检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ye, Feiyang Lin, Baijiong Cao, Xiaofeng Zhang, Yu Tsang, Ivor W. Department of Computer Science and Engineering Southern University of Science and Technology China Australian Artificial Intelligence Institute University of Technology Sydney Australia China School of Artificial Intelligence Jilin University China Shanghai Artificial Intelligence Laboratory China Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research School of Computer Science and Engineering Nanyang Technological University Singapore

In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level subproblem is for scalar optimization. Existing gradient-based MOBLO algorithms need to compute the Hessian matrix, causing the computational inefficient problem. To address this, we propose an efficient first-order multi-gradient method for MOBLO, called FORUM. Specifically, we reformulate MOBLO problems as a constrained multi-objective optimization (MOO) problem via the value-function approach. Then we propose a novel multi-gradient aggregation method to solve the challenging constrained MOO problem. Theoretically, we provide the complexity analysis to show the efficiency of the proposed method and a non-asymptotic convergence result. Empirically, extensive experiments demonstrate the effectiveness and efficiency of the proposed FORUM method in different learning problems. In particular, it achieves state-of-the-art performance on three multi-task learning benchmark datasets. The code is available at https://***/Baijiong-Lin/FORUM. Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Determining Damping Loss in Modeling GHz Acoustic Block through Inverse Analysis for Accurate Ultrasonic Wavefront Computation Apparatus

Determining Damping Loss in Modeling GHz Acoustic Block thro...

引用

IEEE Symposium (IUS) Ultrasonics

作者： Zaifeng Yang Xing Haw Marvin Tan Daniel Ssu-Han Chen Zibo Juan Viet Phuong Bui Kevin Tshun Chuan Chai Ching Eng Png Amit Lal Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) Singapore Institute of Microelectronics (IME) Agency for Science Technology and Research (A*STAR) Singapore School of Electrical and Computer Engineering Cornell University Ithaca New York USA

The Ultrasonic wavefront computation apparatus (UWFCA) is designed to derive the Fourier Transform (FT) using gigahertz acoustic waves generated by piezoelectric transducer arrays. The waves propagate through acoustic blocks and an ultrasonic lens, yielding FT that can be digitized at the focal plane. In the full-wave simulation of the UWFCA, the damping loss within the acoustic blocks is usually approximated using an empirical value. However, the imprecise modeling of the GHz acoustic block can markedly degrade the accuracy of the FT results from UWFCA. To address this issue, we present an inverse analysis method to determine the damping loss in the GHz acoustic block for accurate UWFCA modeling based on measured data. We integrate the total displacement fields at different planes within the GHz acoustic block for various damping loss factors. Thus, the relationship between the loss and different damping loss factors is established. Based on the measured results, we employ regression method and inverse analysis to determine the accurate damping loss factor applicable to the gigahertz acoustic block. The simulated FT result agrees well with the analytical one, and the displacement distributions show how the acoustic waves form an FT pattern.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Simulation Of Ultrasonic Attenuation In Fourier Transform Analog computing

Novel Simulation Of Ultrasonic Attenuation In Fourier Transf...

引用

IEEE Symposium (IUS) Ultrasonics

作者： Xing Haw Marvin Tan Daniel Ssu-Han Chen Viet Phuong Bui Zaifeng Yang Zibo Juan Amit Lal Ching Eng Png Kevin Tshun Chuan Chai Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) Singapore Institute of Microelectronics (IME) Agency for Science Technology and Research (A*STAR) Singapore School of Electrical and Computer Engineering Cornell University Ithaca New York USA

Ultrasonic Fourier Transform analog computing uses acoustic waves propagating across fused silica and an acoustic lens to compute the Fourier Transform. We demonstrate a method to incorporate not only the attenuation of ultrasonic waves in the fused silica medium, but also the transmittance of the acoustic meta-lens into our 3D hybrid simulation integrating both finite element analysis and Fresnel diffraction. Our realistic simulation predicts the effect of acoustic attenuation on the voltage at the receiver pixel array, which guides electrical specifications for the low-noise amplifier at the RX CMOS circuit, to maximize the readout signal-to-noise ratio.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A DHR executor selection algorithm based on historical credibility and dissimilarity clustering

引用

science China(Information sciences) 2023年第11期66卷 288-301页

作者： Sisi SHAO Yimu JI Weili ZHANG Shangdong LIU Fei JIANG Zhigang CAO Fei WU Fukang ZENG Jun ZUO Longfei ZHOU School of Computer Science Nanjing University of Posts and Telecommunications Institue of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Purple Mountain Laboratories Nanjing Center of HPC China Jiangsu HPC and Intelligent Processing Engineer Research Center School of Foreign Languages Information Engineering University The 28th Research Institute of China Electronics Technology Group Corporation

The security of the dynamic heterogeneous redundancy(DHR) architecture relies on the heterogeneity of its executors, which also defines the vulnerability of the mimic system. In order to select executors with reliable and significant dissimilarity as service executors, we propose a DHR executor selection algorithm based on historical credibility and dissimilarity clustering(HCDC), which adds two metrics of executor historical credibility and dissimilarity. First, to maximize the difference between heterogeneous executor pools,clustering is performed based on the dissimilarity of the executor. Second, the executor with the highest historical credibility is selected from the heterogeneous executor pool as the candidate pool. The historical credibility is dynamically updated by the negative feedback control based on the results of the multi-mode adjudicator. Finally, the dynamic scheduling algorithm selects the executors from the candidate pool to form the set of service executors. The simulation results demonstrate that, in comparison to existing methods,the algorithm reduces the attack success rate and average failure rate while increasing system reliability.

关键词： endogenous security mimic defense DHR executor selection historical credibility

来源：评论

学校读者我要写书评

暂无评论

Pipeline Parallelism in Distributed Deep Learning for Diabetic Retinopathy Classification

引用

Procedia computer science 2022年 215卷 393-402页

作者： Shashank Anand Patil Mahesh S Patil Shantala Giraddi Satyadhyan Chickerur Vinayak M Boormane Ganesh Gamanagatti School of Computer Science and Engineering K L E Technological University Hubballi-580031 Karnataka India Center for High Performance Computing K L E Technological University Hubballi-580031 Karnataka India

Deep learning (DL) has been used widely and successfully in a variety of industries. It is challenging for researchers to carry out their experiments to find the optimal learning model because training the deep learning model is a time-consuming operation. Distributed deep learning offers a technique for rapid training of DL models (DDL). It is difficult to create and implement DDL, nevertheless, so it is important to report on the performance analysis of different DDL algorithms for the benefit of the research community. The authors of this proposed study use two GPUs to design, construct, and analyse a pipeline parallelism in DDL and then present an analysis of its performance. As a case study for DDL implementation, the authors employ diabetic retinopathy classification. 0.834 is obtained as the validation F1 score. The performance of DDL is reported and examined by the authors, and it is demonstrated to improve training effectiveness in terms of both time and speed.

关键词： Deep learning Distributed Deep learning Diabetic Retinopathy classification Graphics Processing Unit(GPU) Pipeline Parallelism

来源：评论

学校读者我要写书评

暂无评论

$\text{MR}^{2}$-Net: Retinal OCTA Image Stitching via Multi-Scale Representation Learning and Dynamic Location Guidance

引用

IEEE Journal of Biomedical and Health Informatics 2024年第1期29卷 482-494页

作者： Haiting Mao Yuhui Ma Dan Zhang Yanda Meng Shaodong Ma Yuchuan Qiao Huazhu Fu Caifeng Shan Da Chen Yitian Zhao Jiong Zhang Laboratory of Advanced Theranostic Materials and Technology Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo China School of Cyber Science and Engineering Ningbo University of Technology Ningbo China Department of Computer Science University of Exeter Exeter U.K. Institution of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China Institute of High Performance Computing (IHPC) A*STAR Singapore School of Intelligence Science and Technology Nanjing University Nanjing China Qilu University of Technology Jinan China

Optical coherence tomography angiography (OCTA) plays a crucial role in quantifying and analyzing retinal vascular diseases. However, the limited field of view (FOV) inherent in most commercial OCTA imaging systems poses a significant challenge for clinicians, restricting the possibility to analyze larger retinal regions of high resolution. Automatic stitching of OCTA scans in adjacent regions may provide a promising solution to extend the region of interest. However, commonly-used stitching algorithms face difficulties in achieving effective alignment due to noise, artifacts and dense vasculature present in OCTA images. To address these challenges, we propose a novel retinal OCTA image stitching network, named $\text{MR}^{2}$ -Net, which integrates multi-scale representation learning and dynamic location guidance. In the first stage, an image registration network with a progressive multi-resolution feature fusion is proposed to derive deep semantic information effectively. Additionally, we introduce a dynamic guidance strategy to locate the foveal avascular zone (FAZ) and constrain registration errors in overlapping vascular regions. In the second stage, an image fusion network based on multiple mask constraints and adjacent image aggregation (AIA) strategies is developed to further eliminate the artifacts in the overlapping areas of stitched images, thereby achieving precise vessel alignment. To validate the effectiveness of our method, we conduct a series of experiments on two delicately constructed datasets, i.e., OPTOVUE-OCTA and SVision-OCTA. Experimental results demonstrate that our method outperforms other image stitching methods and effectively generates high-quality wide-field OCTA images, achieving a structural similarity index (SSIM) score of 0.8264 and 0.8014 on the two datasets, respectively.

关键词： Feature extraction Image stitching Retina Image registration Convolutional codes Bioinformatics Representation learning

来源：评论

学校读者我要写书评

暂无评论

FundusGAN: A Hierarchical Feature-Aware Generative Framework for high-Fidelity Fundus Image Generation

arXiv

引用

arXiv 2025年

作者： Hou, Qingshan Wang, Meng Cao, Peng Ke, Zou Liu, Xiaoli Fu, Huazhu Zaiane, Osmar R. Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China Alberta Machine Intelligence Institute University of Alberta Edmonton Canada Ophthalmology Yong Loo Lin School of Medicine National University of Singapore Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore

Recent advancements in ophthalmology foundation models such as RetFound have demonstrated remarkable diagnostic capabilities but require massive datasets for effective pre-training, creating significant barriers for development and deployment. To address this critical challenge, we propose FundusGAN, a novel hierarchical feature-aware generative framework specifically designed for high-fidelity fundus image synthesis. Our approach leverages a Feature Pyramid Network within its encoder to comprehensively extract multi-scale information, capturing both large anatomical structures and subtle pathological features. The framework incorporates a modified StyleGAN-based generator with dilated convolutions and strategic upsampling adjustments to preserve critical retinal structures while enhancing pathological detail representation. Comprehensive evaluations on the DDR, DRIVE, and IDRiD datasets demonstrate that FundusGAN consistently outperforms state-of-the-art methods across multiple metrics (SSIM: 0.8863, FID: 54.2, KID: 0.0436 on DDR). Furthermore, disease classification experiments reveal that augmenting training data with FundusGAN-generated images significantly improves diagnostic accuracy across multiple CNN architectures (up to 6.49% improvement with ResNet50). These results establish FundusGAN as a valuable foundation model component that effectively addresses data scarcity challenges in ophthalmological AI research, enabling more robust and generalizable diagnostic systems while reducing dependency on large-scale clinical data collection. Copyright © 2025, The Authors. All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

FinXABSA: Explainable Finance through Aspect-Based Sentiment Analysis

FinXABSA: Explainable Finance through Aspect-Based Sentiment...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Keane Ong Wihan van der Heever Ranjan Satapathy Erik Cambria Gianmarco Mengaldo Asian Institute of Digital Finance National University of Singapore Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) Singapore College of Design & Engineering National University of Singapore Singapore

This paper presents a novel approach for explain-ability in financial analysis by deriving financially-explainable statistical relationships through aspect-based sentiment analysis, Pearson correlation, Granger causality & uncertainty coefficient. The proposed methodology involves constructing an aspect list from financial literature and applying aspect-based sentiment analysis on social media text to compute sentiment scores for each aspect. Pearson correlation is then applied to uncover financially explainable relationships between aspect sentiment scores and stock prices. Findings for derived relationships are made robust by applying Granger causality to determine the forecasting ability of each aspect sentiment score for stock prices. Finally, an added layer of interpretability is added by evaluating uncertainty coefficient scores between aspect sentiment scores and stock prices. This allows us to determine the aspects whose sentiment scores are most statistically significant for stock prices. Relative to other methods, our approach provides a more informative and accurate understanding of the relationship between sentiment analysis and stock prices. Specifically, this methodology enables an interpretation of the statistical relationship between aspect-based sentiment scores and stock prices, which offers explainability to AI-driven financial decision-making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Health Care and Management based on Block chain and Machine Learning

Health Care and Management based on Block chain and Machine ...

引用

Artificial Intelligence and Knowledge Discovery in Concurrent engineering (ICECONF), International Conference on

作者： Ruhi Bakh VeenaNair Sarkar Jerlin Priya Lovelin Auguskani Galiveeti Poornima Monali N. Shetty Meerjumla Govind Raj Dr. Ambedkar Institute of Management Studies and Research IIHMR UNIVERSITY. Department of Nursing College Aldrab Jazan University Kingdom of Saudi Arabia. High Performance Computing Lab School of Computer Science and Information Science Presidency University Bengaluru Computer Science Engineering Fr. CRCE St. Martin's Engineering College Secunderabad Telangana

With the coming of technology, we currently have an immense measure of information accessible in each field, making it conceivable to offer responses to many issues. We will utilize machine learning and block chain technology to resolve issues with healthcare information the executives in this review. With the guide of machine learning, separating just the relevant information from the data is plausible. Using prepared calculations, this is finished. The reliability of information trade turns into a test after this information has been put away. This is where block chain technology is valuable. Block chain technology's agreement guarantees that information is credible and exchanges are secure. By putting the patient at the focal point of the healthcare framework and upgrading the security and interoperability of health information, block chain technology can possibly further develop health care organization. This article fundamentally centres around settling issues with healthcare information the board using Block chain technology and including a few urgent highlights utilizing Machine Learning. The freshest technology, block chain, offers a strong and secure groundwork. With these offices, block chain has gotten some momentum in an assortment of use areas, including the food business, store network the board, energy, government support offices, and healthcare.

关键词： Telemedicine Government Medical treatment Machine learning Medical services Knowledge discovery Blockchains

来源：评论

学校读者我要写书评

暂无评论

FlyDB: Query Optimization of Blockchain System Based on Hybrid Storage Architecture

FlyDB: Query Optimization of Blockchain System Based on Hybr...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Yang Liu Zehui Xie Nong Xiao Zhiguang Chen Yang Ou Institute for Quantum Information & State Key Laboratory of High-Performance Computing College of Computer National University of Defense Technology Changsha China School of computer science and Engineering Sun Yat-sen University Guangzhou China College of Computer National University of Defense Technology Changsha China

The hybrid storage architecture incorporates a blockchain dual-index structure optimized for byte addressing in non-volatile memory, low-latency features, and the large capacity of SSD. This paper presents a novel LSM-Tree architecture that leverages the byte-addressing characteristics of non-volatile memory. The layers of the level 0 and level 1 are stored in non-volatile memory while employing a local key-value separation strategy to minimize read and write operations during compaction. A logic compression strategy is proposed to handle data compression tasks efficiently. A dual-index structure design is introduced for users to address the scope and multi-keyword queries in the blockchain system. During the compression process, keyword switching occurs during data reordering, ensuring that data within the same SSTable is rearranged according to user preferences. By effectively harnessing the advantages of each level in the hybrid storage architecture, this design significantly reduces both databases write time and the response time for complex queries.

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：