检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Atashgahi, Zahra Liu, Tennison Pechenizkiy, Mykola Veldhuis, Raymond Mocanu, Decebal Constantin van der Schaar, Mihaela Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Netherlands Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands Department of Computer Science University of Luxembourg Luxembourg

Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically reducing computational overheads. Despite these advancements, several critical aspects remain insufficiently explored for feature selection. Questions persist regarding the choice of the DST algorithm for network training, the choice of metric for ranking features/neurons, and the comparative performance of these methods across diverse datasets when compared to dense networks. This paper addresses these gaps by presenting a comprehensive systematic analysis of feature selection with sparse neural networks. Moreover, we introduce a novel metric considering sparse neural network characteristics, which is designed to quantify feature importance within the context of SNNs. Our findings show that feature selection with SNNs trained with DST algorithms can achieve, on average, more than 50% memory and 55% FLOPs reduction compared to the dense networks, while outperforming them in terms of the quality of the selected features. Our code and the supplementary material are available on GitHub (https://***/zahraatashgahi/Neuron-Attribution). © 2024, CC BY-SA.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Approximation of Some Nonlinear Fractional Order BVPs by Weighted Residual Methods

arXiv

引用

arXiv 2024年

作者： Ruman, Umme Islam, Md Shafiqul Department of Computer Science & Engineering Green University of Bangladesh Dhaka Bangladesh Department of Applied Mathematics University of Dhaka Dhaka Bangladesh

To extract the approximate solutions in the case of nonlinear fractional order differential equations with the homogeneous and nonhomogeneous boundary conditions, the weighted residual method is embedded here. We exploit three methods such as Galerkin, Least Square, and Collocation for the efficient numerical solution of nonlinear two-point boundary value problems. Some nonlinear cases are examined for observing the maximum absolute errors by the considered methods, demonstrating the accuracy and reliability of the present technique using the modified Legendre and modified Bernoulli polynomials as weight functions. The mathematical formulations and computational algorithms are more straightforward and uncomplicated to understand. Absolute errors and the graphical representation reflect that our method is more accurate and *** Codes 65-XX © 2024, CC BY.

关键词： Galerkin methods

来源：评论

学校读者我要写书评

暂无评论

Generalized Neural Collapse for a Large Number of Classes 41

Generalized Neural Collapse for a Large Number of Classes

引用

41st International Conference on Machine Learning, ICML 2024

作者： Jiang, Jiachen Zhou, Jinxin Wang, Peng Qu, Qing Mixon, Dustin G. You, Chong Zhu, Zhihui Department of Computer Science The Ohio State University ColumbusOH United States Department of Electrical Engineering & Computer Science University of Michigan Ann ArborMI United States Department of Mathematics The Ohio State University ColumbusOH United States Google Research New York CityNY United States

Neural collapse provides an elegant mathematical characterization of learned last-layer representations, also known as features, and classifier weights within deep classification models. The result not only provides insights into deep models but also catalyzes the development of new techniques for improving them. However, most of the existing empirical and theoretical studies into neural collapse center around scenarios where the number of classes is small relative to the dimensionality of the feature space. This paper introduces a generalization of neural collapse to encompass scenarios where the number of classes surpasses the dimension of feature space, which broadly occurs for language models, information retrieval systems, and face recognition applications. A key technical contribution is the introduction of the concept of softmax code, defined as a collection of points that maximizes the minimum one-vs-rest margin, to describe the arrangement of class-mean features. We provide empirical study to verify the prevalence of generalized neural collapse in practical deep neural networks. Moreover, we provide theoretical study to show that the generalized neural collapse provably occurs under an unconstrained feature model with spherical constraint, subject to specific technical conditions on feature dimension and the number of classes. Copyright 2024 by the author(s)

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Drug Discovery: Unravelling the Potential of Generative Adversarial Networks (GANs) in Pharmaceutical research 3

AI-Driven Drug Discovery: Unravelling the Potential of Gener...

引用

3rd International Conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Burri, Srinivasa Rao Diallo, Mamadou Yero Sharma, Lakshay Dutt, Vishal Western Union DenverCO United States Sharda University Computer Science & Engineering Greater Noida India Indraprastha Institute of Information Technology Computer Science & Applied Mathematics Delhi India Chandigarh University Department of Cse Punjab Mohali India

ISBN: (纸本)9798350342338

This paper examines how AI has revolutionised drug development and medical research using the ChEMBL dataset. The primary study areas are AI-driven therapeutic target identification., computational approaches in drug development., drug repurposing for COVID-19 therapies., and AI methods for natural leather flaw detection. Target selection must balance novelty and confidence., and AI-driven therapeutic target identification is considered. Structure-based virtual screening and profound learning predictions of ligand properties and target activities are considered for application in scaling up to broader chemical spaces. AI is used to discover new links between drugs., targets., and diseases and treat COVID-19. The paper also highlights this field's enforcement challenges and offers solutions. A Generative Adversarial Network (GAN)-based automatic flaw identification system for natural leather is another topic of study. The results show that the suggested strategy is economical and accurate., despite limitations and biases. AI has revolutionised medical diagnostics., medication development., and precision medicine., making this work meaningful. This paper's findings offer a cross-disciplinary perspective on artificial intelligence's potential in healthcare., revealing knowledge gaps and suggesting further research. © 2023 IEEE.

关键词： Artificial Intelligence Chemical Biology Database (ChEMBL) Dataset Computational Approaches COVID-19 Treatments Defect Identification Drug Discovery Drug Repurposing Generative Adversarial Network (GAN) Precision Medicine Therapeutic Target Identification

来源：评论

学校读者我要写书评

暂无评论

Consensus-based Optimal Control Strategy for Multi-microgrid Systems with Battery Degradation Consideration

引用

CSEE Journal of Power and Energy Systems 2024年第5期10卷 1911-1924页

作者： Tonghe Wang Hong Liang Bo He Haochen Hua Yuchao Qin Junwei Cao Institute of Energy Conversion Chinese Academy of SciencesGuangzhou 510640China Meihua Holdings Group Co. Ltd.Langfang 065001China. Department of Astronautical Science and Technology Space Engineering UniversityBeijing 101416China College of Energy and Electrical Engineering Hohai UniversityNanjing211100China Department of Applied Mathematics and Theoretical Physics University of CambridgeCambridgeCB30WAUK. Beijing National Research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China

Consensus has been widely used in distributed control,where distributed individuals need to share their states with their neighbors through communication links to achieve a common ***,the objectives of existing consensus-based control strategies for energy systems seldom address battery degradation cost,which is an important performance indicator to assess the performance and sustainability of battery energy storage(BES)*** this paper,we propose a consensusbased optimal control strategy for multi-microgrid systems,aiming at multiple control objectives including minimizing battery degradation *** consensus is used to synchronize the ratio of BES output power to BES state-of-charge(SoC)among all microgrids while each microgrid is trying to reach its individual *** order to reduce the pressure of communication links and prevent excessive exposure of local information,this ratio is the only state variable shared between *** our complex nonlinear problem might be difficult to solve by traditional methods,we design a compressive sensing-based gradient descent(CSGD)method to solve the control *** simulation results show that our control strategy results in a 74.24%reduction in battery degradation cost on average compared to the control method without considering battery *** addition,the compressive sensing method causes an 89.12%reduction in computation time cost compared to the traditional Monte Carlo(MC)method in solving the control problem.

关键词： Battery degradation compressive sensing consensus distributed control multi-microgrid

来源：评论

学校读者我要写书评

暂无评论

CNN segmentation of skin melanoma in pre-processed dermoscopy images 2

CNN segmentation of skin melanoma in pre-processed dermoscop...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Kadry, Seifedine Verdú, Elena Damasevicius, Robertas Abualigah, Laith Singh, Vijendra Rajinikanth, Venkatesan Department of Applied Data Science Noroff University College Kristiansand Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Higher School of Engineering and Technology Universidad Internacional de la Rioja Logroño26006 Spain Department of Applied Informatics Vytautas Magnus University Kaunas53361 Lithuania Computer Science Department Al Al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia School of Computer Science University of Petroleum and Energy Studies Dehradun248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602105 India

Using medical data to improve diagnosis accuracy has recently become common practice in hospitals. A modern computing environment has enabled real-time diagnosis of medical data using Convolutional Neural Networks (CNNs). To extract and evaluate skin melanoma recorded with digital dermatoscopy images (DDI), we developed a CNN segmentation framework. In this proposal, four phases are proposed: (i) DDI collection and resizing, (ii) DDI enhancement using pre-processing techniques, (iii) CNN segmentation for lesion extraction, (v) Comparing the extracted sections to the ground truth images, and (v) Verifying whether the framework is valid. Using DDI pre-processed with (i) Traditional procedures, (ii) Otsu's thresholding, (iii) Kapur's thresholding, and (iv) Fuzzy-Tsallis thresholding, this proposal examines the different CNN segmentation schemes presented in the literature. For mining skin lesions, the Moth-Flame Algorithm (MFA) combined with tri-level thresholding achieves an optimal threshold for the DDI. With Fuzzy-Tsallis thresholding images, the VGG-UNet performs better than the alternatives. This framework helps to achieve better values of Jaccard (88.47±2.13%), Dice (93.08±1.17%), and Accuracy (98.64±0.71%) on the chosen DDI database. © 2024 Elsevier B.V.. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Investigation of district heating peak load reduction in residential neighbourhoods 18

Investigation of district heating peak load reduction in res...

引用

18th IBPSA Conference on Building Simulation, BS 2023

作者： Mokhtari, Reza Filonenko, Konstantin Junker, Rune Grønborg Madsen, Henrik Li, Rongling Department of Civil Engineering and Mechanical Engineering Technical University of Denmark Brovej 118 Kgs. Lyngby2800 Denmark Department of Applied Mathematics and Computer Science Technical University of Denmark Richard Petersens Plads Building 324 Kgs. Lyngby2800 Denmark

This study explores the potential of utilizing the energy flexibility of heat customers to reduce peak loads and improve the efficiency of district heating systems. Using Modelica and compiled in Dymola, a rule-based controller and dynamic heat price signals were developed to unlock the energy flexibility of buildings. Simulations were conducted to estimate peak load reduction and potential energy savings that could be realized. To investigate this opportunity, we conducted a simulation-based modeling study of a case study consisting of 19 apartment blocks connected to a local district heating network in a certain location. © 2023 *** rights reserved.

关键词： District heating

来源：评论

学校读者我要写书评

暂无评论

Generative Methods for Out-of-distribution Prediction and Applications for Threat Detection and Analysis: A Short Review 1st

Generative Methods for Out-of-distribution Prediction and Ap...

引用

1st International Workshop on Digital Sovereignty in Cyber Security: New Challenges in Future Vision, CyberSec4Europe 2022

作者： Coppolillo, Erica Liguori, Angelica Guarascio, Massimo Pisani, Francesco Sergio Manco, Giuseppe Department of Mathematics and Computer Science University of Calabria Rende Italy Department of Computer Engineering Modeling Electronics an d Systems University of Calabria Rende Italy Institute for High Performance Computing and Networking of Italian National Research Council Rende Italy

ISBN: (纸本)9783031360954

In recent times, Machine Learning has played an important role in developing novel advanced tools for threat detection and mitigation. Intrusion Detection, Misinformation, Malware, and Fraud Detection are just some examples of cybersecurity fields in which Machine Learning techniques are used to reveal the presence of malicious behaviors. However, Out-of-Distribution, i.e., the potential distribution gap between training and test set, can heavily affect the performances of the traditional Machine Learning based methods. Indeed, they could fail in identifying out-of-samples as possible threats, therefore devising robust approaches to cope with this issue is a crucial and relevant challenge to mitigate the risk of undetected attacks. Moreover, a recent emerging line proposes to use generative models to yield synthetic likely examples to feed the learning algorithms. In this work, we first survey recent Machine Learning and Deep Learning based solutions to face both the problems, i.e., outlier detection and generation;then we illustrate the main cybersecurity application scenarios in which these approaches have been adopted successfully. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Automatic liver-vessel examination from CT slice using Kapur's thresholding and watershed algorithm 2

Automatic liver-vessel examination from CT slice using Kapur...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Kadry, Seifedine Abualigah, Laith González Crespo, Rubén Verdú, Elena Damasevicius, Robertas Singh, Vijendra Rajinikanth, Venkatesan Department of Applied Data Science Noroff University College Kristiansand Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Computer Science Department Al Al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia Higher School of Engineering and Technology Universidad Internacional de la Rioja Logroño26006 Spain Department of Applied Informatics Vytautas Magnus University Kaunas53361 Lithuania School of Computer Science University of Petroleum and Energy Studies Dehradun248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602105 India

computerized medical image examination (CMIE) plays a significant role in modern hospitals to achieve the necessary tasks, like segmentation and classification. By segmenting an image, we can extract a particular section for examination. A two-dimensional computed tomography (CT) slice was used for liver-vessel examination (LiVE). A simple automatic technique for supporting LiVE is being developed in this research. A CT slice is collected, a 3D to 2D conversion is done, (ii) Kapur's tri-level thresholding and Hummingbird-Optimizer is used to enhance the CT slice, (iii) the watershed algorithm (WA) is used to extract the vessel, and (iv) the WA is compared and verified against the segmentation methods chosen. WA provides better segmentation results than other methods because it is an automatic approach. Using the chosen image database, the proposed technique achieves an overall segmentation accuracy of >97%. Other segmentation problems can be used in the future to verify the merit of this scheme. © 2024 Elsevier B.V.. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

COVID19 detection in chest x-ray using vision-transformer with different patch dimensions 2

COVID19 detection in chest x-ray using vision-transformer wi...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

computerized disease detection systems (CDDs) have proven effective for automatic screening in recent years. Among the standard procedures in hospitals for faster and more accurate diagnosis is medical imaging-based disease screening. We aim to develop a CDD that detects COVID-19 using chest X-rays pre-trained vision transformers (PVTs). This scheme includes the following steps: (1) collecting images and resizing them, (2) implementing PVT for feature extraction, and (3) binary classifying the results and validating the proposed schemes. To prove the merit of the developed scheme, 4800 images (2400 normal and 2400 COVID-19) are analyzed. MLP classifiers verify the PVT performance using patch sizes of 6, 12, and 24. A patch size 24 results in 97.5% accuracy for the proposed CDD system. When patch sizes are increased to 12, accuracy increases to over 98%. For this specific task, smaller patch sizes are more effective. These high-accuracy results demonstrate the effectiveness of the developed scheme for detecting COVID-19 in chest X-rays. © 2024 Elsevier B.V.. All rights reserved.

关键词： Diagnosis

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：