检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, Kun Lv, Guangyi Wang, Meng Chen, Enhong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China School of Computer Science and Technology University of Science and Technology of China China

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, where much recent progress has been made by advancement of representation learning techniques and inspiration of human behaviors. Among all these methods, attention mechanism plays an essential role by selecting important parts effectively. However, current attention methods either focus on all the important parts in a static way or only select one important part at one attention step dynamically, which leaves a large space for further improvement. To this end, in this paper, we design a novel Dynamic Gaussian Attention Network (DGA-Net) to combine the advantages of current static and dynamic attention methods. More specifically, we first leverage pre-trained language model to encode the input sentences and construct semantic representations from a global perspective. Then, we develop a Dynamic Gaussian Attention (DGA) to dynamically capture the important parts and corresponding local contexts from a detailed perspective. Finally, we combine the global information and detailed local information together to decide the semantic relation of sentences comprehensively and precisely. Extensive experiments on two popular sentence semantic matching tasks demonstrate that our proposed DGA-Net is effective in improving the ability of attention mechanism. © 2021, CC BY.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Local Entropy Based Fuzzy Connectedness Segmentation for Thyroid Ultrasound Images

Local Entropy Based Fuzzy Connectedness Segmentation for Thy...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yixuan Fu Kai Li Junying Chen Key Laboratory of Big Data and Intelligent Robot (SCUT) Ministry of Education School of Software Engineering South China University of Technology Guangzhou China Department of Ultrasound Third Affiliated Hospital of Sun Yat-sen University Guangzhou China

Although deep learning methods are popular in recent years to achieve dominant image segmentation performance, the carefully annotated training images are very difficult to obtain in clinical medicine, and the deep learning model training demands a lot of computing resources which are not always available. To overcome these difficulties, it is very necessary to investigate segmentation algorithms which do not require any training data. In this work, we improve a semi-automatic conventional segmentation algorithm, fuzzy connectedness segmentation, by introducing the local information entropy of the ultrasound image into the fuzzy affinity membership function. The proposed semi-automatic local entropy based fuzzy connectedness (LEFC) segmentation algorithm is further modified by incorporating the popular deep learning methods to make the LEFC algorithm fully automatic. The proposed semi-automatic LEFC algorithm achieves better performance than other representative fuzzy connectedness segmentation algorithms with the accuracy and IoU values increased by 5.9~14% and 5~10.5%, and achieves very close segmentation performance as compared with the best deep learning model in the experiments (0.2% lower accuracy and 0.2% lower IoU compared to CE-Net). Besides, the automatic LEFC algorithm improves the segmentation results obtained by the corresponding deep learning based coarse segmentation modules with the accuracy and IoU increased by 0.2~8% and 0.1~3.8%, respectively. Furthermore, the experiment results demonstrate that the proposed automatic LEFC algorithm obtains stably good segmentation performance even with limited training data, achieving the accuracy and IoU values (at the stable state) 23.6 % and 18.5% higher than those of the corresponding U-Net model which is trained with the samesized dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Selective Similarity Integration for Drug-Target Interaction Prediction

arXiv

引用

arXiv 2022年

作者： Liu, Bin Wang, Jin Sun, Kaiwei Tsoumakas, Grigorios Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and Telecommunications Chongqing400065 China School of Informatics Aristotle University of Thessaloniki Thessaloniki54124 Greece

The discovery of drug-target interactions (DTIs) is a pivotal process in pharmaceutical development. Computational approaches are a promising and efficient alternative to tedious and costly wet-lab experiments for predicting novel DTIs from numerous candidates. Recently, with the availability of abundant heterogeneous biological information from diverse data sources, computational methods have been able to leverage multiple drug and target similarities to boost the performance of DTI prediction. Similarity integration is an effective and flexible strategy to extract crucial information across complementary similarity views, providing a compressed input for any similarity-based DTI prediction model. However, existing similarity integration methods filter and fuse similarities from a global perspective, neglecting the utility of similarity views for each drug and target. In this study, we propose a Fine-Grained Selective similarity integration approach, called FGS, which employs a local interaction consistency-based weight matrix to capture and exploit the importance of similarities at a finer granularity in both similarity selection and combination steps. We evaluate FGS on five DTI prediction datasets under various prediction settings. Experimental results show that our method not only outperforms similarity integration competitors with comparable computational costs, but also achieves better prediction performance than state-of-the-art DTI prediction approaches by collaborating with conventional base models. Furthermore, case studies on the analysis of similarity weights and on the verification of novel predictions confirm the practical ability of FGS. Copyright © 2022, The Authors. All rights reserved.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

Preparation of Uniform SiO2 Insulating Layer on the Inner Wall of TSV by Thermal Oxidation

Preparation of Uniform SiO2 Insulating Layer on the Inner Wa...

引用

Joint e-Manufacturing and Design Collaboration Symposium (eMDC) & International Symposium on Semiconductor Manufacturing (ISSM)

作者： Guo Fengjie Ran Jing Yang Wang Shuo Ma Kui Yang Fa Shun Guizhou Provincial Key Laboratory of Micro and nano Electronics and Software Technology College of Big Data and Information Engineering Guizhou University Guiyang City Guizhou Province China

ISBN: (纸本)9781665471343

SiO 2 insulating layer is an indispensable part of a TSV. In the current process, the SiO 2 insulating layer is commonly deposited on the inner wall of the TSV based on deep trench sputtering method. The thickness at different position (neck, middle, bottom) of the SiO 2 insulating layer, deposited by deep trench sputtering, is non-uniform. In this paper, the thickness uniformity of SiO 2 insulating layer prepared on the inner wall of TSV based on CVD&PVD process and thermal oxidation method is comparatively studied. The experimental results show that, based on the CVD&PVD process, the average thickness of the SiO 2 insulating layer at middle and bottom position of the TSV has changed by - 54.02% and - 58.30% compared with that at the top position, respectively. Based on the thermal oxidation method, the average thickness of the SiO 2 insulating layer at middle and bottom position of the TSV has changed by 1.17% and 0.26% compared with that at the top position, respectively. The thermal oxidation method can realize the SiO 2 insulating layer with uniform thickness on the inner wall of TSV.

关键词： Silicon compounds Semiconductor device manufacture Oxidation Neck Through-silicon vias Sputtering

来源：评论

学校读者我要写书评

暂无评论

Joint Subcarrier and Power Allocation in D2D Communications Underlaying Cellular Networks

Joint Subcarrier and Power Allocation in D2D Communications ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Caihong Kai Yan Wu Xinyue Hu Wei Huang Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Hefei China

ISBN: (数字)9781728131061

ISBN: (纸本)9781728131078

For the high density of users and accompanying network service requirements in the cellular system, Device-to-Device (D2D) communication is a promising technology to cope with the increasing wireless traffic demands by reusing spectrum resources. In practice, the wireless signal is easy to be eavesdropped in D2D communications underlaying cellular networks, hence, ensuring a secure communication for cellular user equipments (CUEs) is an urgent and meaningful problem. In this paper, we propose a joint subcarrier and power allocation scheme for maximizing the sum data rate of D2D pairs, meanwhile protecting the CUEs against eavesdropping. Specifically, in the proposed scheme, we first quantify the security performance with the secrecy data rate, and obtain the closed-form expression for the optimal power allocation of CUEs and D2D pairs by tightening the quality of service (QoS) and secrecy rate requirement constraints of CUEs. Based on the obtained power allocation solution, by searching the optimal mapping relationship between CUEs and D2D pairs, we develop a subcarrier assignment strategy with the Hungarian algorithm to solve it, which can further enhance the sum data rate of D2D pairs. Simulation results demonstrate that the proposed scheme can significantly yield better performance than other schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised vehicle re-identification with progressive adaptation 29

Unsupervised vehicle re-identification with progressive adap...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Peng, Jinjia Wang, Yang Wang, Huibing Zhang, Zhao Fu, Xianping Wang, Meng College of Information and Science Technology Dalian Maritime University Liaoning Dalian China Pengcheng Laboratory Shenzhen Guangdong China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China

ISBN: (纸本)9780999241165

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes;worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as "pseudo target samples". These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Network

arXiv

引用

arXiv 2021年

作者： Fan, Zhaoxin Song, Zhenbo Zhang, Wenping Liu, Hongyan He, Jun Du, Xiaoyong Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Department of Management Science and Engineering Tsinghua University Beijing100084 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, previous methods have made delightful achievements. However, how to deal with catastrophic collapse caused by rotation problems is still under-explored. In this paper, to tackle the issue, we propose a novel Point Cloud-based Rotation-aware Large Scale Place Recognition Network (RPR-Net). In particular, to solve the problem, we propose to learn rotation-invariant features in three steps. First, we design three kinds of novel Rotation-Invariant Features (RIFs), which are low-level features that can hold the rotation-invariant property. Second, using these RIFs, we design an attentive module to learn rotation-invariant kernels. Third, we apply these kernels to previous point cloud features to generate new features, which is the well-known SO(3) mapping process. By doing so, high-level scene-specific rotation-invariant features can be learned. We call the above process an Attentive Rotation-Invariant Convolution (ARIConv). To achieve the place recognition goal, we build RPR-Net, which takes ARIConv as a basic unit to construct a dense network architecture. Then, powerful global descriptors used for retrieval-based place recognition can be sufficiently extracted from RPR-Net. Experimental results on prevalent datasets show that our method achieves comparable results to existing state-of-the-art place recognition models and significantly outperforms other rotation-invariant baseline models when solving rotation problems. Copyright © 2021, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Study on Interaction with High-Abundant Blood Proteins and Identification of Low-Abundant Proteins to 5-Phenyl-1-(P-Tolyl)-1h-1,2,3-Triazole by Serum Proteomics

SSRN

引用

SSRN 2024年

作者： He, Wenying Xie, Cong Wang, Shuai Duan, Hongye Liu, Rongqiang Si, Hongzong Yao, Xiaojun Key Laboratory of Tropical Medicinal Resource Chemistry of Ministry of Education Hainan Normal University Haikou571158 China College of Artificial Intelligence and Big Data for Medical Sciences Shandong First Medical University Jinan250117 China Institute for Computational Science and Engineering Qingdao University Qingdao266071 China College of Chemical and Chemical Engineering Lanzhou University Lanzhou730000 China

In this study, a comprehensive investigation was undertaken to elucidate a simple triazole compound, 5-phenyl-1-(p-tolyl)-1H-1,2,3-triazole (PPTT), its interactions with high-abundant proteins and identification of low-abundant proteins by serum proteomics. Employing a combination of spectroscopic techniques and computational chemistry, the interactions between PPTT and three high-abundance blood globular proteins, namely human serum albumin (HSA), human immunoglobulin G (HIgG), and hemoglobin (BHb), were explored, thereby ascertaining their binding constants and thermodynamic parameters at the molecular level. Subsequently, based on the differential proteomics, utilizing two-dimensional gel electrophoresis (2-DE) in conjunction with matrix-assisted laser desorption time-of-flight mass spectrometry (MALDI-TOF-MS), the research team isolated and identified differentially expressed low-abundance proteins in human blood serum samples following exposure to PPTT. The results showed that there were twenty highly expressed proteins identified from blood serum samples intervened by PPTT. Combining bioinformatics techniques, these proteins were classified, providing preliminary insights like preproprotein or precursors inhibiting the activity of elastase, defending and regulating the immune system, carrying lipid, and other functions into their biological functionalities. One of the differential proteins, apolipoprotein A-1 (ApoA-1) protein, was selected as a possible target to explore the mechanism of action of PPTT intervention on the related signaling pathways involved in Hep G2 cells. These research findings offer scientifically sound guidance for further in-depth exploration, development, and application of the 1,2,3-triazole compound. © 2024, The Authors. All rights reserved.

关键词： Molecular biology

来源：评论

学校读者我要写书评

暂无评论

The Enhanced N-Butanol Gas Sensing Properties Based on Perovskite-Type Znsno3 Nanoflowers

SSRN

引用

SSRN 2024年

作者： Meng, Fanli Zhou, Fangling Mu, Zhuangzhuang Yuan, Zhenyu Zhang, Renze Li, Yudong Zhu, Hongmin Yan, Xin College of Information Science and Engineering Northeastern University Shenyang110819 China Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology Qinhuangdao066004 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Ministry of Education Shenyang110819 China

N-butanol is a volatile organic compound (VOC) that is harmful to human health, and the development of gas sensors for n-butanol vapor detection is necessary. In this work, the nanoflowers-like ZnSnO3 was synthesized via a one-step hydrothermal route followed by an annealing process. The results revealed that optimizing the hydrothermal time to 12 hours resulted in ZnSnO3-2 exhibiting the highest gas response (40.48) towards 100ppm n-butanol at 275°C, boasting a detection limit of 500 ppb. Furthermore, ZnSnO3-2 exhibits excellent gas selectivity and long-term stability. The improved sensing performance of ZnSnO3-2 was attributed to its large specific surface area and abundant oxygen vacancies. Additionally, the gas sensing mechanism for enhancing n-butanol detection was comprehensively analyzed. These results highlight the potential of nanoflower-like ZnSnO3 as a promising candidate for n-butanol gas sensing material, offering both high sensitivity and selectivity. Moreover, this research provides valuable guidance for the development and optimization of gas sensing materials for applications in environmental monitoring and industrial safety. © 2024, The Authors. All rights reserved.

关键词： Perovskite

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：