检索结果-内蒙古大学图书馆

DRL-Based Time-Varying Workload Scheduling With Priority and Resource Awareness

IEEE Transactions on Network and Service Management 2025年第3期22卷 2838-2852页

作者： Liu, Qifeng Fan, Qilin Zhang, Xu Li, Xiuhua Wang, Kai Xiong, Qingyu Chongqing University School of Big Data and Software Engineering Chongqing400044 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing400044 China Nanjing University School of Electronic Science and Engineering Nanjing210023 China Haihe Laboratory of Information Technology Application Innovation Tianjin300072 China Harbin Institute of Technology School of Computer Science and Technology Weihai264209 China Shandong Key Laboratory of Industrial Network Security Weihai264209 China

With the proliferation of cloud services and the continuous growth in enterprises' demand for dynamic multi-dimensional resources, the implementation of effective strategy for time-varying workload scheduling has become increasingly significant. In this paper, we propose a deep reinforcement learning (DRL)-based method for time-varying workload scheduling, aiming to allocate resources efficiently across servers in the cluster. Specifically, we integrate a classifier and queue scorer to construct a priority queue that exploits temporal resource utilization patterns across different workload classes. Then, we design parallel graph attention layers to capture the dimensional features and temporal dynamics of cloud server cluster. Moreover, we propose a DRL algorithm to generate scheduling strategies that can adapt to dynamic environments. Validation on real-world traces from Google cluster demonstrates that our method outperforms existing approaches in key metrics of cloud server cluster management. © 2004-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Deploying Reinforcement Learning Approaches for Smart Home Automation 15

Deploying Reinforcement Learning Approaches for Smart Home A...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sen, Amit Prakash Goyal, Manish Kumar Shalini Arka Jain University Department of Electrical & Electronics Engineering Jharkhand Jamshedpur India Vivekananda Global University Department of Computer Science & Application Jaipur India Department of Management School of Mangement - Pg Karnataka Bangalore India

ISBN: (纸本)9798350370249

Reinforcement mastering is an area of synthetic intelligence that enables machines to adopt actions that optimize their environment or maximize a pre-defined reward. This paper investigates the potential makes use of reinforcement studying for clever domestic automation. Some of distinctive algorithms had been advanced that leverage reinforcement getting to know strategies for clever houses. The paper discusses the advantages of using reinforcement learning for optimizing electricity consumption, increasing comfort, and presenting protection as well as the potential challenges of such deployment. The paper also evaluations several present reinforcement studying-based totally methods applicable for smart domestic automation and highlights ability studies possibilities to address present methodological gaps in an effort to enable the reliable deployment of reinforcement getting to know for clever domestic automation. © 2024 IEEE.

关键词： Deployment Distinctive Domestic Methodological Potential Protection Reinforcement

来源：评论

学校读者我要写书评

暂无评论

Fall Detection and Alerts in Hearing Aids for Deaf using Generative AI

Fall Detection and Alerts in Hearing Aids for Deaf using Gen...

引用

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

作者： Bharat Tripathi Madan Lal Saini Manish Jain Apoorva Saxena Narendra Pal Department of Computer Application Allenhouse Institute of Technology Kanpur India Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab India Department of Computer Application Allenhouse Business School Kanpur India Department of Computer Science & Engineering Axis Institute of Technology & Management Kanpur India Department of Computer Science & Engineering Invertis University Bareilly India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

Individuals with sensorineural hearing loss often experience difficulty comprehending speech when background noise is present. This paper investigates the extent of this problem in various listening scenarios and with different types of background sounds. Additionally, the section explores the contributing factors to this challenge such as reduced audibility, reduced frequency selectivity, loudness recruitment, and dead regions in the cochlea where there are no surviving inner hair cells and or neurons. The sections evaluate different techniques for compensating for the effects of these factors. While signal-processing methods using the output of a single microphone to compensate for reduced frequency selectivity have had limited success, techniques utilizing multiple microphones have proven effective. Amplitude compression has also been effective in compensating for the effects of loudness recruitment, enabling individuals to understand speech across a wide range of sound levels. Next, the paper delves into the technical aspects of implementing fall detection systems in hearing aids. learning algorithms are also investigated for their potential in enhancing fall detection accuracy and minimizing false alarms. Furthermore, the importance of user-friendly interfaces and customization features in ensuring the effectiveness and acceptance of fall detection alerts is also highlighted. The paper also addresses the ethical and privacy considerations associated with fall detection in hearing aids. It emphasizes the need for transparent data handling practices and user consent, while also addressing potential concerns related to user autonomy and intrusion.

关键词： Hair Privacy Neurons Signal processing algorithms Signal processing Hearing aids Fall detection Transient analysis Recruitment Microphones

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Smart Antenna System for Electromagnetic Compatibility 2

Design and Development of a Smart Antenna System for Electro...

引用

2nd International Conference on Artificial Intelligence and Machine Learning applications, AIMLA 2024

作者： Goyal, Manish Kumar Malathi, H. Choudhary, Binod Kumar Vivekananda Global University Department of Computer Science & Application Jaipur India School of Sciences Department of Biotechnology and Genetics Karnataka Bangalore India ARKA JAIN University Department of Electrical & Electronics Engineering Jharkhand Jamshedpur India

ISBN: (纸本)9798350349221

This technical abstract introduces the design and development of a smart Antenna gadget for Electromagnetic Compatibility (EMC). The clever antenna device pursuits to lessen unwanted interference in wireless verbal exchange systems, and also to locate time Electromagnetic interference (EMI) alerts and optimize running conditions. This antenna gadget is built on both software and hardware systems. Its design relies on the improvement of antenna arrays, which make use of adaptive sign-processing techniques with the intention of reaping the desired EMC necessities. The antenna array, with its signal-processing architecture, gives the possibility of at the same time optimizing radiation samples and electrical parameters by way of electronically scanning the antenna in more than one direction and taking into consideration disturbances in the environment. The layout additionally incorporates an optimized weight matrix that is used to optimize the antenna's signal-processing structure. Subsequently, the advanced system is simulated and evaluated for its overall performance, and the results are compared with theoretical predictions. © 2024 IEEE.

关键词： Antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Leveraging Adaptive Algorithms for Real-Time Data Analysis 15

Leveraging Adaptive Algorithms for Real-Time Data Analysis

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sahoo, Girija Shankar Hannah Jessie Rani, R. Goyal, Manish Kumar Mohammed, Vazeer Ali Jana, D Little Femilin Wasatkar, Namrata N. Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Electrical and Electronics Engineering Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Application Jaipur India Lewis University Illinois Department of Computer & Information System United States Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350370249

This paper proposes the use of adaptive algorithms for real-time data analysis. Adaptive algorithms are a set of practical methods used for acting information-driven optimization and studying. They have a wide variety of applications and may be implemented to a selection of facts analysis obligations. This paper offers an overview of existing adaptive algorithms and descriptions of several new programs in the area of actual-time facts analysis. In particular, the paper discusses the notion of adaptive thresholding, which allows for practical real-time evaluation of large datasets. The paper also provides a novel technique for making use of these algorithms in an online learning environment. Results from simulations illustrate the ability of the proposed method in real-international packages. Sooner or later, the paper presents numerous key lessons discovered and affords recommendations for future research and packages in this area. © 2024 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction

arXiv

引用

arXiv 2024年

作者： Li, Guozheng Wang, Peng Ke, Wenjun Guo, Yikai Ji, Ke Shang, Ziyu Liu, Jiajun Xu, Zijie School of Computer Science and Engineering Southeast University China Ministry of Education China Beijing Institute of Computer Technology and Application China

Relation extraction (RE) aims to identify relations between entities mentioned in texts. Although large language models (LLMs) have demonstrated impressive in-context learning (ICL) abilities in various tasks, they still suffer from poor performances compared to most supervised fine-tuned RE methods. Utilizing ICL for RE with LLMs encounters two challenges: (1) retrieving good demonstrations from training examples, and (2) enabling LLMs exhibit strong ICL abilities in RE. On the one hand, retrieving good demonstrations is a non-trivial process in RE, which easily results in low relevance regarding entities and relations. On the other hand, ICL with an LLM achieves poor performance in RE while RE is different from language modeling in nature or the LLM is not large enough. In this work, we propose a novel recall-retrieve-reason RE framework that synergizes LLMs with retrieval corpora (training examples) to enable relevant retrieving and reliable in-context reasoning. Specifically, we distill the consistently ontological knowledge from training datasets to let LLMs generate relevant entity pairs grounded by retrieval corpora as valid queries. These entity pairs are then used to retrieve relevant training examples from the retrieval corpora as demonstrations for LLMs to conduct better ICL via instruction tuning. Extensive experiments on different LLMs and RE datasets demonstrate that our method generates relevant and valid entity pairs and boosts ICL abilities of LLMs, achieving competitive or new state-of-the-art performance on sentence-level RE compared to previous supervised fine-tuning methods and ICL-based methods. © 2024, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

An Effective Diagnosis of Alzheimer's Disease with the Use of Deep Learning based CNN Model 7

An Effective Diagnosis of Alzheimer's Disease with the Use o...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Sharmili, K.C. Suja, G.P. Pandian, E. Walid, Md. Abul Ala Arunachalam, Sripriya Babu, G.Charles Computer Science Stella Maris College 17 Cathedral Road Chennai India Computer Science Muslim Arts College Thiruvithancode629174 India Sri Muthukumaran Institute of Technology Mangadu Master of Computer Application Chennai69 India Department of Computer Science and Engineering Khulna9203 Bangladesh Computer Applications-PG School of Computing Sciences VELS Institute of Science Technology & Advanced Studies - VISTAS Velan Nagar P.V. Vaithiyalingam Road Pallavaram Chennai600 117 India GRIET Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350397253

In recent years, Alzheimer's disease has become a major health concern. Over 45 million individuals worldwide suffer from this illness. Alzheimer's disease is a neurodegenerative illness of unidentified etiology and process that causes cognitive deterioration, and it mostly affects the elderly. Dementia, the gradual and irreversible loss of brain cells, is the leading cause of Alzheimer's disease. Those with this illness lost the ability to think, read, and do other basic tasks. A machine learning system may aid in this situation by making accurate predictions about the onset of illness. Dementia diagnosis in a broad patient population is the major objective. This research presents the findings and analysis of many Machine Learning models for identifying dementia. To alleviate this obstacle and help in the diagnosis of AD will create a deep-learning architecture that uses stacked auto-encoders and a softmax output layer. The proposed technique can analyze numerous classes in a single setting, unlike earlier procedures, and only needs a small number of labeled training samples and basic domain expertise to get started. In the present studies, a substantial improvement in performance when it came to classifying all diagnostic subgroups. Using the proposed technique can run these time series through a Convolutional Neural Network (CNN) and ResNet50 model to extract the distinguishing patterns across stages. With an F1-score of 0.99 and an accuracy of 99.91 percent, the CNN-based technique outperformed the standard feature-based classifiers by a significant margin. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors

arXiv

引用

arXiv 2024年

作者： Li, Guozheng Wang, Peng Liu, Jiajun Guo, Yikai Ji, Ke Shang, Ziyu Xu, Zijie School of Computer Science and Engineering Southeast University Bangladesh Ministry of Education China Beijing Institute of Computer Technology and Application China

Relation extraction (RE) is an important task that aims to identify the relationships between entities in texts. While large language models (LLMs) have revealed remarkable in-context learning (ICL) capability for general zero and few-shot learning, recent studies indicate that current LLMs still struggle with zero and few-shot RE. Previous studies are mainly dedicated to design prompt formats and select good examples for improving ICL-based RE. Although both factors are vital for ICL, if one can fundamentally boost the ICL capability of LLMs in RE, the zero and few-shot RE performance via ICL would be significantly improved. To this end, we introduce MICRE (Meta In-Context learning of LLMs for Relation Extraction), a new meta-training framework for zero and few-shot RE where an LLM is tuned to do ICL on a diverse collection of RE datasets (i.e., learning to learn in context for RE). Through meta-training, the model becomes more effectively to learn a new RE task in context by conditioning on a few training examples with no parameter updates or task-specific templates at inference time, enabling better zero and few-shot task generalization. We experiment MICRE on various LLMs with different model scales and 12 public RE datasets, and then evaluate it on unseen RE benchmarks under zero and few-shot settings. MICRE delivers comparable or superior performance compared to a range of baselines including supervised fine-tuning and typical in-context learning methods. We find that the gains are particular significant for larger model scales, and using a diverse set of the meta-training RE datasets is key to improvements. Empirically, we show that MICRE can transfer the relation semantic knowledge via relation label name during inference on target RE datasets. © 2024, CC BY.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Predicting Bank Loan Approval with Artificial Intelligence

Predicting Bank Loan Approval with Artificial Intelligence

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Raj Ratan Sudeept Singh Yadav Ritika Malhotra Avneesh Kumar School of Computer Application and Technology Galgotias University Greater Noida India School of Computer Science and Engineering Galgotias University Greater Noida India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

In the contemporary financial landscape, banks play a crucial role in facilitating individuals and businesses with their monetary needs. Central to their operations is the assessment of borrower creditworthiness through loan approval processes, ensuring the security of loans extended. However, traditional manual assessment is not only time-consuming but also prone to human error. Therefore, there is an urgent need to develop an automated and reliable credit approval system. In this study, diverse machine learning calculations are compared to decide the ideal show for anticipating whether a bank ought to endrose a advance for a person. Employing a dataset gotten from Kaggle, diverse machine learning methods to a degree logistic reversion, decision trees, K-nearest neighbors (KNN), haphazard woodlands and neural networks are exploited. The animation of these models is evaluated handling measurements to a degree veracity, accuracy, review and F1 score. In particular, the influence of the model is improved by taking into account a number of factors that include the borrower's personal characteristics, such as tax liabilities, purpose of the loan, credit history, loan amount and home ownership, in addition to traditional checking account information. This holistic approach allows for a more accurate estimation of the likelihood of loan default. Furthermore, the logistic regression model proves to be the top performer with an impressive accuracy of 81.89%. Additionally, a trait importance analysis is performed to identify the variables that have the greatest impact on loan approval decisions. The results underline the superiority of ML models over conventional statistical approaches and illustrate their potential to significantly improve the accuracy of loan forecasting.

关键词： Logistic regression Accuracy Machine learning algorithms Reviews Finance Predictive models Nearest neighbor methods Prediction algorithms Security Random forests

来源：评论

学校读者我要写书评

暂无评论

Mobile edge computing-enabled blockchain: contract-guided computation offloading

引用

Journal of Supercomputing 2023年第7期79卷 7970-7996页

作者： Li, Yijun Lin, Ziqiong Zhang, Wenjie Zheng, Yifeng Yang, Jingmin School of Computer Sciences Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Fujian Province University Fujian Zhangzhou363000 China Department of Electronic Engineering National Taipei University of Technology Taipei106335 Taiwan

The core problem of blockchain is to solve the proof-of-work puzzle, which is a high energy-consumption task. To address the resource limit problem, the combination of blockchain and mobile edge computing (MEC) has attracted widespread concern. In this paper, we consider a resource trading problem for a MEC-enabled blockchain system with multiple miners and one edge computing service provider (ESP), in which ESP has no previous knowledge of miners’ private information. We focus on how to perform resource trading between miners and ESP to maximize ESP’s profit under incomplete information? To tackle this problem, the resource trading process is modeled as a monopoly market using contract theory. The ESP acts as a monopolist and needs to set a contract containing service time and price for the miners. The miners can be classified into multiple types based on the private information and select one contract item designed for its type. We first analyze the necessary and sufficient conditions for feasible contracts and derive the optimal contract that maximizes the ESP’s profit for complete information scenario. For incomplete information, the service demand and the number of transactions contained in the block are the private information of miners and not known by ESP, we explore the properties of a feasible contract to reduce the complexity and propose a Lagrange multiplier algorithm to obtain the optimal contract in this scenario. Finally, the feasibility and optimality of the contract have been shown through simulation results. In addition, our proposed method can achieve results close to that of complete information scenario and has a maximum performance improvement of 17.19% comparing with linear pricing strategy in incomplete information scenario. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Blockchain

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：