检索结果-内蒙古大学图书馆

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

Improving Matrix-vector Multiplication via Lossless Grammar-Compressed Matrices

arXiv

引用

arXiv 2022年

作者： Ferragina, Paolo Gagie, Travis Köppl, Dominik Manzini, Giovanni Navarro, Gonzalo Striani, Manuel Tosoni, Francesco Department of Computer Science University of Pisa Italy Faculty of Computer Science Dalhousie University Canada M&D Data Science Center Tokyo Medical Dental University Japan Millennium Institute for Foundational Research on Data Department of Computer Science University of Chile Chile Department of Sciences and Technological Innovation University of Piemonte Orientale Italy

As nowadays Machine Learning (ML) techniques are generating huge data collections, the problem of how to efficiently engineer their storage and operations is becoming of paramount importance. In this article we propose a new lossless compression scheme for real-valued matrices which achieves efficient performance in terms of compression ratio and time for linear-algebra operations. Experiments show that, as a compressor, our tool is clearly superior to gzip and it is usually within 20% of xz in terms of compression ratio. In addition, our compressed format supports matrix-vector multiplications in time and space proportional to the size of the compressed representation, unlike gzip and xz that require the full decompression of the compressed matrix. To our knowledge our lossless compressor is the first one achieving time and space complexities which match the theoretical limit expressed by the k-th order statistical entropy of the input. To achieve further time/space reductions, we propose column-reordering algorithms hinging on a novel column-similarity score. Our experiments on various data sets of ML matrices show that, with a modest preprocessing time, our column reordering can yield a further reduction of up to 16% in the peak memory usage during matrix-vector multiplication. Finally, we compare our proposal against the state-of-the-art Compressed Linear Algebra (CLA) approach showing that ours runs always at least twice faster (in a multi-thread setting) and achieves better compressed space occupancy for most of the tested data sets. This experimentally confirms the provably effective theoretical bounds we show for our compressed-matrix approach. © 2022, CC BY-NC-ND.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal

arXiv

引用

arXiv 2023年

作者： Sedova, Anastasiia Zellinger, Lena 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

An accurate and substantial dataset is essential for training a reliable and well-performing model. However, even manually annotated datasets contain label errors, not to mention automatically labeled ones. Previous methods for label denoising have primarily focused on detecting outliers and their permanent removal – a process that is likely to over- or underfilter the dataset. In this work, we propose AGRA: a new method for learning with noisy labels by using Adaptive GRAdient-based outlier removal1. Instead of cleaning the dataset prior to model training, the dataset is dynamically adjusted during the training process. By comparing the aggregated gradient of a batch of samples and an individual example gradient, our method dynamically decides whether a corresponding example is helpful for the model at this point or is counter-productive and should be left out for the current update. Extensive evaluation on several datasets demonstrates AGRA’s effectiveness, while a comprehensive results analysis supports our initial hypothesis: permanent hard outlier removal is not always what model benefits the most from. © 2023, CC BY.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Resilient Skies: Advancing Climate-Resilient UAVs for Energy-Efficient B5G Communication in Challenging Environments

Resilient Skies: Advancing Climate-Resilient UAVs for Energy...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Abdu Saif Nor Shahida Mohd Shah Aiman Alnoamani Ali Ameen Edward Curry Vailet Hikmat Faraj Al Khattat Saeed Hamood Alsamhi Department of Communication and Computer Engineering Faculty of Engineering and IT Taiz University Taiz Yemen Faculty of Engineering Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia Faculty of Computer Science Lincoln University College Kuala Lumpur Malaysia Insight Center for Data Analytics University of Galway Galway Ireland Faculty of Engineering Universiti Putra Wireless and Photonics Networks Research Center Malaysia

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

Due to severe climatic circumstances exacerbated by climate change, deploying Beyond Fifth Generation (B5G) networks is critical. Unmanned Aerial Vehicles (UAVs) have become indispensable for B5G connectivity in inclement weather conditions such as snow, fog, and rain. This paper investigates energy-efficient B5G connectivity and climate-resilient UAVs. We evaluate the performance of UAV coverage and energy efficiency at different elevation angles under various weather conditions, including snow, fog, and rain. Additionally, we discuss the challenges environments and propose solutions to improve climate-resilient and energy-efficient B5G communication. Emphasizing the adverse effects of climate change on communication networks, The paper’s findings highlight the significant impact of weather conditions on UAV coverage, B5G communication networks, and energy efficiency. This research paves the way for a more resilient and sustainable future.

关键词： Climate change Rain Snow Autonomous aerial vehicles Throughput Energy efficiency Loss measurement

来源：评论

学校读者我要写书评

暂无评论

TPE-H2MWD:an exact thumbnail preserving encryption scheme with hidden Markov model and weighted diffusion

引用

Frontiers of Information Technology & Electronic Engineering 2023年第8期24卷 1169-1180页

作者： Xiuli CHAI Xiuhui CHEN Yakun MA Fang ZUO Zhihua GAN Yushu ZHANG School of Artificial Intelligence Henan Engineering Research Center for Industrial Internet of ThingsHenan UniversityZhengzhou450046China Henan Key Laboratory of Cyberspace Situation Awareness Zhengzhou450001China School of Software Intelligent Data Processing Engineering Research Center of Henan ProvinceInstitute of Intelligent Network SystemHenan UniversityKaifeng475004China College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing211106China

With the substantial increase in image transmission,the demand for image security is ***-like images can be obtained by conventional encryption schemes,and although the security of the images can be guaranteed,the noise-like images cannot be directly previewed and *** on the rank-then-encipher method,some researchers have designed a three-pixel exact thumbnail preserving encryption(TPE2)scheme,which can be applied to balance the security and availability of images,but this scheme has low encryption *** this paper,we introduce an efficient exact thumbnail preserving encryption ***,blocking and bit-plane decomposition operations are performed on the plaintext *** zigzag scrambling model is used to change the bit positions in the lower four bit ***,an operation is devised to permute the higher four bit planes,which is an extended application of the hidden Markov ***,according to the difference in bit weights in each bit plane,a bit-level weighted diffusion rule is established to generate an encrypted image and still maintain the same sum of pixels within the *** results show that the proposed scheme improves the encryption efficiency and can guarantee the availability of images while protecting their privacy.

关键词： Hidden Markov model Weighted diffusion Balance between usability and privacy Image encryption

来源：评论

学校读者我要写书评

暂无评论

NOBGP: A Novel Optimized Balanced Graph Partitioning Algorithm 19th

NOBGP: A Novel Optimized Balanced Graph Partitioning Algorit...

引用

19th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Chen, Jiebin Hu, Ziqiang Ye, Renjie Zhang, Qishan Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Xianda College of Economics and Humanities Shanghai International Studies University Shanghai China

ISBN: (纸本)9789819623723

Large-scale graphs have become prevalent with the advent of the big data era. Distributed graph computing systems are commonly used for processing and analyzing large-scale graphs, with graph partitioning being a key prerequisite for their efficient computation. Graph partitioning aims to balance the load across partitions while minimizing the number of cut-edges. Moreover, it should achieve high efficiency and scalability. However, the existing popular graph partitioning algorithms do not fully take into account the internal topology of real-world graphs, which affects the final partition quality and convergence. Meanwhile, they easily fall into the local optimum due to partition load constraints. This paper introduces a Novel Optimized Balanced Graph Partitioning algorithm (NOBGP). First, we propose an initialization strategy based on label propagation of core vertices to achieve initial partitions with good locality and accelerate convergence. Second, we optimize the label propagation process to ensure balanced partitions and propose a probability-based disruption strategy to avoid the local optimum. We implement NOBGP on the distributed graph computing framework GraphX. Extensive experimental results on real-world graphs show that the proposed algorithm is scalable and performs better than the existing algorithms. We also run PageRank and Louvain applications using the graph partitioning results to demonstrate the efficiency of our algorithm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Advances in Glaucoma Detection Through Machine Learning Technology

Advances in Glaucoma Detection Through Machine Learning Tech...

引用

Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), International Conference on

作者： Rushikesh Burle Sanskruti Gaurkhede Leelkanth Dewangan Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India Computer science And Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India Artificial Intelligence and Data science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

In the event that glaucoma is not treated promptly, blindness may become permanent. It ranks second among the factors that might lead to blindness in the eyes. One example of a recent imaging technology that looks within the eye is the fundus camera. Glaucoma is diagnosed using a variety of techniques, such as the retinal nerve fibre layer analyzer, The Topcon image net technique and optical coherence tomography. Despite its expensive cost and the dearth of available research in this field, the optic cup to disc ratio is used to diagnose glaucoma. The degree of glaucomatous damage is mostly determined by the appearance of the optic cup. The beaker slowly gets better and inhabits most of the judgement as the glaucoma becomes worse. If glaucoma is not pickled trendy a timely manner, blindness may become irreversible. It is the second most common cause of ocular blindness. A contemporary imaging tool called the fundus camera is utilised to view within the eye. Among the methods used to diagnose glaucoma include the retinal nerve fibre layer analyzer, optical coherence tomography, and the Topcon image net approach. Despite its high cost and paucity of research, glaucoma is diagnosed using the optic cup to discus relation. The degree of glaucomatous damage is mostly determined by the appearance of the optic cup. The cup expands as glaucoma progresses until it finally occupies the majority of the eye.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expanding Non-Patient COVID-19 data: Towards the FAIRification of Migrants' data in Tunisia, Libya and Niger

引用

data Intelligence 2022年第4期4卷 955-970,1034,1038,1044,1047,1054页

作者： Mariem Ghardallou Morgane Wirtz Sakinat Folorunso Zohra Touati Ezekiel Ogundepo Klara Smits Ali Mtiraoui Mirjam van Reisen University of Sousse Faculty of Medicine of SousseDepartment of Community MedicineResearch Laboratory LR12ES03Tunisia4002Sousse Tilburg University 1002 Tunisthe Netherlands Department of Mathematical Sciences Olabisi Onabanjo UniversityP.M.B 2002Ago-IwoyeOgun StateNigeria 120005Nigeria Data Science Nigeria Lagos 105102 Leiden University 1310 Leidenthe Netherlands Leiden University Medical Centre Leiden University1310 Leidenthe Netherlands Virus Outbreak Data Network-Africa

This article describes the FAIRification process(which involves making data Findable, Accessible, Interoperable and Reusable—or FAIR—for both machines and humans) for data related to the impact of COVID-19 on migrants, refugees and asylum seekers in Tunisia, Libya and Niger, according to the scheme adopted by GO FAIR. This process was divided into three phases: pre-FAIRification, FAIRification and postFAIRification. Each phase consisted of seven steps. In the first phase, 118 in-depth interviews and 565 press articles and research reports were collected by students and researchers at the University of Sousse in Tunisia and researchers in Niger. These interviews, articles and reports constitute the dataset for this research. In the second phase, the data were sorted and converted into a machine actionable format and published on a FAIR data Point hosted at the University of Sousse. In the third phase, an assessment of the implementation of the FAIR Guidelines was undertaken. Certain barriers and challenges were faced in this process and solutions were found. For FAIR data curation, certain changes need to be made to the technical process. People need to be convinced to make these changes and that the implementation of FAIR will generate a long-term return on investment. Although the implementation of FAIR Guidelines is not straightforward, making our resources FAIR is essential to achieving better science together.

关键词： FAIRification process FAIR Guidelines FAIR data Tunisia Niger Libya COVID Migrants VODAN-Africa

来源：评论

学校读者我要写书评

暂无评论

PSI Protocol with Structured Encryption

引用

Jisuanji Xuebao/Chinese Journal of computers 2022年第12期45卷 2652-2666页

作者： Yang, Jia-Hui Chen, Lan-Xiang Mu, Yi Zeng, Ling-Fang Xue, Yu-Jie Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fujian Normal University Fuzhou350117 China Zhejiang Lab Hangzhou311121 China Faculty of Data Science City University of Macau Macau999078 China

With the advancement of information technology, local storage and computing capacity cannot well support massive data. The emergence of cloud computing makes data outsourcing a new trend. However, data outsourcing compromises data security and privacy. Therefore, searchable symmetric encryption (SSE) was introduced as a potential solution. The traditional SSE scheme is mainly for text data types. In order to achieve searchable encryption of a wider range of data types, Kamara et al. proposed the concept of structured encryption (STE) in 2010. Structured encryption can realize searchable encryption of complex data structures. It can be used to encrypt social network graphs to achieve retrieval of encrypted data, but cannot be applied to the computation and statistical analysis of social network graphs. Therefore, we design the private set intersection protocol max-PSI, and apply it to the structured encrypted social network graph data, and propose a structured encrypted PSI scheme, STE_max-PSI, to realize any number of nodes in the encrypted graph and the calculation of the maximum intersection size of the set of neighbor nodes. In the encrypted social network graph, it can query the node with the highest affinity of any node (we think two nodes with the most common neighbors have the highest affinity). The proposed scheme utilized a garbled Bloom filter (GBF) to achieve richer query functions for more complex data structures, while protecting the privacy of data. The GBF has negligible false positives when querying elements. Compared with the existing PSI protocols, our scheme can greatly improve the query accuracy. Experiments on the real dataset show that the query accuracy of our scheme is better than the existing schemes. © 2022, science Press. All right reserved.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning

引用

Procedia computer science 2023年 216卷 57-66页

作者： Mira Hayati Kahlil Muchtar Roslidar Novi Maulina Irfan Syamsuddin Gregorius Natanael Elwirehardja Bens Pardamean Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh 23111 Indonesia Telematics Research Center (TRC) Universitas Syiah Kuala Banda Aceh 23111 Indonesia Faculty of Medicine Universitas Syiah Kuala Banda Aceh 23111 Indonesia Department of Computer and Networking Engineering Politeknik Negeri Ujung Pandang Makassar 90245 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Diabetic retinopathy (DR) is a type of diabetes mellitus that attacks the retina of the eye. DR will cause patients to experience blindness slowly. Generally, DR can be detected by using a special instrument called an ophthalmoscope to view the inside of the eyeball. However, in conditions where there is a very small difference between the normal image and the DR image, computer-based assistance is needed for maximizing image reading value. In this research, a method of image quality improvement will be carried out which will then be integrated with a classification algorithm based on deep learning. The results of image improvement using Contrast Limited Adaptive Histogram Equalization (CLAHE) shows that the average accuracy of the method on several models is very competitive, 91% for the VGG16 model, 95% for InceptionV3, and 97% for EfficientNet compared to the results original image which only has an accuracy of 87% for VGG16 model, 90% for InceptionV3 model, and 95% for EfficientNet. However, in ResNet34 better accuracy is obtained in the original image with an accuracy of 95% while in the CLAHE image the accuracy value is only 84%. The results of this comprehensive evaluation and recommendation of famous backbone networks can be useful in the computer-aided diagnosis of diabetic retinopathy.

关键词： Diabetic retinopathy Deep Learning CNN Image Enhancement CLAHE

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：