检索结果-内蒙古大学图书馆

International Conference on Data Engineering

作者： Haitian Hang Xiu Tang Jianling Sun Lingfeng Bao David Lo Haoye Wang College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China School of Computing and Information Systems Singapore Management University Singapore School of Computer and Computing Science Hangzhou City University China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Auto-scaling is crucial for achieving elasticity in cloud databases as well as other cloud systems. Predictive auto-scaling, which leverages forecasting techniques to adjust resources based on predicted workload, has been widely adopted. However, the inherent inaccuracy of forecasting presents a significant challenge, potentially causing resource under-provisioning. To address this challenge, we propose robust predictive auto-scaling that considers the uncertainty in forecasts. Unlike previous predictive approaches that rely on single-valued forecasts, we leverage probabilistic forecasting techniques to generate quan-tile forecasts, providing a more comprehensive understanding of the potential future workloads. By formulating the auto-scaling problem as a robust optimization problem, we enable the implementation of auto-scaling strategies with customizable levels of robustness, which can be determined by considering various quantile levels of forecasts. Moreover, we enhance the adaptability of our strategy by incorporating different quantile levels through-out the entire decision horizon, allowing for dynamic adjustments in the conservatism of our auto-scaling decisions. This enables us to strike a balance between resource efficiency and system robustness. Through extensive experiments, we demonstrate the effectiveness of our approach in achieving robust auto-scaling in cloud databases, while maintaining reasonable resource efficiency.

关键词： Uncertainty Databases Elasticity Probabilistic logic Data engineering Robustness Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Heuristic Algorithm for Solving COVID-19’s Social Distancing at Universities Campus

引用

Computer systems Science & Engineering 2022年第6期41卷 933-944页

作者： Hassan Al-Tarawneh Khalid Al-Kaabneh Aysh Alhroob Hazem Migdady Issam Alhadid Department of Data sciences and Artificial Intelligence Al-Ahlyyia Amman UniversityAmmanJordan Department of Software Engineering Isra UniversityAmmanJordan Department of CSMIS Oman college of management and technologyMuscatOman Faculty of Information Technology and Systems University of JordanAqabaJordan

Social distancing during COVID-19 has become one of the most important measures in reducing the risks of the spread of the virus. Implementing thesemeasures at universities is crucial and directly related to the physical attendance ofthe populations of students, professors, employees, and other members on campus. This research proposes an automated scheduling approach that can help universities and schools comply with the social distancing regulations by providingassistance in avoiding huge assemblages of people. Furthermore, this paper proposes a novel course timetable-scheduling scheme based on four main ***, a distance of two meters must be maintained between each student inside theclassroom. Second, no classrooms should contain more than 20% of their regularcapacity. Third, there would be no back-to-back classes. Lastly, no lectures shouldbe held simultaneously in adjacent classrooms. The proposed approach wasimplemented using a variable neighborhood search (VNS) approach with an adaptive neighborhood structure (AD-NS) to resolve the problem of scheduling coursetimetables at Al-Ahlyyia Amman University. However, the experimental resultsshow that the proposed techniques outperformed the standard VNS tested on university course timetabling benchmark dataset ITC2007-Track3. Meanwhile, theapproach was tested using datasets collected from the faculty of information technology at Al-Ahlyyia Amman University (Jordan). Where the results showed that,the proposed technique could help educational institutes to resume their regularoperations while complying with the social distancing guidelines.

关键词： COVID-19 social distance variable neighborhood search adaptive neighborhood structure university course timetable

来源：评论

学校读者我要写书评

暂无评论

Enhancing Automated Android Application Security through Hybrid Static and Dynamic Analysis Techniques

Enhancing Automated Android Application Security through Hyb...

引用

Human-Computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： G.E. Manukulasooriya R.S.I. Munasingha Harinda Fernando H.K.I. Uthpali A.V.S.H. Yeshani Deemantha Siriwardana Department of Computer Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798350394634

ISBN: (纸本)9798350394641

The rapid growth of mobile applications has led to serious security challenges, resulting in vulnerabilities. Automation in security testing methods is becoming popular, with the Automated Vulnerability Detection methodology being one such method. This work introduces a hybrid approach for detecting vulnerabilities in Android applications, combining static and dynamic analysis. The approach is accessible to both general users and expert developers, allowing for the identification of ingrained vulnerabilities in the source code. The hybrid model’s effectiveness is assessed in various applications with different security flaws, providing a solid solution for automated vulnerability detection in Android applications, enhancing security and resilience in the mobile ecosystem.

关键词： Human computer interaction Solid modeling Source coding Solids Mobile applications Security Robots

来源：评论

学校读者我要写书评

暂无评论

Development of Classification System for Corporate Portal User Requests 7

Development of Classification System for Corporate Portal Us...

引用

7th International Conference on information Technologies in Engineering Education, Inforino 2024

作者： Chelyshev, Eduard Bobryakov, Alexander Raskatova, Marina Shcherbakov, Dmitry Naryadkina, Nadezhda National Research University 'MPEI' Dept. of Computing Machines Systems and Networks Moscow Russia National Research University 'MPEI' Dept. of Control and Information Technology Moscow Russia National Research University 'MPEI' Smolensk branch Smolensk Russia National Research University 'MPEI' Dept. of Industrial Thermal Power Systems Moscow Russia

ISBN: (纸本)9798350371369

The paper is devoted to the development of classification system for corporate portal user requests using machine learning algorithms. Text corpus preprocessing including irrelevant characters removal, normalization and stop words exception was performed. Two different feature generation methods were tried for vector representation building of words: the TF-IDF method and the FastText vector space model. Data set was split into training, validation and test samples. Experimental search for the optimal value of the feature space dimension using the TF-IDF method was carried out. Four classification algorithms were applied to solve the task: logistic regression, Gaussian naïve Bayesian classifier, k-nearest neighbors classifier and artificial neural network. The classifiers were trained on the training sample. The grid search algorithm was used for the most appropriate hyperparameter detection. The developed system performance was tested using several classification metrics on the validation and test samples. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Injections Attacks Efficient and Secure Techniques Based on Bidirectional Long Short Time Memory Model

引用

Computers, Materials & Continua 2023年第9期76卷 3605-3622页

作者： Abdulgbar A.R.Farea Gehad Abdullah Amran Ebraheem Farea Amerah Alabrah Ahmed A.Abdulraheem Muhammad Mursil Mohammed A.A.Al-qaness School of Big Data&Software Engineering Chongqing UniversityChongqing401331China Department of Management Science Engineering Dalian University of TechnologyDalian116024China Software College Northeastern UniversityShenyang110169China Department of Information Systems College of Computer and Information ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Management Science and Engineering South China University of TechnologyGuangzhou510641China Department of Computer Engineering and Mathematics University of Rovira i VirgiliTarragonaSpain College of Physics and Electronic Information Engineering Zhejiang Normal UniversityJinhua321004China

E-commerce,online ticketing,online banking,and other web-based applications that handle sensitive data,such as passwords,payment information,and financial information,are widely *** web developers may have varying levels of understanding when it comes to securing an online *** Query language SQL injection and cross-site scripting are the two vulnerabilities defined by the OpenWeb Application Security Project(OWASP)for its 2017 Top Ten List Cross Site Scripting(XSS).An attacker can exploit these two flaws and launch malicious web-based actions as a result of these *** published articles focused on these attacks’binary *** article described a novel deep-learning approach for detecting SQL injection and XSS *** datasets for SQL injection and XSS payloads are combined into a single *** dataset is labeledmanually into three labels,each representing a kind of *** work implements some pre-processing algorithms,including Porter stemming,one-hot encoding,and the word-embedding method to convert a word’s text into a *** model used bidirectional long short-term memory(BiLSTM)to extract features automatically,train,and test the payload *** payloads were classified into three types by BiLSTM:XSS,SQL injection attacks,and *** outcomes demonstrated excellent performance in classifying payloads into XSS attacks,injection attacks,and non-malicious ***’s high performance was demonstrated by its accuracy of 99.26%.

关键词： Web security SQL injection XSS deep learning RNN LSTM BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Scaling Auditory Cognition via Test-Time Compute in Audio Language Models

arXiv

引用

arXiv 2025年

作者： Dang, Ting Gao, Yan Jia, Hong School of Computing and Information Systems The University of Melbourne Australia Department of Computer Science and Technology University of Cambridge United Kingdom

Large language models (LLMs) have shown exceptional versatility in natural language processing, prompting recent efforts to extend their multimodal capabilities to speech processing through the development of audio large language models (Audio LLMs). While Audio LLMs excel in tasks such as speech recognition and synthesis, it remains unclear how they perform when faced with the auditory cognitive challenges posed by real-world environments, such as audio comprehension and listening recall, particularly in the presence of background noise or overlapping speech. Unlike text-based LLMs, which have access to vast amounts of text data for pre-training, retraining Audio LLMs with diverse auditory cognitive scenes is difficult due to the limited datasets that simulate real-world auditory cognitive scenarios and the challenge of acquiring auditory cognitive labels for training. While test-time compute (TTC) methods have been shown to enhance the capabilities of text-based LLMs during inference, a key challenge lies in designing these TTC methods to improve the auditory capabilities of Audio LLMs. This study aims to address these two research gaps by: i) exploring the auditory cognitive capabilities of Audio LLMs, and ii) enhancing their capabilities using TTC approaches. We have investigated five different Audio LLMs for auditory cognition using a self-collected database and have proposed five TTC approaches to enhance auditory cognitive capabilities during inference. Our findings reveal that Audio LLMs performance decreases in more challenging auditory cognitive tasks. The proposed TTC approaches significantly enhance cognitive auditory capabilities, advancing the development of more adaptable and resilient Audio LLMs for practical applications such as assistive listening devices, voice-based AI assistants, and communication technologies. © 2025, CC BY-NC-ND.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

LDREG: LOCAL DIMENSIONALITY REGULARIZED SELF-SUPERVISED LEARNING 12

LDREG: LOCAL DIMENSIONALITY REGULARIZED SELF-SUPERVISED LEAR...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Huang, Hanxun Campello, Ricardo J.G.B. Erfani, Sarah Ma, Xingjun Houle, Michael E. Bailey, James School of Computing and Information Systems The University of Melbourne Australia Department of Mathematics and Computer Science University of Southern Denmark Denmark School of Computer Science Fudan University China Department of Computer Science New Jersey Institute of Technology United States

Representations learned via self-supervised learning (SSL) can be susceptible to dimensional collapse, where the learned representation subspace is of extremely low dimensionality and thus fails to represent the full data distribution and modalities. Dimensional collapse - also known as the "underfilling" phenomenon -is one of the major causes of degraded performance on downstream tasks. Previous work has investigated the dimensional collapse problem of SSL at a global level. In this paper, we demonstrate that representations can span over high dimensional space globally, but collapse locally. To address this, we propose a method called local dimensionality regularization (LDReg). Our formulation is based on the derivation of the Fisher-Rao metric to compare and optimize local distance distributions at an asymptotically small radius for each data point. By increasing the local intrinsic dimensionality, we demonstrate through a range of experiments that LDReg improves the representation quality of SSL. The results also show that LDReg can regularize dimensionality at both local and global levels. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Measuring Confounding Bias in Mixed Multidimensional Data: Case of Coerced Multiple Linear Regression Adjustment 8th

On Measuring Confounding Bias in Mixed Multidimensional Dat...

引用

8th International Conference on information and Communication technology for Intelligent systems, ICTIS 2024

作者： Peious, Sijo Arakkal Kaushik, Minakshi Shah, Syed Attique Sharma, Rahul Suran, Shweta Draheim, Dirk Information Systems Group Tallinn University of Technology Tallinn Estonia School of Computing and Digital Technology—CDT Birmingham City University Birmingham United Kingdom The Open University Walton Hall Milton Keynes United Kingdom Ajay Kumar Garg Engineering College Ghaziabad India

ISBN: (纸本)9789819766833

Currently, we witness a significantly increased understanding, that disaggregation of data is the key to better-informed decision-making and enactment. The UN 2030 Agenda for Sustainable Development prominently stresses the importance of disaggregated data for achieving its goals. We argue that the key benefit of data disaggregation is the increased potential to understand confounding effects. Unfortunately, in today’s tool landscape, it lacks systematic support for understanding confounders. Therefore, in this paper, we contribute as follows. We integrate a means of confounder adjustment, i.e. multiple linear regression adjustment, as a new feature into the data analysis tool GrandReport, which works in mixed mode, i.e. for both numerical and categorical data in parallel. Next, we conduct experiments on an extended air pollutants dataset from several cities. We utilize the tool GrandReportl to investigate the correlation between standardized air quality indices and CO2 levels before and after confounder adjustment in regard with additional city data. We argue that the experiments provide evidence for the usefulness and usability of the suggested approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Blockchain and IIoT Enabled Solution for Social Distancing and Isolation Management to Prevent Pandemics

引用

Computers, Materials & Continua 2023年第7期76卷 687-709页

作者： Muhammad Saad Maaz Bin Ahmad Muhammad Asif Muhammad Khalid Khan Toqeer Mahmood Elsayed Tag Eldin Hala Abdel Hameed College of Computing and Information Sciences Karachi Institute of Economics&TechnologyKarachiPakistan Department of Computer Science Lahore Garrison UniversityLahorePakistan Department of Computer Science National Textile UniversityFaisalabad37610Pakistan Faculty of Engineering and Technology Future University in Egypt New Cairo11835Egypt Faculty of Computer and Information Systems Fayoum UniversityFaiyumEgypt Khaybar Applied College Taibah UniversityMedinaSaudi Arabia

Pandemics have always been a nightmare for humanity,especially in developing *** lockdowns are considered one of the effective ways to deal with spreading such ***,developing countries cannot afford such solutions because these may severely damage the country’s ***,this study presents the proactive technological mechanisms for business organizations to run their standard business processes during pandemic-like situations *** novelty of this study is to provide a state-of-the-art solution to prevent pandemics using industrial internet of things(IIoT)and blockchain-enabled *** to existing studies,the immutable and tamper-proof contact tracing and quarantine management solution is *** use of advanced technologies and information security is a critical area for practitioners in the internet of things(IoT)and corresponding ***,this study also emphasizes information security,end-to-end solution,and experimental ***,a wearable wristband is proposed,incorporating 4G-enabled ultra-wideband(UWB)technology for smart contact tracing mechanisms in industries to comply with standard operating procedures outlined by the world health organization(WHO).Secondly,distributed ledger technology(DLT)omits the centralized dependency for transmitting contact tracing ***,a privacy-preserving tracing mechanism is discussed using a public/private key cryptography-based authentication ***,based on geofencing techniques,blockchain-enabled machine-to-machine(M2M)technology is proposed for quarantine *** step-by-step methodology and test results are proposed to ensure contact tracing and quarantine *** existing research studies,the security aspect is also considered in the realm of *** practical implementation of the proposed solution also obtains the *** results indicate the successful implementation of blockchain-enabled contac

关键词： Blockchain contact tracing distributed ledger technology geo-fencing internet of things industrial internet of things isolation management social distancing ultra-wideband

来源：评论

学校读者我要写书评

暂无评论

Towards Data-Driven Network Intrusion Detection systems: Features Dimensionality Reduction and Machine Learning

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2022年第14期16卷 123-135页

作者： Maabreh, Majdi Obeidat, Ibrahim Elsoud, Esraa Abu Alnajjai, Asma Alzyoud, Rahaf Darwish, Omar Department of Information Technology Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University P.O. Box 330127 Zarqa13133 Jordan Department of Computer Information Systems Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa Jordan Information Security and Applied Computing Department Eastern Michigan University MI United States

Cyber attacks have increased in tandem with the exponential expansion of computer networks and network applications throughout the world. Fortunately, various machine/deep learning models have demonstrated excellent accuracy in predicting network attacks in the literature;nonetheless, having simple and understandable models might be a big benefit in network monitoring systems. In this study, we evaluate four feature selection algorithms to find the minimal set of predictive features of network attacks, seven classical machine learning algorithms, and the deep learning algorithm on one million random instances of the CSE-CIC-IDS2018 big data set for network intrusions. The feature selection algorithms highlighted the importance of features related to forwarding direction (FWD) and two flow measures (FLOW) in predicting the binary traffic type;benign or attack. Furthermore, the results revealed that not all features are required to build efficient ML/DL in detecting network attacks, four features unanimously selected by the feature selection algorithms were enough to build comparable ML models to those trained on all features. This might lead to models that are more suitable for deployment in terms of complexity, explainability, and scalability. Moreover, by selecting four unanimity features instead of all traffic features, the training time may be decreased by 10% to 50%. © 2022. All Rights Reserved.

关键词： Network security

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：