检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Qiliang Gu Shuo Zhao Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Shandong Engineering Research Center of Big Data Applied Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

To address the challenges associated with insufficiently extracting and utilizing features at different levels, overlooking the connection between label meanings and text, and facing problems of over-compression or information loss when extracting global information using recurrent neural networks in the field of multi-label text categorization, this paper introduces an innovative model known as MFFLEN (MultiFeature Fusion and Label Embedding Neural Network). First, a back-translated enhanced label set is constructed by back-translated splicing enhancement of the original label set. This set, together with the text, is then input into the embedding layer, which consists of the pre-trained model of bert-baseChinese, thus establishing the initial connection between the text and the labels within the same vector space. Then, to comprehensively extract multi-level semantic features, the model uses a convolutional layer to extract local features and an embedding layer to extract sentence-level features. A bidirectional attention embedded GRU (BAE-GRU) layer is used to extract hybrid finegrained features, which are then fed into the attention layer to further extract hybrid labeled features based on labeling information. Finally, these three different types of features are fused and multi-label text classification results are obtained using a classifier. The experiments proved that the MFFLEN model achieved 73.82% and 88.44% macro-F1 and 88.00% and 88.86% micro-F1 on the two datasets CAIL 2018 Small and CAIL 2018 Split, respectively, which is better than other baseline models.

关键词： Measurement Recurrent neural networks Splicing Text categorization Semantics Multi label classification Logic gates Feature extraction Vectors data mining

来源：评论

学校读者我要写书评

暂无评论

Design of novel circular lattice photonic crystal fiber suitable for transporting 48 OAM modes

引用

Optoelectronics Letters 2021年第8期17卷 501-506页

作者： Alaaeddine Rjeb Habib Fathallah Saleh Chebaane Mohsen Machhout Laboratory of Electronic and Microelectronic Physics DepartmentFaculty of Sciences of MonastirUniversity of MonastirMonastir 5000Tunisia Laboratory of Artificial Intelligence and Data Engineering Applications Computer DepartmentFaculty of Sciences of BizerteUniversity of CarthageBizerte 7000Tunisia Physics Department College of ScienceUniversity of Hai'ilKingdom of Saudi Arabia

In this paper,we propose and numerically investigate a novel circular lattice photonic crystal fiber(CL-PCF)using controllable GeO_(2) doped silica,suitable for modes carrying quantized orbital angular momentum(OAM).Large effective index separations between 25 supported vector modes(≥10^(-4))are confirmed over large bandwidth(C+L bands)leading to 48 OAM modes bearing *** simulations show that the modes in the proposed CLPCF have good features including low and flat dispersion(within 51.82 ps/km/nm),low confinement loss(lower than 0.002 d B/m),high effective mode area(88.5μm^(2))and low nonlinearity(1.22 W^(-1)·km^(-1)).These promising results show that the proposed CL-PCF could be an arguably candidate in fiber-based OAM multiplexing or other applications using OAM states.

关键词： fiber OAM circular

来源：评论

学校读者我要写书评

暂无评论

LGDB-Net: Dual-Branch Path for Building Extraction from Remote Sensing Image

LGDB-Net: Dual-Branch Path for Building Extraction from Remo...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Ronghuan Zhang Jing Zhao Ming Li Qingzhi Zou Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Extracting buildings from remote sensing images using deep learning techniques is a widely applied and crucial task. Convolutional Neural Networks (CNNs) adopt hierarchical feature representation, showcasing powerful capabilities in extracting local information but facing challenges in capturing global features. Transformers can address this limitation, but they perform poorly in extracting local features and significantly increase memory requirements and computational complexity. To overcome these challenges, we propose a method for building extraction from remote sensing images called LGDB-Net (Local-Global Dual-Branch Network), employing a dual-branch approach. Firstly, inspired by Swin Transformer, we designed GB-Former(Global Branch-Former) as the backbone network to model global information. We use a linear multi-head self-attention mechanism to reduce time and memory complexity while maintaining a large global receptive field. Additionally, we replace the traditional multi-layer perceptron with a convolution-enhanced multi-layer perceptron to improve channel feature representation, reduce model parameters, and enhance segmentation performance. Secondly, we use multiple Depth-wise Conv3×3 + LN (Layer Normalization) + GeLU (Gaussian Error Linear Unit) modules as the auxiliary branch for local detailed feature extraction. Finally, we adopt a multi-scale feature fusion strategy to integrate feature information from both branches. We conduct a series of experiments on three datasets: WHU, Massachusetts, and Inria. The experimental results demonstrate that the proposed method not only effectively improves segmentation accuracy with lower building omission and commission rates but also significantly reduces model parameters and computational complexity.

关键词： Accuracy Computational modeling Memory management Neural networks Feature extraction Transformers Sensors data mining Computational complexity Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Cross-modal retrieval based on Attention Embedded Variational Auto-Encoder

Cross-modal retrieval based on Attention Embedded Variationa...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Kaili Zhou Yiyun Xing Yushui Geng Jing Zhao Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

This study proposes a cross-modal retrieval technique, which employs an Attention Embedded Variational AutoEncoder (AE-VAE) to tackle the problem of reduced retrieval accuracy resulting from data noise and data absence in cross-modal retrieval tasks. First, the variational auto-encoder(VAE) is used as an infrastructure to transform modal data into latent variables by encoding and decoding different modal features, thus preserving the semantic structure of the raw modal data and suppressing noise and missing information in the data. Secondly, to better capture the important semantic features of image and text modalities, an improved multi-attention module is introduced in the encoder. In addition, a cross-modal alignment module is designed to further align the latent variables of different modalities in the latent space to solve the confusion problem and improve the accuracy and robustness of cross-modal retrieval. Finally, experiments are conducted on four public datasets, CUB, SUN, AwA1 and AwA2, and the experimental results show that our proposed model is effective in improving the accuracy and robustness of retrieval.

关键词： Accuracy Uncertainty Noise Semantics Transforms Probabilistic logic Robustness

来源：评论

学校读者我要写书评

暂无评论

Full-field electroretinography examinations of the human eye with the eye diagnostic device PEP-2000-First results

引用

Current Directions in Biomedical Engineering 2022年第2期8卷 636-639页

作者： Schieding, Nikola Reuter, Thomas Grundmann, Andreas Walther, Sebastian Klee, Sascha ICM-Institut Chemnitzer Maschinen-und Anlagenbau E.V. Otto-Schmerbach-Str. 19 Chemnitz 09117 Germany Department of General Health Studies Division Biostatistics and Data Science Karl Landsteiner University of Health Sciences Krems an der Donau Austria Institute of Biomedical Engineering and Informatics Faculty of Computer Sciences and Automation TU Ilmenau Ilmenau Germany

Full-field electroretinography (full-field ERG) forms the diagnostic basis for numerous pathologies of the eye. For this reason, fast and accurate diagnostics in the field of ophthalmology are essential. Two examination techniques, full-field ERG and pupillometry were combined in a diagnostic device developed by ICM e.V. to reduce the examination process for both examiners and patients. In this paper, the device is examined for the quality of the full-field ERG measurements. A feasibility study with 12 healthy subjects (3 f, 9 m, 36.33 ± 11.94 years) was conducted to evaluate the device. The results showed that the peak times for both light-and dark-adapted measurements were within the range of the researched literature values. However, the amplitudes were markedly lower in both measurements compared to the averaged literature values (dark-adapted about 8.5-fold and light-adapted about 5.5-fold) and are clearly outside the range of values researched. The main reason for this is the use of cup electrodes, which were placed on the skin of the lower eyelid. Nevertheless, plausible and comparable analysis values could be obtained with the eye diagnostic device PEP-2000. Further studies with wire electrodes will be performed. © 2022 by Walter de Gruyter Berlin/Boston.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion

arXiv

引用

arXiv 2023年

作者： Sedova, Anastasiia Roth, Benjamin Research Group Data Mining and Machine Learning University of Vienna Austria UniVie Doctoral School Computer Science University of Vienna Austria Faculty of Philological and Cultural Studies University of Vienna Austria

Self-supervised knowledge-graph completion (KGC) relies on estimating a scoring model over (entity, relation, entity)-tuples, for example, by embedding an initial knowledge graph. Prediction quality can be improved by calibrating the scoring model, typically by adjusting the prediction thresholds using manually annotated examples. In this paper, we attempt for the first time cold-start calibration for KGC, where no annotated examples exist initially for calibration, and only a limited number of tuples can be selected for annotation. Our new method ACTC finds good per-relation thresholds efficiently based on a limited set of annotated tuples. Additionally to a few annotated tuples, ACTC also leverages unlabeled tuples by estimating their correctness with Logistic Regression or Gaussian Process classifiers. We also experiment with different methods for selecting candidate tuples for annotation: density-based and random selection. Experiments with five scoring models and an oracle annotator show an improvement of 7% points when using ACTC in the challenging setting with an annotation budget of only 10 tuples, and an average improvement of 4% points over different budgets. © 2023, CC BY.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Enhanced Public-Key Searchable Encryption Scheme for Cloud-Based EHR Systems

Enhanced Public-Key Searchable Encryption Scheme for Cloud-B...

引用

International Conference on e-health Networking, Applications and Services (HealthCom)

作者： Xiangqian Kong Lanxiang Chen Faculty of Data Science City University of Macau Macau China Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fujian Normal University Fuzhou China

Due to the swift development of cloud computing technology, an increasing number of healthcare organizations tend to store electronic health records (EHR) on cloud storage servers. To ensure patient privacy, sensitive information within EHR data must undergo encryption prior to being uploaded to the cloud server. Nonetheless, this encryption process alters the data's original structural characteristics, presenting a significant challenge in achieving effective and flexible EHR utilization, such as plaintext keyword search. Considering the privacy and practicality of EHR. This paper introduces a new cloud-based EHR system that integrates public-key encryption with the keyword search (PEKS) scheme. This system enables authorized users to conduct searches for specific keywords on encrypted EHR data, all while maintaining the highest level of data security. Compared to existing PEKS-based EHR system solutions, our approach is not limited by a secure channel, reducing communication overhead while taking full advantage of the large storage space and high computational performance of the cloud server to realize flexible and effective search capabilities. Furthermore, our solution effectively prevents online keyword guessing attacks from outside adversaries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Diabetes Health Intervention dataset 25

Multi-Label Diabetes Health Intervention Dataset

引用

25th International computer science and Engineering Conference, ICSEC 2021

作者： Keawpradub, Dheeraj Vasupongayya, Sangsuree Wonghirandecha, Aekkorn College of Digital Science Prince of Songkla University Master of Science in Data Science Hat Yai Songkhla Thailand Prince of Songkla University Faculty of Engineering Department of Computer Engineering Hat Yai Songkhla Thailand Myhealthgroup Company Limited Doctor of Medicine Hat Yai Songkhla Thailand

ISBN: (纸本)9781665411974

This research presents the creation of a dataset for training a machine learning model in order to predict health intervention for the treatment in patients with type 2 diabetes. The dataset is designed as a Multi-label dataset. The process of dataset creation is taken medical professionals into account. The datasets are created based on the characteristics and trends of patients with type 2 diabetes in Songkhla Province, Thailand, between 2019 and 2020, together with the factors analyzed by physicians with respect to taking medical history of diabetic patients. The result shows that a dataset is generated having 545 samples with 15 variables and 5 multi-labeled responses. © 2021 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similarity Computation Model with Attention Mechanism

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similar...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Shuo Zhao Yiyun Xing Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Text semantic similarity is a crucial research area in Natural Language Processing (NLP). However, traditional methods for calculating the similarity of short Chinese texts often fall short in accuracy and other crucial aspects. The Bidirectional Long Short-Term Memory Network (BiLSTM) has demonstrated remarkable performance in computing the similarity of short Chinese texts by effectively capturing long-range dependencies and semantic information. Additionally, the multi-head attention mechanism considers the interaction between different text locations and semantic information, enhancing the model’s representative capacity. Building upon this foundation, our paper proposes an enhanced model known as SCTbilstmAttRdrop (SCTAR). This model is constructed based on a multilayer BiLSTM architecture and incorporates an SE-gated convolutional module and a convolutional multi-head attention-aware model. We conducted extensive evaluations using two Chinese short text datasets, Chinese-SNLI and CCKS2018_Task3. The experimental results unequivocally demonstrate that our SCTAR model surpasses other common methods in terms of accuracy, precision, recall, and F1 scores when tasked with computing the similarity of Chinese short texts.

关键词： Accuracy Attention mechanisms Computational modeling Semantics Bidirectional control Feature extraction Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

Practical and Malicious Private Set Intersection with Improved Efficiency

SSRN

引用

SSRN 2023年

作者： Zhu, Yizhao Chen, Lanxiang Mu, Yi Faculty of Data Science City University of Macau 999078 China College of Computer and Cyber Security Fujian Normal University Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou China

We propose a novel two-party private set intersection (PSI) protocol, which achieves ideal and constant receiver-to-sender and linear sender-to-receiver communication overhead, linear computational complexity, along with receiver size-hiding and lightweight computation cost. In comparison with other PSI protocols, the proposed protocol is more practical as it does not require any fully homomorphic computation. We propose three variants to demonstrate efficiency optimization, size-hiding feature extension, and online/offline settings for real-world applications, respectively, to offer a practical control between security and efficiency. Finally, we prove that our proposed protocols are secure against malicious participants under our security model. © 2023, The Authors. All rights reserved.

关键词： Efficiency

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：