检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Jiaxin Zhang, Lingling Liu, Jun Guo, Tianlin Wu, Wenjun The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China The Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an710049 China

We introduce a novel task, called Generalized Relation Discovery (GRD), for open-world relation extraction. GRD aims to identify unlabeled instances in existing pre-defined relations or discover novel relations by assigning instances to clusters as well as providing specific meanings for these clusters. The key challenges of GRD are how to mitigate the serious model biases caused by labeled pre-defined relations to learn effective relational representations and how to determine the specific semantics of novel relations during classifying or clustering unlabeled instances. We then propose a novel framework, SFGRD, for this task to solve the above issues by learning from semi-factuals in two stages. The first stage is semi-factual generation implemented by a tri-view debiased relation representation module, in which we take each original sentence as the main view and design two debiased views to generate semi-factual examples for this sentence. The second stage is semi-factual thinking executed by a dual-space tri-view collaborative relation learning module, where we design a cluster-semantic space and a class-index space to learn relational semantics and relation label indices, respectively. In addition, we devise alignment and selection strategies to integrate two spaces and establish a self-supervised learning loop for unlabeled data by doing semi-factual thinking across three views. Extensive experimental results show that SFGRD surpasses state-of-the-art models in terms of accuracy by 2.36% ∼5.78% and cosine similarity by 32.19%∼ 84.45% for relation label index and relation semantic quality, respectively. To the best of our knowledge, we are the first to exploit the efficacy of semi-factuals in relation extraction. Copyright © 2024, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Optimization of Performance Models for Interlayer Meltblown Nonwovens with Random Forest

Optimization of Performance Models for Interlayer Meltblown ...

引用

Health big data and Intelligent Healthcare (ICHIH), International Conference on

作者： PengJie Wang Ya Li YuHeng Liang Xiaolin Zhu TongFei Li Wei Lv Zhuhai College of Science and Technology Alibaba Cloud College of Big Data Application Zhuhai China Information Technology Application Innovation Platform Department YGSOFT INC. Zhuhai China

In the context of rapid societal and technological advancements, there has been a pronounced elevation in public health awareness. Among various protective measures, meltblown nonwoven materials have emerged as an indispensable component in protective masks, offering a crucial respiratory barrier for users. This study endeavors to provide an in-depth examination of this pivotal material. By systematically analyzing extensive datasets of meltblown fabric manufacturing processes and taking into account key parameters such as receiving distance, air velocity, and material thickness, this paper, grounded on historical production parameters, harnesses advanced machine learning techniques to meticulously design and optimize the performance control model for interlayer melt-blown nonwoven materials. The central aim of this research is to further enhance the efficacy of this material in health protection applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Personalized Care for Multiple Sclerosis with IoT Wearables and Deep Learning

Personalized Care for Multiple Sclerosis with IoT Wearables ...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Vetriselvi, D. Sampathrajan, Rajeshkumar Deepa, A. Sujatha, V. Deepa, P. Pandi Murugan, S. Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai India McKinsey & Company Fort WorthTX United States Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Department of Electronics and Communication Engineering Shree Sathyam College of Engineering and Technology Tamil Nadu Salem India Department of Artificial Intelligence and Data Science Agni College of Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350374933

This research work presents a new method for improving individualized treatment for patients with Multiple Sclerosis (MS) by combining Internet of Things (IoT) wearables with deep learning (DL) methods, namely Long Short-Term Memory (LSTM) networks. MS is a long-term autoimmune disorder that affects the central nervous system. It is marked by unexpected episodes of worsening symptoms and periods of improvement, highlighting the need for tailored therapy. The widespread use of IoT devices presents unique possibilities for the ongoing monitoring of many physiological and activity measurements important to the development and symptoms of MS. Using LSTM networks, which are very proficient in analyzing temporal sequences, create a prediction model that may anticipate exacerbations of MS symptoms and customize therapies appropriately. Through the analysis of longitudinal data obtained from IoT devices, our model acquires knowledge about unique patterns of illness development and treatment response. This knowledge allows us to create customized care plans for individuals. These paths include proactive activities such as adjusting medication, making lifestyle changes, and seeking early medical advice. The goal is to reduce the worsening of symptoms, improve the quality of life, and optimize treatment results for individuals with MS. The proposed method shows potential for transforming the treatment of MS by offering proactive and patient-centered therapy adaptable to individual requirements and the dynamics of the illness. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enhanced Machine Learning Models for Predictive Maintenance in Industrial IoT 2

Cloud-Enhanced Machine Learning Models for Predictive Mainte...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Usharani, R. Sivagami, V.M. Saravanan, K. Pushparani, S. Rekha, K. Sashi Department of Computational Intelligence School of Computing Faculty of Engineering and Technology Srm Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Information Technology Sri Venkateswara College of Engineering Sriperumbudur Tamil Nadu Chennai India Department of Artificial Intelligence and Data Science Care College of Engineering Tamil Nadu Trichy India Department of Computer Science and Engineering Meenakshi College of Engineering Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India

ISBN: (纸本)9798350384277

This study examines the implementation and impact of Cloud-Enhanced Machine Learning Models in the realm of Predictive Maintenance within Industrial Internet of Things (IIoT) settings. Emphasizing the integration of cloud computing with machine learning, the research focuses on how this synergy improves the accuracy and efficiency of maintenance predictions in industrial environments. Key metrics evaluated include prediction accuracy, operational efficiency, cost savings, and reduction in equipment downtime. The study demonstrates a significant increase in prediction accuracy, from 65% to 88%, attributed to the advanced data processing and analytical capabilities of cloud-enhanced machine learning. Operational efficiency saw marked improvements, with a 50% reduction in response times and a 25% increase in maintenance scheduling efficiency, leading to a 20% rise in asset utilization rates. Financially, the implementation led to a 37% reduction in annual maintenance costs and a 40% decrease in both the cost per downtime incident and long-term repair expenses. Most notably, the study recorded a 62.5% reduction in both the duration and frequency of downtime incidents. These results highlight the transformative potential of integrating cloud computing and machine learning in IIoT for predictive maintenance, showcasing significant advancements in predictive accuracy, operational efficiency, cost-effectiveness, and overall reduction in downtime. The study underscores the critical role of technological innovation in advancing industrial maintenance strategies, leading to more proactive, efficient, and economically viable operations. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Bayesian Over-the-Air FedAvg via Channel Driven Stochastic Gradient Langevin Dynamics

Bayesian Over-the-Air FedAvg via Channel Driven Stochastic G...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Boning Zhang Dongzhu Liu Osvaldo Simeone Guangxu Zhu School of Computing Science University of Glasgow Department of Engineering King's College London Shenzhen Research Institute of Big Data

The recent development of scalable Bayesian inference methods has renewed interest in the adoption of Bayesian learning as an alternative to conventional frequentist learning that offers improved model calibration via uncertainty quantification. Recently, federated averaging Langevin dynamics (FALD) was introduced as a variant of federated averaging that can efficiently implement distributed Bayesian learning in the presence of noiseless communications. In this paper, we propose wireless FALD (WFALD), a novel protocol that realizes FALD in wireless systems by integrating over-the-air computation and channel-driven sampling for Monte Carlo updates. Unlike prior work on wireless Bayesian learning, WFALD enables (i) multiple local updates between communication rounds; and (ii) stochastic gradients computed by mini-batch. A convergence analysis is presented in terms of the 2- Wasserstein distance between the samples produced by WFALD and the targeted global posterior distribution. Analysis and experiments show that, when the signal-to-noise ratio is sufficiently large, channel noise can be fully repurposed for Monte Carlo sampling, thus entailing no loss in performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementing Multi-factor Authentication in Cloud Services for Enhanced Security

Implementing Multi-factor Authentication in Cloud Services f...

引用

2024 IEEE International Conference on Recent Advances in science and Engineering technology, ICRASET 2024

作者： Rekha, K. Sashi Sivagami, V.M. Usharani, R. Amutha, T. Pushparani, S. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Sri Venkateswara College of Engineering Department of Information Technology Tamil Nadu Chennai India Srm Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computational Intelligence Kattankulathur Chennai India Care College of Engineering Department of Artificial Intelligence & Data Science Tamil Nadu Trichy India Meenakshi College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350388602

The cloud services which are now the most common data transmission and endanger organizations' confidential information, it's more and more visible that security of any data should be a main priority for companies. MFA, which consists of adopting multi factor approach to authentication and thereby provides multiple types of verification thus ensures effective security, is leveraged to ensure resource access. This paper proposes a full-fledged way of implementing MFA for cloud services in order to strengthen the security given and manage the constatoing risks. The proposed methodology consists of main stages like requirements determining, technology reviewing, risks assessment, technology design, integration with cloud services, users training, pilot deployment and testing, implementation and configuration, monitoring and maintenance as well as constant improvement. Through a systemic approach, the organizations can be equipped with the capability to personalize the MFA solutions according to their security goals, to bring the cloud environments on board, as well as to ensure that the organizations comply with the security standards as set by various governing bodies. This research adds a grain of salt to the development of cloud security good practices through offering a disciplined approach to MFA implementation, which allows partners to harden their cloud assets and protect against growing cyber threats. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study and Impact Analysis of Different Oversampling Techniques for CIP 1

A Comparative Study and Impact Analysis of Different Oversam...

引用

1st International Conference on Technologies for Smart Green Connected Society 2021, ICTSGS 2021

作者： Bora, Dibya Jyoti Navlani, Avinash Mohari, Ankit Department of Information Technology Kaziranga University Assam India School of Data Science & Forecasting Devi Ahilya Vishwavidyalaya Indore India Department of Information Technology School of Computing Science Kaziranga University Assam India

ISBN: (纸本)9781607685395

In the area of data science, machine learning-based classification techniques are the first choice for an accurate analysis of a huge amount of data. The first requirement while developing such classification techniques is the robustness that it will imply for accurate and efficient classification. However, it is seen that many times these algorithms suffer from class-imbalance problems, shortly CIP. Due to CIP, many difficulties arise during the learning process, which as a whole result in a poor classification process. Resampling the data set is one common technique for dealing with CIP were in general oversampling the size of the rare class is made. We have different oversampling techniques available in the literature like SMOTE, ADYSN, and Random Oversample are the noted ones. In this paper, an effort is made to compare these different techniques as well as their impact on classification performance. © The Electrochemical Society

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tensor Nuclear Norm Based Matrix Regression Based Projections for Feature Extraction of Hyperspectral Images 26

Tensor Nuclear Norm Based Matrix Regression Based Projection...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Qiu, Hong Jin, Heng Wang, Renfang Liu, Xiufeng Gao, Guang Zhejiang Wanli University College of Big Data and Software Engineering Ningbo315200 China Shanghai Ocean University College of Information Shanghai200120 China Technical University of Denmark Department of Technology Management and Economics Denmark Co. Ltd. Ningbo China

ISBN: (纸本)9798350331684

With high spectral resolution, hyperspectral image(HSI) data will result in the Hughes phenomenon, which brings a huge challenge to hyperspectral image classification(HIC). Feature extraction can be applied to address this problem. But several traditional methods often ignore the spatial structure information of HSI data. In this paper, we propose a tensor nuclear norm based matrix regression based projections(TNMRP) for feature extraction of hyperspectral images. Firstly, TNMRP preprocesses the data by a filling method. Then, it automatically builds the graph of block-tensor samples and uses the optimal sparse coding coefficients to obtain the weight matrix. Finally, based on tensor representation, TNMRP calculates the optimal projection matrix. Experiments of classification on Indian Pines and Pavia University databases demonstrate the effectiveness of our proposed method. © 2023 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Learning-Based Machine Fault Diagnosis Using EMD-Gammatone Spectrogram with Limited Labeled Audio dataset

Few-Shot Learning-Based Machine Fault Diagnosis Using EMD-Ga...

引用

2025 IEEE International Conference on big data and Smart Computing, bigComp 2025

作者： Zabin, Mahe Ayon, Syed Tasnimul Karim Siraj, Farhan Md Shuvo, Mehedi Hasan Choi, Ho-Jin Uddin, Jia Korea Advanced Institute of Science and Technology School of Computing Daejeon Korea Republic of BRAC University Department of Computer Science and Engineering Dhaka Bangladesh Dhaka University of Engineering & Technology Department of Computer Science and Engineering Dhaka Gazipur Bangladesh Woosong University AI and Big Data Department Endicott College Daejeon Korea Republic of

The deep learning models are computationally burdensome, and their accuracy depends on the number of labeled datasets used in training. The scarcity of the labeled dataset in industrial machine diagnosis is a significant concern as it is pretty impossible to collect data from faulty machines in industrial environments. To address this issue, in this paper, we presented a few-shot learning-based machine fault diagnosis model on a lightweight SqueezeNet architecture using generated texture images from audio sensor data. Subsets of two public audio datasets, MIMII and ToyADMOS, containing limited data- 10 images per class were used to validate the model. The experimental results demonstrate that the model has exhibited 89.6% and 98.3% accuracy for MIMII and ToyADMOS, respectively, with only ten labeled images of each fault class. As the model has only 73 thousand trainable parameters and requires only 300 KB of memory, it is expected to be deployable in a portal device for machine fault diagnosis. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards Effective and Efficient Error Handling Code Fuzzing Based on Software Fault Injection

Towards Effective and Efficient Error Handling Code Fuzzing ...

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Kang Chen Ming Wen Haoxiang Jia Rongxin Wu Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology (HRUST) Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security Jin YinHu Laboratory Wuhan China School of Informatics Xiamen University Xiamen China School of Computer Science and Technology HUST Wuhan China Cluster and Grid Computing Lab

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

Software systems often encounter various errors or exceptions in practice, and thus proper error handling code is essential to ensure the reliability of software systems. Unfortunately, error handling code is often bug-prone, while sufficiently testing them is challenging as such code often cannot be triggered under normal conditions. Motivated by this, recent studies have proposed to leverage software fault injection (SFI) based fuzzing to discover potential bugs in complicated error handling code. Despite the promising results achieved, their effectiveness and efficiency are still compromised in practice due to the huge search space of error sites, inadequate fuzzing guidance, and the overhead induced by context-sensitive SFI. To achieve effective and efficient testing of error handling code, this study presents AFL-FI, which first utilizes a similarity-based method to identify suspicious error sites, and then incorporates the idea of error site coverage to guide the fuzzing process. Finally, the design of lightweight context-sensitive SFI enables AFL-FI to execute test cases efficiently. We evaluate AFL-FI on eight large-scale open-source projects, and the results show that it can outperform existing state-of-the-art fuzzing tools significantly in terms of branch code coverage. More importantly, AFL-FI has discovered 13 previously unknown bugs, and all of them have been confirmed while 12 of them have been fixed. Besides, our evaluation also demonstrates that all the key designs of AFL- F I are effective that contribute significantly to its overall performance.

关键词： Codes Computer bugs Fuzzing Software systems Software reliability Testing

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：