检索结果-内蒙古大学图书馆

23rd RoEduNet Conference: Networking in Education and Research, RoEduNet 2024

作者： Deak, Tiberiu Deaconescu, Razvan Kroning, Martin Monti, Antonello POLITEHNICA of Bucharest Bucharest Computer Science and Engineering Department Romania RWTH Aachen University Institute for Automation of Complex Power Systems Aachen Germany RWTH Aachen University Aachen Institute for Automation of Complex Power Systems Germany Fraunhofer Center Digital Energy Fraunhofer FIT Aachen Germany

ISBN: (纸本)9798331540388

The capacity of software to adapt its functionalities based on user preferences or hardware requirements is of utmost importance. Improved user satisfaction and overall system performance are just two of the advantages. Kernel configuration serves as a practical example. Situated at the core of an operating system, the kernel is responsible for critical tasks such as process management and memory allocation. Its configuration process has naturally evolved to address the needs of users and systems, as well as specific hardware requirements. However, given the complexity of such projects, the entire configuration process can quickly become overwhelming, especially for users unfamiliar with kernel internals. This paper introduces a 32-bit kernel with a more user-friendly configuration process, facilitated by a step-by-step configuration menu and default configuration profiles. The kernel implements essential features such as file system support, a syscall interface, process control, and physical and virtual memory management. © 2024 IEEE.

关键词： configurability kernel operating systems

来源：评论

学校读者我要写书评

暂无评论

A data-driven distributed fault detection scheme based onsubspace identification technique for dynamic systems

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 2023年第7期33卷 3107-3128页

作者： Cheng, C. Wang, Q. Nikitin, Y. Liu, C. Zhou, Y. Chen, H. School of Computer Science and Engineering Changchun University of Technology Changchun China Department of Mechatronic Systems Kalashnikov Izhevsk State Technical University Izhevsk Russia School of Mechatronic Engineering and Automation Shanghai University Shanghai China School of Artificial Intelligence Shanghai University Shanghai China Institute of Energy Systems Energy Efficiency and Energy Economics TU Dortmund University Dortmund Germany Department of Chemical and Materials Engineering University of Alberta Edmonton Alberta Canada

With the aid of the subspace technique and the average consensus algorithm, the main objective of this article is to develop a data-driven design of distributed fault detection for dynamic systems using the measurement in a complex sensor network. Specifically, the design process consists of two stages: distributed off-line learning and distributed online fault detection. Among them, the distributed off-line learning stage involves the average consensus algorithm and parameter identification by subspace technique. It is worth mentioning that, the distributed fault detection approach has the same performance as the centralized fault detection approach and avoids complex information exchange. In the end, a numerical simulation example and a case study of the three-phase flow facility are illustrated to show that the proposed distributed approach can accomplish the fault detection task successfully.

关键词： average consensus data-driven designs distributed fault detection sensor networks subspaceidentification

来源：评论

学校读者我要写书评

暂无评论

VPN Traffic Classification Based on CNN 14

VPN Traffic Classification Based on CNN

引用

14th IEEE International Conference on computer Research and Development, ICCRD 2022

作者： Feng, Ruixiao Hu, Taiwei Jia, Xiajin College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China School of Mechatronic Engineering and Automation Shanghai University Shanghai China

ISBN: (纸本)9781728177212

Classifying network traffic has long been an active field of research, and it is also a key part of network traffic analysis. However, as the use of network traffic encryption and masking grows in the recent years, traditional network classification methods have become less effective. To overcome the traditional methods' disadvantages of not being accurate enough to classify real world scenario network traffic that is encrypted and randomly mixed with flows from different services and applications, we proposed a method that utilizes payload-based technique and a convolutional neural network model that was modified from existing network structures. Our data preprocessing converts the byte flow of the packet payload into two dimensional arrays for training and classification. Comparing to existing methods that are not purposed for encrypted traffic classification, our method achieves better accuracy, yet remains less resource-intensive relative to using other deep neural networks, making it more suitable to deploy in network infrastructures for practical use. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A CNN-LSTM Based Approach for Image Captioning 7

A CNN-LSTM Based Approach for Image Captioning

引用

7th IET Smart Cities Symposium, SCS 2023

作者： Balık, Esra Kaya, Mehmet Kaya, Buket Department of Sofware Engineering Bandırma Onyedi Eylül University Balıkesir Turkey Department of Computer Engineering Fırat University Elazığ Turkey Dept. of Electronics and Automation Fırat University Elazığ Turkey

ISBN: (纸本)9781839539831

In this age of information and visual data, it has become necessary in many fields to draw meaningful conclusions from these visual data and express them in a textual context. A visual data makes it more understandable and valuable with a textual explanation. It will also greatly accelerate the scanning of large amounts of data in many application areas. In basic fields such as education or medicine, visual-text pairs are of great importance to use as materials. In addition, many autonomous vehicles can be designed that enable disabled individuals to use visual and textual information together. Such studies have gained a wider application area, especially with the advancement of deep learning technology. In this study, a study was carried out on the Flickr8k dataset using Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) technologies to title visual data. This model provides an integrated structure for understanding visual data and producing textual descriptions. The accuracy of the caption value created with the BLEU-1 metric was evaluated. In addition, other studies carried out together with this study were discussed and information was given about the performance of these methods. © The Institution of engineering & Technology 2023.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Evaluating Feature Importance in the Context of Simulation-Based Inference for Cortical Circuit Parameter Estimation 17th

Evaluating Feature Importance in the Context of Simulatio...

引用

17th International Conference on Brain Informatics, BI 2024

作者： Sandron, Alessandro Valero, Alejandro Orozco García, Juan Miguel Mancini, Gabriele Pelayo, Francisco Morillas, Christian Panzeri, Stefano Martínez-Cañada, Pablo University of Padua Padua Italy University of Granada Granada Spain Istituto Italiano di Tecnologia Genoa Italy Department of Pharmacy and Biotechnology University of Bologna Bologna Italy Hamburg Germany Department of Computer Engineering Automation and Robotics University of Granada Granada Spain

ISBN: (纸本)9789819632930

Extracellular electrophysiology recordings capturing the activity of neuronal populations, e.g., Local Field Potentials (LFPs), have offered important insights into cortical dynamics. Yet there is still a lack of clarity about how features and characteristics of these extracellular potentials relate to the properties and function of the underlying neural populations. Mechanistic models combined with simulation-based inference (SBI) algorithms have emerged as an effective strategy for developing predictive tools that fit well with available empirical data and can be used to predict key parameters that describe neural activity. Numerous SBI techniques rely on summary statistics or interpretable features to approximate the likelihood or posterior. However, at present, a significant challenge is assessing how each feature impacts the SBI model’s predictions. Here, we developed an approach to determine feature importance in the context of cortical circuit parameter inference. We first created a dataset that includes a million distinct simulations from a spiking cortical microcircuit model of recurrently connected excitatory and inhibitory populations. Biophysics-based causal filters were coupled with spikes to generate realistic LFP data. We then extracted a set of meaningful features from simulated LFP data that were used to train an SBI algorithm. To evaluate feature importance, we employed SHAP values, a prominent tool in machine learning for interpreting the contribution of each feature to the prediction outcomes. Our findings demonstrate the effectiveness of our approach in pinpointing the most critical features, such as dfa, rs_range, low_freq_power or transition_variance, for inferring parameters of a recurrent cortical circuit model based on electrophysiological data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electrophysiology

来源：评论

学校读者我要写书评

暂无评论

Hybrid Makes Better: Privacy-Preserving Medical Image Classification Based on Federated Learning

Hybrid Makes Better: Privacy-Preserving Medical Image Classi...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Wang, Zhi Chi, Haotian Li, Yonggang Zhang, Yuxuan Jiang, Shunrong Du, Xiaojiang Guizani, Mohsen China University of Mining and Technology School of Computer Science Xuzhou221116 China Shanxi University School of Automation and Software Engineering Taiyuan030006 China Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ United States Mohamed Bin Zayed University of Artificial Intelligence Department of Machine Learning Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350351255

The power of machine learning makes it available for medical image classification. However, machine learning requires large medical datasets to improve accuracy, which will involve patients' private information and lead to their privacy leakage. Federated learning is a trending technique to both protect patients' privacy and improve the accuracy of medical image classification. Unfortunately, current research shows that federated learning faces the risk of privacy leakage. In this paper, we propose a privacy-preserving scheme FHDM. Specifically, we construct a local hybrid differential privacy algorithm (LHDP) against patients' privacy leakage. This hybrid algorithm utilizes both Gaussian and Laplace differential privacy without enlarging the privacy budget. We prove that the algorithm applies to the model parameter. Moreover, we design loss optimization and global optimization strategies on the algorithm to achieve higher accuracy in medical image classification. Finally, we validate FHDM in terms of privacy-preserving and model accuracy on real datasets. Experiments show that FHDM effectively protects privacy and improves the average accuracy by 10.0% compared to adopting the LDP-based scheme with the same medical image dataset and privacy budget. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Stochastic scheduling of power system in the presence of electric vehicle and renewable sources considering security and economic indexes using an improved mutation particle swarm optimization (M-PSO) algorithm

引用

International Journal of Hydrogen Energy 2023年第77期48卷 30085-30101页

作者： Zhang, Chunqian Li, Mengyuan Zhang, Jinfang Jia, Shuang Nahaei, Sanam Saeid Department of Electrical Automation Hebei University of Water Resources and Electric Engineering Cangzhou 061001 China Computer Department Hebei University of Water Resources and Electric Engineering Cangzhou 061001 China Enrolment and Vocation Guidance Office Hebei University of Water Resources and Electric Engineering Cangzhou 061001 China Electrical Engineering Department Sun-Life Company Baku Azerbaijan

Increased air pollution and global temperature as well as motor vehicle fuel consumption have depleted fossil fuel resources and increased environmental problems caused by the consumption of such fuels. In addition to methods such as combined heat and power (CHP) technology and distributed generation (DG) of energy at the consumption site, renewable energy sources and EVs are considered suitable methods for achieving this goal, which is prepared by the grid or battery electric energy. Generation uncertainty due to the lack of solar radiation and constant wind blow at different hours of the day is the only challenge for using renewable energies. Moreover, system reliability is a concept that refers to the safe and reliable operation of the system. In general, the wider and more important the system, the more attention that is paid to calculating its reliability in planning and decision making. This study aims to examine the problem of probabilistic power system planning by calculating the power system reliability, evaluating the effect of the presence of these vehicles on security and economic indicators and renewable energy sources, and modeling uncertainties using a Least Squares Generative Adversarial Network (LSGANs) method with generating various scenarios for solar irradiance and wind speed. Furthermore, the Kantorovich distance matrix (KDM) is used to reduce the number of generated scenarios. In the proposed model, the conditional value-at-risk (CVaR) method is implemented to assess and control the risk caused by uncertainties of the proposed problem. Using the power stored in the EV battery is evaluated to cover wind and solar energy source uncertainties. © 2023 Hydrogen Energy Publications LLC

关键词： Conditional value-at-risk Electric vehicle Improved mutation particle swarm optimization Least squares generative adversarial network Renewable energy sources

来源：评论

学校读者我要写书评

暂无评论

Automatic Cataract and Cholesterol Detection System Based on Recurrent Neural Network (RNN): A Comparison with Convolutional Neural Network (CNN) and Siamese Neural Network (SNN) 1

引用

19th International Conference of Intelligent Unmanned Systems, ICIUS 2023

作者： Lie, Zener S. Widodo, Jatmiko A. F. Hanesi, Isabel K. P. Moningka, Matthew R. N. Mariana, Y. Astuti, Winda Akmeliawati, Rini Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia Product Design program Industrial Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia Robotics and Automation Research Group School of Electrical and Mechanical Engineering The University of Adelaide North Terrace Campus Adelaide Australia

ISBN: (数字)9789819765911

ISBN: (纸本)9789819765904

In Indonesia, the majority of blindness cases, approximately 81%, are attributed to cataract. Additionally, 35% of the population has higher cholesterol levels than the standard normal range. The lack of specialized medical equipment, such as the slit-lamp (Ruparelia in Dalhousie Med J 49(1), [1]) bio-microscope, and trained professionals, especially in rural areas, make it difficult to detect these conditions through eye examinations. To address this issue, a supervised machine learning method, the Recurrent Neural Network (RNN), has been utilized to create an iris scanner system that can identify cataract and high cholesterol in a patient. This system will classify eyes into three categories, i.e., cataract, high cholesterol, and normal iris. The computer simulations indicate that this technique is more accurate and requires less training time compared to the existing Convolutional Neural Network (ANN) and Siamese Neural Network (SNN)-based method, while achieving 100% accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ADD 2023: the Second Audio Deepfake Detection Challenge

ADD 2023: the Second Audio Deepfake Detection Challenge

引用

2023 Workshop on Deepfake Audio Detection and Analysis, DADA 2023

作者： Yi, Jiangyan Tao, Jianhua Fu, Ruibo Yan, Xinrui Wang, Chenglong Wang, Tao Zhang, Chu Yuan Zhang, Xiaohui Zhao, Yan Ren, Yong Xu, Le Zhou, Junzuo Gu, Hao Wen, Zhengqi Liang, Shan Lian, Zheng Nie, Shuai Li, Haizhou State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Beijing China Department of Electrical and Computer Engineering National University of Singapore Singapore The Chinese University of Hong Kong Hong Kong

Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further accelerate and foster research on detecting and analyzing deepfake speech utterances. Different from previous challenges (e.g. ADD 2022), ADD 2023 focuses on surpassing the constraints of binary real/fake classification, and actually localizing the manipulated intervals in a partially fake speech as well as pinpointing the source responsible for generating any fake audio. Furthermore, ADD 2023 includes more rounds of evaluation for the fake audio game sub-challenge. The ADD 2023 challenge includes three subchallenges: audio fake game (FG), manipulation region location (RL) and deepfake algorithm recognition (AR). This paper describes the datasets, evaluation metrics, and protocols. Some findings are also reported in audio deepfake detection tasks. © 2023 CEUR-WS. All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Detection of Customer Opinions with Deep Learning Method for Metaverse Collaborating Brands

Detection of Customer Opinions with Deep Learning Method for...

引用

2022 International Conference on Data Analytics for Business and Industry, ICDABI 2022

作者： Aygun, Irfan Kaya, Buket Kaya, Mehmet Celal Bayar University Department of Software Engineering Manisa Turkey Firat University Department of Electronics and Automation Elaziǧ Turkey Firat University Department of Computer Engineering Elaziǧ Turkey

ISBN: (纸本)9781665490580

In recent years, metaverse projects have been developed that both increase the number of users and bring a new concept to the use of the internet. With this development, collaborations are frequently established within the business world with metaverse projects that attract the attention of companies. In the study, the gains of the companies operating in the metaverse after these activities were examined. Thanks to the tweets collected before and after the companies participated in the metaverse, it was analyzed how potential users interpreted their participation in the metaverse. In this context, sentiment analysis experiments were conducted for five different clothing, sportswear, and retail companies (Adidas, Balenciaga, H&M, Nike, and Zara) serving in similar fields of activity. The BERT architecture, which is a language representation model, was used in the experiments, and it was seen that the positive shares on Twitter for companies increased greatly. After the companies transitioned to Metaverse, the biggest change in positive Twitter posts was seen in Nike, with 47%, and in second place, positive Twitter posts about Balenciaga increased by 42%. Experiments show that firms' assets in the metaverse create a positive perception within one month. © 2022 IEEE.

关键词： Sentiment analysis

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：