检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Fürst, Darren Aßmuth, Andreas Department of Electrical Engineering Media and Computer Science Ostbayerische Technische Hochschule Amberg-Weiden Amberg Germany Faculty of Computer Science and Electrical Engineering Kiel University of Applied Sciences Kiel Germany

Cloud services have become an essential infrastructure for enterprises and individuals. Access to these cloud services is typically governed by Identity and Access Management systems, where user authentication often relies on passwords. While best practices dictate the implementation of multi-factor authentication, it’s a reality that many such users remain solely protected by passwords. This reliance on passwords creates a significant vulnerability, as these credentials can be compromised through various means, including side-channel attacks. This paper exploits keyboard acoustic emanations to infer typed natural language passphrases via unsupervised learning, necessitating no previous training data. Whilst this work focuses on short passphrases, it is also applicable to longer messages, such as confidential emails, where the margin for error is much greater, than with passphrases, making the attack even more effective in such a setting. Unlike traditional attacks that require physical access to the target device, acoustic side-channel attacks can be executed within the vicinity, without the user’s knowledge, offering a worthwhile avenue for malicious actors. Our findings replicate and extend previous work, confirming that cross-correlation audio preprocessing outperforms methods like mel-frequency-cepstral coefficients and fast-fourier transforms in keystroke clustering. Moreover, we show that partial passphrase recovery through clustering and a dictionary attack can enable faster than brute-force attacks, further emphasizing the risks posed by this attack vector. Copyright © 2025, The Authors. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent System Based on Stacking Technique for Rice Yield Prediction

Multi-Agent System Based on Stacking Technique for Rice Yiel...

引用

Electronic engineering (ICEEM), International Conference on

作者： Hayam R. Seireg Yasser M. Omar Ahmed Elmahalawy Department of Computer Science and Engineering Faculty of Electronic Engineering Menoufia University Menouf Egypt Department of Computer Science Faculty of Computing and Information Technology AASTMT Cairo Egypt

Artificial intelligence (AI) has expanded its influence across various sectors including education, healthcare, and agriculture. In the agricultural setting, the multiagent system (MAS) is recognized as a powerful tool for optimizing resource allocation, enhancing decision-making processes, and improving overall farm productivity. Accurate prediction of rice yield levels is paramount importance in the agricultural sector. It allows farmers, policymakers, and stakeholders to make informed decisions regarding crop management. Individual machine-learning algorithms (MLA) have been used to predict rice yield levels, but they may not fully exploit the available information. Therefore, the novel system implemented based on stacking techniques to solve complex problems. The objective of this paper is to present an efficient system that leverages MAS based on a novel proposed stacking technique (Extra Trees Classifier (ETC), Random Forest Classifier (RFC), Linear Discriminant Analysis (LDA) and Gaussian Naive Bayes (GNB)) for improving the rice yield level prediction within the agricultural environment. Each algorithm brings its unique approach to handling complex relationships, and modeling class separability. The findings from this study provided valuable insights for decision-making in interconnected sectors and facilitating optimal business planning. The dataset incorporated climate variables such as monthly maximum and minimum temperatures and rainfall. The final result of the dataset consists of 1266 rows and 18 features. The results showed that the novel proposed stacking technique achieved the highest prediction accuracy 87% and the best individual Decision tree classifier obtained 77.5%. The novel proposed stacking technique increases the accuracy by 9.5% compared to the best individual MLA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MSConv: Multiplicative and Subtractive Convolution for Face Recognition

arXiv

引用

arXiv 2025年

作者： Zhou, Si Si, Yain-Whar Yuan, Xiaochen Li, Xiaofan Liu, Xiaoxiang Zhang, Xinyuan Lin, Cong Gong, Xueyuan School of Intelligent Systems Science and Engineering Jinan University Guangdong China Department of Computer and Information Science University of Macau China Faculty of Applied Sciences Macau Polytechnic University China

In Neural Networks, there are various methods of feature fusion. Different strategies can significantly affect the effectiveness of feature representation, consequently influencing the model’s ability to extract representative and discriminative features. In the field of face recognition, traditional feature fusion methods include feature concatenation and feature addition. Recently, various attention mechanism-based fusion strategies have emerged. However, we found that these methods primarily focus on the important features in the image, referred to as salient features in this paper, while neglecting another equally important set of features for image recognition tasks, which we term differential features. This may cause the model to overlook critical local differences when dealing with complex facial samples. Therefore, in this paper, we propose an efficient convolution module called MSConv (Multiplicative and Subtractive Convolution), designed to balance the model’s learning of salient and differential features. Specifically, we employ multi-scale mixed convolution to capture both local and broader contextual information from face images, and then utilize Multiplication Operation (MO) and Subtraction Operation (SO) to extract salient and differential features, respectively. Experimental results demonstrate that by integrating both salient and differential features, MSConv outperforms models that only focus on salient features. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Enhanced Gorilla Troops Optimizer with Deep Learning Enabled Cybersecurity Threat Detection

引用

computer systems science & engineering 2023年第6期45卷 3037-3052页

作者： Fatma S.Alrayes Najm Alotaibi Jaber S.Alzahrani Sana Alazwari Areej Alhogail Ali M.Al-Sharafi Mahmoud Othman Manar Ahmed Hamza Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Prince Saud Al Faisal Institute for Diplomatic Studies RiyadhSaudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversitySaudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Information Systems College of Computer and Information SciencesKing Saud UniversitySaudi Arabia Department of Computer Science College of Computers and Information TechnologyUniversity of BishaSaudi Arabia Department of Computer Science Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Recent developments in computer networks and Internet of Things(IoT)have enabled easy access to *** the government and business sectors face several difficulties in resolving cybersecurity network issues,like novel attacks,hackers,internet criminals,and so ***,malware attacks and software piracy pose serious risks in compromising the security of *** can steal confidential data which results infinancial and reputational *** advent of machine learning(ML)and deep learning(DL)models has been employed to accomplish security in the IoT cloud *** article pre-sents an Enhanced Artificial Gorilla Troops Optimizer with Deep Learning Enabled Cybersecurity Threat Detection(EAGTODL-CTD)in IoT Cloud *** presented EAGTODL-CTD model encompasses the identification of the threats in the IoT cloud *** proposed EAGTODL-CTD mod-el mainly focuses on the conversion of input binaryfiles to color images,where the malware can be detected using an image classification *** EAG-TODL-CTD model pre-processes the input data to transform to a compatible *** threat detection and classification,cascaded gated recurrent unit(CGRU)model is exploited to determine class ***,EAGTO approach is employed as a hyperparameter optimizer to tune the CGRU parameters,showing the novelty of our *** performance evaluation of the EAGTODL-CTD model is assessed on a dataset comprising two class labels namely malignant and *** experimental values reported the supremacy of the EAG-TODL-CTD model with increased accuracy of 99.47%.

关键词： Cybersecurity computer networks threat detection internet of things cloud computing deep learning

来源：评论

学校读者我要写书评

暂无评论

Investigation of adequate closed form travelling wave solution to the space-time fractional non-linear evolution equations

引用

Journal of Ocean engineering and science 2022年第3期7卷 292-303页

作者： Mohammad Asif Arefin M.Ayesha Khatun M.Hafiz Uddin Mustafa Inc Department of Mathematics Jashore University of Science and TechnologyJashore 7408Bangladesh Department of Computer Engineering Biruni UniversityIstanbulTurkey Department of Mathematics Science FacultyFirat UniversityElazigTurkey Department of Medical Research China Medical University HospitalChina Medical UniversityTaichungTaiwan

This work aims to construct exact solutions for the space-time fractional(2+1)-dimensional dispersive longwave(DLW)equation and approximate long water wave equation(ALW)utilizing the twovariable(G′/G,1/G)-expansion method and the modified Riemann-Liouville fractional *** recommended equations play a significant role to describe the travel of the shallow water *** fractional complex transform is used to convert fractional differential equations into ordinary differential *** wave solutions have been successfully achieved using the proposed approach and the symbolic computer Maple *** Maple package program was used to set up and validate all of the computations in this *** choosing particular values of the embedded parameters,we pro-duce multiple periodic solutions,periodic wave solutions,single soliton solutions,kink wave solutions,and more forms of soliton *** achieved solutions might be useful to comprehend nonlinear *** is worth noting that the implemented method for solving nonlinear fractional partial dif-ferential equations(NLFPDEs)is efficient,and simple to find further and new-fangled solutions in the arena of mathematical physics and coastal engineering.

关键词： Riemann-Liouville fractional derivative Space-time fractional(2+1)-dimensional dispersive long wave equation Approximate long water wave equation Wave transformation The two-variable(G′/G,1/G)-expansion method

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of the Resolution of Ge-on-Si Photodetectors for 1μ m Infrared Signals 1

Comparative Study of the Resolution of Ge-on-Si Photodetecto...

引用

1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022

作者： Jahangiri, Mojtaba Sberna, Paolo Sammak, Amir Nihtianov, Stoyan Mathematics and Computer Science Delft University of Technology Faculty of Electrical Engineering Department of Microelectronics Delft Netherlands Delft Netherlands

ISBN: (纸本)9798350398069

Most of the studies on narrow-band near-infrared detection reported so far are related to the 1.3μm and 1.55μm spectral windows. There is insufficient research work done on radiation detection in the narrow band around 1 μm wavelength, which is just outside the Si (0.95μ m) and GaAs (0.85μ m) effective cut-off spectral sensitivity. This paper presents a p+n Ge-on-Si detector with a customized large active window, employing the PureGaB technology, to detect radiation in a very narrow band around 1μ m. The advantages of the proposed detector are: (1) CMOS-compatibility and micro-spectroscopic capability;(2) low dark current and high photoresponsivity, compared to similar devices reported in the literature;(3) enhanced sensitivity to weak radiation by realizing an ultra-shallow and very thin depletion region. These detectors can be good candidates for measuring the YAG laser radiation and measuring stray radiation in photolithography. © 2022 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

An investigation on catalytic performance and reaction mechanisms of Fe/OMS-2 for the oxidation of carbon monoxide, ethyl acetate, and toluene

引用

Journal of Environmental sciences 2022年第2期34卷 258-268页

作者： Ning Dong Mengyue Chen Qing Ye Dan Zhang Hongxing Dai Key Laboratory of Beijing on Regional Air Pollution Control Department of Environmental ScienceSchool of Environmental and Chemical EngineeringFaculty of Environment and LifeBeijing University of TechnologyBeijing 100124China Beijing Key Laboratory for Green Catalysis and Separation Key Laboratory of Beijing on Regional Air Pollution ControlKey Laboratory of Advanced Functional MaterialsEducation Ministry of Chinaand Laboratory of Catalysis Chemistry and NanoscienceDepartment of Environmental Chemical EngineeringSchool of Environmental and Chemical EngineeringFaculty of Environment and LifeBeijing University of TechnologyBeijing 100124China

The octahedral molecular sieve(OMS-2)-supported Fe( xFe/OMS-2: x = 1, 3, 5, and 10) catalysts were prepared using the pre-incorporation method. Physicochemical properties of the as-synthesized materials were characterized by means of various techniques, and their catalytic activities for CO, ethyl acetate, and toluene oxidation were evaluated. Among all of the samples, performed the best, with the reaction temperature required to achieve 90% conversion( T 90%) being 160 ℃ for CO oxidation, 210 ℃ for ethyl acetate oxidation, and 285 ℃ for toluene oxidation. Such a good catalytic performance of 5Fe/OMS-2 was associated with its high(Mn^(3+) + Mn^(2+)) content and adsorbed oxygen species concentration, and good lowtemperature reducibility and lattice oxygen mobility as well as strong interaction between Fe and OMS-2. In addition, catalytic mechanisms of the oxidation of three pollutants over the 5Fe/OMS-2 catalyst were also studied. It was found that CO, ethyl acetate or toluene was first adsorbed, then the related intermediates were formed, and finally the formed intermediates were completely converted into CO_(2) and H_(2)O.

关键词： Cryptomelane-type OMS-2 Supported iron catalyst CO oxidation Volatile organic compound oxidation Toluene oxidation

来源：评论

学校读者我要写书评

暂无评论

ML Techniques for Employee Performance Prediction

ML Techniques for Employee Performance Prediction

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical systems, ICSES 2024

作者： Kumar, Brajesh Agrawal, Prateek Uike, Dipesh Lourens, Melanie Bhati, Indira Peter, M. Chandrakumar Dr. Apj Abdul Kalam Women's Institute of Technology Department of Computer Science & Engineering Bihar Darbhanga India India Dr. Ambedkar Institute of management studies and research Maharashtra Nagpur India Durban University of Technology Faculty of Management Sciences South Africa Department of Management India PeriyarManiammai Institute of Science and Technology Department of Software Engineering Tamilnadu Thanjavur India

ISBN: (纸本)9798331543617

When it comes to maximizing the effectiveness of a business and promoting professional growth, employee performance prediction is an extremely important factor. This research article investigates the use of machine learning (ML) approaches to forecast employee performance, with a particular emphasis on the incorporation of different algorithms from different sources to improve accuracy and dependability. Methods that have been used for a long time, such as linear regression and decision trees, are evaluated alongside more recent approaches, such as ensemble methods and deep learning. To refine the prediction models, our research makes use of approaches such as feature selection and dimensionality reduction. These techniques are utilized by utilizing previous performance data, demographic information, and behavioral indicators. It has been demonstrated through the analysis that sophisticated machine learning techniques, in particular ensemble and deep learning models, are superior to traditional methods when it comes to anticipating employee performance. Our findings offer HR departments concrete insights that can be used to adopt data-driven methods for performance management, which will eventually contribute to improved organizational outcomes and increased employee satisfaction. This paper offers opportunities for future development in predictive analytics within the field of human resources and emphasizes the potential of machine learning to alter performance evaluation systems. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning at the Relation and Event Level for Rumor Detection 48

Contrastive Learning at the Relation and Event Level for Rum...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Xu, Yingrui Hu, Jingyuan Ge, Jingguo Wu, Yulei Li, Tong Li, Hui Chinese Academy of Sciences Institute of Information Engineering Beijing China University of Chinese Academy of Sciences School of Cyber Security Beijing China University of Exeter Faculty of Environment Science and Economy Department of Computer Science United Kingdom

ISBN: (纸本)9781728163277

Existing studies for rumor detection rely heavily on a large number of labeled data to operate in a fully-supervised manner. However, manual data annotation in realistic cases is very expensive and time-consuming. In this paper, we propose a novel self-supervised Relation-Event based Contrastive Learning (RECL) framework for rumor detection to address the above issue. Specifically, we present both the relation-level and event-level augmentation strategies to generate contrastive samples, which capture both the semantics revealed by repost relations and the structural features of rumor events. Moreover, contrastive learning tasks are devised to generate informative graph representations by utilizing self-supervision signals of unlabeled data. Extensive experimental results on real-world datasets demonstrate the effectiveness of our model, especially with limited labeled data. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

PACTDet - An Artificially Intelligent Approach to Detect Pulmonary Illnesses: Pneumonia, Asthma, COVID-19, and Tuberculosis 1

引用

2nd International Conference on Information Technologies and Intelligent Decision Making systems, ITIDMS 2022

作者： Tasmi, Sidratul Tanzila Raihan, Md. Mohsin Sarker Nasif, Atahar Imtiaz Shams, Abdullah Bin Department of Computer Science and Engineering Islamic University of Technology Dhaka1704 Bangladesh Chattogram Bangladesh Department of Computer Science Faculty of Science University of British Columbia 3333 University Way KelownaBCV1V 1V7 Canada The Edward S. Rogers Sr. Department of Electrical Computer Engineering University of Toronto TorontoONM5S 3G4 Canada

ISBN: (数字)9783031313530

ISBN: (纸本)9783031313523

Pulmonary Illness has become very common due to different emerging viruses, bacteria, pollution, and lifestyle. If these diseases are not diagnosed in a patient, they may have a severe impact and fatal conditions in a patient’s life. In this paper, we propose a methodology for the diagnosis of common pulmonary diseases: Pneumonia, Bronchial Asthma, COVID-19, and Tuberculosis based on symptoms. Our research paper functions as a technological doctor, which can detect the probability of a person having a certain category of pulmonary disease. The patient can then take necessary precautions and treatment for an early cure and minimize the severity of the disease. In this research, common classification-based machine learning algorithms: Random Forest, Decision Tree, Support Vector Machine, and Gradient Boosting algorithms were used after preprocessing the dataset from 2 sources. We have developed an Artificial Neural Network (ANN) model that can successfully detect the type of pulmonary disease with an accuracy of 99%. This application can help medical workers in their decision-making process regarding a patient, and the widespread, inexpensive application of this can help save people’s lives globally. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： COVID-19

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：