检索结果-内蒙古大学图书馆

International Conference on e-health Networking, applications and Services (HealthCom)

作者： Boyuan Peng Yiyang Liu Xin Zhu Jie Huang Wenwen Wang Li Fang Qin Zhou Graduate Department of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Fukushima Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Chiyodaku Tokyo Japan Graduate Department of Computer Science and Engineering Division of Information Systems The University of Aizu Aizu-Wakamatsu Fukushima Japan Department of Obstetrics and Gynecology Tongji Hospital Huazhong University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350350548

ISBN: (纸本)9798350350555

Semi-supervised learning (SSL) is a promising solution for the problem of insufficient medical labeled data. However, it is still a challenging task to segment transvaginal ultrasound (TVUS) images because of their poor contrast and speckle noise. In this study, we propose Multi-StudentNet, a semi-supervised deep-learning framework for endometrial segmentation in TVUS images. This method employs multiple student models to effectively integrate labeled and unlabeled data, improving the reliability and performance of segmentation while significantly reducing the need for extensive manual labeling. By leveraging the weights of multiple models, our framework facilitates feature sharing, which enhances model robustness. Specifically, Multi-StudentNet achieves a Dice coefficient (DSC) of 0.81 and a specificity of 0.99. Our multi-student models consistently outperform single-student models across various conditions, including normal, polyp, and cancer cases. Extensive experiments demonstrate that Multi-StudentNet achieves state-of-the-art performance in both accuracy and robustness.

关键词： Image segmentation Ultrasonic imaging Accuracy Manuals Speckle Semisupervised learning Robustness data models Optimization Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

MassSpecGym: A benchmark for the discovery and identification of molecules 38

MassSpecGym: A benchmark for the discovery and identificatio...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Bushuiev, Roman Bushuiev, Anton de Jonge, Niek F. Young, Adamo Kretschmer, Fleming Samusevich, Raman Heirman, Janne Wang, Fei Zhang, Luke Dührkop, Kai Ludwig, Marcus Haupt, Nils A. Kalia, Apurva Brungs, Corinna Schmid, Robin Greiner, Russell Wang, Bo Wishart, David S. Liu, Li-Ping Rousu, Juho Bittremieux, Wout Rost, Hannes Mak, Tytus D. Hassoun, Soha Huber, Florian van der Hooft, Justin J.J. Stravs, Michael A. Böcker, Sebastian Sivic, Josef Pluskal, Tomáš Institute of Organic Chemistry and Biochemistry The Czech Academy of Sciences Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Republic Bioinformatics Group Wageningen University & Research Netherlands Department of Computer Science University of Toronto Canada Bioinformatics Institute for Computer Science Friedrich Schiller University Jena Germany Department of Computer Science University of Antwerp Belgium Department of computing science University of Alberta Canada Alberta Machine Intelligence Institute Canada Department of Molecular Genetics University of Toronto Canada Bright Giant GmbH Department of Computer Science Tufts University United States Department of Biological Sciences University of Alberta Canada Department of Computer Science Aalto University Finland Mass Spectrometry Data Center National Institute of Standards and Technology United States Department of Chemical and Biological Engineering Tufts University United States Centre for Digitalisation and Digitality University of Applied Sciences Düsseldorf Germany Department of Biochemistry University of Johannesburg South Africa Eawag Swiss Federal Institute of Aquatic Science and Technology Switzerland

The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym - the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at https://***/pluskal-lab/MassSpecGym. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FRSM: A Novel Fault-Tolerant Approach for Redundant-Path-Enabled Service Migration in Mobile Edge Computing 1

引用

29th International Conference on Web Services, ICWS 2022 Held as Part of the Services Conference Federation, SCF 2022

作者： Zhao, Jiale Dai, Mengxuan Xia, Yunni Ma, Yong He, Meibin Peng, Kai Li, Jianqi Li, Fan Fu, Xiaodong School of Computer Chongqing University Chongqing400030 China School of Computer and Information Engineering Jiangxi Normal University Nanchang330022 China Department of Big Data and AI of Jiangxi Telecom Nanchang330029 China Engineering College Huaqiao University Quanzhou362021 China Global Energy Interconnection Research Institute Co. Ltd. Beijing102209 China Key Laboratory of Fundamental Synthetic Vision Graphics and Image Science for National Defense Sichuan University Chengdu610065 China Data Science Research Center Faculty of Science Kunming University of Science and Technology Kunming650031 China

ISBN: (数字)9783031235795

ISBN: (纸本)9783031235788

Mobile Edge Computing (MEC) provides users with low-latency, highly responsive services by deploying Edge Servers (ESs) near applications. MEC allows any edge-hosted application or service to be migrated between different edge resource providers without being locked into a single provider. Nevertheless, due to its complexity and dynamics, the real edge computing environment is prone to errors and failures, reducing the reliability of edge service migration. This paper proposes a novel fault-tolerant method for redundant path service migration. The method utilizes sliding-window-based model and identifies a set of service migration paths, enabling the evaluation of the time-varying failure rate of ESs. The method combines resubmission and replication mechanisms and decides the edge service migration scheme by selecting multiple redundant migration paths. We also conduct extensive simulations and show that our proposed method outperforms traditional solutions in several metrics. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

QUALYST: data Quality Assessment System for Thailand Open Government data

QUALYST: Data Quality Assessment System for Thailand Open Go...

引用

International Joint Conference on computer science and Software engineering (JCSSE)

作者： Tanapat Samakit Chutiporn Anutariya Marut Buranarach ICT Department Computer Science & Information Management School of Engineering and Technology Asian Institute of Technology Thailand Data Science and Analytics Research Group National Electronics and Computer Technology Center Thailand

Open Government data (OGD) refers to the provision of data produced by the government to the general public, in a format that is readily readable and can be used by machines with ease. It can also promote transparency, improve decision-making, enhance accountability, create economic opportunities, and encourage civic engagement. The OGD can help citizens understand the government and its legitimacy and transparency. Thus, when the government shares its data with people, it helps to create trust by being transparent, accountable, and promoting innovative solutions that benefit everyone. However, each published dataset has no indication of its quality assessment at all; thus, making it difficult for citizens to assess the reliability of the data from the OGD. Therefore, a data quality assessment for OGD should be developed. This will help create effective datasets which in turn help users understand the data. This study proposes QUALYST, a system that assesses Thailand's OGD dataset and validates it for analytic and visualization purposes. The study focuses on designing the data storage and implementing the assessment system. Furthermore, the proposed data quality dimensions, the developed data pipeline, and the assessment process are elaborated. Finally, the prototype system is demonstrated using Thailand's OGD datasets with examples in a visualized format.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Functional Network Connectivity in White Matter: A Group Informed ICA-Based Network Approach 22

Functional Network Connectivity in White Matter: A Group Inf...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Itkyal, Vaibhavi S. Iraji, Armin Fu, Zening Calhoun, Vince D. Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology Emory University GA United States Department of Electrical and Computer Engineering Georgia Institute of Technology GA United States Tri-institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University Georgia Institute of Technology Emory University GA United States Department of Neuroscience Emory University GA United States Georgia State University Department of Computer Science Atlanta GA United States

ISBN: (纸本)9798331520526

White matter (WM) has traditionally been undervalued in functional brain connectivity studies due to its weaker blood-oxygenation-level-dependent (BOLD) signals compared to gray matter (GM). Conventional atlas-based approaches often overlook the individualized aspects of functional networks, limiting their applicability for WM. In this study, we introduce the first WM intrinsic connectivity network (ICN) templates derived from a large dataset of over 100,000 scans, demonstrating the feasibility of estimating individualized WM networks using multivariate-spatially constrained ICA (scICA). By combining WM and GM ICNs, our work provides an expanded framework for evaluating functional network connectivity (FNC) across both tissue types, offering new insights into the integrative role of WM in functional connectivity. This approach holds particular promise for enhancing the understanding of connectivity alterations in clinical populations, such as individuals with schizophrenia. © 2025 IEEE.

关键词： independent component analysis schizophrenia White matter

来源：评论

学校读者我要写书评

暂无评论

(Benefits of Internet of Things (IoT) applications in Health care - An Overview)

(Benefits of Internet of Things (IoT) Applications in Health...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Preeti Chaudhary Satya Prakash Yadav Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Mersin Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Nicosia Mersin Turkey Research Center for AI and IoT Faculty ofEngineering University of Kyrenia Kyrenia Mersin Turkey Computer Science and Engineering Graphic Era Hill University Dehradun Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management (GLBITM) Greater Noida India

In a nutshell, the IoT refers to the idea of integrating high-tech technology in the form of "smart" gadgets and sensors into a single setting to gather data. There are still numerous areas in which machines cannot compete favorably with people, but data collection and analysis are undeniably two of their strongest points. The Internet of Things makes it possible to fully or partially automation data, it involves related activities, which is obviously very important for the healthcare industry. What exactly is the Internet connected medical things, and how exactly might it make a significant impact on the sector? By having to apply the concept of the internet of things (IoT) to the field of medicine, several significant advancements have become possible, including the ability to automatically control the thermostat of containers while transmitting inoculations and antibiotics, the accurate tracking of the ailments of a lot of illnesses without a need for additional meetings with a general practitioner, the correct and most useful use of meds, and a great deal more. All of this is realizable because of the capability of MedTech gadgets to carry out continuous monitoring system. The potential applications of internet of things technology in healthcare are very interesting. Let’s review the ways in which this technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Big data: A Comprehensive Analysis and Future Directions

Unleashing the Power of Big Data: A Comprehensive Analysis a...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Annu Sharma Gaurav Kumar Mansoor Farooq Manish Kumar Gupta Saranya Raj Ashok Kumar Rai Department of Computer Science & Application RajaRajeshwari College of Engineering Bengaluru Karnataka India Department of Computer Science & Engineering Indian Institute of Science Education and Research Bhopal Bhopal Madhya Pradesh India Department of Management Studies University of Kashmir Jammu & Kashmir India Department of Information Technology & Computer Application Madan Mohan Malaviya University of Technology Gorakhpure UP India Department of Data Science & Engineering Dronacharya Group of Institutions Greater Noida Uttar Pradesh India Department of Computer Science & Engineering Madan Mohan Malaviya University of Technology Gorakhpure UP India

Big data (BD) has emerged as a transformative force, offering unprecedented opportunities for organizations to extract valuable insights and drive informed decision-making. This research paper presents a comprehensive analysis of the current state of BD, explores its potential applications across industries, and outlines future directions for maximizing its benefits. This paper examines the key components of BD, including data collection, storage, processing, and analytics. It investigates the technologies and methodologies that enable efficient handling of large volumes of structured and unstructured data. Additionally, it explores the impact of cloud computing, artificial intelligence (ai), and the Internet of Things (IoT) on the growth and utilization of BD. Overall, this research paper provides a comprehensive analysis of BD, its current applications, challenges, and future directions. It serves as a valuable resource for researchers, practitioners, and policymakers seeking to unlock the full power of BD and harness its benefits across diverse domains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SirLLM: Streaming Infinite Retentive LLM

arXiv

引用

arXiv 2024年

作者： Yao, Yao Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China

As Large Language Models (LLMs) become increasingly prevalent in various domains, their ability to process inputs of any length and maintain a degree of memory becomes essential. However, the one-off input of overly long texts is limited, as studies have shown that when input lengths exceed the LLMs' pre-trained text length, there is a dramatic decline in text generation capabilities. Moreover, simply extending the length of pre-training texts is impractical due to the difficulty in obtaining long text data and the substantial memory consumption costs this would entail for LLMs. Recent efforts have employed streaming inputs to alleviate the pressure of excessively long text inputs, but this approach can significantly impair the model's long-term memory capabilities. Motivated by this challenge, we introduce Streaming Infinite Retentive LLM (SirLLM), which allows LLMs to maintain longer memory during infinite-length dialogues without the need for fine-tuning. SirLLM utilizes the Token Entropy metric and a memory decay mechanism to filter key phrases, endowing LLMs with both long-lasting and flexible memory. We designed three distinct tasks and constructed three datasets to measure the effectiveness of SirLLM from various angles: (1) DailyDialog;(2) Grocery Shopping;(3) Rock-Paper-Scissors. Our experimental results robustly demonstrate that SirLLM can achieve stable and significant improvements across different LLMs and tasks, compellingly proving its effectiveness. When having a coversation, "A sir could forget himself," but SirLLM never does! Our code is publicly available at https://***/Zoeyyao27/SirLLM. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ML_Recognition: A Robust Model for Handwritten Digit Recognition Using Machine Learning Classifiers 3

ML_Recognition: A Robust Model for Handwritten Digit Recogni...

引用

3rd International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2023

作者： Abdelminaam, Diaa Salama Madbouly, Magda M. Zeid, Magdy Abd-Elghany Abualigah, Laith Misr International University Faculty of Computer Science Cairo Egypt Benha University Faculty of Computers and Artificial Intelligence Benha Egypt Alexandria University Faculty of Computer and Data Science Alexandria Egypt Alobour High Institute for Computer and Informatics Ibrahim Abd Elatif Gomaa Computer Science Department Cairo Egypt Lebanese American University Department of Electrical and Computer Engineering Byblos13-5053 Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Middle East University Meu Research Unit Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia

ISBN: (纸本)9798350306231

Handwritten digit recognition is a branch of machine learning in which a computer is taught to recognize hand-written numbers. Classification and regression are applied using deep learning and machine learning algorithms. In this paper, we discussed the efficiency of different algorithms: Random Forest, KNN, Naive Bayes, SVM, CNN, and Decision Tree Algorithm. Those algorithms were applied in the handwritten digit recognition process using the MINIST data set. By comparing each algorithm by training every one of them on the data set, then by testing, we got the best algorithm to get the optimal results with the highest accuracy. After comparing the results of each algorithm, it has shown that the neural network has the best results with 97.3% classification accuracy followed by K- the nearest neighbor with 97.2%. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

SELF-ATTENTION RECURRENT SUMMARIZATION NETWORK WITH REINFORCEMENT LEARNING FOR VIDEO SUMMARIZATION TASK

SELF-ATTENTION RECURRENT SUMMARIZATION NETWORK WITH REINFORC...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Phaphuangwittayakul, Aniwat Guo, Yi Ying, Fangli Xu, Wentian Zheng, Zheng Department of Computer Science and Engineering East China University of Science and Technology China National Engineering Laboratory for Big Data Distribution and Exchange Technologies China Shanghai Engineering Research Center of Big Data and Internet Audience China

ISBN: (纸本)9781665438643

With the exponential growth of video data, video summarization techniques are urgently needed for reducing people's efforts in the videos' content exploration by generating succinct but informative summaries from original lengthy videos. Though supervised video summarization approaches have demonstrated the state-of-the-art performance, unsupervised methods are still highly demanded due to resourcefully expensive human annotations and the subjectiveness of video summarization tasks. In this paper, a novel unsupervised-based Deep Self-attention Recurrent summarization network with Reinforcement Learning (DSR-RL) for video summarization is proposed. The model can learn the input video sequence and suggest the key-shot summary without additional human annotations by integrating self-attention, BRNN, and reinforcement learning mechanisms. The DSR-RL improves not only importance score through the attention map vector of self-attention network but also the diversity of summaries via the reward function of reinforcement learning. Our method outperforms the state-of-the-art unsupervised video summarization methods on both SumMe and TVSum datasets. The source code is available at https://***/phaphuang/DSR-RL. © 2021 IEEE

关键词： Reinforcement learning

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：