检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Alghamdi, Wael Asoodeh, Shahab Calmon, Flavio P. Gomez, Juan Felipe Kosut, Oliver Sankar, Lalitha Wei, Fei The School of Engineering and Applied Science Harvard University United States The Department of Computing and Software McMaster University Canada The School of Electrical Computer and Energy Engineering Arizona State University United States

We introduce a new differential privacy (DP) accountant called the saddle-point accountant (SPA). SPA approximates privacy guarantees for the composition of DP mechanisms in an accurate and fast manner. Our approach is inspired by the saddle-point method-a ubiquitous numerical technique in statistics. We prove rigorous performance guarantees by deriving upper and lower bounds for the approximation error offered by SPA. The crux of SPA is a combination of large-deviation methods with central limit theorems, which we derive via exponentially tilting the privacy loss random variables corresponding to the DP mechanisms. One key advantage of SPA is that it runs in constant time for the n-fold composition of a privacy mechanism. Numerical experiments demonstrate that SPA achieves comparable accuracy to state-of-the-art accounting methods with a faster runtime. © 2022, CC BY.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Scenario-Assisted Deep Reinforcement Learning

arXiv

引用

arXiv 2022年

作者： Yerushalmi, Raz Amir, Guy Elyasaf, Achiya Harel, David Katz, Guy Marron, Assaf Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot76100 Israel School of Computer Science and Engineering The Hebrew University of Jerusalem Givat Ram Jerusalem91904 Israel Software and Information Systems Engineering Ben-Gurion University of the Negev Beer-Sheva8410501 Israel

Deep reinforcement learning has proven remarkably useful in training agents from unstructured data. However, the opacity of the produced agents makes it difficult to ensure that they adhere to various requirements posed by human engineers. in this work-in-progress report, we propose a technique for enhancing the reinforcement learning training process (specifically, its reward calculation), in a way that allows human engineers to directly contribute their expert knowledge, making the agent under training more likely to comply with various relevant constraints. Moreover, our proposed approach allows formulating these constraints using advanced model engineering techniques, such as scenario-based modeling. This mix of black-box learning-based tools with classical modeling approaches could produce systems that are effective and efficient, but are also more transparent and maintainable. We evaluated our technique using a case-study from the domain of internet congestion control, obtaining promising results. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DNMDA: Deep Non-negative Matrix Factorization with Multi-level integration for MiRNA-Drug interaction Prediction

DNMDA: Deep Non-negative Matrix Factorization with Multi-lev...

引用

iEEE international Conference on Bioinformatics and Biomedicine (BiBM)

作者： Yujie Qi Jiaxin Yang Yu-An Huang Zhu-Hong You Zimai Zhang Lun Hu Xi Zhou Pengwei Hu Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Xinjiang University The School of Software Urumqi China School of Engineering and Applied Science Columbia University NY USA School of Computer Science Northwestern Polytechnical University Xian China Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Urumqi China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Numerous studies have demonstrated that the interaction between miRNAs and drugs plays a pivotal role in regulating gene expression and cellular function. Therefore, predicting these interactions is crucial for the development of novel drugs and personalized therapies. Existing methods for predicting miRNA-drug interactions often fail to leverage the full spectrum of molecular and biological features and overlook complex high-dimensional patterns. Deep non-negative matrix factorization (DNMF) addresses these limitations by extracting higher-level representations, thereby enhancing prediction accuracy and robustness. Building on this, this paper proposes a model called DNMDA. in this model, we integrate multiple similarity networks for both miRNAs and drugs and then extract their features through three key modules. Moreover, autoencoders are used to combine various feature sets, allowing for the capture of complementary information and enhancing the model’s capacity for making precise and reliable predictions. The resulting features are consolidated into a unified feature vector for each miRNA-drug pair. Ultimately, these feature vectors and their associated labels are provided to the classifier for training. To verify the predictions, a five-fold cross-validation was conducted. The five-fold cross-validation demonstrated a clear advantage in DNMDA’s metrics, underscoring its reliability in predicting potential miRNA-drug interactions. This claim is further supported by the predictive results section in the paper, offering concrete evidence of DNMDA’s efficacy in this field.

关键词： Drugs Training Accuracy Biological system modeling Computational modeling Scalability Predictive models Feature extraction Vectors Data models

来源：评论

学校读者我要写书评

暂无评论

OCD Diagnosis with Multiple Spatial Similarity-Aware Learning and Diffusion Structure-Aware Graph Convolutional Network

OCD Diagnosis with Multiple Spatial Similarity-Aware Learnin...

引用

iEEE international Conference on Bioinformatics and Biomedicine (BiBM)

作者： Yu Liang Chen Zhao Tianfu Wang Ziwen Peng Peng Yang Baiying Lei School of Computer Science and Software Shenzhen University Shenzhen China Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Shenzhen China Center for the Study of Applied Psychology South China Normal University Guangzhou China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Obsessive-Compulsive Disorder (OCD) is a hereditary mental illness, and unaffected first-degree relative (UFDR) is also at high risk. This study constructed a framework based on traditional machine learning and deep learning methods to identify OCD and UFDR. Specifically, we propose Multiple Spatial Similarity-Aware Learning (MSSL) models to construct Brain Functional Connectivity Networks (BFCNs) and use Diffusion Structure-Aware Graph Convolutional Network (DSAGCN) for feature learning. Two regularization terms are added to the MSSL model, one is to limit the similarity of functional connectivity of adjacent brain regions, and the other is to constrain the similarity of signals in adjacent brain regions. in this strategy, redundant information can be removed while constructing the interrelationships of various brain regions, which can reflect the interrelationships between brain *** graph diffusion is introduced to the DSAGCN model, which can not only solve the edge noise problem caused by the graph structure constructed by the custom adjacency matrix but also enrich the node features by using the position information of the nodes on the reconstructed graph *** framework has been validated on our dataset collected from local hospitals, and the experimental results show that our proposed method outperforms the state-of-the-art.

关键词： Representation learning Deep learning Graph convolutional networks Hospitals Noise Brain modeling Feature extraction Data mining Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Studying Risks of Hybrid Reengineering on Air-Transportation Systems Management “A Case Study on Jordanian Civil Aviation Regulatory Commission (CARC)”

Studying Risks of Hybrid Reengineering on Air-Transportation...

引用

information Technology (ACiT)

作者： Al Refai Mohammed N. Taani M.K. K. Ahmed Ali Otoom Ghassan Samara Hanandeh E. S Hayel Khafajeh Software Engineering Dep. Zarqa University Zarqa Jordan Cybersecurity and Cloud Computing Dep. Applied Science Private University Amman Jordan Department of Computer Science Zarqa University Zarqa Jordan Artificial Intelligence Dep. Zarqa University Zarqa Jordan

This study examines decision-making in software re-engineering within businesses, focusing on the challenges and considerations involved. Financial constraints, time, and staff efforts are critical factors in these decisions. The study identifies difficulties faced by top-level management with legacy systems, existing systems, underused systems, and packaged software due to user resistance and customer dissatisfaction. The primary goal of the study is to assess the importance of software quality factors, especially from the users' perspective, in making re-engineering decisions. it uses the iSO 9126 Model to analyze quality elements in the case study software, aiming to provide guidance for deciding whether to proceed with re-engineering. The study explores functionality, reliability, usability, efficiency, maintainability, and portability as factors influencing re-engineering decisions, based on the iSO 9126 model. To understand user interactions and program performance, the study used unstructured participant observation in the case study software, highlighting the challenges faced by top management due to user resistance. These findings were further confirmed through face-to-face interviews with software users and department employees, offering insights into their perspectives on software quality elements. The results reveal that, despite some flaws, the system has valuable features and capabilities. Most employees express a desire to undergo re-engineering to enhance service quality, align with iSO 9126 standards, and leverage the expertise of competent staff for re-engineering activities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Prediction of Fuel Consumption and Carbon Emissions in Light-Duty Vehicles using Convolutional Recurrent imputation Network

Enhanced Prediction of Fuel Consumption and Carbon Emissions...

引用

international Conference on computer, Electrical & Communication engineering (iCCECE)

作者： T. Lalitha Jerzy Ryszard Szymański Marta Żurek-Mortka Mithileysh Sathiyanarayanan K. R. Srilekha Computer Science School of Information Science Presidency University Bengaluru Karnataka India Department of Electrical Drives and Industrial Electronics Faculty of Transport Electrical Engineering and Computer Sciences Casimir Pulaski University of Radom Poland Europe Lukasiewicz Research Network Institute for Sustainable Technologies Kazimierza Pułaskiego Radom Poland Europe MIT Square London I M.Tech Integrated(Software Engineering) VIT University Vellore Tamilnadu India

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

Fuel utilization and emission estimation are essential for assessing the consequence of materials and strict emission control measures due to the startling rate of weather changes. The world's socioeconomic issues are significantly impacted by the growing worldwide average temperature and its effects on climate change. The melting of the polar ice caps, that is a direct result of this rise, leads to a number of other problems, such as the polar animal’s death, coastal flooding, and exposure to bacteria and earliest microorganisms that are frozen in the snow and could cause many more global pandemics and invisible illnesses. in this paper, Enhanced Prediction of Fuel Consumption and Carbon Emissions in Light-Duty Vehicles using Dynamic Graph Convolutional Recurrent imputation Network (EP-FCCE-DGCRiN) are proposed.. The effectiveness of the EP-FCCE-DGCRiN technique is compared to other existing methods. This research offers evidence-based suggestions to lessen the environmental effects of vehicles for both manufacturers and consumers depending upon the outcomes of the Descriptive Statistics analysis.

关键词： Temperature measurement Pandemics Snow Sea measurements Carbon dioxide imputation Fuels Vehicle dynamics Socioeconomics Meteorology

来源：评论

学校读者我要写书评

暂无评论

introduction

Lecture Notes in Electrical Engineering

引用

Lecture Notes in Electrical engineering 2024年 1110 LNEE卷

作者： Bellotti, Francesco Grammatikakis, Miltos D. Mansour, Ali Roch, Massimo Ruo Seepold, Ralf Solanas, Agusti Berta, Riccardo University of Genoa Genoa Italy Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Greece Lab-STICC CNRS U MR 6285 École nationale supérieure de techniques avancées Bretagne Brest France Department of Electronics and Telecommunications Politecnico di Torino Turin Italy Department of Computer Science HTWG Konstanz-University of Applied Sciences Konstanz Germany Department of Computer Engineering and Mathematics Universitat Rovira i Virgili Tarragona Catalonia Spain

来源：评论

学校读者我要写书评

暂无评论

EPPR: Blockchain for educational record sharing and recommendation using the Ethereum platform

EPPR: Blockchain for educational record sharing and recommen...

引用

作者： Alkouz, Akram HajYasien, Ahmed Alarabeyyat, Abdulsalam Samara, Khalid Al-Saleh, Mohammed i. Computer Information Sciences Higher Colleges of Technology Abu Dhabi United Arab Emirates Software Engineering Department Faculty of Prince Abdullah Bin Ghazi of Information Technology Al-Balqa' Applied University As-Salt Jordan Department of Computer Science Jordan University of Science and Technology Al Ramtha Irbid Jordan

There has been a great deal of discussion of the challenges on privacy of Educational Professional Personal Record (EPPR). Therefore, it is required to reassess the current models, in which various parties generate, exchange and observe a huge amount of personal data with regard to EPPR. Ethereum blockchain has shown that trusted, auditable transactions are detectible using a decentralised network of nodes. in this paper, we propose a novel decentralised framework to manage EPPR using Ethereum blockchain. The framework provides the owner of the EPPR a comprehensive immutable log and accessibility to their educational records across the educational record editors and consumers. Furthermore, it provides a recommender engine to endorse skills and competencies to the education record owners and similar candidates for educational records editors and consumers. The aim of the proposed framework is to enable educational stakeholders to participate in the network as blockchain miners rewarded by pseudonymised data. Copyright © 2021 inderscience Enterprises Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Security Risk Assessment Methodologies in The internet of Things: Survey and Taxonomy

Security Risk Assessment Methodologies in The Internet of Th...

引用

iEEE international Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： imad Yassine Talal Halabi Martine Bellaiche Computer and Software Engineering Polytechnique Montréal Quebec Canada Applied Computer Science University of Winnipeg Manitoba Canada

ISBN: (纸本)9781665478373

internet of Things (ioT) is the next-generation internet paradigm where billions of smart objects embedded with software and sensing capabilities are connected to the backbone network. ioT has applications in many fields such as healthcare, manufacturing, commerce, agriculture, energy production, and transportation. The advent of industry 4.0 has enabled the democratization of ioT deployment and the emergence of innovative business models. However, ioT systems carry numerous security and privacy risks. Traditional security risk assessment methodologies cannot be effectively applied in the ioT context, because they do not necessarily take into account the complexity and dynamics of ioT. This paper presents a survey of security risk assessment methodologies for ioT to aid security researchers, policymakers, and stakeholders in developing novel risk assessment frameworks that are more fit for ioT. The paper reviews various security standards, industry best practices, and security controls related to ioT security assessment, then proposes a taxonomy of risk assessment methodologies. This will help identify the gaps and pave the way for future research to improve the security and resilience of ioT systems by putting more emphasis on the high presence of zero-day vulnerabilities and the role that Artificial intelligence will play in threat assessment.

关键词： Privacy Taxonomy Fourth industrial Revolution Security Risk management internet of Things Standards

来源：评论

学校读者我要写书评

暂无评论

Conventional/Phase Shift Dual Drive Mach-Zehnder Modulation Measured Type Based Radio over Fiber Systems

引用

Journal of Optical Communications 2024年第s1期45卷 s123-s131页

作者： Amiri, i.S. Rashed, Ahmed Nabih Zaki Rahman, Ziaur Paul, Bikash Kumar Ahmed, Kawsar Computational Optics Research Group Advanced Institute of Materials Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Applied Sciences Ton Duc Thang University Ho Chi Minh City Viet Nam Electronics and Electrical Communications Engineering Department Faculty of Electronic Engineering Menoufia University Menouf32951 Egypt School of Computer Science and Software Engineering RMIT University 414-418 Swanston Street MelbourneVIC3000 Australia Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Santosh Tangail1902 Bangladesh Group of Bio-photomatiχ Mawlana Bhashani Science and Technology University Santosh Tangail1902 Bangladesh Department of Software Engineering Daffodil International University Sukrabad Dhanmondi Dhaka1207 Bangladesh

This work clarified the conventional/phase shift dual Mach-Zehnder modulation measured technique for upgrading radio over fiber (ROF) systems. Four levels of pulse amplitude modulation and non-return to zero code scheme are employed in different previous studies for upgrading ROF systems. The possible transmission distance is extended to 150 km and a bit rate of 40 Gb/s for achieved acceptable max. Q factor of 13.7498 and minimum bit error rates of 1.82×10-43. The total optical received power is measured at fiber cable length for maximum distance. Also, in the same way, the signal power levels are measured after fiber optic cable and avalanche photo detector optical receiver. The proposed model has presented the enhancement percentage ratio of 13.654% over the previous models in signal quality enhancement. © 2020 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Q factor measurement

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：