检索结果-内蒙古大学图书馆

Proceedings of the 38th IEEE/ACM International Conference on Automated software engineering

作者： Cheryl Lee Tianyi Yang Zhuangbin Chen Yuxin Su Michael R. Lyu Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China School of Software Engineering Sun Yat-sen University Zhuhai China. School of Software Engineering Sun Yat-sen University Zhuhai China

ISBN: (纸本)9798350329964

Ensuring the reliability and user satisfaction of cloud services necessitates prompt anomaly detection followed by diagnosis. Existing techniques for anomaly detection focus solely on real-time detection, meaning that anomaly alerts are issued as soon as anomalies occur. However, anomalies can propagate and escalate into failures, making faster-than-real-time anomaly detection highly desirable for expediting downstream analysis and intervention. This paper proposes Maat, the first work to address anomaly anticipation of performance metrics in cloud services. Maat adopts a novel two-stage paradigm for anomaly anticipation, consisting of metric forecasting and anomaly detection on forecasts. The metric forecasting stage employs a conditional denoising diffusion model to enable multi-step forecasting in an auto-regressive manner. The detection stage extracts anomaly-indicating features based on domain knowledge and applies isolation forest with incremental learning to detect upcoming anomalies. Thus, our method can uncover anomalies that better conform to human expertise. Evaluation on three publicly available datasets demonstrates that Maat can anticipate anomalies faster than real-time comparatively or more effectively compared with state-of-the-art real-time anomaly detectors. We also present cases highlighting Maat's success in forecasting abnormal metrics and discovering anomalies.

关键词： could computing

来源：评论

学校读者我要写书评

暂无评论

Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs 31

Idea23D: Collaborative LMM Agents Enable 3D Model Generation...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Chen, Junhao Li, Xiang Ye, Xiaojun Li, Chao Fan, Zhaoxin Zhao, Hao Tsinghua University China Tsinghua Shenzhen International Graduate School Tsinghua University China School of Software and Microelectronics Peking University China College of Computer Science Zhejiang University China College of Computer Science and Technology Harbin Engineering University China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing School of Artificial Intelligence Beihang University China

ISBN: (纸本)9798891761964

With the success of 2D diffusion models, 2D AIGC content has already transformed our lives. Recently, this success has been extended to 3D AIGC, with state-of-the-art methods generating textured 3D models from single images or text. However, we argue that current 3D AIGC methods still don't fully unleash human creativity. We often imagine 3D content made from multimodal inputs, such as what it would look like if my pet bunny were eating a doughnut on the table. In this paper, we explore a novel 3D AIGC approach: generating 3D content from IDEAs. An IDEA is a multimodal input composed of text, image, and 3D models. To our knowledge, this challenging and exciting 3D AIGC setting has not been studied before. We propose the new framework Idea23D, which combines three agents based on large multimodal models (LMMs) and existing algorithmic tools. These three LMM-based agents are tasked with prompt generation, model selection, and feedback reflection. They collaborate and critique each other in a fully automated loop, without human intervention. The framework then generates a text prompt to create 3D models that align closely with the input IDEAs. We demonstrate impressive 3D AIGC results that surpass previous methods. To comprehensively assess the 3D AIGC capabilities of Idea23D, we introduce the Eval3DAIGC-198 dataset, containing 198 multimodal inputs for 3D generation tasks. This dataset evaluates the alignment between generated 3D content and input IDEAs. Our user study and quantitative results show that Idea23D significantly improves the success rate and accuracy of 3D generation, with excellent compatibility across various LMM, Text-to-Image, and Image-to-3D models. Code and dataset are available at https://***/. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Accelerating the Task Activation and Data Communication for Dataflow Computing 22

Accelerating the Task Activation and Data Communication for ...

引用

Workshop Proceedings of the 51st International Conference on Parallel Processing

作者： Du Zheng Zhao Wenjie Wen Zhiwei Luo Qiuming Department of Computer Science and Technology Tsinghua University China College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)9781450394451

The hybrid dataflow/von-Neumann [1] architectures may differ in implementations but all follow similar principles: they harness the parallelism and data synchronization inherent to the dataflow model, yet maintain the programmability of the von-Neumann model. In this paper, we raise a new kind of hybrid dataflow/von-Neumann architectures, which contains TAU (Task Activated Unit) and SPM [9] (scratchpad memory) components, by which we can enhance parallel efficiency. We also implement the prototype design, integrated with peripheral devices and verify the whole system on FPGA. Finally, we deploy operating system on the hardware system and profile the performance. The experimental results show that the performance is improved by 3.07%∼10.32% under the random data flow graph, the performance of inter-core communication is improved by 4% and the hardware acceleration effect is achieved.

关键词： scratchpad memory RISC-V Dataflow/von-Neumann architecture parallel computation

来源：评论

学校读者我要写书评

暂无评论

Vim4Path: Self-Supervised Vision Mamba for Histopathology Images

Vim4Path: Self-Supervised Vision Mamba for Histopathology Im...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Ali Nasiri-Sarvi Vincent Quoc-Huy Trinh Hassan Rivaz Mahdi S. Hosseini Department of Computer Science and Software Engineering (CSSE) Concordia University Canada Institute for Research in Immunology and Cancer of the University of Montreal Canada Department of Electrical and Computer Engineering (ECE) Concordia University Canada

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Representation learning from Gigapixel Whole Slide Images (WSI) poses a significant challenge in computational pathology due to the complicated nature of tissue structures and the scarcity of labeled data. Multi-instance learning methods have addressed this challenge, leveraging image patches to classify slides utilizing pretrained models using Self-Supervised Learning (SSL) approaches. The performance of both SSL and MIL methods relies on the architecture of the feature encoder. This paper proposes leveraging the Vision Mamba (Vim) architecture, inspired by state space models, within the DINO framework for representation learning in computational pathology. We evaluate the performance of Vim against Vision Transformers (ViT) on the Camelyon16 dataset for both patch-level and slide-level classification. Our findings highlight Vim’s enhanced performance compared to ViT, particularly at smaller scales, where Vim achieves an 8.21 increase in ROC AUC for models of similar size. An explainability analysis further highlights Vim’s capabilities, which reveals that Vim uniquely emulates the pathologist workflow—unlike ViT. This alignment with human expert analysis highlights Vim’s potential in practical diagnostic settings and contributes significantly to developing effective representation-learning algorithms in computational pathology. We release the codes and pretrained weights at https://***/AtlasAnalyticsLab/Vim4Path.

关键词： Representation learning Training computer vision Adaptation models Computational modeling Self-supervised learning computer architecture

来源：评论

学校读者我要写书评

暂无评论

A High-Gain DC-DC Boost Converter for Solar Microgrid Systems Using a Switching Inductor and a Capacitor 1

A High-Gain DC-DC Boost Converter for Solar Microgrid System...

引用

1st International Conference on Advances in computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Prasanth, S. Priyadarsini, S. Lakshmi, R. Sneha, G. Ajitha, S.S. Saravanakumar, R. Narendra, Konnaiah Gari Unnamalai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Kovilpatti India PSR Engineering College Department of Computer Science and Engineering Tamil Nadu Sivakasi India Siddharth Institute of Engineering and Technology Department of Elecrical and Electroncis Engineering Puttur India St. Joseph's Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Iconix Software Solution Tamil Nadu Tirunelveli India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electonics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331518578

This paper outlines the design and implementation of a solar microgrid-specific high-gain DC-DC booster converter that makes use of a variable inductor and capacitors. To improve the suitability of photovoltaic (PV) panels for incorporation into microgrids, the proposed converter efficiently increases their low-voltage outputs. Conventional boost converters can't offer that kind of voltage increase because they lose too much performance and put too much strain on their internal components. The converter increases the voltage gain dramatically while maintaining a high degree of efficiency thanks to a switching inductor-capacitor network. The main breakthrough is an inventive multi-stage energy transfer and storage device that cleverly employs a switching inductor and capacitor. This configuration increases the output voltage while decreasing the voltage and current ripples, which in turn reduces the amount of electromagnetic interference (EMI) and increases the life of the components. Thorough assessments of the converter's working via theoretical modeling and simulation studies confirm its performance across several load and input situations common to solar microgrids. The prototype's testing findings show a significant voltage increase and a peak efficiency of over 95% when compared to traditional boost converters. Moreover, the converter's reliable performance over a wide range of voltage sources and workload scenarios proves its suitability for practical solar applications. As a result, the proposed high-gain boost converter will greatly improve the efficiency and reliability of solar microgrids, leading to a rise in the use of renewable energy sources in DGS. © 2025 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

LLMSecConfig: An LLM-Based Approach for Fixing software Container Misconfigurations

arXiv

引用

arXiv 2025年

作者： Ye, Ziyang Le, Triet Huynh Minh Babar, M. Ali CREST - The Centre for Research on Engineering Software Technologies Adelaide Australia School of Computer and Mathematical Sciences The University of Adelaide Adelaide Australia

Security misconfigurations in Container Orchestrators (COs) can pose serious threats to software systems. While Static Analysis Tools (SATs) can effectively detect these security vulnerabilities, the industry currently lacks automated solutions capable of fixing these misconfigurations. The emergence of Large Language Models (LLMs), with their proven capabilities in code understanding and generation, presents an opportunity to address this limitation. This study introduces LLMSecConfig, an innovative framework that bridges this gap by combining SATs with LLMs. Our approach leverages advanced prompting techniques and Retrieval-Augmented Generation (RAG) to automatically repair security misconfigurations while preserving operational functionality. Evaluation of 1,000 real-world Kubernetes configurations achieved a 94% success rate while maintaining a low rate of introducing new misconfigurations. Our work makes a promising step towards automated container security management, reducing the manual effort required for configuration maintenance. © 2025, CC BY.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

AutoMESC: Automatic Framework for Mining and Classifying Ethereum Smart Contract Vulnerabilities and Their Fixes

AutoMESC: Automatic Framework for Mining and Classifying Eth...

引用

Euromicro Conference on software engineering and Advanced Applications (SEAA)

作者： Majd Soud Ilham Qasse Grischa Liebel Mohammad Hamdaqa Department of Computer Science Reykjavik University Reykjavik Iceland Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada

Due to the risks associated with vulnerabilities in smart contracts, their security has gained significant attention in recent years. However, there is a lack of open datasets on smart contract vulnerabilities and their fixes that allows for data-driven research. Towards this end, we propose an automated framework for mining and classifying Ethereum’s smart contract vulnerabilities and their corresponding fixes from GitHub and from the Common Vulnerabilities and Exposures (CVE) records in the National Vulnerability Database. We implemented the proposed method in a fully automated framework, which we call AutoMESC. AutoMESC uses seven of the most well-known smart contract security tools to classify and label the collected vulnerabilities based on vulnerability types. Furthermore, it collects metadata that can be used in data-intensive smart contract security research (e.g., vulnerability detection, vulnerability classification, severity prediction, and automated repair). We used AutoMESC to construct a sample dataset and made it publicly available. Currently, the dataset contains 6.7K smart contract vulnerability-fix pairs written in Solidity. We assess the quality of the constructed dataset in terms of accuracy, provenance, and relevance, and compare it with existing datasets. AutoMESC is designed to collect data continuously and keep the corresponding dataset up-to-date with newly discovered smart contract vulnerabilities and their fixes from GitHub and CVE records.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wireless Charger Design of Robot Vacuum Cleaners with Power Repeaters for High Compatibility

引用

Journal of Electromagnetic Analysis and Applications 2022年第5期14卷 47-64页

作者： Anglin Li Dariusz Kacprzak Aiguo Patrick Hu Department of Electrical Computer and Software Engineering The University of Auckland Auckland New Zealand

Curved coils constructed by flexible printed circuit board (PCB) or hand-wound Litz-wire have been steadily becoming popular due to its applicable potential on devices that have a curved body. Inductive Power Transfer (IPT) systems based on curved coils and flexible ferrite sheets may provide more flexible charging solutions for various electronic devices such as rice cookers and robot vacuum cleaners. Power repeaters are also used in IPT systems to extend wireless charging range by guiding magnetic fields to the receiving coil. The interaction of these three topics could be inspiring. In this paper, two adjustable power repeaters are applied to an IPT charging system with various curved receiving coils designed for vacuum cleaners. Two power repeaters share the identical structure as the Tx coil and could be rotated to mirror symmetrically. The input and output power are calculated by analyzing the equivalent circuit model. The self-inductance, mutual inductance, and coupling coefficient of the proposed system are obtained via finite element method simulation with variable rotating angles. Three typical IPT designs have also been simulated in ANSYS Maxwell and compared with the proposed magnetic design. The comparison indicates the enhancing feature of the passive power repeaters on coupling performance and the ability to guide the magnetic flux for better magnetic field coupling. Furthermore, two types of co-simulations defined by the power source via Simplorer are conducted to explore how much power could be transferred. The tuned system is shown to be able to provide about 32 W under 100 kHz operating frequency for charging the battery of a robot vacuum cleaner. The results from theoretical calculation and simulation align well with each other.

关键词： Passive Power Repeaters Inductive Power Transfer Curved Coil Robot Vacuum Cleaners

来源：评论

学校读者我要写书评

暂无评论

Igniting Curiosity: Engaging Students in Electricity and Magnetism Through Visually Instructive STEM Activities

Igniting Curiosity: Engaging Students in Electricity and Mag...

引用

IEEE Education engineering (EDUCON)

作者： Dulsha Kularatna-Abeywardana Rajith Abeywardana Department of Electrical Computer and Software Engineering The University of Auckland Auckland New Zealand Little Engineers Limited Auckland New Zealand

ISBN: (数字)9798331539498

ISBN: (纸本)9798331539504

This paper presents a series of hands-on workshops aimed at improving electricity education for high school students and teachers. The workshops address the common challenges of fear and misunderstanding surrounding the subject by providing interactive, visually instructive activities that connect theoretical concepts to real-life applications. Aimed at enhancing students' conceptual understanding and building their confidence, these workshops have proven to be engaging and effective across a wide range of age groups. The results from initial implementation indicate a positive shift in both students' and teachers' attitudes towards electricity education. Future directions include expanding these workshops globally, introducing teacher training components, and targeting specific focus groups, including various ethnicities, genders, and socio-economic backgrounds, to increase their impact and inclusivity. This initiative aims to provide accessible and sustainable solutions for electricity education in diverse educational contexts.

关键词： Training Surveys Visualization Ethnicity Electricity Conferences Iterative methods Socioeconomics Next generation networking STEM

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

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：