检索结果-内蒙古大学图书馆

FinOps-driven optimization of cloud resource usage for high-performance computing using machine learning

JOURNAL OF COMPUTATIONAL science 2024年 79卷

作者： Nawrocki, Piotr Smendowski, Mateusz AGH Univ Krakow Fac Comp Sci Al A Mickiewicza 30 PL-30059 Krakow Poland

Cloud computing is gaining popularity in high-performance computing applications. Its utilization enables advanced simulations when local computing resources are limited. However, cloud usage may increase costs and entail resource unavailability risks. This article presents an original approach that employs machine learning to predict long-term cloud resource usage. This enables optimizing resource utilization through appropriate reservation plans, reducing the associated costs. The solution developed utilizes statistical models, XGBoost, neural networks and the Temporal Fusion Transformer. Long-term prediction of cloud resource consumption, especially the Cloud Resource Usage Optimization System that is critical for prolonged simulations, involves using prediction results to dynamically create resource reservation plans across various virtual machine types for HPC on the Google Cloud Platform. Experiments using real -life production data demonstrate that the TFT prediction model improved prediction quality (by 31.4%) compared to the best baseline method, particularly in adapting to chaotic changes in resource consumption. However, it should be noted that the best prediction model in terms of error magnitude might not be the most suitable for resource reservation planning. This was validated by the neural network -based method, introducing an FR metric for forecast evaluation. Resource reservation plans were assessed both qualitatively and quantitatively, focusing on various aspects like a service -level agreement compliance and potential downtime. This paper is an extension of work originally presented during the international conference on Computational science - ICCS 2023, entitled "Long -Term Prediction of Cloud Resource Usage in High -Performance computing".

关键词： Cloud computing High-performance computing Long-term resource prediction Resource reservation machine learning Time series forecasting FinOps

来源：评论

学校读者我要写书评

暂无评论

Quantum computing and data Mining Recent Advancements: A Review 10

Quantum Computing and Data Mining Recent Advancements: A Rev...

引用

10th international conference on Web Research, ICWR 2024

作者： Shayegan, Mohammad Javad Janati, Arash University of Science and Culture Department of Computer Engineering Tehran Iran

ISBN: (纸本)9798350394986

A significant amount of interest has been generated in recent years in the convergence of quantum computing and data mining due to quantum algorithms' potential to revolutionize information extraction from vast datasets, as well as their ability to utilize quantum principles and natural capabilities to perform far more efficiently and efficiently than classic algorithms. We provide a comprehensive and detailed review of the current state of quantum computing algorithms in the field of data mining and machine learning, highlighting key developments, challenges, and their implementation. In particular, machine learning can benefit from QC mechanics like superposition and entanglement due to the use of q-bits as well as other superior advantages provided by quantum computing, such as Grover algorithm. It is important to note that classic machine learning models differ in terms of the types of learning, prediction models, and operating on data as well as performance over time, along with their counterparts, such as supervised and unsupervised models, which are naturally more sophisticated. Our review will also discuss how integrating and merging the two fields of machine learning and quantum computing, and their mechanics, will affect the aspect of time and resource © 2024 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Anomalous Sound Detection Using Hybrid machine learning Techniques

Unsupervised Anomalous Sound Detection Using Hybrid Machine ...

引用

international conference on Big data and Smart computing (BigComp)

作者： Yun, Eunsun Jeong, Minjoong Korea Inst Sci & Technol Informat Supercomp Applicat Ctr Seoul South Korea Univ Sci & Technol UST Data & High Performance Comp Sci Daejeon South Korea

ISBN: (纸本)9798350370027;9798350370034

The early detection of defects in mechanical equipment is of paramount importance in the industrial field. Research into data analysis methodologies for extracting valuable data from mechanical equipment has highlighted the significant value of these technologies. One such study is the early and accurate detection of anomalies in the acoustic data of machinery. In this paper, we propose an effective technique for the detection and classification of rare event anomalies in the data derived from the rotational noise of automotive motors. MFCC extraction and smoothing techniques were used to select minimal features for optimal performance, and Principal Component Analysis (PCA) was applied to extract salient features. These features are capable of distinguishing between normal and anomalous data. Additionally, an unsupervised learning algorithm was applied to the dataset to differentiate between normal and anomaly data. Experimental results showed that the proposed method can effectively detect sound anomalies with a high accuracy of 99.4% and is also capable of detailed classification of anomalous data.

关键词： anomaly sound detection sound feature extraction K-means machine learning motor anomaly diagnosis PCA smoothing sound analysis

来源：评论

学校读者我要写书评

暂无评论

Harnessing machine learning for Precise Rainfall Forecasting: A Comparative Study

Harnessing Machine Learning for Precise Rainfall Forecasting...

引用

2024 international conference on Advances in computing Research on science Engineering and Technology, ACROSET 2024

作者： Pathania, Anuj Rahi, Parvez Khan, Aazim Singh, Tarandeep Singh, Bhanupratap Chandigarh University Department of Computer Science Mohali India

ISBN: (纸本)9798350388800

This work looks into machine learning as a means of enhancing rainfall prediction. A logistic regression model is trained using meteorological data, including meteorological parameters such as temperature, wind speed, and humidity, from different locations. Preprocessing of the data addresses missing values and uses feature engineering to extract useful features. Using performance evaluation criteria such as accuracy, precision, and recall, the model achieves excellent accuracy in differentiating between wet and non-rainy days. This shows how machine learning can be used for weather forecasting. The study highlights the significance of feature generation and data preparation for precise forecasts, which can improve decision-making and be useful for applications in emergency response, agriculture, and water resource management. © 2024 IEEE.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

machine learning in Sensors for Collision Avoidance

Machine Learning in Sensors for Collision Avoidance

引用

international conference on computing, Networking and Communications (ICNC)

作者： Karakus, Erkan Wei, Tao Yang, Qing Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA

ISBN: (纸本)9798350371000;9798350370997

Sensors generate a huge amount of data that need to be transferred to a computing device for processing. Such large data transfer takes time and consumes energy. This paper presents a new sensing and computing architecture, referred to as MLIS (machine learning in Sensors). MLIS allows a part of machine learning to be done on sensor board thereby dramatically reducing the amount of data transferred to the computing device and hence improving overall system performance and energy efficiency. Using an energy-based probabilistic graphical model, RBM (Restricted Boltzmann machine), we built a new ADAS (Advanced Driver-Assistance System) computing platform for autonomous driving with phased-array-radar as sensors. A working prototype has been built to provide proof of concept for our new architecture. The prototype is implemented using a TI's mmWave (millimeter Wave) radar board and a Vivado HLS implementation of the RBM on the Xilinx xc7z020-clg400-1 device. Extensive experiments have been carried out using the prototype on realistic scenes on our campus. Experimental results have shown that the proposed architecture can reduce the data to be transferred by a factor of 8 while maintaining 98% accuracy. Based on the experimental settings, we present two case studies that have shown a remarkable reduction in collision probability if applying the new architecture to autonomous vehicles.

关键词： In-sensor computing computer architecture mmWave radar deep learning object detection and identification

来源：评论

学校读者我要写书评

暂无评论

KnobTune: A Dynamic database Configuration Tuning Strategy Leveraging Historical Workload Similarities

KnobTune: A Dynamic Database Configuration Tuning Strategy L...

引用

2024 international conference on computing, machine learning and data science, cmlds 2024

作者： Zhan, Yueyang Xi, Rui Liao, Jianming Fan, Shuhuan Hou, Mengshu University of Electronic Science and Technology of China Sichuan Chengdu China

ISBN: (纸本)9798400716393

Confronted with an abundance of adjustable parameters and ever-shifting workloads, database configuration tuning grapples with persistent challenges. The intricate task of thoroughly optimizing all these configuration "knobs"to attain peak performance proves arduous and time-consuming. Current strategies often necessitate numerous performance assessments preceding configuration tuning, alongside the selection of pivotal knobs aimed at reducing the parameter space. Nonetheless, crafting a database configuration tuning strategy that accommodates dynamically fluctuating workloads remains a formidable challenge, owing to the substantial variations in optimization requirements across diverse application scenarios and workloads. This paper introduces an innovative configuration tuning approach, coined as KnobTune. Initially, it leverages SHAP (SHapley Additive exPlanations) values to assess the significance of historical tuning tasks' key knobs. Subsequently, it integrates SQL textual features and internal database operational metrics as workload attributes, assigning weights based on their similarity to historical workloads to select key knobs. Comparative evaluations of some benchmarks are conducted to validate the efficacy of this methodology. The results show that our proposed strategy adeptly identifies and adjusts critical knobs when confronted with varying workloads, delivering substantial enhancements in performance optimization compared to prevailing approaches. © 2024 ACM.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

NBA game outcomes prediction using several machine learning algorithms and Voting Classifier 7

NBA game outcomes prediction using several machine learning ...

引用

7th international conference on data science and Information Technology, DSIT 2024

作者： Wu, Yancai Central South University Changsha China

ISBN: (纸本)9798350384093

National Basketball Association, namely NBA, is the most hot league. For various purposes, people try to predict the outcome of NBA games. This paper applies the data of NBA matches from 2004-2022 and numerous machine learning classifiers, like Logistics Regression and Support Vector Classifier, to do with the train samples and the test samples. Then, the voting classifier is used to vote among all models to reach the highest score of 84.78%. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing the computing Efficiency Through data Compression for machine learning 2

Enhancing the Computing Efficiency Through Data Compression ...

引用

2nd international conference on data science and Information System, ICDSIS 2024

作者： Elavarasi, K. Vishnupriya, K. Ifet College Of Engineering Department Of Information Technology Tamilnadu India

ISBN: (纸本)9798350381665

As machine learning data sizes continue to rise, this work offers a unique solution to improve computing efficiency by means of data compression. This starts by going over the problem's history and emphasizing the difficulties brought on by growing data complexity. Recurrent Neural Networks (RNNs) are used in this technique in conjunction with the BIRCH Algorithm to compress data. Which is show via extensive experimentation that this method is efficient in decreasing data size greatly while maintaining important information. The findings show significant gains in overall performance, resource efficiency, and model training speed. By tackling important computational issues, this research helps to address contemporary machine learning applications. Finally, The results highlights the significance of effective data compression methods for managing growing datasets, opening the door for improvements in computing effectiveness and model performance. © 2024 IEEE.

关键词： data compression

来源：评论

学校读者我要写书评

暂无评论

Quantum-Driven Big data Processing

Quantum-Driven Big Data Processing

引用

2024 international conference on Advances in Modern Age Technologies for Health and Engineering science, AMATHE 2024

作者： Handa, Devansh Nikhil, Kindi Krishna Duvarakanath, S. Murali, K. Amrita School Of Computing Amrita Vishwa Vidyapeetham Department Of Computer Science And Engineering Bengaluru India Amrita School Of Engineering Amrita Vishwa Vidyapeetham Department Of Mathematics Bengaluru India

ISBN: (纸本)9798350371567

The proposed study realizes a novel quantum machine learning (QML) architecture that allows heuristic function evaluation and can actually perform quantum circuits during massive data processing. The Quantum-Circuit fusion or the Quantum-data fusion approach to information technology is the latest strategy revolutionizing the major applications with vast computing needs in present time. Our method, which is task - agnostic, is aimed to increase the machine operations speed and scale as the concepts of quantum computing are applied. In this research article, the theoretical background and perspectives are described, so generally, the idea of the combination of quantum circuits is clarified. The research delivery shows as well of this combination as its importance and possibilities, offering a new and cool method in the competitive era of data-driven computational sciences, especially in the field of quantum machine learning. Within classical machine quantum-circuit fusion the potential capability to handle a large data set and obtain the new viewpoints consequently quantum machine learning progress represents a promising route. © 2024 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Finance: Unleashing machine learning's Potential for a New Financial Era

Revolutionizing Finance: Unleashing Machine Learning's Poten...

引用

2024 international conference on Advances in computing Research on science Engineering and Technology, ACROSET 2024

作者： Kour, Manjit Chandigarh University University School of Business Punjab Mohali India

ISBN: (纸本)9798350388800

machine learning has developed into a crucial tool for the financial industry, allowing financial organizations to enhance their processes and offerings. This paper gives a general overview of machine learning's uses and methods in the financial industry. Additionally, the paper includes case studies of effective machine learning applications in the financial industry, emphasizing the advantages of machine learning for fraud detection, risk management, trading and investment, customer service and personalization, credit scoring, and loan approval. The paper stresses how crucial it is to deal with issues like data quality and quantity, explainability and interpretability, regulation and ethical considerations, integration with legacy systems, and a talent and skills deficit. The future scope of machine learning in financial sector is discussed which highlights that how machine learning is going to change future financial landscape for good and will become an integral part of financial sector. © 2024 IEEE.

关键词： Decentralized finance

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：