检索结果-内蒙古大学图书馆

15th Global Information Infrastructure and Networking Symposium, GIIS 2025

作者： Keyela, Patatchona Cherkaoui, Soumaya Polytechnique Montreal Computer Engineering and Software Engineering Dept. Montreal Canada

ISBN: (纸本)9798331520113

RAN slicing technology is a key aspect of the Open RAN paradigm, allowing simultaneous and independent provision of various services such as ultra-reliable low-latency communications (URLLC), enhanced mobile broadband (eMBB), and massive machine-type communications (mMTC) through virtual networks that share a single radio access infrastructure. Efficient resource allocation is crucial for RAN slicing, as each service has specific quality of service (QoS) requirements, and a balance between different services must be maintained. Although heuristic and reinforcement learning (RL) techniques have been explored to achieve efficient resource allocation, these approaches face notable limitations: heuristic algorithms face complexity issues that limit their effectiveness in large networks, RL solutions are constrained by their dependency on training data and struggle to adapt to new scenarios and environments. This paper proposes a framework that leverages quantum optimization techniques to optimize radio resource blocks allocation in Open RAN slicing for URLLC and eMBB services. We provide a classical problem formulation and the quantum implementation using the constrained quadratic model on Dwave quantum annealing platform, showcasing the potential of quantum optimization techniques to deliver in real-time optimal solutions for optimization problems in 5G and beyond networks. © 2025 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Learning-Based MRI Response Predictions from OCT Microvascular Models to Replace Simulation-Based Frameworks 28th

Learning-Based MRI Response Predictions from OCT Microvascu...

引用

28th Annual Conference on Medical Image Understanding and Analysis, MIUA 2024

作者： Rustamov, Jaloliddin Rustamov, Zahiriddin Badawi, Nadia Lesage, Frederic Zaki, Nazar Damseh, Rafat Department of Computer Science and Software Engineering United Arab Emirates University Al Ain United Arab Emirates Biomedical Engineering Institute Ecole Polytechnique de Montreal MontrealQC Canada

ISBN: (纸本)9783031669545

Computational quantification of magnetic resonance imaging (MRI) response from neurovascular structures is used to investigate potential biomarkers for different types of cerebrovascular deteriorations at the microscopic scale. Simulation-based MRI requires fully resolved microvascular structures, with geometric and physiological parameters, from tissue volumes captured using microscopic imaging modalities, e.g., optical coherence tomography (OCT). The preparation of such input models hinders large cohort studies and requires extensive manual effort. Here, we propose using 3D neural networks as an alternative learning-based solution over MRI simulation schemes. We trained state-of-the-art 3D neural networks to predict the spin echo (SE) MRI response from OCT microvascular volumes. By validating against simulated signals, our result demonstrates that the 3D ResNet-based regression network achieves a high accuracy to predict MRI signals with an average mean square error (MSE) 2 of 82.8% and explained variance score of 82.9%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Open RAN Slicing with Quantum Optimization

arXiv

引用

arXiv 2025年

作者： Keyela, Patatchona Cherkaoui, Soumaya Computer Engineering and Software Engineering Dept. Polytechnique Montreal Montreal Canada

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Open RAN Slicing with Quantum Optimization

Open RAN Slicing with Quantum Optimization

引用

International Global Information Infrastructure Symposium (GIIS)

作者： Patatchona Keyela Soumaya Cherkaoui Computer Engineering and Software Engineering Dept. Polytechnique Montreal Montreal Canada

ISBN: (数字)9798331520113

ISBN: (纸本)9798331520120

关键词： Annealing Training data Open RAN Quality of service Reinforcement learning Ultra reliable low latency communication Quantum annealing Resource management Optimization Faces

来源：评论

学校读者我要写书评

暂无评论

Automated, Unsupervised, and Auto-parameterized Inference of Data Patterns and Anomaly detection

arXiv

引用

arXiv 2024年

作者： Qin, Qiaolin Li, Heng Merlo, Ettore Lamothe, Maxime Dept. of Computer and Software Engineering Polytechnique Montreal Montreal Canada

With the advent of data-centric and machine learning (ML) systems, data quality is playing an increasingly critical role for ensuring the overall quality of software systems. Data preparation, an essential step towards high data quality, is known to be a highly effort-intensive process. Although prior studies have dealt with one of the most impacting issues, data pattern violations, these studies usually require data-specific configurations (i.e., parameterized) or use carefully curated data as learning examples (i.e., supervised), relying on domain knowledge and deep understanding of the data, or demanding significant manual effort. In this paper, we introduce RIOLU: Regex Inferencer autO-parameterized Learning with Uncleaned data. RIOLU is fully automated, automatically parameterized, and does not need labeled samples. RIOLU can generate precise patterns from datasets in various domains, with a high F1 score of 97.2%, exceeding the state-of-the-art baseline. In addition, according to our experiment on five datasets with anomalies, RIOLU can automatically estimate a data column’s error rate, draw normal patterns, and predict anomalies from unlabeled data with higher performance (up to 800.4% improvement in terms of F1) than the state-of-the-art baseline, even outperforming ChatGPT in terms of both accuracy (12.3% higher F1) and efficiency (10% less inference time). A variant of RIOLU, with user guidance, can further boost its precision, with up to 37.4% improvement in terms of F1. Our evaluation in an industrial setting further demonstrates the practical benefits of *** Codes 68P01 © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A deep Intrusion detection System in Lambda Architecture Based on Edge Cloud Computing for IoT 4

A Deep Intrusion Detection System in Lambda Architecture Bas...

引用

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Alghamdi, Rubayyi Bellaiche, Martine Ecole Polytechnique de Montreal Computer and Software Engineering Department Montreal Canada

ISBN: (纸本)9780738131702

IoT devices enable a massive amount of data to be aggregated and analyzed for anomaly detection. The nature of heterogeneous devices introduces the challenge of collecting and handling these massive datasets to perform data analyses to discover cyber attacks in near real-time. However, the traditional IDS cannot deal with such a problem due to scalability limitations and insufficient storage and processing capabilities. Moreover, issues such as network bandwidth, real-time support, and security limit the power of cloud server-based IDSs. This paper presents an edge-cloud deep IDS model in Lambda architecture for IoT security to address these challenges. Our system decreases the training phase's time compared to traditional machine learning algorithms and increases the accuracy of true positive detected attacks. Furthermore, neural network layers lead deep learning to achieve better performance and flexibility compared to conventional machine learning. Our solution enables the detection of suspicious activities in real-time and allows to classify them by analyzing historical data in a batch process. © 2021 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Scalable Distributed Architecture for Trace Analysis

SSRN

引用

SSRN 2023年

作者： Tran, Quoc-Hao Dagenais, Michel R. Department of Computer and Software Engineering Ecole Polytechnique de Montreal MontrealQC Canada

Trace analysis is a powerful tool for troubleshooting with information from the production environment, especially with the rising complexity of software applications. Recent trends in favor of microservices and High-Performance Computing cluster architectures bring challenges in distributed tracing, both in terms of scalability and usability. Various tracing platforms like Jaeger and Prometheus were created to trace distributed systems, each of them focusing on solving a specific problem. Modern projects like Prometheus, come with a set of end-to-end tools for tracing, and offer powerful query capabilities into its trace database. However, the query & aggregation operators offered by these frameworks are tightly coupled to its ecosystem. Meanwhile, supporting external services, and developing custom operators, results in a trade-off that implies losing a large number of supported features. Our work offers a distributed tracing framework, based on existing solutions, with processing time as well as storage and memory scalability in mind. Furthermore, it provides a standard paradigm for developing new query operators with ease, without sacrificing useful features. The evaluation demonstrates that the proposed approach is feasible, flexible enough to support different trace types, and introduces a minimal overhead. This is important towards making distributed tracing more easily adopted for heterogeneous systems. © 2023, The Authors. All rights reserved.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

A Large-Scale Exploratory Study of Android Sports Apps in the Google Play Store

arXiv

引用

arXiv 2023年

作者： Chembakottu, Bhagya Li, Heng Khomh, Foutse Dept. of Computer and Software Engineering Polytechnique Montreal Canada

Context: Prior studies on mobile app analysis often analyze apps across different categories or focus on a small set of apps within a category. These studies either provide general insights for an entire app store which consists of millions of apps, or provide specific insights for a small set of apps. However, a single app category can often contain tens of thousands to hundreds of thousands of apps. For example, according to AppBrain, there are 46,625 apps in the "Sports" category of Google Play apps. Analyzing such a targeted category of apps can provide more specific insights than analyzing apps across categories while still benefiting many app developers interested in the category. Objective: This work aims to study a large number of apps from a single category (i.e., the sports category). Our work can provide two folds contributions: 1) identifying insights that are specific to tens of thousands of sports apps, and 2) providing empirical evidence on the benefits of analyzing apps in a specific category. Method: We perform an empirical study on over two thousand sports apps in the Google Play Store. We study the characteristics of these apps (e.g., their targeted sports types and main functionalities) through manual analysis, the topics in the user review through topic modeling, as well as the aspects that contribute to the negative opinions of users through analysis of user ratings and sentiment. Results: We identified sports apps that cover 16 sports types (e.g., Football, Cricket, Baseball) and 15 main functionalities (e.g., Betting, Betting Tips, Training, Tracking). We also extracted 14 topics from the user reviews, among which three are specific to sports apps (accuracy of prediction, up-to-dateness, and precision of tools). Finally, we observed that users are mainly complaining about the advertisements and quality (e.g., bugs, content quality, streaming quality) of sports apps. Conclusion: It is concluded that analyzing a targeted category of apps (e.g.,

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Human Action Recognition with Dynamic Feature Selection

Transformer-Based Human Action Recognition with Dynamic Feat...

引用

Canadian Conference on computer and Robot Vision, CRV

作者： Soufiane Lamghari Guillaume-Alexandre Bilodeau Nicolas Saunier Dept. of Computer and Software Engineering LITIV Polytechnique Montreal Montreal Canada Dept. of Civil Geological and Mining Eng. Polytechnique Montreal Montreal Canada

Human action recognition in videos is an important task of computer vision that aims to automatically recognize and classify human actions in video sequences. However, accurately recognizing human actions can be challenging due to the complexity and variability of human motion and appearance. In this paper, we propose ActiViT, a novel approach for human action recognition in videos based on a Transformer architecture. Unlike existing methods that rely on convolutional or recurrent layers, our model is entirely based on the Transformer encoder, enabling us to leverage valuable information in action image patches features. We demonstrate that by dynamically selecting key patches guided by specific human poses, our model learns informative features useful for distinguishing between different actions. Our experimental results on real-world datasets convincingly demonstrate the effectiveness of our model and the importance of selecting discriminative key poses for action recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Reversible Three-Phase Transformer Model for Energization Transients Based on Topological Remnant Flux Calculation 4

A Reversible Three-Phase Transformer Model for Energization ...

引用

4th Annual IEEE Kansas Power and Energy Conference, KPEC 2023

作者： Rezaei-Zare, Afshin Mostafaei, Mohsen Gras, Henry Martinez-Duro, Manuel Mahseredjian, Jean York University Dept. of Electrical Engineering and Computer Science TorontoONM3J 1P3 Canada Ecole Polytechnique de Montreal Dept. of Electrical Engineering MontrealQCH3T 1J4 Canada Electricite de France R&d Palaiseau91120 France

ISBN: (纸本)9798350335408

As a component in power systems, the power transformer plays an important role. Hence, precise modeling can provide useful information about transformer behavior in steady-state and transient conditions. Due to some limitations of available transformer modeling methods, especially in transients, a reversible three-phase transformer model is presented in this paper based on topological remnant flux calculation. In this model, the equivalent magnetic circuit is based on the duality principle. This concept facilitates the connection of an equivalent magnetic circuit to the leakage inductances. The two important factors for transformer energization modeling are air-core inductance and remnant fluxes in different core parts. The calculation of air-core inductance is explained in the paper comprehensively. The simulation results of the proposed topological model for a real 96 MVA, 410/6.8 kV power transformer with a shell-type core in EMTP software shows a nice match between simulated inrush currents with considering remnant flux and the measured ones. © 2023 IEEE.

关键词： Power transformers

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：