检索结果-内蒙古大学图书馆

6th International Conference on computer Science and engineering, UBMK 2021

作者： Yurtseven, Ilke Bagriyanik, Selami Ayvaz, Serkan Big Data Analytics Bahçeşehir University Istanbul Turkey Software Engineering Department Nisantasi University Istanbul Turkey Computer Engineering Department Yildiz Technical University Istanbul Turkey

ISBN: (纸本)9781665429085

With significant usage of social media to socialize in virtual environments, bad actors are now able to use these platforms to spread their maUcious activities such as hate speech, spam, and even phishing to very large crowds. Especially, Twitter is suitable for these types of activities because it is one of the most common social media platforms for microblogging with millions of active users. Moreover, since the end of 2019, Covid-19 has changed the lives of individuals in many ways. While it increased social media usage due to free time, the number of cyber-attacks soared too. To prevent these activities, detection is a very crucial phase. Thus, the main goal of this study is to review the state-of-art in the detection of malicious content and the contribution of AI algorithms for detecting spam and scams effectively in social media. © 2021 IEEE

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Exploring Large Language Models for Natural Language Processing

Exploring Large Language Models for Natural Language Process...

引用

International Conference on Computational and Characterization Techniques in engineering & Sciences (CCTES)

作者： Ayodeji Olalekan Salau Esuku Dickson Emmanuel Ahmed Alemran Chandra Kumar Dixit Sepiribo Lucky Braide Department of Electrical/Electronics and Computer Engineering College of Engineering Afe Babalola University AdoEkiti Nigeria Department of Software Engineering Medicine College Misan University Iraq Institute of Engineering and Technology Dr. Shakuntala Misra National Rehabilitation University Lucknow Uttar Pradesh India Department of Electrical and Electronics Engineering Rivers State University Port Harcourt Nigeria

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

Large language models have become increasingly popular in natural language processing due to their ability to generate high-quality text and perform various language-related tasks. However, there are growing concerns regarding the ethical implications of these models, particularly concerning potential misuse and bias. This paper delves into the advancements and limitations of large language models for Natural Language Processing (NLP), exploring their ability to improve language understanding and generation. The paper also examines the challenges these models face in terms of computational power and model interpretability. Finally, the paper provides recommendations for future research to address these concerns, ensuring the responsible development of large language models and their integration into the future of NLP and Artificial Intelligence (AI).

关键词： Economics Ethics Data privacy Large language models Computational modeling Biological system modeling Training data Natural language processing Security Faces

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Higher Education using RF and SVM for Pedagogical Enhancement

Machine Learning in Higher Education using RF and SVM for Pe...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Fateh Bahadur Kunwar Satyajee Srivastava R Dhivya Monika Gulati Taruna Anand D Antony Arul Raj Department of Computer Science and Engineering Geetanjali Institute of Technical Studies Udaipur India Department of Computer Science and Engineering School of Engineering and Technology Manav Rachna International Institute of Research and Studies Faridabad India Department of Information Technology M.Kumarasamy College of Engineering Karur India MMIM Maharishi Markandeshwar (Deemed to be University) Ambala India Department of Humanities and Social Sciences Graphic Era (Deemed to be) University Dehradun India Department of Software Systems PSG College of Arts & Science Coimbatore India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

AI's revolutionary potential in higher education is examined in this proposal, including how it could revolutionize teaching, learning, administration, and research. Adaptive learning platforms, intelligent tutoring systems, and virtual learning assistants may change how students learn by improving engagement, providing quick feedback, and enabling tailored learning. The suggested process includes preprocessing, feature extraction, and model training. Preprocessing involves de-anonymizing, tokenizing, and removing punctuation, spaces, and numbers before analysis. The linear transformation method PCA extracts features. Training the systems uses the RF -SVM approach, which combines the advantages of RF and SVM. The suggested RF -SVM model beats two RF and SVM models with an average accuracy of 90.39 *** improves resource use, strategic decision-making, and research capacity in university management. The RF-SVM model's success in academia highlights the practicality of AI-driven solutions.

关键词： Support vector machines Radio frequency Training Accuracy Education Symbols Feature extraction Tokenization Integrated circuit modeling Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Aligning Academic with Industrial Needs: Investigating DevOps 24

Aligning Academic with Industrial Needs: Investigating DevOp...

引用

Proceedings of the 28th International Conference on Evaluation and Assessment in software engineering

作者： Saima Rafi Muhammad Azeem Akbar Sajjad Mahmood School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh United Kingdom Software Engineering LUT University Finland Information and Computer Science Department King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia

ISBN: (纸本)9798400717017

Over recent years, DevOps has gained more attention within the software industry, owing to its pivotal role in facilitating continuous software delivery. The significant demand for DevOps practitioners necessitates substantial adjustments in conventional software engineering courses in higher educational institutions. Recent studies have highlighted DevOps principles, challenges, best practices, and tools to facilitate continuous delivery and deployment pipelines from an industrial perspective. As numerous universities are now introducing courses related to DevOps for students majoring in software engineering and computer science, this high demand for DevOps practitioners requires non-trivial adjustments in traditional software engineering courses and educational methodologies, including practices for teaching DevOps, training in DevOps, the level to which DevOps is currently taught and applied to measure the gap between teaching practices compared to industrial requirements. Our vision paper aims to highlight the crucial need for updated policies and tools to improve DevOps training in higher education, providing guidelines. By aligning academic curricula with industry standards, we can ensure students are better equipped for the demands of the workforce, fostering a seamless transition from academia to industry and promoting innovation in software engineering practices.

关键词： Challenges DevOps Guidelines Industry Practices Teaching

来源：评论

学校读者我要写书评

暂无评论

Delay-optimized Topology Management of a Wirelessly Networked Disaster Area

Delay-optimized Topology Management of a Wirelessly Networke...

引用

IEEE International Symposium on Embedded Multicore Socs (MCSoC)

作者： Michael Conrad Meyer Yu Wang Department of Computer Science and Electrical Engineering Eastern Washington University Spokane WA USA Software Research and Development Division TriOrb Inc Kitakyushu Japan

Major disasters can often destroy communication networks. To address this issue, companies such as NTT have developed movable base stations (MBSs), which can be easily deployed to construct an emergency communication network. A sample of how MBSs can be connected to form a network can be seen in Fig. 1. However, these networks have performance drawbacks. In order to improve their performance, we propose an algorithm that determines the best way for the MBSs to be connected. The proposed model and algorithm resulted in a reduction in the overall delay and average delay of the system compared to the greedy algorithm. For the realistic constraints, the genetic algorithm (GA) was so successful that its worst-case delay almost matched the average delay of the greedy algorithm. The simulations did show that for extremely high communication rates or extremely slow processing rates, the impact of the topology on the system delay was minimal, and thus both algorithms had similar results. This is because the system bottleneck in these cases is the processing times. However, for the realistic network constraints, the GA outperforms the greedy algorithm by approximately 40% in the fog system and 90% in the cloud system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding the Helpfulness of Stale Bot for Pull-based Development: An Empirical Study of 20 Large Open-Source Projects

arXiv

引用

arXiv 2023年

作者： Khatoonabadi, Sayedhassan Costa, Diego Elias Mujahid, Suhaib Shihab, Emad Lab Department of Computer Science & Software Engineering Concordia University MontrealQC Canada MontrealQC Canada Mozilla Corporation MontrealQC Canada

Pull Requests (PRs) that are neither progressed nor resolved clutter the list of PRs, making it difficult for the maintainers to manage and prioritize unresolved PRs. To automatically track, follow up, and close such inactive PRs, Stale bot was introduced by GitHub. Despite its increasing adoption, there are ongoing debates on whether using Stale bot alleviates or exacerbates the problem of inactive PRs. To better understand if and how Stale bot helps projects in their pull-based development workflow, we perform an empirical study of 20 large and popular open-source projects. We find that Stale bot can help deal with a backlog of unresolved PRs as the projects closed more PRs within the first few months of adoption. Moreover, Stale bot can help improve the efficiency of the PR review process as the projects reviewed PRs that ended up merged and resolved PRs that ended up closed faster after the adoption. However, Stale bot can also negatively affect the contributors as the projects experienced a considerable decrease in their number of active contributors after the adoption. Therefore, relying solely on Stale bot to deal with inactive PRs may lead to decreased community engagement and an increased probability of contributor abandonment. Copyright © 2023, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents

arXiv

引用

arXiv 2024年

作者： Ning, Kaiwen Chen, Jiachi Zhang, Jingwen Li, Wei Wang, Zexu Feng, Yuming Zhang, Weizhe Zheng, Zibin The School of Software Engineering Sun Yat-Sen University Peng Cheng Laboratory China The School of Software Engineering Sun Yat-Sen University China The School of Computer Science and Technology Harbin Institute of Technology China Peng Cheng Laboratory China The Department of New Networks Peng Cheng Laboratory China

Artificial intelligence (AI) agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in Large Language Models (LLMs) have introduced a transformative paradigm for AI agents, enabling them to interact with external resources and tools through prompt techniques. This advancement has significantly extended the capabilities of LLMs, positioning LLM-based AI Agents as an important research area. In such agents, the workflow integrates developer-written code, which manages framework construction and logic control, with LLM-generated natural language that enhances dynamic decision-making and interaction. However, discrepancies between developer-implemented logic and the dynamically generated content of LLMs in terms of behavior and expected outcomes can lead to defects, such as tool invocation failures and task execution errors. These issues introduce specific risks, leading to various defects in LLM-based AI Agents, including service interruptions and incorrect output. Despite the importance of these issues, there is a lack of systematic work that focuses on analyzing LLM-based AI Agents to uncover defects in their code. To address this gap, we present the first study focused on identifying and detecting defects in LLM Agents. We collected and analyzed 6, 854 relevant posts from StackOverflow to define and classify eight types of agent defects. For each defect type, we provided detailed descriptions and illustrated with an example. Then, we designed a static analysis tool, named Agentable, to detect the defined defects. Agentable leverages Code Property Graphs (CPGs) and LLMs to analyze Agent workflows by efficiently identifying specific code patterns and analyzing natural language descriptions. To evaluate Agentable, we constructed two datasets: AgentSet, which consists of 84 real-world Agent projects, and AgentTest, which contains 78 Agent projects specifically designed to include various types of defect

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Earth observation payloads on-board a 3U CubeSat and their scientific purpose for monitoring aerosols and surface temperature hotspots 74

Earth observation payloads on-board a 3U CubeSat and their s...

引用

74th International Astronautical Congress, IAC 2023

作者： Vlassov, David Hudon-Castillo, Yianni Chazbek, Rachad Restrepo-Vermette, Joël Lord-Quintric, Rémi Perraton-Elorza, Amauri Nomezine, Anthony Beltrame, Giovanni 2500 Chem. de Polytechnique MontréalQCH3T 1J4 Canada Computer and Software Engineering Department 2500 Chem. de Polytechnique MontréalQCH3T 1J4 Canada

The technical student society PolyOrbite from the university of Polytechnique Montreal in Québec, Canada is designing a nanosatellite mission with a homemade 3U CubeSat that will observe the Earth's surface with the help of infrared and visible spectrum cameras. These payloads will give information on aerosols and various surface temperature hotspots on earth. The CubeSat will be able to monitor cities, agricultural lands, wildfires, glaciers and more. The main goal would be to monitor Canadian grounds and work with scientists and students in various fields to help push knowledge about our planet. Besides having a scientific purpose, the CubeSat will also be used for technological demonstration. Two innovative technologies for space missions will be tested: Artificial intelligence with on earth machine learning and model sampling, and compressed sensing. To achieve these goals, the project objectives split into two categories: scientific and engineering. The scientific part will consist in making the link between scientists and engineers. The team will need to know the studied targeted area and what information to get from it. The received data will have to be analysed, making it important to design an easy-to-use platform that will encompass needed information. The engineering part consists of integrating payloads and new technologies into the CubeSat, the main challenges being: • Payload choice: Since budget and time are limited, choosing a cost-effective payload system will be mandatory. Commercial-use cameras are the number one options since they are less expensive than space grade equipment. • Payload calibration: Having a thermal payload, an adequate temperature calibration need to be done to minimize biases on temperature measurement and increase the scientific value of the data. Multiple calibration protocols will be done to assure this task. • Gathering data, filtering data and sending it to the ground station network: The data gathered from both payloads c

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lifelong Scalable Generative System via Online Maximum Mean Discrepancy 39

Lifelong Scalable Generative System via Online Maximum Mean ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Fei Bors, Adrian G. School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science University of York YorkYO10 5GH United Kingdom

ISBN: (纸本)157735897X

Diffusion-based models have been recently shown to be high-quality data generators. However, their performance severely degrades when training on non-stationary changing data distributions in an online manner, due to the catastrophic forgetting. In this paper, we propose enabling the diffusion model with a novel Dynamic Expansion Memory Unit (DEMU) methodology that adaptively creates new memory buffers, to be added to a memory system, in order to preserve information deemed critical for training the model. Having a selective memory unit is essential for training diffusion networks, which are expensive to train, especially when deployed in resource-constrained environments. A Maximum Mean Discrepancy (MMD) based expansion mechanism, that evaluates probabilistic distances between each of the previously defined memory buffers and the newly given data, and uses them as expansion signals, is employed for ensuring the diversity of information learning. We propose a new model expansion mechanism to automatically add new diffusion models as experts in a mixture system, which enhances the multi-domain image generation performance. Also a novel memory compaction approach is proposed to automatically remove statistically overlapping memory units, through a graph relationship evaluation, preventing the limitless expansion of DEMU. Comprehensive results show that the proposed approach performs better than the state-of-the-art. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Buffer storage

来源：评论

学校读者我要写书评

暂无评论

What You Print is Not What You Get Anymore: Man-in-The-Middle Attacks on Intellectual Property and Integrity of 3d Printers

SSRN

引用

SSRN 2023年

作者： Alkofahi, Hamza Alawneh, Heba Skjellum, Anthony Software Engineering Department Jordan University of Science and Technology Irbid Jordan Cybersecurity Department Jordan University of Science and Technology Irbid Jordan Computer Science and Engineering Department The University of Tennessee at Chattanooga ChattanoogaTN United States

Additive Manufacturing (AM) was originally invented to reduce the cost of the prototyping process. Overtime, the technology evolved to be faster, more accurate, and affordable. These factors, in addition to the potential use of AM in parts production, have helped rapidly drive the growth of AM in both industrial and personal uses. Thus, there is a concomitant demand to understand the cybersecurity implications of such systems. In our research, we present an in-depth security review of Stratasys Dimension Elite and show how manufacturers of such high-end 3D printers failed to protect the confidentiality and integrity of the printed 3D models. Revealing the intricate dimensions of cyber threats within the realm of AM and laying the foundation for understanding the multifaceted nature of attacks, offering insights into vulnerabilities and potential consequences. Moreover, we demonstrate three significant attacks. First, the Sniffing Attack demonstrates the interception and theft of 3D models during the printing process. Second, the Replacement Attack showcases the infiltration of the printing workflow, allowing the malicious substitution of a legitimate 3D model with a tampered version. Lastly, the Sabotaging Attack reveals the manipulation of a 3D model's internal structure during printing, highlighting risks to the printed objects' quality and functionality. By bringing to light these attacks, this research contributes not only to enhancing the security posture of Stratasys Dimension Elite but also to advancing the broader understanding of security challenges in additive manufacturing. © 2023, The Authors. All rights reserved.

关键词： 3D printing

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：