research Center(CBRC) Computer Electrical and Mathematical Sciences and Engineering(CEMSE)DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955Saudi Arabia School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou 310018China Ningbo Institute of Information Technology Application Chinese Academy of SciencesNingbo 315040China Computational Systems Biology Lab Department of Biochemistry and Molecular Biology and Institute of BioinformaticsUniversity of GeorgiaAthensGA 30602USA

Deep learning(DL)has shown explosive growth in its application to bioinformatics and has demonstrated thrillingly promising power to mine the complex relationship hidden in large-scale biological and biomedical data.A number of comprehensive reviews have been published on such applications,ranging from high-level reviews with future perspectives to those mainly serving as tutorials.

关键词： has such she

Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Lei Zhang, Yuzhong Zhang, Jiadong Qian, Xuejun Gong, Chen Sun, Kun Ding, Zhongxiang Wang, Xing Li, Zhenhui Liu, Zaiyi Shen, Dinggang The School of Health Science and Engineering University of Shanghai for Science and Technology Shanghai China The School of Biomedical Engineering ShanghaiTech University China The School of Computer Science and Engineering Nanjing University of Science and Technology China Ruijin Hospital Shanghai Jiaotong University School of Medicine China Department of Radiology Key Laboratory of Clinical Cancer Pharmacology and Toxicology Research of Zhejiang Province China The Shanghai General Hospital Shanghai JiaoTong University China Department of Radiology The Third Affiliated Hospital of Kunming Medical University China Department of Radiology Guangdong Provincial Peo-ple's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China School of Biomedical Engineering State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence Co. Ltd. Shanghai200232 China Shanghai Clinical Research and Trial Center Shanghai201210 China

Automated breast tumor segmentation on the basis of dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) has shown great promise in clinical practice, particularly for identifying the presence of breast disease. However, accurate segmentation of breast tumor is a challenging task, often necessitating the development of complex networks. To strike an optimal tradeoff between computational costs and segmentation performance, we propose a hybrid network via the combination of convolution neural network (CNN) and transformer layers. Specifically, the hybrid network consists of a encoder-decoder architecture by stacking convolution and deconvolution layers. Effective 3D transformer layers are then implemented after the encoder subnetworks, to capture global dependencies between the bottleneck features. To improve the efficiency of hybrid network, two parallel encoder subnetworks are designed for the decoder and the transformer layers, respectively. To further enhance the discriminative capability of hybrid network, a prototype learning guided prediction module is proposed, where the category-specified prototypical features are calculated through online clustering. All learned prototypical features are finally combined with the features from decoder for tumor mask prediction. The experimental results on private and public DCE-MRI datasets demonstrate that the proposed hybrid network achieves superior performance than the state-of-the-art (SOTA) methods, while maintaining balance between segmentation accuracy and computation cost. Moreover, we demonstrate that automatically generated tumor masks can be effectively applied to identify HER2-positive subtype from HER2-negative subtype with the similar accuracy to the analysis based on manual tumor segmentation. The source code is available at https://***/ZhouLlab/PLHN. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

Data-driven Global Ocean Modeling for Seasonal to Decadal Prediction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Zijie Lyu, Pumeng Ling, Fenghua Bai, Lei Luo, Jing-Jia Boers, Niklas Yamagata, Toshio Izumo, Takeshi Cravatte, Sophie Capotondi, Antonietta Ouyang, Wanli School of Computer Science Fudan University Shanghai China Shanghai Artificial Intelligence Laboratory Shanghai China School of Future Technology Nanjing University of Information Science and Technology Nanjing China Earth System Modelling School of Engineering and Design Technical University of Munich Munich Germany Potsdam Institute for Climate Impact Research Potsdam Germany Application Laboratory Japan Agency for Marine-Earth Science and Technology Yokohama Japan Tahiti French Polynesia LEGOS IRD UT3 CNES CNRS Université de Toulous Toulouse France Nouméa New Caledonia Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder Colorado Boulder United States NOAA Physical Sciences Laboratory Colorado Boulder United States

Accurate ocean dynamics modeling is crucial for enhancing understanding of ocean circulation, predicting climate variability, and tackling challenges posed by climate change. Despite improvements in traditional numerical models, predicting global ocean variability over multi-year scales remains challenging. Here, we propose ORCA-DL (Oceanic Reliable foreCAst via Deep Learning), the first data-driven 3D ocean model for seasonal to decadal prediction of global ocean circulation. ORCA-DL accurately simulates three-dimensional ocean dynamics and outperforms state-of-the-art dynamical models in capturing extreme events, including El Niño-Southern Oscillation and upper ocean heatwaves. This demonstrates the high potential of data-driven models for efficient and accurate global ocean forecasting. Moreover, ORCA-DL stably emulates ocean dynamics at decadal timescales, demonstrating its potential even for skillful decadal predictions and climate projections. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital elevation model

Connecting embeddings for knowledge graph entity typing 58

学校读者我要写书评

暂无评论

Connecting embeddings for knowledge graph entity typing

58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

作者： Zhao, Yu Zhang, Anxiang Xie, Ruobing Liu, Kang Wang, Xiaojie Fintech Innovation Center School of Economic Information Engineering Southwestern University of Finance and Economics Chengdu China School of Computer Science Carnegie Mellon University Pittsburgh United States WeChat Search Application Department Tencent Beijing China Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China School of Computer Science Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781952148255

Knowledge graph (KG) entity typing aims at inferring possible missing entity type instances in KG, which is a very significant but still under-explored subtask of knowledge graph completion. In this paper, we propose a novel approach for KG entity typing which is trained by jointly utilizing local typing knowledge from existing entity type assertions and global triple knowledge from KGs. Specifically, we present two distinct knowledge-driven effective mechanisms of entity type inference. Accordingly, we build two novel embedding models to realize the mechanisms. Afterward, a joint model with them is used to infer missing entity type instances, which favors inferences that agree with both entity type instances and triple knowledge in KGs. Experimental results on two real-world datasets (Freebase and YAGO) demonstrate the effectiveness of our proposed mechanisms and models for improving KG entity typing. The source code and data of this paper can be obtained from: https://***/Adam1679/ConnectE. © 2020 Association for Computational Linguistics

关键词： Knowledge graph

A Survey on Small Sample Imbalance Problem: Metrics, Feature Analysis, and Solutions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Shuxian Gui, Jie Dong, Minjing Yu, Baosheng Gui, Zhipeng Dong, Lu Tang, Yuan Yan Kwok, James Tin-Yau School of Cyber Science d Engineering Southeast University Nanjing210000 China School of Cyber Science and Engineering Southeast University Nanjing211189 China Engineering Research Center of Blockchain Application Supervision and Management Southeast University Nanjing211189 China Purple Mountain Laboratories Nanjing210000 China Department of Computer Science City University of Hong Kong Hong Kong Lee Kong Chian School of Medicine Nanyang Technological University Singapore School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China Collaborative Innovation Center of Geospatial Technology Wuhan University Wuhan430079 China Department of Computer and Information Science University of Macau China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

—The small sample imbalance (S&I) problem is a major challenge in machine learning and data analysis. It is characterized by a small number of samples and an imbalanced class distribution, which leads to poor model performance. In addition, indistinct inter-class feature distributions further complicate classification tasks. Existing methods often rely on algorithmic heuristics without sufficiently analyzing the underlying data characteristics. We argue that a detailed analysis from the data perspective is essential before developing an appropriate solution. Therefore, this paper proposes a systematic analytical framework for the S&I problem. We first summarize imbalance metrics and complexity analysis methods, highlighting the need for interpretable benchmarks to characterize S&I problems. Second, we review recent solutions for conventional, complexity-based, and extreme S&I problems, revealing methodological differences in handling various data distributions. Our summary finds that resampling remains a widely adopted solution. However, we conduct experiments on binary and multiclass datasets, revealing that classifier performance differences significantly exceed the improvements achieved through resampling. Finally, this paper highlights open questions and discusses future trends. Copyright © 2025, The Authors. All rights reserved.

关键词： Taxonomies

Enhancement of HELM operations using multi-node hadoop cluster and cloud platform

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2023年第1期2782卷

作者： Hitesh Kumar Sharma Prashant Ahlawat Bhawana Kaushik Surekha Sandeep Singh Kang Raman Chadha School of Computer Science University of Petroleum & Energy Studies (UPES) Energy Acres Bidholi Dehradun-248007 Uttarakhand India Department of Computer Science and Engineering University Institute of Engineering Chandigarh University Gharuan Mohali Chandigarh India Bachelor of Computer Application GL Bajaj Institute of Management Greater Noida India ABES Engineering College Ghaziabad Uttar Pradesh India

Secure matrix computation is the most used and fundamental operation for analysis of large sets of data existing in today's world. It also has extended its domain into machine learning by protecting the confidentiality of the input data. Homomorphic encryption algorithms are being used to achieve secure computation. These algorithms focus on performing computation on secured data, in order to ensure data security and prevent data from unauthorized access. Our motive is to achieve secure HELM (Homomorphic Encrypted Large Matrix) operations and there are some already defined algorithms for this purpose like BGV 8Background Verification) and few others. As IT industry is adapting cloud solutions to work on distributed environment. Cloud provides enhanced functionalities, but with this, we have to work on securing the data. In modern world when we use Encryption algorithm to secure the data and each time when we want to perform any operation then we have to decrypt the data. These types of operation are costlier to perform in a distributed environment. Therefore, there is a need to develop a new methodology, which does not decrypt the cipher text every time for performing some operations. In addition, the operations must be cost and time optimized. In this research work, we perform large matrix multiplications using the BGV homomorphic scheme and further deploy them on Hadoop clusters to perform parallel computations on the big data sets.

关键词：