检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Tyagi, Sahil Swany, Martin Computing and Engineering Indiana University Luddy School of Informatics Department of Intelligent Systems Engineering BloomingtonIN United States

ISBN: (纸本)9781665480451

Distributed deep learning (DDL) training systems are designed for cloud and data-center environments that assumes homogeneous compute resources, high network bandwidth, sufficient memory and storage, a s w ell a s independent and identically distributed (IID) data across all nodes. However, these assumptions don't necessarily apply on the edge, especially when training neural networks on streaming data in an online manner. Computing on the edge suffers from both systems and statistical heterogeneity. systems heterogeneity is attributed to differences in compute resources and bandwidth specific to each device, while statistical heterogeneity comes from unbalanced and skewed data on the edge. Different streaming-rates among devices can be another source of heterogeneity when dealing with streaming data. If the streaming rate is lower than training batch-size, device needs to wait until enough samples have streamed in before performing a single iteration of stochastic gradient descent (SGD). Thus, low-volume streams act like stragglers slowing down devices with high-volume streams in synchronous training. On the other hand, data can accumulate quickly in the buffer if the streaming rate is too high and the devices can't train at line-rate. In this paper, we introduce ScaDLES to efficiently train on streaming data at the edge in an online fashion, while also addressing the challenges of limited bandwidth and training with non-IID data. We empirically show that ScaDLES converges up to 3.29× faster compared to conventional distributed SGD. © 2022 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Improving Fundus Detection Precision in Diabetic Retinopathy Using Derivative-Based Deep Neural Networks

引用

Computer Modeling in engineering & Sciences 2025年第3期142卷 2487-2511页

作者： Asma Aldrees Hong Min Ashit Kumar Dutta Yousef Ibrahim Daradkeh Mohd Anjum Department of Informatics and Computer Systems College of Computer ScienceKing Khalid UniversityAbha61421Saudi Arabia School of Computing Gachon UniversitySeongnam13120Republic of Korea Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityAd DiriyahRiyadh13713Saudi Arabia Department of Computer Engineering and Information College of Engineering in Wadi AlddawasirPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia Department of Computer Engineering Aligarh Muslim UniversityAligarh202002India

Fundoscopic diagnosis involves assessing the proper functioning of the eye’s nerves,blood vessels,retinal health,and the impact of diabetes on the optic *** disorders are a major global health concern,affecting millions of people worldwide due to their widespread *** photography generates machine-based eye images that assist in diagnosing and treating ocular diseases such as diabetic *** a result,accurate fundus detection is essential for early diagnosis and effective treatment,helping to prevent severe complications and improve patient *** address this need,this article introduces a Derivative Model for Fundus Detection using Deep NeuralNetworks(DMFD-DNN)to enhance diagnostic *** selects key features for fundus detection using the least derivative,which identifies features correlating with stored fundus *** filtering relies on the minimum derivative,determined by extracting both similar and varying *** this research,the DNN model was integrated with the derivative *** images were segmented,features were extracted,and the DNN was iteratively trained to identify fundus regions *** goal was to improve the precision of fundoscopic diagnosis by training the DNN incrementally,taking into account the least possible derivative across iterations,and using outputs from previous *** hidden layer of the neural network operates on the most significant derivative,which may reduce precision across *** derivatives are treated as inaccurate,and the model is subsequently trained using selective features and their corresponding *** proposed model outperforms previous techniques in detecting fundus regions,achieving 94.98%accuracy and 91.57%sensitivity,with a minimal error rate of 5.43%.It significantly reduces feature extraction time to 1.462 s and minimizes computational overhead,thereby improving operational efficiency and ***,the propo

关键词： Deep neural network feature extraction fundus detection medical image processing

来源：评论

学校读者我要写书评

暂无评论

Efficient 3D Hilbert Curve Encoding and Decoding Algorithms

引用

Chinese Journal of Electronics 2022年第2期31卷 277-284页

作者： JIA Lianyin LIANG Binbin LI Mengjuan LIU Yong CHEN Yinong DING Jiaman Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Library Yunnan Normal University School of Information Science and Engineering Guangxi University for Nationalities School of Computing Informatics and Decision Systems Arizona State University

Hilbert curve describes a one-to-one mapping between multidimensional space and 1 D *** traditional 3D Hilbert encoding and decoding algorithms work on order-wise manner and are not aware of the difference between different input data and spend equivalent computing costs on them, thus resulting in a low efficiency. To solve this problem, in this paper we design efficient 3D state views for fast encoding and decoding. Based on the state views designed, a new encoding algorithm(JFK-3HE) and a new decoding algorithm(JFK-3HD) are proposed. JFK-3HE and JFK-3HD can avoid executing iteratively encoding or decoding each order by skipping the first 0 s in input data, thus decreasing the complexity and improving the efficiency. Experimental results show that JFK-3HE and JFK-3HD outperform the state-of-the-arts algorithms for both uniform and skew-distributed data.

关键词： order-wise manner multidimensional space encoding state-of-the-arts algorithms encoding algorithm parallel algorithms JFK-3HE statistical distributions decoding solid modelling design efficient 3D JFK-3HD traditional 3D Hilbert encoding equivalent computing costs different input data decoding algorithm Hilbert curve state views iterative methods

来源：评论

学校读者我要写书评

暂无评论

Circumstance Evaluation Using Extreme Value Analysis on Charging Station Data: The Case of DEI Blue in Greece 14th

Circumstance Evaluation Using Extreme Value Analysis on Cha...

引用

14th International Conference on Information, Intelligence, systems, and Applications, IISA 2023

作者： Panagoulias, Dimitrios P. Sarmas, Elissaios Marinakis, Vangelis Tsihrintzis, George A. Department of Informatics University of Piraeus Piraeus18534 Greece Decision Support Systems Lab School of Electrical and Computer Engineering National Technical University of Athens Zografou-Athens15773 Greece

ISBN: (纸本)9783031674259

We apply Extreme Value Analysis on sets of Electric Vehicle (EV) charging data with the goal to extract indications in the data of future trends in the demand for EV charging. The datasets have been provided by DEI blue, a service designed to provide integrated e-mobility solutions to individuals, companies and public administration throughout Greece. Eventhough the data are limited as they have been collected during a period of only twelve months, our analysis still reveals trends in the data highlighting a probable seasonality. The seasonality is observed during periods of extreme heat, regional population mobility and incoming visitors. These occurrences impact technical aspects of battery efficiency, grid capacity and a shift of behavioural usage patterns. Our findings cannot be ignored by policy makers as they are expected to intensify in the years to come due to the fast-rising number of EVs in use. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Electrification

来源：评论

学校读者我要写书评

暂无评论

Sensing-Assisted Channel Estimation in ISAC systems 14th

Sensing-Assisted Channel Estimation in ISAC Systems

引用

14th EAI International Conference on Wireless and Satellite systems, WiSATS 2024

作者： Yin, Rui Shi, Yexin Qi, Wei Chen, Xianfu Wu, Celimuge Ji, Yusheng School of Information and Electrical Engineering Hangzhou City University Hangzhou310018 China College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Shenzhen CyberAray Network Technology Company Ltd Shenzhen China Graduate School of Informatics and Engineering The University of Electro-Communications Tokyo182-8585 Japan Information Systems Architecture Research Division National Institute of Informatics Tokyo101-8430 Japan

ISBN: (纸本)9783031862021

In future Sixth-Generation (6G) mobile communication, satellite communication is a crucial means of extending mobile networks worldwide. However, in satellite communication systems, the transmission capacity between ground stations and users has become a bottleneck for satellite communication systems. For this issue, Integrated Sensing and Communication (ISAC) technology and Artificial Intelligence (AI), which has been widely studied, has the potential to offer excellent solutions. This paper explores a Uformer-based sensing-assisted communication system that enhances channel estimation accuracy through the design of a Uformer-based channel estimation enhancement algorithm. By formulating a global optimization problem, we seek to improve resource efficiency through finding the optimal resource allocation schemes. Initially, the system utilizes radar data to obtain reconstructed channels and employs communication data for channel estimation. The proposed neural network model then fuses these data into a new and more accurate channel state information. Finally, we present a resource allocation algorithm and validate the performance of all proposed algorithms through simulations. © ICST Institute for Computer Sciences, Social informatics and Telecommunications engineering 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Fostering interdisciplinary data cultures through early career development: The RDA/US data share fellowship

引用

Data Science Journal 2021年第1期20卷 1-19页

作者： Kouper, Inna Scheidt, Lois A. Plale, Beth A. Department of Informatics School of Informatics Computing and Engineering Indiana University Bloomington United States School of Information Studies University of Wisconsin Milwaukee United States Department of Intelligent Systems and Engineering School of Informatics Computing and Engineering Indiana University Bloomington United States

Openness and interdisciplinarity in research and data are among the challenges that are frequently discussed in the context of changing scientific and scholarly practices. Gradually, the visions of open and widely shared data are being reconciled with complex realities that stem from the disciplinary differences in data cultures. In this paper we discuss interdisciplinarity through data as a way to create research environments that are more flexible and, as a result, more amenable to change. We report our findings from facilitating and evaluating a data-oriented early-career fellowship program that was administered as part of the Research Data Alliance (RDA), a global organization that aims to enable open sharing and re-use of data. We identify ways to foster interdisciplinary data cultures among the future researchers and professionals and propose recommendations for future programs. While the short-term early career programs cannot address the systemic factors that impact openness and interdisciplinarity, such as the systems of reward and recognition or the funding structures, they can introduce mechanisms that support diversity, learning, and leadership and, ultimately, contribute to a culture change. © 2021 The Author(s).

关键词： Data culture Data stewardship Early career training Open science

来源：评论

学校读者我要写书评

暂无评论

Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs 41

Bounded and Uniform Energy-based Out-of-distribution Detecti...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Shenzhi Liang, Bin Liu, An Gui, Lin Yao, Xingkai Zhang, Xiaofang School of Computer Science and Technology Soochow University Suzhou China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Department of Informatics King's College London London United Kingdom

Given the critical role of graphs in real-world applications and their high-security requirements, improving the ability of graph neural networks (GNNs) to detect out-of-distribution (OOD) data is an urgent research problem. The recent work GNNSAFE (Wu et al., 2023) proposes a framework based on the aggregation of negative energy scores that significantly improves the performance of GNNs to detect node-level OOD data. However, our study finds that score aggregation among nodes is susceptible to extreme values due to the unboundedness of the negative energy scores and logit shifts, which severely limits the accuracy of GNNs in detecting node-level OOD data. In this paper, we propose NODESAFE: reducing the generation of extreme scores of nodes by adding two optimization terms that make the negative energy scores bounded and mitigate the logit shift. Experimental results show that our approach dramatically improves the ability of GNNs to detect OOD data at the node level, e.g., in detecting OOD data induced by Structure Manipulation, the metric of FPR95 (lower is better) in scenarios without (with) OOD data exposure are reduced from the current SOTA by 28.4% (22.7%). The code is available via https://***/ShenzhiYang2000/NODESAFE. Copyright 2024 by the author(s)

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Initial Exploration and Understanding of Parameters for Successful Enterprise Architecture Implementation 11

Initial Exploration and Understanding of Parameters for Succ...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Khairina, Dyna Marisa Purwanto, Purwanto Nugraheni, Dinar Mutiara Kusumo School of Postgraduate Studies Universitas Diponegoro Program in Information Systems Semarang Indonesia Universitas Diponegoro Faculty of Engineering Department of Chemical Engineering Semarang Indonesia Universitas Diponegoro Faculty of Science and Mathematics Department of Informatics Semarang Indonesia

ISBN: (纸本)9798350389654

This study provides an initial exploration and further understanding of the factors that are parameters in evaluating the success of Enterprise Architecture (EA) implementation. An evaluation process is needed to ensure that the EA project implementation provides effectiveness, efficiency, and feasibility of the EA information system as well as assessing previous project experience to avoid future EA project risks. The research aims to present a Systematic Literature Review based on the stages of identification, screening, eligibility, and inclusion so that 14 main articles are selected for review with strong actual relevance. The study results provide insights and references that can be used to further explore key factors in evaluating the success of EA implementation in the future. It was found that there were ten factors that most influenced the evaluation of the success of EA implementation and it was concluded that two potential factors were the most influential and required further exploration in evaluating the success of EA implementation which could be applied in various sectors/dimensions. This study contributes as an initial reference for overcoming problems in investigating and exploring the factors that influence the success of EA implementation as an effort to assess the success of achieving future organizational goals. © 2024 IEEE.

关键词： Enterprise Architecture Parameters Success Factors Systematic Literature Review

来源：评论

学校读者我要写书评

暂无评论

Enhancing Quantum NLP Robustness - Analysis on Noisy Models for Quantum Sentiment Classification 11

Enhancing Quantum NLP Robustness - Analysis on Noisy Models ...

引用

11th International Conference on Advanced informatics: Concept, Theory and Application, ICAICTA 2024

作者： Ruskanda, Fariska Zakhralativa Halim, Michael Jonathan Kurniawan, Farizki Syafalni, Infall Mulyawan, Rahmat Higo, Akio School of Electrical Engineering and Informatics Bandung Institute of Technology Indonesia Bandung Institute of Technology Artificial Intelligence Center Bandung Indonesia University Center of Excellence on Microelectronics Bandung Institute of Technology Indonesia School of Engineering The University of Tokyo Systems Design Lab Tokyo Japan

ISBN: (纸本)9798331520311

This research aims to improve the robustness of Quantum Natural Language Processing (QNLP) models in the presence of noise. Using Lambeq, an open-source library for quantum NLP, we focus on sentiment classification tasks to evaluate the impact of noisy quantum models. Our study involves the application of three types of optimizers: Simultaneous Perturbation Stochastic Approximation (SPSA), Nelder-Mead, and Adam. The performance and resilience of these optimizers are assessed under various noise conditions to determine their effectiveness in maintaining model accuracy and stability. The research shows that the Adam optimizer outperforms SPSA and NelderMead in QNLP simple sentiment analysis tasks, both in noiseless and noisy environments. Adam achieved 96.67 % accuracy in noiseless conditions, significantly higher than SPSA's 83.33 % and Nelder-Mead's 53.33%, highlighting its superior performance in optimizing quantum circuits. Moreover, in noisy simulation, Adam outperforms others with 70.00% accuracy performance. The work is useful for NLP implementations in quantum computers. This research is essential because the noisy nature of current quan-tum computers makes it difficult for QNLP models to perform accurately and reliably. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Detection of Students in Need of Immediate Care in Programming Classes using Machine-Learning Techniques 12

Detection of Students in Need of Immediate Care in Programmi...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Ohara, Tadashi Hashiyama, Tomonori Umezu, Nobuyuki The University of Electro-Communications Graduate School of Informatics and Engineering Dept. of Informatics 1-5-1 Chofugaoka Tokyo Chofu182-8585 Japan Ibaraki University Graduete School of Science and Engineering Dept. of Mechanical Systems Engineering 4-12-1 Nakanarusawa Hitachi Ibaraki316-0033 Japan

ISBN: (纸本)9798350340181

In this study, we propose a novel method for detecting students who need immediate care by the supervisors in a programming class using machine-learning techniques. The system estimates the students' need for help based on their PC operations including active applications while studying. We implemented a stand-alone application to record the situation. We conducted experiments to investigate the relationship between PC input and the need for help. We found a negative correlation between the number of keystrokes and the need for help, and a positive correlation between the need for help and PDF viewer browsing. The correlation between the supervisor's decisions and the estimate by DNN was 0.42 (p=0.00), suggesting the possibility of detecting students who need immediate help using a machine-learning approach. Our future work includes to collect meta information and to construct a model to estimate the need for help and evaluate its accuracy in real-time. © 2023 IEEE.

关键词： Deep neural networks

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：