检索结果-内蒙古大学图书馆

Deep Learning in Smart Healthcare: A GAN-based Approach for Imbalanced Alzheimer's Disease Classification

Procedia Computer Science 2024年 241卷 146-153页

作者： Hina Tufail Abdul Ahad Ira Puspitasari Ibraheem Shayea Paulo Jorge Coelho Ivan Miguel Pires Department of Computer Science University of Management and Technology Sialkot Pakistan Information System Study Program Faculty of Science and Technology Universitas Airlangga School of Software Northwestern Polytechnical University Xian Shaanxi P.R. China Department of Electronics and Communication Engineering Istanbul Technical University(ITU) Turkey Polytechnic University of Leiria Leiria Portugal Institute for Systems Engineering and Computers at Coimbra (INESC Coimbra) Coimbra Portugal Instituto de Telecomunicações Escola Superior de Tecnologia e Gestão de Águeda Universidade de Aveiro Águeda Portugal

Alzheimer's disease (AD) is a type of dementia that leads to memory loss and impairment, which afects patients’ lives badly. It is not curable yet, but its progression can be slowed down if detected at earlier stages. In this research study, we propose a transfer learning-based convolutional neural network (CNN) model to classify magnetic resonance imaging (MRI) into one of four stages of Alzheimer's disease. One of the major limitations of the deep learning-based classification model is the non-availability of healthcare datasets related to AD. The widely used Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset has a major class imbalance issue. We propose a generative adversarial network (GAN) based data augmentation technique to overcome the data imbalance. This promotes the investigation of applying GANs to generate synthetic samples for minority classes in Alzheimer's disease datasets to enhance classification performance. The results show the progression in the overall classification process of AD.

关键词： Alzheimer disease (AD) Deep learning Convolutional Neural Network (CNN) Computer-aided diagnosis (CAD)

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services

TechRxiv

引用

TechRxiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Huang, Huawei Mao, Shiwen School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore School of Software Engineering Sun Yat-Sen University Zhuhai China Department of Electrical and Computer Engineering Auburn University Auburn United States

As Metaverse emerges as the next-generation Internet paradigm, the ability to efficiently generate content is paramount. AI-Generated Content (AIGC) emerges as a key solution, yet the resource-intensive nature of large Generative AI (GAI) models presents challenges. To address this issue, we introduce an AIGC-as-a-Service (AaaS) architecture, which deploys AIGC models in wireless edge networks to ensure broad AIGC services accessibility for Metaverse users. Nonetheless, an important aspect of providing personalized user experiences requires carefully selecting AIGC Service Providers (ASPs) capable of effectively executing user tasks, which is complicated by environmental uncertainty and variability. Addressing this gap in current research, we introduce the AI-Generated Optimal Decision (AGOD) algorithm, a diffusion model-based approach for generating the optimal ASP selection decisions. Integrating AGOD with Deep Reinforcement Learning (DRL), we develop the Deep Diffusion Soft Actor-Critic (D2SAC) algorithm, enhancing the efficiency and effectiveness of ASP selection. Our comprehensive experiments demonstrate that D2SAC outperforms seven leading DRL algorithms. Furthermore, the proposed AGOD algorithm has the potential for extension to various optimization problems in wireless networks, positioning it as a promising approach for future research on AIGC-driven services. The implementation of our proposed method is available at: https://***/Lizonghang/AGOD. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Huang, Huawei Mao, Shiwen The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The School of Software Engineering Sun Yat-Sen University Zhuhai China The Department of Electrical and Computer Engineering Auburn University Auburn United States

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

k-mer-based approaches to bridging pangenomics and population genetics

arXiv

引用

arXiv 2024年

作者： Roberts, Miles D. Davis, Olivia Josephs, Emily B. Williamson, Robert J. Genetics and Genome Sciences Program Michigan State University East LansingMI48824 United States Department of Computer Science and Software Engineering Rose-Hulman Institute of Technology Terre HauteIN47803 United States Department of Biology and Biomedical Engineering Rose-Hulman Institute of Technology Terre HauteIN47803 United States Department of Plant Biology Michigan State University East LansingMI48824 United States Ecology Evolution and Behavior Program Michigan State University East LansingMI48824 United States Plant Resilience Institute Michigan State University East LansingMI48824 United States

Many commonly studied species now have more than one chromosome-scale genome assembly, revealing a large amount of genetic diversity previously missed by approaches that map short reads to a single reference. However, many species still lack multiple reference genomes and correctly aligning references to build pangenomes is challenging, limiting our ability to study this missing genomic variation in population genetics. Here, we argue that k-mers are a crucial stepping stone to bridging the reference-focused paradigms of population genetics with the reference-free paradigms of pangenomics. We review current literature on the uses of k-mers for performing three core components of most population genetics analyses: identifying, measuring, and explaining patterns of genetic variation. We also demonstrate how different k-mer-based measures of genetic variation behave in population genetic simulations according to the choice of k, depth of sequencing coverage, and degree of data compression. Overall, we find that k-mer-based measures of genetic diversity scale consistently with pairwise nucleotide diversity (π) up to values of about π = 0.025 (R2 = 0.97) for neutrally evolving populations. For populations with even more variation, using shorter k-mers will maintain the scalability up to at least π = 0.1. Furthermore, in our simulated populations, k-mer dissimilarity values can be reliably approximated from counting bloom filters, highlighting a potential avenue to decreasing the memory burden of k-mer based genomic dissimilarity analyses. For future studies, there is a great opportunity to further develop methods to identifying selected loci using k-mers. © 2024, CC BY.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Computability, complexity, consistency and controllability: A Four C’s Framework for cross-disciplinary ethical algorithm research

arXiv

引用

arXiv 2021年

作者： Perrier, Elija Centre for Quantum Software and Information University of Technology Sydney SydneyNSW2000 Australia Humanising Machine Intelligence Program The Australian National University Canberra Australia

The ethical consequences, constraints upon and regulation of algorithms arguably represent the defining challenges of our age, asking us to reckon with the rise of computational technologies whose potential to radically transforming social and individual orders and identity in unforeseen ways is already being realised. Fittingly, concurrent with the emergence of such epoch-shaping technologies has emerged a rapidly expanding and multi-disciplinary set of research disciplines focused on these very questions. As the inexorable march of computational technologies encroaches across society and academic disciplines, it is natural that diverse specialisations including computer science, moral philosophy, engineering, jurisprudence and economics should turn their attention to the algorithmic zeitgeist. Yet despite the multi-disciplinary impact of this algorithmic turn, there remains some way to go in motivating cross-disciplinary collaboration is crucial to advancing feasible proposals for the ethical design, implementation and regulation of algorithmic and automated systems. In this work, we provide a framework to assist cross-disciplinary collaboration by presenting a ‘Four C’s Framework’ covering key computational considerations researchers across such diverse fields should consider when approaching these questions: (i) computability, (ii) complexity, (iii) consistency and (iv) controllability. In addition, we provide examples of how insights from ethics, philosophy and population ethics are relevant to and translatable within sciences concerned with the study and design of algorithms. Our aim is to set-out a framework which we believe is useful for fostering cross-disciplinary understanding of pertinent issues in ethical algorithmic literature which is relevant considering the feasibility of ethical algorithmic governance, especially the impact of computational constraints upon algorithmic governance. © 2021, CC BY.

关键词： Computability and decidability

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Classifier Using Sliding Patches For Detection of Mammographical Findings

A Deep Learning Classifier Using Sliding Patches For Detecti...

引用

Medical Information Processing and Analysis (SIPAIM), International Symposium on

作者： Diego Mellado Marvin Querales Julio Sotelo Eduardo Godoy Fabian Pardo Scarlett Lever Steren Chabert Rodrigo Salas PhD. Program in Health Sciences and Engineering Universidad de Valparaíso Valparaíso Chile School of Medical Technology Universidad de Valparaíso Valparaíso Chile Departamento de Informática UTFSM Santiago Chile PhD. Program in Applied Software Engineering Universidad de Valparaíso Valparaíso Chile School of Medicine Universidad de Valparaíso Valparaíso Chile School of Biomedical Engineering Universidad de Valparaíso Valparaíso Chile

Mammography is known as one of the best forms to screen possible breast cancer in women, and recently deep learning models have been developed to assist the radiologist in the diagnosis. However, their lack of interpretability has become a significant drawback to their extended use in clinical practice. This paper introduces a novel approach for detecting and localising pathological findings in mammography exams through the use of a EfficientNet-based deep learning model. The model is trained using cropped segments of labelled pathological findings from Vindr Mammography Dataset. Achieving an average F1-score of 72.7 %, and reaching on mass and suspicious calcifications an F1-Score of 79.9 % and 84.5 % respectively. Using this classifier we propose a method to visualise from local information the regions of interest where pathological findings could be present on the complete image. Plus, we describe the limitations regarding area coverage of these patches on the model’s capability of generalization and certainty on its predictions, explaining its functionality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating a network simulator with the high level architecture for the co-simulation of cyber-physical systems

Integrating a network simulator with the high level architec...

引用

2020 Simulation Innovation Workshop, SIW 2020

作者： Roth, Thomas Nguyen, Cuong Burns, Martin Neema, Himanshu Smart Grid and Cyber-Physical Systems Program Office National Institute of Standards and Technology GaithersburgMD20899 United States Institute for Software Integrated Systems Vanderbilt University NashvilleTN37212 United States

Cyber-physical systems (CPS) use logical computation informed by measurements of the environment to actuate changes on the physical world. These systems have significant impact on people, and must be designed for resilience against fault and attack. However, due to their large scale, assurance of CPS trustworthiness is better suited to modeling and simulation than deployment of a real system. This paper describes an approach to integrate a network simulator with the High Level Architecture (HLA) to investigate the effects of different network conditions on CPS performance. Using this approach, an HLA interaction class can be configured to use network simulation rather than the default reliable HLA delivery mechanism. A technique similar to regions defined in HLA data distribution management is used to allow each federate to receive the same interactions at different logical time steps, as simulated by the network simulator. This is implemented in a piece of reusable code shared by federates that sits between the runtime infrastructure (RTI) and application code. The implementation can be used to create a test harness around the federates that represent the operation of a CPS to validate its behavior under unreliable network conditions. © 2020 Simulation Innovation Workshop.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Fostering mathematical literacy amongst primary school students using realistic mathematics education approach

引用

AIP Conference Proceedings 2023年第1期2619卷

作者： Ratih Ayu Apsari Sariyasa Nourma Pramestie Wulandari Tabita Wahyu Triutami Agus Adi Putrawan Mathematics Education Study Program Universitas Mataram Mataram Indonesia Mathematics Education Study Program Universitas Pendidikan Ganesha Singaraja Indonesia Software Engineering Technology Politeknik Negeri Bali Badung Indonesia

The present study aims at comparing different ways of conducting lesson on two-digits multiplication for primary school students using algorithm and Realistic Mathematics Education (RME) approach. Qualitative experiment with user observation method had deliberately chosen as the design of the study as the intention is to figure out the impact of treatment while the subjects stay in natural setting of their habitat. There are three third grade classes consist of 61 primary school students in Singaraja, Bali – Indonesia who participated in this study. The participants were experienced different learning method, which are: (1) conventional class with multiplication algorithm followed by area model, (2) RME followed by multiplication algorithm and (3) RME. The data were gathered from students’ written work on the literacy test. Afterwards, a descriptive quantitative method was performed to analyze the data. The result showed that the third group in which RME approach was employed gained the best average scores to solve the literacy problems. Meanwhile, the second group in which the RME lesson was followed by multiplication algorithm gained the best average scores in solving routine problems. The study implies that RME approach contributes to the better mathematical literacy skills for young students.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Curriculum Learning for Semi-supervised Segmentation of 3D CT-Scans 28th

Adaptive Curriculum Learning for Semi-supervised Segmentati...

引用

28th International Conference on Neural Information Processing, ICONIP 2021

作者： Nartey, Obed Tettey Yang, Guowu Agyapong, Dorothy Araba Yakoba Wu, JinZhao Sarpong, Asare K. Frempong, Lady Nadia Big Data Research Center School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China The School of Computer Science and Electronic Information Guangxi University Nanning530004 China Biomedical Engineering Program Kwame Nkrumah University of Science and Technology Kumasi Ghana School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Medicine Department of Radiology and Imaging Sciences Emory University 1364 Clitton Rd. AtlantaGA30322 United States

ISBN: (纸本)9783030921842

Semi-supervised learning algorithms make use of both labelled training data and unlabelled data. However, the visual domain gap between these sets poses a challenge which prevents deep learning models from obtaining the results they have achieved most especially in the field of medical imaging. Recently, self-training with deep learning has become a powerful approach to leverage labelled training and unlabelled data. However, a challenge of generating noisy pseudo-labels and placing over-confident labelling belief on incorrect classes leads to deviation from the solution. To solve this challenge, the study investigates a curriculum-styled approach for deep semi-supervised segmentation which relaxes and treats pseudo-labels as continuous hidden variables by developing an adaptive pseudo-label generation strategy to jointly optimized the pseudo-label generation and selection process. A regularization scheme is further proposed to smoothen the probability outputs and sharpen the less represented pseudo-label regions. The proposed method was evaluated on three publicly available Computer Tomography (CT) scan benchmarks and extensive experiments on all modules have demonstrated the efficacy of the proposed method. © 2021, Springer Nature Switzerland AG.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Modeling for small cell networks in 5G communication environment

引用

Telecommunication Systems 2022年第2期80卷 189-214页

作者： Kim, Tae-Yeun Singh, A. K. Ko, Hoon National Program of Excellence in Software Center Chosun University Gwangju Republic of Korea Department of Computer Science and Engineering National Institute of Technology Patna Patna India Research Institute of Computer Information Communications Chungbuk National University E8-7 Chungdae-ro 1 Seowon-ku Chungcheongbuk-do South Korea Instituto Superior de Engenharia do Porto Instituto Politecnico do Porto R. Dr. Antonio Bernardino de Almeida 431 Porto Portugal

The small cell structure in which many cells are arranged per unit area by reducing the size of cells is a candidate technology for an increase in transmission capacity in the 5G environment. However, the decrease in the size of the cell led to additional problems such as increased inter cell interference and frequent cell changes owing to the movement of the terminal. Therefore, the aim of this study was to propose small cell dynamic channel allocation (SDCA) and hybrid and dynamic channel allocation (HDCA) using conventional reuse methods to improve the macro cell performance while efficiently utilizing scarce frequency resources. The proposed method facilitates an improved performance that is lacking for macro-cell users in the center area of the cell boundary for the network where conventional macro cells and small cells are superposed. Furthermore, to improve the performance, it can provide resources that are lacking in the small cells of the center. To evaluate the performance, the proposed method was compared to frequency reuse factor1 (FRF1), frequency reuse factor3 (FRF3), and fractional frequency reuse (FFR) methods in terms of the signal-to-interference/noise-ratio (SINR) of users of each macro cell and small cell, outage, capacity for each user, and total system capacity. As a result of comparing the SINR, it was confirmed that the performance of the macro cell users has improved by an average of 43.88% compared to FRF1, FRF3, and FFR, and the performance of small cell users has improved by an average of 4.31%. Comparison results show that the outage proportions of the macro and small cell users are 61.29% and 70.59% lower on average, respectively. A comparison of results show that the capacities of the macro and small cell users have also improved by 22.5% and 14.5% on average, respectively. As the comparison results of the total system capacity indicate, the proposed method shows an average improvement of 11.67%. In cases in which the added resources o

关键词：

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：