检索结果-内蒙古大学图书馆

UPB Scientific Bulletin, Series C: Electrical engineering and computer Science 2023年第4期85卷 163-180页

作者： Wu, Chenhao Fu, Xueliang Li, Honghui Hu, Hua Li, Xue Dept. of Computer and Information Engineering Inner Mongolia Agricultural University China

Total suspended matter (TSM) is an important parameter of the water environment. Because of the optical complexity in water body, it is difficult to accurately invert the TSM concentration by current traditional methods. In this paper, using Sentinel-2 remote sensing images as the data source combined with measured data, taking Wuliangsu Lake as the study area, a new intelligent algorithm combining the adaptive ant colony exhaustive optimization algorithm (A-ACEO) feature selection method with genetic algorithm (GA) optimized back propagation neural network (BPNN) model (GA-BP) is proposed for inversion of TSM concentration. The ant colony algorithm (ACO) is improved to select remote sensing feature bands for TSM concentration by introducing relevant optimization strategies. The GA-BP model is built by optimizing BPNN using GA with the selected feature bands as input and comparing with the traditional BPNN model. The results show that using feature bands selected by the presented A-ACEO algorithm as inputs, can effectively reduce complexity and improve inversion performance of the model, under the condition of the same model, which can provide valuable references for monitoring the TSM concentration in Wuliangsu Lake. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Study on Energy Saving Method in Wastewater Process Control System

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第11期72卷 1485-1490页

作者： Nahm, Eui-Seok Dept. of AI Computer Engineering Far East University Korea Republic of

In this paper, an energy saving method for wastewater treatment biological process is proposed. In the wastewater treatment biological process, the effect on the output according to the change in input takes 4 to 6 hours due to the characteristics of the biological reaction. However, existing studies did not take this into consideration and implemented a prediction system for input versus output using data from the same time. In order to solve this problem, this paper 1) generates input/output data considering the biological reaction time of output by input, 2) builds an artificial neural network prediction model using this data, and 3) determines the minimum water quality from this model to achieve the target water quality. The blower was controlled by calculating the blowing volume. We proposed a mathematical method that considers the biological response time of output by input, and in this case, a method of implementing an artificial neural network model and a method of controlling actual airflow volume were proposed. As a result, it was possible to reduce the power consumption that occurred when trying to achieve the target water quality by unconditionally increasing the existing DO. Copyright © The Korean Institute of Electrical Engineers.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

A Study on Modeling of Activated Sludge Process in Wastewater Treatment System Utilizing XAI(eXplainable AI)

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第2期72卷 263-269页

作者： Nahm, Eui-Seok Dept. of AI Computer Engineering Far East University Korea Republic of

In this paper, to solve the problem of model-based control due to data reliability in the sewage treatment system active sludge process, an explanable artificial intelligence (XAI, eXplainable AI) was applied to implement neural network model for dissolved oxygen in an active sludge process. By applying four reliable items of effluent water quality to explainable artificial intelligence techniques, the input water quality items of the model were determined. Among the explainable artificial intelligence techniques, in the technique using connection strength, the concept of GAN was used to divide it into positive and negative numbers and compete with each other. As a result, the performance of the model was maintained even though the input variables of the model were reduced from 6 to 5. The learning error and evaluation error of the final model were 0.13 and 0.20, respectively. In the case of the learning model, the error increased slightly in the evaluation model compared to the conventional method with 6 input variables, but this difference is almost meaningless in terms of the actual value of DO, so the proposed technique is much more efficient compared to reducing the input variables from 6 to 5. Copyright © The Korean Institute of Electrical Engineers.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Threat Detection Using Neural Network and Machine Learning Approaches in Kubernetes Environments 6

Multi-Class Threat Detection Using Neural Network and Machin...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Aly, Abdelrahman Fayez, Mahmoud Al-Qutt, Mirvat Hamad, Ahmed M. Dept. Computer Systems Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt

ISBN: (纸本)9798350373875

Kubernetes, an open-source platform for automating deployment, scaling, and management of containerized applications, has become a cornerstone in modern IT infrastructure. Alongside its widespread adoption, Kubernetes faces a series of sophisticated security challenges, especially in managing numerous containers. This research uniquely focuses on multi-class threat detection, classifying various types of security threats within Kubernetes environments. Machine learning is emerging as a powerful tool in cybersecurity, offering new ways to detect and mitigate threats. However, there is a shortage of comprehensive research on its application within Kubernetes, especially for detecting multiple types of security threats. This research aims to bridge this gap by introducing a machine learning-based technique for improved threat detection in Kubernetes environments. We propose an advanced detection method using the Naive Bayes algorithm, complemented by comprehensive feature engineering and dimensionality reduction using neural networks. The most effective model, which combines Principal Component Analysis (PCA) and Autoencoder with the Naive Bayes classifier, achieved an Fl Score of 0.95 and an accuracy of 91%. © 2024 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Electromagnetic Performances and Loss of Vernier Motor and Synchronous Motor According to Eddy Current Effect

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第1期72卷 57-64页

作者： Kim, Nam-Ho Kim, Chan-Ho Ji, Tae-Hyuk Yoon, Han-Joon Oh, Ho-Jin Jung, Sang-Yong Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Dep. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In this article, the analysis of electromagnetic performances and loss according to the operating ranges are conducted through the comparative study with surfaced mounted permanent magnet synchronous machine(SPMSM) and vernier PM machine(VPMM), which is classified into flux modulation pole and no flux modulation pole types. We investigated SPMSM and VPMM show different flux weakening capability at high speed, VPMM can maintain high torque due to the flux modulation effect but SPMSM was not. We revealed that high torque and power factor are related with the gear ratio closely for VPMM and SPMSM. Furthermore, VPMM with high gear ratio model is subjected to the influence of eddy current which causes degradation of the output torque and the loss of rotor core tends to be increased depending on levels of flux modulation. Copyright © The Korean Institute of Electrical Engineers.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Analyzing File Access Characteristics for Deep Learning Workloads on Mobile Devices 5

Analyzing File Access Characteristics for Deep Learning Work...

引用

5th International Conference on Advances in Electrical engineering and computer Applications, AEECA 2024

作者： Lee, Jeongha Lim, Soojung Bahn, Hyokyung Ewha University Dept. of Computer Engineering Seoul Korea Republic of Ewha University Dept. of Computer Engineering Seoul Korea Republic of

ISBN: (纸本)9798350355253

Recent advances in artificial intelligence technologies have led to a significant increase in deep learning workloads on mobile devices. Given the limited resources of smartphones, much of the research in mobile deep learning has concentrated on offloading these workloads to edge or cloud servers. While computing resources are crucial, storage I/O remains a critical performance bottleneck for mobile devices, yet the file access characteristics of deep learning have not been thoroughly explored. This paper investigates the file access traces of deep learning workloads on mobile devices, comparing them to traditional workloads. The main findings include: 1) Write access constitutes 48-94% of total file accesses, aligning with conventional mobile apps but contrasting with most desktop applications;2) Write access in mobile deep learning workloads exhibits repetitive long-loop patterns, offering insights for enhancing file cache performance;3) Despite its prevalence, write access demonstrates low access skewness;4) Frequency of file accesses proves more informative than recency in predicting re-access likelihood. The insights from this study are expected to guide the efficient management of future smartphone systems by addressing the unique file access dynamics of deep learning. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Kubernetes Platform with a Load-Aware Orchestration Strategy

引用

SN computer Science 2025年第3期6卷 1-15页

作者： Marchese, Angelo Tomarchio, Orazio Dept. of Electrical Electronic and Computer Engineering University of Catania Catania Italy

Microservice architecture is increasingly favored for building large-scale applications designed for deployment in distributed and resource-constrained cloud-to-edge computing environments. As a cloud-native approach, microservices are particularly powerful due to their loosely coupled, independently deployable, and scalable characteristics. These features enable distributed deployment and flexible integration across robust cloud data centers and heterogeneous, often resource-limited, edge nodes. To fully leverage these advantages, there is a need for advanced placement algorithms that can optimize application performance by utilizing the strengths of microservices. In response to these challenges, we propose to extend Kubernetes with a load-aware orchestration strategy, which enhances its capability to deploy microservice applications within shared clusters characterized by dynamic resource usage patterns. Our approach orchestrates applications dynamically, based on real-time resource usage, allowing for continuous adjustment of their placement to match evolving conditions. Evaluation of a prototype system in a testbed environment demonstrates that this approach offers substantial benefits compared to the standard Kubernetes scheduler. © The Author(s) 2025.

关键词： Cloud continuum Container technology Kubernetes descheduler Kubernetes scheduler Microservice architecture

来源：评论

学校读者我要写书评

暂无评论

Land Cover Extraction from Satellite Imagery using U-Net Model 18

Land Cover Extraction from Satellite Imagery using U-Net Mod...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Rani, K. Pushpa Sreedevi, Pogula Dastagiriah, C. Rao, K. Srinivas Subbaraju, G.V. Padmavathi, Jasti Mlr Institute of Technology Dept. of Computer Science and Engineering Hyderabad India G. Pulla Reddy Engineering College Dept. of Computer Science and Engineering Kurnool India Anurag University Dept. of Computer Science and Engineering Hyderabad India Scetw Dept. of Computer Science and Engineering Hyderabad India Hyderabad India

ISBN: (纸本)9789380544519

Satellite imagery offers extensive information that can be used for a variety of societal applications, from the number of buildings in a metropolis to the land cover types of a specific area. However, extracting such information is a difficult task. In the past, images were scanned manually by domain experts to extract features like buildings, infrastructure, and vegetation, which would take weeks or even months depending on the image size. To address this challenge, we trained our model using U-Net architecture, a deep learning model, because of its advantages in multiscale feature learning and faster processing. Data augmentation is done on the dataset in order to enhance the amount of data and prevent overfitting artificially. The trained model achieved an F1 score of 92% and an impressive precision score of 95%. This automated method can be scaled to large sets of data, reducing the need for human labeling. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Data augmentation Deep learning Machine learning Multiscale feature learning U-Net architecture

来源：评论

学校读者我要写书评

暂无评论

Evaluating Various Techniques for Twitter Sentiment Analysis for Election Results 1

Evaluating Various Techniques for Twitter Sentiment Analysis...

引用

1st International Conference on Pioneering Developments in computer Science and Digital Technologies, IC2SDT 2024

作者： Mishra, Prerna Punia, Divya Sikka, Geeta Sharma, Ajay K Sikka, Kushagra NIT Delhi Dept. of Computer Science and Engineering India University of Florida Dept. of Computer Science and Engineering Gainsville United States

ISBN: (纸本)9798350365016

The Indian General Election of 2019 is proof of the rise in political content on social media platforms, reflecting user attitudes and behaviors towards the electoral process. This paper examines the collective behavior of Twitter users during the election period and assesses the feasibility of election prediction through social media analysis in India. This work presents weekly sentiment analysis on election-related Twitter content. It analyzes how social media content can be used as a reliable factor of public sentiment during elections and has recourse to be a predictive parameter alongside other factors. The simulation results show that VADER outperforms various state-of-the-art techniques with a mean absolute error of 1.345 for candidate-wise predictions, significantly outperforming Textblob (5.445), Pattern analyzer (5.135), and pre-trained BERT (28.335) while yielding similar results for party-wise and alliance-wise analyses. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Multiple Approaches Towards Authentication Using Keystroke Dynamics 2

Multiple Approaches Towards Authentication Using Keystroke D...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Arsh, Aditya Kar, Nirmalya Das, Smita Deb, Subhrajyoti Dept. of Computer Science & Engineering NIT Agartala Tripura India Dept. of Computer Science & Engineering ICFAI University Tripura India

In the realm of global computer security, safeguarding sensitive data and computer systems stands as an ongoing challenge. Striking the delicate balance between convenient access for legitimate users and thwarting imposter attacks is imperative. Traditional authentication methods, primarily reliant on username and password schemes, have been the longstanding cornerstone of cyber system authentication. Yet, this conventional approach is marred by inherent vulnerabilities, including password exchange, shoulder surfng, brute force attacks, dictionary attacks, speculation, phishing, and emerging threats. In response to these shortcomings, biometrics technology has emerged as a reliable alternative for authentication and verification, with Keystroke Dynamics being a well-established method. This research advances Keystroke Dynamics-based authentication through cutting-edge technologies, including machine learning, deep learning, and neural networks. A quantitative assessment demonstrates remarkable results - Machine Learning achieves 99.9% accuracy with the Random Forest model, Deep Learning combines CNN with GRU to reach 99.31% accuracy, and the DBN model registers at 98.01%. In the realm of neural networks, Bi-CNN and FFM-NN excel, with accuracy rates of 96.8% and 94.7%, respectively. These findings lay the foundation for robust, secure authentication systems, ensuring the protection of sensitive data and computer assets in our interconnected world. © 2024 Elsevier B.V.. All rights reserved.

关键词： Authentication

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：