检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wu, Xingfang Li, Heng Khomh, Foutse Department of Computer Engineering and Software Engineering Polytechnique Montreal MontrealQC Canada

Logs are an essential source of information for people to understand the running status of a software system. Due to the evolving modern software architecture and maintenance methods, more research efforts have been devoted to automated log analysis. In particular, machine learning (ML) has been widely used in log analysis tasks. In ML-based log analysis tasks, converting textual log data into numerical feature vectors is a critical and indispensable step. However, the impact of using different log representation techniques on the performance of the downstream models is not clear, which limits researchers and practitioners’ opportunities of choosing the optimal log representation techniques in their automated log analysis workflows. Therefore, this work investigates and compares the commonly adopted log representation techniques from previous log analysis research. Particularly, we select six log representation techniques and evaluate them with seven ML models and four public log datasets (i.e., HDFS, BGL, Spirit and Thunderbird) in the context of log-based anomaly detection. We also examine the impacts of the log parsing process and the different feature aggregation approaches when they are employed with log representation techniques. From the experiments, we provide some heuristic guidelines for future researchers and developers to follow when designing an automated log analysis workflow. We believe our comprehensive comparison of log representation techniques can help researchers and practitioners better understand the characteristics of different log representation techniques and provide them with guidance for selecting the most suitable ones for their ML-based log analysis workflow. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Studying Logging Practice in Machine Learning-based Applications

arXiv

引用

arXiv 2023年

作者： Foalem, Patrick Loic Khomh, Foutse Li, Heng Department of Computer Engineering and Software Engineering Polytechnique Montreal MontrealQC Canada

Logging is a common practice in traditional software development. Several research works have been done to investigate the different characteristics of logging practices in traditional software systems (e.g., Android applications, JAVA applications, C/C++ applications). Nowadays, we are witnessing more and more development of Machine Learning-based applications (ML-based applications). Today, there are many popular libraries that facilitate and contribute to the development of such applications, among which we can mention: Pytorch, Tensorflow, Theano, MXNet, Scikit-Learn, Caffe, and Keras. Despite the popularity of ML, we don’t have a clear understanding of logging practices in ML applications. In this paper, we aim to fill this knowledge gap and help ML practitioners understand the characteristics of logging in ML-based applications. In particular, we conduct an empirical study on 110 open-source ML-based applications. Through a quantitative analysis, we find that logging practice in ML-based applications is less pervasive than in traditional applications including Android, JAVA, and C/C++ applications. Furthermore, the majority of logging statements in ML-based applications are in info and warn levels, compared to traditional applications where info is the majority of logging statement in C/C++ application and debug, error levels constitute the majority of logging statement in Android application. We also perform a quantitative and qualitative analysis of a random sample of logging statements to understand where ML developers put most of logging statements and examine why and how they are using logging. These analyses led to the following observations: (i) ML developers put most of the logging statements in model training, and in non-ML components. (ii) Data and model management appear to be the main reason behind the introduction of logging statements in ML-based applications. Indeed, ML developers use logging statements to keep track of the different stages of d

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Bug Characteristics in Quantum software Ecosystem

SSRN

引用

SSRN 2023年

作者： El Aoun, Mohamed Raed Li, Heng Khomh, Foutse Tidjon, Lionel Department of Computer Engineering and Software Engineering Polytechnique Montreal MontrealQC Canada

Recent advancements in quantum computing, exemplified by IBM's quantum computers, underscore the importance of quantum software. Differing fundamentally from classical programming, quantum programming's probabilistic state and inherent error-prone nature due to quantum instabilities pose unique challenges. This study investigates bug characteristics in quantum software projects to inform effective testing and debugging strategies. We analyzed bug reports from 125 quantum software projects on GitHub and found them more error-prone and costly to rectify compared to classical software. Key areas where bugs manifested include the compiler, gate operation, and state preparation components. The predominant bug types are Program anomaly, Configuration, and Data type & structure bugs. A notable challenge in quantum software development is the absence of comprehensive quantum computation libraries and specific quantum gate operation definitions. Additionally, there's a demand for dedicated data manipulation libraries akin to Numpy for quantum computing. Our insights spotlight areas for future research, emphasizing the need for specialized debugging tools for quantum circuits. © 2023, The Authors. All rights reserved.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Faithfulness measurable masked language models 24

Faithfulness measurable masked language models

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Andreas Madsen Siva Reddy Sarath Chandar Mila Montreal Canada and Computer Engineering and Software Engineering Department Polytechnique Montreal Montreal Canada Mila Montreal Canada and Computer Science and Linguistics McGill University Montreal Canada and Facebook CIFAR AI Chair Mila Montreal Canada and Computer Engineering and Software Engineering Department Polytechnique Montreal Montreal Canada and Canada CIFAR AI Chair

A common approach to explaining NLP models is to use importance measures that express which tokens are important for a prediction. Unfortunately, such explanations are often wrong despite being persuasive. Therefore, it is essential to measure their faithfulness. One such metric is if tokens are truly important, then masking them should result in worse model performance. However, token masking introduces out-of-distribution issues, and existing solutions that address this are computationally expensive and employ proxy models. Furthermore, other metrics are very limited in scope. This work proposes an inherently faithfulness measurable model that addresses these challenges. This is achieved using a novel fine-tuning method that incorporates masking, such that masking tokens become indistribution by design. This differs from existing approaches, which are completely model-agnostic but are inapplicable in practice. We demonstrate the generality of our approach by applying it to 16 different datasets and validate it using statistical in-distribution tests. The faithfulness is then measured with 9 different importance measures. Because masking is in-distribution, importance measures that themselves use masking become consistently more faithful. Additionally, because the model makes faithfulness cheap to measure, we can optimize explanations towards maximal faithfulness; thus, our model becomes indirectly inherently explainable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Normal and Resilient Mode FPGA-based Access Gateway Function Through P4-generated RTL

Normal and Resilient Mode FPGA-based Access Gateway Function...

引用

International Workshop on Design of Reliable Communication Networks (DRCN)

作者： Mostafa Abbasmollaei Tarek Ould-Bachir Yvon Savaria Department of Computer and Software Engineering Department of Electrical Engineering Polytechnique Montréal Montreal Canada

ISBN: (数字)9798350348972

ISBN: (纸本)9798350348989

Customizing packet processing is crucial in the evolving network landscape, especially with the rise of 5G telecommunications and beyond. software-Defined Networking and programmable data planes, powered by the P4 language and FPGA-based platforms, offer dynamic network customization that can be used to implement resilient networks. With their high performance and programmability, FPGAs present cost-effective alternatives for diverse network applications, including offloading packet processing from servers. This paper introduces a configurable FPGA-based data plane implementing the Access Gateway Function (AGF). It offers a resilient operating mode to enhance network reliability and availability. The paper leverages the P4 language and the VitisNetP4 Intellectual Property to create RTL streams, enabling AGF on a pure FPGA target. The reported experimental results demonstrate that the proposed architecture can support 50K user flows with a resource utilization lower than 15% of that available in an Ultrascale+ FPGA (xcu280-fsvh2892-21-e). This leaves massive logic resources available to incorporate fault mitigation techniques and spare streams needed to enhance resiliency. Moreover, the presented workflow maintains an average latency of approximately 9 microseconds for each downstream or upstream packet.

关键词： 5G mobile communication Logic gates Telecommunications Telecommunication network reliability Servers Resource management software defined networking

来源：评论

学校读者我要写书评

暂无评论

Motivating Users to Attend to Privacy: A Theory-Driven Design Study

arXiv

引用

arXiv 2024年

作者： Shiri, Varun Xiong, Maggie Cheng, Jinghui Guo, Jin L.C. Department of Computer and Software Engineering Polytechnique Montreal MontrealQC Canada School of Computer Science McGill University MontrealQC Canada

In modern technology environments, raising users’ privacy awareness is crucial. Existing efforts largely focused on privacy policy presentation and failed to systematically address a radical challenge of user motivation for initiating privacy awareness. Leveraging the Protection Motivation Theory (PMT), we proposed design ideas and categories dedicated to motivating users to engage with privacy-related information. Using these design ideas, we created a conceptual prototype, enhancing the current App Store product page. Results from an online experiment and follow-up interviews showed that our design effectively motivated participants to attend to privacy issues, raising both the threat appraisal and coping appraisal, two main factors in PMT. Our work indicated that effective design should consider combining PMT components, calibrating information content, and integrating other design elements, such as visual cues and user familiarity. Overall, our study contributes valuable design considerations driven by the PMT to amplify the motivational aspect of privacy communication. Copyright © 2024, The Authors. All rights reserved.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Real-Time Simultaneous Localization and Mapping with LiDAR Intensity

Real-Time Simultaneous Localization and Mapping with LiDAR I...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Wenqiang Du Giovanni Beltrame Department of Computer Engineering and Software Engineering Polytechnique Montreal University of Montreal Montreal QC Canada

We propose a novel real-time LiDAR intensity image-based simultaneous localization and mapping method, which addresses the geometry degeneracy problem in un-structured environments. Traditional LiDAR-based front-end odometry mostly relies on geometric features such as points, lines and planes. A lack of these features in the environment can lead to the failure of the entire odometry system. To avoid this problem, we extract feature points from the LiDAR-generated point cloud that match features identified in LiDAR intensity images. We then use the extracted feature points to perform scan registration and estimate the robot ego-movement. For the back-end, we jointly optimize the distance between the corresponding feature points, and the point to plane distance for planes identified in the map. In addition, we use the features extracted from intensity images to detect loop closure candidates from previous scans and perform pose graph optimization. Our experiments show that our method can run in real time with high accuracy and works well with illumination changes, low-texture, and unstructured environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TraceLens: Early Detection of software Anomalies Using Critical Path Analysis 25

TraceLens: Early Detection of Software Anomalies Using Criti...

引用

Companion of the 16th ACM/SPEC International Conference on Performance engineering

作者： Masoumeh Nourollahi Amir Haghshenas Michel Dagenais Department of Computer and Software Engineering École Polytechnique de Montréal Montreal QC Canada

ISBN: (纸本)9798400711305

Runtime smell detection in software systems, particularly through system call analysis, has garnered significant attention in recent years. Although various machine learning techniques have been employed to enhance detection accuracy and reduce false positives, limited focus has been given to their practical application in early real-time anomaly detection. To address this gap, we propose a deep learning-based approach, called TraceLens, designed for the early detection of performance-related issues in software systems. Unlike traditional methods that rely on system call data, our approach leverages critical path analysis, enabling more efficient and targeted anomaly detection. Experimental results demonstrate that this approach achieves detection performance comparable to methods that use system calls, while significantly improving data collection efficiency. In addition, the critical path dataset highlights software dependencies, both internal and external, providing deeper insight into the dynamic behavior of software systems.

关键词： anomaly detection

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

IoT-Based Disaster Detection Model Using Social Networks and Machine Learning 4

IoT-Based Disaster Detection Model Using Social Networks and...

引用

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

作者： Alfalqi, Khalid Bellaiche, Martine Polytechnique de Montreal Computer and Software Engineering Department Montreal Canada

ISBN: (纸本)9780738131702

The internet of things is the revolutionary concept of the traditional internet so that all the physical objects or devices can connect to the internet or each other for sharing information or perform specific functions through the network. Social network usage in disaster detection models can play an essential role by sharing information and update the user's status when a disaster occurs. Besides, big data has demonstrated its value as a tool to aid and mitigate any disaster by processing a massive amount of data in a short period. This paper discusses that it is essential to have a proper disaster detection system to respond quickly once disasters occur. Besides, it proposes a novel method to detect the exact location of a disaster by utilizing a Snapchat map. Moreover, IoT, social networks and big data can accelerate the disaster detection system if they use together;by using data from the social networks and data from IoT devices, we can manage, monitor, analyze and detect disaster. The main objective of this paper is to propose a new and efficient IoT-based disaster Detection model (DDM) to find the exact location of a disaster for the collected data from social networks (SN) and other IoT devices using big data (BD) and machine learning (ML). © 2021 IEEE.

关键词： Big data

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：