检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Sim, Rachael Hwee Ling Zhang, Yehong Hoang, Trong Nghia Xu, Xinyi Low, Bryan Kian Hsiang Jaillet, Patrick Department of Computer Science National University of Singapore Singapore Peng Cheng Laboratory China School of Electrical Engineering and Computer Science Washington State University United States Dept. of Electrical Engineering and Computer Science MIT United States

ISBN: (纸本)9781713899921

Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation. Existing data valuation methods fairly value and reward each party based on shared data or model parameters but neglect the privacy risks involved. To address this, we introduce differential privacy (DP) as an incentive. Each party can select its required DP guarantee and perturb its sufficient statistic (SS) accordingly. The mediator values the perturbed SS by the Bayesian surprise it elicits about the model parameters. As our valuation function enforces a privacy-valuation trade-off, parties are deterred from selecting excessive DP guarantees that reduce the utility of the grand coalition's model. Finally, the mediator rewards each party with different posterior samples of the model parameters. Such rewards still satisfy existing incentives like fairness but additionally preserve DP and a high similarity to the grand coalition's posterior. We empirically demonstrate the effectiveness and practicality of our approach on synthetic and real-world datasets. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

LDPC CODES FOR IRIG-106 WAVEFORMS: PART I–CODE DESIGN 58

LDPC CODES FOR IRIG-106 WAVEFORMS: PART I–CODE DESIGN

引用

58th Annual International Telemetering Conference, ITC 2023

作者： Perrins, Erik Department of Electrical Engineering and Computer Science University of Kansas United States

Low density parity check (LDPC) codes allow a communications link to operate reliably at signal to noise ratios that are very close to the Shannon limit. Because of this, in the early 2000s they were studied in connection with SOQPSK-TG and were eventually adopted into the IRIG-106. The deployment for SOQPSK-TG has proved to be very successful, which has motivated interest in finding an LDPC solution for PCM/FM and ARTM CPM. Such a solution, however, has proved to be elusive for reasons that were not entirely clear in the past. In this paper, we lay out the fundamental considerations that must be made in order to design LDPC codes for a specific modulation format. In doing so, we show that SOQPSK-TG enjoys specific similarities with BPSK that allowed an "easy path" toward an LDPC solution in IRIG-106. Most importantly, we show that when the design process begins at the proper starting point, it is just as easy to design LDPC codes that are customized to a particular modulation. We then apply this straightforward design process to PCM/FM and ARTM CPM and demonstrate that the resulting LDPC codes perform around one dB from the respective channel capacities of these modulations. In our companion paper, we develop parallel decoder architectures for these schemes that can achieve high throughput. As such, these codes can be considered to fill in the options for LDPC codes that are currently absent in the IRIG-106 standard. © 2023 International Foundation for Telemetering. All rights reserved.

关键词： Forward error correction

来源：评论

学校读者我要写书评

暂无评论

Optimal IoT Based Improved Deep Learning Model for Medical Image Classification

引用

computers, Materials & Continua 2022年第11期73卷 2275-2291页

作者： Prasanalakshmi Balaji B.Sri Revathi Praveetha Gobinathan Shermin Shamsudheen Thavavel Vaiyapuri Department of Computer Science King Khalid UniversitySaudi Arabia School of Electrical Engineering Vellore Institute of TechnologyIndia Department of Computer Science Jazan UniversitySaudi Arabia College of Computer Engineering and Science Prince Sattam bin Abdulaziz UniversitySaudi Arabia

Recently medical image classification plays a vital role in medical image retrieval and computer-aided diagnosis *** deep learning has proved to be superior to previous approaches that depend on handcrafted features;it remains difficult to implement because of the high intra-class variance and inter-class similarity generated by the wide range of imaging modalities and clinical *** Internet of Things(IoT)in healthcare systems is quickly becoming a viable alternative for delivering high-quality medical treatment in today’s e-healthcare *** recent years,the Internet of Things(IoT)has been identified as one of the most interesting research subjects in the field of health care,notably in the field of medical image *** medical picture analysis,researchers used a combination of machine and deep learning techniques as well as artificial *** newly discovered approaches are employed to determine diseases,which may aid medical specialists in disease diagnosis at an earlier stage,giving precise,reliable,efficient,and timely results,and lowering death *** on this insight,a novel optimal IoT-based improved deep learning model named optimization-driven deep belief neural network(ODBNN)is proposed in this *** context,primarily image quality enhancement procedures like noise removal and contrast normalization are *** the preprocessed image is subjected to feature extraction techniques in which intensity histogram,an average pixel of RGB channels,first-order statistics,Grey Level Co-Occurrence Matrix,Discrete Wavelet Transform,and Local Binary Pattern measures are *** extracting these sets of features,the May Fly optimization technique is adopted to select the most relevant *** selected features are fed into the proposed classification algorithm in terms of classifying similar input images into similar *** proposed model is evaluated in terms of accuracy,precision,recall,and f-

关键词： Deep belief neural network mayfly optimization gaussian filter contrast normalization grey level variance local binary pattern discrete wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Enhancing Educational Technology in Lectures for School Students with Learning Disabilities: A Comprehensive Analysis

引用

SN computer science 2024年第6期5卷 1-17页

作者： Adjiovski, Benjamin Bogatinoska, Dijana Capeska Ismajloska, Mersiha Malekian, Reza University of Information Science and Technology “St. Paul the Apostle” Department of Electrical Electronic and Computer Engineering University of Pretoria

Learning disabilities present formidable obstacles for children in their educational journeys, often overlooked or misunderstood. This research aims to address two critical issues: the differentiation between learning and intellectual disabilities, and the resistance of teachers to integrating technology into education. In response, a comprehensive approach was adopted. Firstly, a mobile application was developed to screen for potential learning disabilities, offering teachers insights into individual student challenges and personalized lecture adaptations. Secondly, a quasi-experimental pretest–posttest study was conducted, comparing student performance following traditional and technologically supported lectures. Results from the study revealed significant score improvements among students identified as potentially having learning disabilities when exposed to technologically supported lectures. Conversely, students not identified as potential cases remained within the normal range of performance. These findings underscore the potential of technology to enhance educational outcomes for children with learning disabilities while highlighting the importance of recognizing and addressing these challenges in educational settings. By bridging the gap between identification and intervention, this research contributes to a more inclusive and effective educational environment. © The Author(s) 2024.

关键词： Assistive technology Inclusive education Learning disabilities Mobile application screening Technology in education

来源：评论

学校读者我要写书评

暂无评论

Tensorial Evolutionary Computation for Spatial Optimization Problems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 154-166页

作者： Si-Chao, Lei Xiaolin, Xiao Yue-Jiao, Gong Yun, Li Jun, Zhang the School of Computer Science and Engineering South China University of Technology Guangzhou510006 China the Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen610056 China the School of Computer Science South China Normal University Guangzhou510006 China the Department of Electrical and Electronic Engineering Hanyang University Seoul15588 Korea Republic of

—Spatial optimization problems (SOPs) refer to a class of problems where the decision variables require spatial organization. Existing methods based on evolutionary algorithms (EAs) fit conventional evolutionary operators by flattening the spatial representations of SOPs to one dimension, which hence loses crucial spatial structures of the potential solutions. To address this issue, this article proposes a tensorial evolutionary algorithm (TEA) by formulating a tensor space of the SOPs, where the population of candidate solutions is represented as a third-order tensor. Accordingly, we design a tensor-product crossover operator and a two-phase mutation consisting of a local convolutional mutation operator and a global Gaussian mutation operator in the tensor space. These operators are all implemented based on tensor operations. Under the consideration of spatial context on individual solutions, we devise three types of evolutionary tensors, namely, the crossover tensor, the convolutional mutant tensor, and the Gaussian mutant tensor for the three tensorial evolutionary operators correspondingly. The resultant TEA is tested using two typical real-world SOPs, namely, the facility layout problem and the image steganography problem. Comparative experimental studies validate the effectiveness and robustness of TEA. © 2024 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

On k-Planar Graphs Without Short Cycles 32

On k-Planar Graphs Without Short Cycles

引用

32nd International Symposium on Graph Drawing and Network Visualization, GD 2024

作者： Bekos, Michael A. Bose, Prosenjit Büngener, Aaron Dujmović, Vida Hoffmann, Michael Kaufmann, Michael Morin, Pat Odak, Saeed Weinberger, Alexandra Department of Mathematics University of Ioannina Greece School of Computer Science Carleton University Ottawa Canada Department of Computer Science University of Tübingen Germany School of Electrical Engineering and Computer Science University of Ottawa Canada Department of Computer Science ETH Zürich Switzerland Faculty of Mathematics and Computer Science Fern Universität in Hagen Germany

ISBN: (纸本)9783959773430

We study the impact of forbidding short cycles to the edge density of k-planar graphs;a k-planar graph is one that can be drawn in the plane with at most k crossings per edge. Specifically, we consider three settings, according to which the forbidden substructures are 3-cycles, 4-cycles or both of them (i.e., girth ≥ 5). For all three settings and all k ∈ {1, 2, 3}, we present lower and upper bounds on the maximum number of edges in any k-planar graph on n vertices. Our bounds are of the form c n, for some explicit constant c that depends on k and on the setting. For general k ≥ 4 our bounds are of the form c √ kn, for some explicit constant c. These results are obtained by leveraging different techniques, such as the discharging method, the recently introduced density formula for non-planar graphs, and new upper bounds for the crossing number of 2- and 3-planar graphs in combination with corresponding lower bounds based on the Crossing Lemma. © Michael A. Bekos, Prosenjit Bose, Aaron Büngener, Vida Dujmović, Michael Hoffmann, Michael Kaufmann, Pat Morin, Saeed Odak, and Alexandra Weinberger.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Drawing Order Diagrams Through Two-Dimension Extension

引用

Journal of Graph Algorithms and Applications 2023年第9期27卷 783-802页

作者： Dürrschnabel, Dominik Hanika, Tom Stumme, Gerd Knowledge & Data Engineering Group Research Center for Information System Design & Department of Electrical Engineering and Computer Science University of Kassel Germany Institute of Computer Science University of Hildesheim Germany Berlin School of Library and Information Science Humboldt-Universität zu Berlin Germany

Ordinal real-world data such as concept hierarchies, ontologies, genealogies, or task dependencies in scheduling often has the property to not only contain pairwise comparable, but also incomparable elements. Order diagrams provide an important tool for understanding and thus discovering knowledge in such data. Easily readable drawings of such order diagrams are hard to come by, even for small ordered sets. Many attempts were made to transfer classical graph drawing approaches to order diagrams. Although these methods produce satisfying results for some ordered sets, they unfortunately perform poorly in general. In this work, we present the novel algorithm DimDraw to decompose an ordered set (e.g., a concept hierarchy) in linear orders and to produce a corresponding order diagram. This algorithm is based on a relation between the dimension of an ordered set and the bipartiteness of its transitive incompatibility graph. To evaluate the quality of the algorithm, a user study was conducted where generated drawings were compared with ones from state-of-the-art drawing algorithms. © 2023 Brown University. All rights reserved.

关键词： Set theory

来源：评论

学校读者我要写书评

暂无评论

Efficient Learning in Predictive Coding Networks Using Global Error Signals

Efficient Learning in Predictive Coding Networks Using Globa...

引用

7th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2025

作者： Lee, Soha Park, Hyeyoung School of Electrical Engineering and Computer Science Kyungpook National University Daegu Korea Republic of

ISBN: (纸本)9798331507022

The error backpropagation is a representative learning algorithm widely adopted across deep learning networks. Despite its success in achieving high learning performance and generalization, error backpropagation has been criticized for its biological implausibility. One of its primary limitations lies in the weight transport problem, where, unlike the human brain, error backpropagation requires the same weights used in forward propagation to be accessible in the backward propagation. In addition, the sequential calculation of error backpropagation restricts parallelization that results in reduced efficiency. To solve these problems, predictive coding networks have emerged as an alternative. Inspired by predictive coding in computational neuroscience, it offers a biologically plausible learning framework. However, as network depth increases, predictive coding can suffer from significant computational costs, which decreases efficiency. In this paper, we propose an approach that enhances the efficiency of predictive coding by using global error signals. We also evaluate the effectiveness of our method on benchmark datasets, demonstrating improved learning performance and computational efficiency. © 2025 IEEE.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Improved Manta Ray Foraging Optimizer-based SVM for Feature Selection Problems:A Medical Case Study

引用

Journal of Bionic engineering 2024年第1期21卷 409-425页

作者： Adel Got Djaafar Zouache Abdelouahab Moussaoui Laith Abualigah Ahmed Alsayat Faculty of informatics University of Science and Technology Houari BoumedieneAlgiersAlgeria LRIA Laboratory University of Science and Technology Houari BoumedieneAlgiersAlgeria Computer Science Department University of Mohamed El Bachir El IbrahimiBordj Bou ArreridjAlgeria Computer Science Department University of Ferhat AbbasSetifAlgeria Computer Science Department Prince Hussein Bin Abdullah Faculty for Information TechnologyAl al-Bayt UniversityMafraq 25113Jordan Department of Computer Science College of Computer and Information SciencesJouf UniversityJoufSaudi Arabia Department of Electrical and Computer Engineering Lebanese American University13-5053ByblosLebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman UniversityAmman 19328Jordan MEU Research Unit Middle East UniversityAmman 11831Jordan Applied science research center Applied science private universityAmman 11931Jordan School of Computer Sciences Universiti Sains Malaysia11800 PenangMalaysia School of Engineering and Technology Sunway University Malaysia27500 Petaling JayaMalaysia

Support Vector Machine(SVM)has become one of the traditional machine learning algorithms the most used in prediction and classification ***,its behavior strongly depends on some parameters,making tuning these parameters a sensitive step to maintain a good *** the other hand,and as any other classifier,the performance of SVM is also affected by the input set of features used to build the learning model,which makes the selection of relevant features an important task not only to preserve a good classification accuracy but also to reduce the dimensionality of *** this paper,the MRFO+SVM algorithm is introduced by investigating the recent manta ray foraging optimizer to fine-tune the SVM parameters and identify the optimal feature subset *** proposed approach is validated and compared with four SVM-based algorithms over eight benchmarking ***,it is applied to a disease Covid-19 *** experimental results show the high ability of the proposed algorithm to find the appropriate SVM’s parameters,and its acceptable performance to deal with feature selection problem.

关键词： Support vector machine Parameters tuning Feature selection Bioinspired algorithms Manta ray foraging optimizer

来源：评论

学校读者我要写书评

暂无评论

Towards an Internet-like Power Grid

引用

Journal of Modern Power Systems and Clean Energy 2022年第1期10卷 1-11页

作者： Iasonas Kouveliotis-Lysikatos Nikos Hatziargyriou Yanli Liu Felix Wu Department of Electrical Engineering and Computer Science KTH-Royal Institute of TechnologyTeknikringen 3310040StockholmSweden School of Electrical and Computer Engineering National Technical University of Athens15773 AthensGreece School of Electrical and Information Engineering Tianjin UniversityTianjin300072China Department of Electrical and Electronic Engineering The University of Hong KongHong KongChina Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeleyCA 94720USA

The great challenges faced by modern power systems require a fresh look at the conventional operation paradigm. The significant challenges faced by modern power systems require an innovative method for the conventional operation paradigm. We claim that the decarbonization of the power grid and extensive electrification of numerous sectors of human activity can only be fostered by a self-adaptable and smart power grid that manifests similar qualities to those of the Internet. The Internet is constructed on a layered architecture that facilitates technology innovations and its intelligence is distributed throughout a hierarchy of networks. In this paper, the fundamental differences between the network data flows and power flows are examined, and the basic requirements for an innovative operation paradigm are highlighted. The current power grid is operated in a highly inflexible, centralized manner to meet increased security goals. A new highly flexible, distributed architecture can be realized by distributing the operation responsibility in smaller areas or even in grid components that can make autonomous decisions. The characteristics of such a power grid are presented, and the key features and advances for the on-going transition to a sustainable power system are identified. Finally, a case study on distributed voltage control is presented and discussed.

关键词： Smart grid Internet distributed intelligence decentralized architecture

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：