检索结果-内蒙古大学图书馆

20th International Conference on Data science, ICDATA 2024, held as part of the World Congress in computer science, computer engineering and Applied Computing, CSCE 2024

作者： Uddin, J. M. Imtinan Hall, Hayden Long, Jessica Kimbrell, Connor Obrien, Isabel Mendiratta, Sudave Koo, Patrick Wang, Yingfeng Qin, Hong Department of Computer Science and Engineering The University of Tennessee at Chattanooga Chattanooga United States The University of Tennessee Health Science Center Chattanooga United States Erlanger Health System Chattanooga United States Department of Computer Science Old Dominion University Norfolk United States

ISBN: (纸本)9783031858550

Preexisting comorbidities like COPD and smoking history increase SARS-CoV-2 risk, but the impact of homelessness and mental health remains underexplored. This study investigates the correlation between homelessness and COVID-19 hospitalizations in patients with COPD, mental illness, smoking habit, and age using national EHR data from All of Us, including 129,524 patients, 3,547 of whom were homeless. A statistical examination using logistic regression confirmed that homelessness increases hospitalization odds, with 19.83% of homeless COVID-19 patients hospitalized, compared to 15.08% in the general population. SHAP plots, an explainable AI method highlighted significant interactions between homelessness, COPD, smoking, gender, and mental disorders on COVID-19 hospitalizations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

The Side-Channel Vulnerability in Network Protocol 11

The Side-Channel Vulnerability in Network Protocol

引用

11th International Conference on Communication and Network Security, ICCNS 2021

作者： Ru, Kaiqi Zheng, Yaning Feng, Xuewei Wang, Dongxia National Key Laboratory of Science and Technology on Information System Security Institute of System Engineering AMS PLA China Department of Computer Science and Technology Tsinghua University China National Key Laboratory of Science and Technology on Information System Security China

ISBN: (纸本)9781450386425

Some recent studies have found that there are some side-channel vulnerabilities in the operating system. Attackers would exploit the side-channel vulnerability for malicious purpose, such as hijack connections, denial of service attacks, etc. Currently, most attacks are detected manually. In this paper, we found that the reason for the existence of network protocol side-channel vulnerability is the use of shared resources. Since the state of shared resource affects all connections, when a connection uses a shared resource, information about that connection can be inferred by observing the usage of the shared resource. In order to find the shared resources, we implemented a tool called TASR which is a method of static analysis. The first is to find out what shared resources are available by the definition of shared resources in static analysis. Then, the data packet is used as the taint source to search the tainted shared resources. The second step is to analyze the taint-transmission-path according to the acquired tainted shared variable. Then it can find the side-channel vulnerability. By using this method on TCP, UDP and ICMP protocols, we find the following four shared variables: challenge_count, tcp_memory_allocated, tcp_memory_pressure, sysctl_icmp_msg_per_sec. It is difficult for tcp_memory allocated and tcp_memory pressure to exploit, because they will go through multiple strict checks. Using challenge_count can hijack the connection and inject malicious packets. Using sysctl_icmp_msg_per_sec can assist in DNS cache poisoning attack. © 2021 ACM.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Using Lock-Free Design for Throughput-Optimized Cache Eviction 25

Using Lock-Free Design for Throughput-Optimized Cache Evicti...

引用

Abstracts of the 2025 ACM SIGMETRICS International Conference on Measurement and Modeling of computer systems

作者： Chao Dong Fang Wang Hong Jiang Dan Feng Key Laboratory of Information Storage System (Wuhan National Laboratory for Optoelectronics) Engineering Research Center of data storage systems and Technology (School of Computer Science and Technology) Ministry of Education of China Huazhong University of Science and Techonolgy Wuhan Hubei China Department of Computer Science and Engineering University of Texas at Arlington Arlington Texas USA

ISBN: (纸本)9798400715938

This paper presents a practical approach to cache eviction algorithm design, called Mobius, that optimizes the concurrent throughput of caches and reduces cache operation latency by utilizing lock-free data structures, while maintaining high cache hit ratios. Mobius includes two key designs. First, Mobius employs two lock-free FIFO queues to manage cache items, ensuring that all cache operations are executed efficiently in concurrency. Second, Mobius integrates a consecutive detection mechanism that merges multiple modifications during eviction into a single operation, thereby reducing data races. The implementation of Mobius in CacheLib and RocksDB highlights its high concurrency in both synthetic and real-world workloads.

关键词： cache eviction policy

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Model for Foreign Exchange Prediction 2nd

A Machine Learning Model for Foreign Exchange Prediction

引用

2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： San, Tan Jun Ajibade, Samuel-Soma M. Ajibade, Temiloluwa Iyanuoluwa Jasser, Muhammed Basheer Ayodele, Olamide Emmanuel Oyewopo, Abdulgafar Olorunleke Adediran, Anthonia Oluwatosin Majeed, Anwar P. P. Abdul Luo, Yang Department of Data Science and Artificial Intelligence Faculty of Engineering and Technology Sunway University Selangor Petaling Jaya Malaysia Department of Computer Engineering Istanbul Ticaret University Istanbul Turkey Department of Business Management Scholar School System Birmingham United Kingdom School of Engineering and Technology Sunway University Selangor Darul Ehsan Petaling Jaya47500 Malaysia Department of Banking and Finance Ekiti State University Ekiti State Ado Ekiti Nigeria Department of Business Administration Kwara State University Malete Nigeria Department of Real Estate Faculty of Built Environment Universiti Malaya Kuala Lumpur Malaysia Suzhou Taicang215400 China

ISBN: (纸本)9789819639489

The rise of deep learning algorithms has sparked interest in the financial domain. The foreign exchange market (FOREX) is the globally leading financial market with millions of active stakeholders. Research in deep learning for forecasting price movements has shown its efficacy in financial markets. Notably, LSTM have empirically proven the best performance among other machine learning techniques. However, studies have shown the lack of deep learning hybrid comparisons to fortify empirical claims, especially in the FX market characterized for its high volatility and variance among currency pairs. This study develops a generalized LSTM model to forecast the major pairs and conducts a comparative analysis with a secondary hybrid deep learning model to assess and solidify the robustness of deep learning methods in forex forecasting. The empirical scenario simulates a classification problem employing cross-validation techniques to optimize the models’ generalization rigorously. Evaluation of the model utilized the accuracy, precision, recall, and f1-score metrics. Results indicated the performance of the models from best to worst were LSTM, SRNN and followed by CNN indicating the importance of testing deep learning approaches in different empirical setups. Conclusively, this study highlights the need challenges in forex forecasting and raises the need for more robust assessments on machine learning models forecasting capabilities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of Transformer-based language models for Nucleotide Sequence Analysis

arXiv

引用

arXiv 2024年

作者： Ghosh, Nimisha Santoni, Daniele Saha, Indrajit Felici, Giovanni Odisha Bhubaneswar India Institute for System Analysis and Computer Science "Antonio Ruberti" National Research Council of Italy Rome Italy Department of Computer Science and Engineering National Institute of Technical Teachers’ Training and Research West Bengal Kolkata India

In recent times, Transformer-based language models are making quite an impact in the field of natural language processing. As relevant parallels can be drawn between biological sequences and natural languages, the models used in NLP can be easily extended and adapted for various applications in bioinformatics. In this regard, this paper introduces the major developments of Transformer-based models in the recent past in the context of nucleotide sequences. We have reviewed and analysed a large number of application-based papers on this subject, giving evidence of the main characterizing features and to different approaches that may be adopted to customize such powerful computational machines. We have also provided a structured description of the functioning of Transformers, that may enable even first time users to grab the essence of such complex architectures. We believe this review will help the scientific community in understanding the various applications of Transformer-based language models to nucleotide sequences. This work will motivate the readers to build on these methodologies to tackle also various other problems in the field of bioinformatics. © 2024, CC BY.

关键词： Nucleotides

来源：评论

学校读者我要写书评

暂无评论

Multiple-replica integrity auditing schemes for cloud data storage

Multiple-replica integrity auditing schemes for cloud data s...

引用

作者： Lin, Yangfei Li, Jie Jia, Xiaohua Ren, Kui Graduate School of System and Information Engineering University of Tsukuba Ibaraki Japan Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai China Department of Computer Science City University of Hong Kong Hong Kong Department of Computer Science and Engineering State University of New York at Buffalo New YorkNY United States

Cloud computing has been an essential technology for providing on-demand computing resources as a service on the Internet. Not only enterprises but also individuals can outsource their data to the cloud without worrying about purchase and maintenance cost. The cloud storage system, however, is not fully trustable. Cloud data integrity auditing is crucial for defending against the security threats of data in the untrusted multicloud environment. Storing multiple replicas is a commonly used strategy for the availability and reliability of critical data. In this paper, we summarize and analyze the state-of-the-art multiple-replica integrity auditing schemes in cloud data storage. We present the system model and security threats of outsourcing data to the cloud with classification of ongoing developments. We also summarize the existing data integrity auditing schemes for multicloud data storage. The important open issues and potential research directions are addressed. © 2019 John Wiley & Sons, Ltd.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

IoT based Smart Cradle for Neonatal Monitoring 6

IoT based Smart Cradle for Neonatal Monitoring

引用

6th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2022

作者： Sonia, R. Jayadeva, Sujay Mugaloremutt Ragavendiran, S.D. Prabu Revathi, N. Arumugam, Jeevanantham Kumar, S Sandeep B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Tamil Nadu Vandalur600048 India Jss Academy of Higher Education and Research Department of Health System Management Studies Karnataka Mysuru570004 India Rvs Technical Campus Department of Computer Science and Engineering Tamil Nadu Coimbatore641402 India Panimalar Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai600123 India Kongu Engineering College Department of Information Technology Tamil Nadu Perundurai638060 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram522502 India

ISBN: (纸本)9781665482714

India has the highest percentage of working women and mothers. It also has a record for the highest number of babies being born every single day. These two statements highly contradict each other. When a woman gives birth to a baby, she needs to spend almost a year or two taking care of the necessities of the baby. But when a need to leave the baby for a certain time arises regularly, it becomes tougher for them to do so. This study provides a solution to this problem. This research aims at the construction of a smart cradle. This cradle is des igned using various input elements, output elements, a controller module, and a mobile application. The input elements consist of a temperature sensor, a sound sensor or a microphone,a moisture sensor, and a music player. The output elements include the motor and The controller used in this study is the NodeMCU module. Cloud storage is also used and it is provided by the Arduino loT software. The sensors in the smart cradle begin recording relevant parameters such as temperature, humidity, and sound as soon as it is turned on. The information is then uploaded to the cloud The data is then processed in the cloud for analysis. If indeed the child's temperatures is over the safe range, the user receives a warning. Moisture levels above normal suggest that the infant has urinated The sound of the baby crying will be recorded in the microphone. The output elements are energized as a result of the sensor's data. If the baby has a high fever or has to go to the bathroom, the app will notify the parent. © 2022 IEEE.

关键词： Microphones

来源：评论

学校读者我要写书评

暂无评论

FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection

FedMoS: Taming Client Drift in Federated Learning with Doubl...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Xiong Wang Yuxin Chen Yuqing Li Xiaofei Liao Hai Jin Bo Li National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients’ selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal ${{\mathcal{O}}}\left({{T^{ - 2/3}}}\right)$ convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PIR: Remote Sensing Image-Text Retrieval with Prior Instruction Representation Learning

arXiv

引用

arXiv 2024年

作者： Pan, Jiancheng Ma, Muyuan Ma, Qing Bai, Cong Chen, Shengyong The Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System Science Tsinghua University Beijing10084 China The College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China The College of Science Zhejiang University of Technology Hangzhou310023 China The School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

Remote sensing image-text retrieval constitutes a foundational aspect of remote sensing interpretation tasks, facilitating the alignment of vision and language representations. This paper introduces a prior instruction representation (PIR) learning paradigm that draws on prior knowledge to instruct adaptive learning of vision and text representations. Based on PIR, a domain-adapted remote sensing image-text retrieval framework PIR-ITR is designed to address semantic noise issues in vision-language understanding tasks. However, with massive additional data for pre-training the vision-language foundation model, remote sensing image-text retrieval is further developed into an open-domain retrieval task. Continuing with the above, we propose PIR-CLIP, a domain-specific CLIP-based framework for remote sensing image-text retrieval, to address semantic noise in remote sensing vision-language representations and further improve open-domain retrieval performance. In vision representation, we utilize the prior-guided knowledge of the remote sensing scene recognition by building a belief matrix to select key features for reducing the impact of semantic noise. In text representation, we use the previous time step to cyclically activate the current time step to enhance text representation capability. A cluster-wise Affiliation Loss (AL) is proposed to constrain the inter-classes and to reduce the semantic confusion zones in the common subspace. Comprehensive experiments demonstrate that PIR could enhance vision and text representations and outperform the state-of-the-art methods of closed-domain and open-domain retrieval on two benchmark datasets, RSICD and RSITMD. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Research on Image Captioning Based on Vision-language Pre-trained Models

Research on Image Captioning Based on Vision-language Pre-tr...

引用

International Conference on Big Data and Information Analytics (BigDIA)

作者： Shiwei Zou Yuxiang Xie Jie Yan Yingmei Wei Xidao Luan Department of System Engineering National University of Defense Technology Hunan China Key Laboratory of Big Data Department of System Engineering National University of Defense Technology Hunan Changsha China Department of Computer Science Changsha University Hunan China

Image captioning is a vision-language task that targets at describing an image by generating a coherent sentence automatically. This technology allows computers to understand and describe images like humans, enabling further processing of images. It combines computer vision and natural language processing, which has broad applications. This paper investigates the use of vision-language pre-trained models for image captioning. In this article, an encoder-decoder hybrid model based on PVT and BERT is pre-trained on a large number of image-text pairs, possessing both understanding and generation capabilities. It consists of three components: 1) an image encoder and a text encoder to extract image and text features respectively; 2) a multi-modal encoder to align the two modalities; and 3) a text decoder to generate text descriptions. This paper focuses on enhancing the image encoder of the model, which is crucial for image captioning models as it extracts high-resolution image features. Reducing training time and computational costs can also improve the applicability of pre-trained models. Improvements are made to the original model by modifying the ViT model architecture of the image encoding module. A feature pyramid structure and a spatial reduction attention mechanism is introduced to extract high-resolution image features while reducing computational complexity and memory usage, thereby enhancing the universality of the model. The model adopts a pure Transformer architecture, discarding the convolutional structure, and achieves excellent performance.

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：