检索结果-内蒙古大学图书馆

31st International Working conference on Requirements engineering: Foundation for software Quality, REFSQ 2025

作者： Shah, Faiz Ali Sabir, Ahmed Sharma, Rajesh Pfahl, Dietmar Institute of Computer Science University of Tartu Tartu Estonia

ISBN: (纸本)9783031885303

[Motivation] Automatic analysis of user reviews to understand user sentiments toward app functionality (i.e. app features) helps align development efforts with user expectations and needs. Recent advances in Large Language Models (LLMs) such as ChatGPT have shown impressive performance on several new tasks without updating the model’s parameters i.e. using zero or a few labeled examples, but the capabilities of LLMs are yet unexplored for feature-specific sentiment analysis. [Problem] The goal of our study is to explore the capabilities of LLMs to perform feature-specific sentiment analysis of user reviews. This study compares the performance of state-of-the-art LLMs, including GPT-4, ChatGPT, and different variants of Llama-2 chat, against previous approaches for extracting app features and associated sentiments in zero-shot, 1-shot, and 5-shot scenarios. [Result] The results indicate that GPT-4 outperforms the rule-based SAFE by 17% in f1-score for extracting app features in the zero-shot scenario, with 5-shot further improving it by 6%. However, the fine-tuned RE-BERT exceeds GPT-4 by 6% in f1-score. For predicting positive and neutral sentiments, GPT-4 achieves f1-scores of 76% and 45% in the zero-shot setting, which improve by 7% and 23% in the 5-shot setting, respectively. [Contribution] Our study conducts a thorough evaluation of both proprietary and open-source LLMs to provide an objective assessment of their performance in extracting feature-sentiment pairs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Functional Suitability and Evaluation Metrics for Autonomous Data Center Management: A Case Study of DCAMP

Functional Suitability and Evaluation Metrics for Autonomous...

引用

IEEE International conference on software Architecture Workshops (ICSAW)

作者： Violet Deepa Sera Sumit Kalra Department of Computer Science and Engineering Indian Institute of Technology IIT Jodhpur Jodhpur India

ISBN: (数字)9798331533366

ISBN: (纸本)9798331533373

In response to the escalating demand for data usage and the imperative for stringent environmental sustainability, future data centers are being conceptualized for unconventional locations such as underwater, outer space, and remote areas. These boundaryless data centers necessitate sophisticated management solutions capable of autonomous operation with minimal human intervention. The novel Data Center Autonomous Management Platform (DCAMP) framework, leverages artificial intelligence, machine learning, automation, and contemporary software methodologies to construct an autonomous management platform with a focus on continuous improvement through robust knowledge management and human-in-the-loop based governance. This paper presents a comprehensive architectural evaluation of the DCAMP framework, assessing its quality attributes in accordance with ISO/IEC standards. Key performance indicators and metrics for managing boundaryless data centers are defined, and a usecase simulation evaluating the Functional Suitability characteristic of the DCAMP framework is discussed. Our findings demonstrate that DCAMP provides a compelling solution, offering high output accuracy and enhanced task efficiency, even amidst evolving requirements. The target audience for this paper includes researchers and practitioners in software and systems engineering. It is particularly relevant for data center managers, system administrators, infrastructure managers, SRE cloud engineers, and infrastructure researchers, offering them metrics and evaluation criteria to assess the effectiveness of autonomous data centers which need continuous adaptation.

关键词： Data centers Automation Uncertainty software architecture Machine learning systems engineering and theory Human in the loop software Standards Next generation networking

来源：评论

学校读者我要写书评

暂无评论

PIXHELL: When Pixels Learn to Scream

arXiv

引用

arXiv 2025年

作者： Guri, Mordechai Ben-Gurion University of the Negev Israel Department of Software and Information Systems Engineering Offensive-Cyber Research Lab

This paper presents a technique for generating sound by leveraging the electrical properties of liquid crystal displays (LCDs). The phenomenon occurs due to vibrational noise produced by capacitors within the LCD panel during rapid pixel state transitions. By modulating these transitions through specially crafted bitmap patterns projected onto the screen, we demonstrate how weak yet audible acoustic signals can be generated directly from the display. We designed, implemented, evaluated, and tested a system that repurposes the LCD as a sound-emitting device. Potential applications for this technique include low-power auditory feedback systems, short-range device communication, air-gap covert channels, secure auditory signaling, and innovative approaches to human-computer interaction. Copyright © 2025, The Authors. All rights reserved.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

SMP-NoC: A Flexible and Efficient Shared Memory Protection Unit on Network-on-Chip 24th

SMP-NoC: A Flexible and Efficient Shared Memory Protection ...

引用

24th International conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wu, Teng He, Ying Wei, Shengjun Hu, Changzhen School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Beijing Key Laboratory of Software Security Engineering Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9789819615445

Network-on-Chip (NoC) is crucial for modern multicore systems, offering high throughput and low latency. However, its shared memory faces threats like illegal access and DDoS attacks. To enhance security, Memory Protection Units (MPUs) with permission tables are used to control access. NoC-MPU architecture uses TLBs and permission tables for request checks and domain isolation via CIDs, but this can cause high latency. To address this, DPU and NSM are combined for dynamic permission updates, though the tables remain static. Our paper introduces a novel Flexible and Efficient Real-Time Memory Protection Unit for NoC, featuring a hardware sandbox and taint-track monitor for pre-testing access requests. It supports dynamic memory region adjustments based on four permissions (RX, RWX, RW, R) and includes an access controller to counter DoS and side channel attacks. The design significantly boosts NoC security with minimal overheads: just 6.2% in throughput, 7.8% in area, and 4.8% in power, outperforming current solutions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： hardware-level sandbox Network-on-Chip(NoC) shared Memory taint-track monitor

来源：评论

学校读者我要写书评

暂无评论

S3Simulator: A Benchmarking Side Scan Sonar Simulator Dataset for Underwater Image Analysis 27th

S3Simulator: A Benchmarking Side Scan Sonar Simulator Datase...

引用

27th International conference on Pattern Recognition, ICPR 2024

作者： Kamal Basha, S. Nambiar, Athira Department of Computational Intelligence Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9783031784439

Acoustic sonar imaging systems are widely used for underwater surveillance in both civilian and military sectors. However, acquiring high-quality sonar datasets for training Artificial Intelligence (AI) models confronts challenges such as limited data availability, financial constraints, and data confidentiality. To overcome these challenges, we propose a novel benchmark dataset of Simulated Side-Scan Sonar images, which we term as ‘S3Simulator dataset’. Our dataset creation utilizes advanced simulation techniques to accurately replicate underwater conditions and produce diverse synthetic sonar imaging. In particular, the cutting-edge AI segmentation tool i.e. Segment Anything Model (SAM) is leveraged for optimally isolating and segmenting the object images, such as ships and planes, from real scenes. Further, advanced computer-Aided Design tools i.e. SelfCAD and simulation software such as Gazebo are employed to create the 3D model and to optimally visualize within realistic environments, respectively. Further, a range of computational imaging techniques are employed to improve the quality of the data, enabling the AI models for the analysis of the sonar images. Extensive analyses are carried out on S3simulator as well as real sonar datasets to validate the performance of AI models for underwater object classification. Our experimental results highlight that the S3Simulator dataset will be a promising benchmark dataset for research on underwater image analysis. https://***/bashakamal/S3Simulator. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Shop Floor Productivity Improvement in Original Equipment Manufacturer Company Using ODOO ERP

Shop Floor Productivity Improvement in Original Equipment Ma...

引用

International ECTI Northern Section conference on Electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Pharadon Suwannatara Saranya Maneeroj Somjai Boonsiri Department of Mathematics and Computer Science Faculty of Science Chulalongkorn University Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

The Original Equipment Manufacturer (OEM) is one solution for starting a new business in this era due to the difficulties of managing the supply chain, manufacturing processes, and high startup costs. However, the majority of Thai industries operate relying on human labor and basic mechanization, leading to inefficiencies. This paper presents the implementation of Enterprise Resource Planning (ERP) systems using Odoo, an open-source ERP software, to address these inefficiencies. This research focuses on implementing the Odoo ERP system on the shop floor of an OEM company, addressing challenges in the planning and production departments. The current business process (As-is process) contains several problems. Through gap analysis and customization of the Odoo ERP modules, the system provides streamlined processes according to the new planning and production business process (To-be process), reducing delays and providing real-time access to information. The implementation results show that the system supports OEM company on the shop floor process and enhances overall productivity.

关键词： Productivity Training Supply chains Companies Real-time systems Enterprise resource planning Planning Delays systems support Business

来源：评论

学校读者我要写书评

暂无评论

Enhancing Video Action Recognition with Spatial–Temporal Convolutional Attention Networks 15th

Enhancing Video Action Recognition with Spatial–Temporal Co...

引用

15th International conference on Intelligent Computing and Networking, IC-ICN 2024

作者： Kumar, Pramod Quraishi, Aadam Rusho, Maher Ali Raparthi, Mohan Degadwala, Sheshang Computer Science and Technology Ganga Institute of Technology and Management Haryana Jhajjar Kablana124104 India Intervention Treatment Institute HoustonTX United States Degree Program University of Colorado Boulder CO United States Software Engineer Alphabet Life Science DallasTX75063 United States Department of Computer Engineering Sigma University Gujarat Vadodara India

ISBN: (纸本)9789819786305

Effectively harnessing feature correlations is crucial for optimal performance in video action recognition tasks, whether in spatial or temporal dimensions. Convolutional operations excel at capturing local features through correlations among nearby points, while self-attention mechanisms capture global information by enabling interactions among all feature points. However, the limitations of a single convolutional layer in comprehending holistic feature correlations and the tendency of self-attention layers to overlook local positional characteristics necessitate an innovative approach. We introduce the Spatial–Temporal Convolutional Attention Network, comprising the Spatial Convolutional Attention Network and the Temporal Convolutional Attention Network. This approach strategically combines the strengths of self-attention for global context and convolution for local features, mitigating the limitations of individual layers. Key innovations include [explicitly state innovations]. To reinforce the uniqueness of our approach, we provide specific comparisons with existing methods, highlighting its superiority. In rigorous experiments, our proposed network demonstrates enhanced recognition performance, quantified through metrics such as accuracy and F1 score improvements over baseline models. By effectively capturing feature correlations, our approach elevates the neural network's capacity for spatiotemporal modeling, marking a significant advancement in video action recognition. Elevating the neural network's capacity for spatiotemporal modeling. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

RBMD: RoBERTa-Based Module Detection in Multi-Programming Language software systems

RBMD: RoBERTa-Based Module Detection in Multi-Programming La...

引用

International conference on Web Research (ICWR)

作者： Masoud Kargar Shahin Sharbaf Movassaghpour Ali Bayani Department of Computer Engineering Islamic Azad University Tabriz Branch Tabriz Iran Robotics and Soft Technologies Research Center Islamic Azad University Tabriz Branch Tabriz Iran

ISBN: (数字)9798331508913

ISBN: (纸本)9798331508920

The dynamic nature of web and software systems requires modularization methods that can adapt to frequent updates and diverse structures while maintaining scalability and efficiency. In this research, we propose a RoBERTa-based Module Detection framework that leverages transformer models to classify and manage software modules using the semantic content of source code, comments, and related textual data. Unlike traditional dependency graph-based methods, which face computational bottlenecks, our content-driven approach offers a streamlined, scalable solution for software systems. This framework represents a significant step in automating modularization, eliminating the need for extensive documentation, and leveraging semantic content to manage complexity in modern software development. Experimental results demonstrate the method's efficiency: for Mozilla Version 3.7, the model achieved 92.55 % accuracy and 92.47 % F1-score after four epochs, while for Version 134.0, it reached 98.13% accuracy and 98.02 % F1-score with rapid convergence and minimal training loss. Additionally, the model achieved an outstanding accuracy and F1-score of 99.70 % for Chromium.

关键词： Training Accuracy Computational modeling Source coding Scalability Semantics software systems Transformers Natural language processing software development management

来源：评论

学校读者我要写书评

暂无评论

Intelligent Eye Strain Relief Glasses using IoT and Naive Bayes Solutions for Digital Wellness

Intelligent Eye Strain Relief Glasses using IoT and Naive Ba...

引用

Emerging systems and Intelligent Computing (ESIC), International conference on

作者： Thanalakshmi S G Geethamahalakshmi H. Azath Prabu K T Kumanan C. Srinivasan Department of Management Studies Gojan School of Business and Technology Redhills Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Easwari Engineering College Chennai Tamil Nadu India School of Computing Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Gojan School of Business and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Dr MGR Educational and Research Institute Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

Eye strain and its effects on general health have become more pressing issues due to the pervasive nature of digital devices in modern life. This work offers a new approach by combining the Internet of Things (IoT) with Naive Bayes classification for smart eyewear that reduces eye strain. The proposed system aims to reduce digital eye strain by adapting the lens's characteristics in real-time to user behavior and ambient factors. Using the IoT architecture, data like screen time, distance from the device, and ambient lighting conditions may be captured in real-time when users interact with digital displays. Using Naive Bayes classification, this data is processed to identify probable causes of eye strain and suggest suitable eyewear changes to reduce pain. The proposed system provides a preventative method of fostering digital well-being using software and hardware components, such as sensors, microcontrollers, and machine learning algorithms. These smart glasses provide hope for a future free of the negative impacts of digital device use on eye health by making personal recommendations based on each user's unique requirements.

关键词： Visualization Personal digital devices Real-time systems software Sensor systems Naive Bayes methods Internet of Things Strain Smart glasses Lenses

来源：评论

学校读者我要写书评

暂无评论

Poster: Empirical Evaluation of SC-MCC Meta Program Efficiency Using Dynamic Symbolic Execution Engine

Poster: Empirical Evaluation of SC-MCC Meta Program Efficien...

引用

International conference on software Testing, Verification, and Validation, ICST

作者： Monika Rani Golla Sangharatna Godboley Dept. of Computer Science and Engineering National Institute of Technology Warangal Warangal India Dept. of Computer Science and Engineering NITMiner Technologies National Institute of Technology Warangal Warangal India

ISBN: (数字)9798331508142

ISBN: (纸本)9798331508159

Exploring all the feasible paths in order to generate test cases is costly when dynamic symbolic execution is considered. Hence, there comes the interpolation concept that minimizes the cost to some extent. The earlier work on custom interpolation introduced a resource annotator that instruments the program and generates multiple meta programs (LLVM IRs) in order to generate optimal MCD/DC-based test cases. The proposed approach leverages a Meta Program Generator (MPG) to create a single meta program that encapsulates SC-MCC sequences within “assert” statements, aligned with their corresponding predicates. The effectiveness of this approach is demonstrated through experiments on benchmark programs, comparing it with traditional methods. The results indicate improved efficiency and the generation of a higher number of feasible SC-MCC sequences, making our approach a promising advancement in software testing and symbolic execution. We experimented with 75 Rigorous Examination of Reactive systems (RERS) benchmark programs for experimentation. It is observed that our implementation has obtained more feasible SC-MCC sequences in 41 out of 75 programs.

关键词： software testing Interpolation Costs Automatic programming Accuracy Instruments Benchmark testing Dynamic scheduling Engines

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：