检索结果-内蒙古大学图书馆

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Srivastava, Agam Chandra, Aryaman Biji, C.L. Kalairassan, G. Dheeba, G. Vellore Institute of Technology Dept of Information Security Vellore India Vellore Institute of Technology Dept of Software Systems Vellore India Vellore Institute of Technology Dept of Analytics Vellore India Vellore Institute of Technology Dept of Design and Automation Vellore India

ISBN: (纸本)9798331540821

The global surge in automation and development of cutting-edge robotic technologies has led to a shift in industrial landscape. However, the biggest hurdle in this move is the initialization process, demanding time-consuming configuration of multiple parameters before the robot can be ready for further programming. This research endeavors to develop a comprehensive framework which provides a basis for initial configuration of robots, specifically tailored for pick and place applications. The proposed framework seamlessly integrated with UR5 robots via the Python server provided in the framework. Based on the detections made leveraging the ML computational part of the framework via vision input, the framework computes the optimal trajectories for precise manipulation of objects during pick and place operation. This study lays the foundation for future breakthroughs in automation, providing a fundamental blueprint for evolving processes in the field. © 2024 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization

arXiv

引用

arXiv 2024年

作者： Chen, Zhi Jiang, Lingxiao Centre for Research on Intelligent Software Engineering School of Computing and Information Systems Singapore Management University Singapore

In the rapidly evolving field of machine learning, training models with datasets from various locations and organizations presents significant challenges due to privacy and legal concerns. The exploration of effective collaborative training settings, which are capable of leveraging valuable knowledge from distributed and isolated datasets, is increasingly *** study investigates key factors that impact the effectiveness of collaborative training methods in code next-token prediction, as well as the correctness and utility of the generated code, showing the promise of such methods. Additionally, we evaluate the memorization of different participant training data across various collaborative training settings, including centralized, federated, and incremental training, showing their potential risks in leaking data. Our findings indicate that the size and diversity of code datasets are pivotal factors influencing the success of collaborative trained code models. We demonstrate that federated learning achieves competitive performance compared to centralized training while offering better data protection, as evidenced by lower memorization ratios in the generated code. However, federated learning can still produce verbatim code snippets from hidden training data, potentially violating data privacy or copyright. Our study further explores the patterns of effectiveness and memorization in incremental learning, emphasizing the importance of the sequence in which individual participant datasets are introduced. Also, we identify the memorization phenomenon of cross-organizational clones as a prevalent challenge in both centralized and federated learning scenarios. Our findings highlight the persistent risk of data leakage during inference, even when training data remains unseen. We conclude with strategic recommendations for practitioners and researchers to optimize the use of multisource datasets, thereby propelling the cross-organizational collaboration forward. Cop

关键词： Collaborative learning

来源：评论

学校读者我要写书评

暂无评论

LaneDraw: Cascaded lane and its bifurcation detection with nested fusion

引用

Science China(Technological Sciences) 2021年第6期64卷 1238-1249页

作者： REN KeYan HOU HaoChen LI SiYang YUE TianYi Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Engineering Research Center for IoT Software and Systems Beijing 100124China

Lane and its bifurcation detection is a vital and active research topic in low cost camera-based autonomous driving and advanced driver assistance system(ADAS). The common lane detection pipeline usually predicts lane segmentation mask firstly, and then makes line fitting by parabola or spline post-processing. However, if the speed of the lane and its bifurcation detection is fast and robust enough, we think curve fitting is not a necessary step. The goal of this work is to get accurate lane segmentation,identification of every lane, adaptability of lane numbers and the right combination of lane bifurcation. In this work, we relabeled lane and its bifurcation with solid line if the image of Tu Simple dataset has both of them. In the data training process, we apply a data balance strategy for the heavily biased lane and non-lane data. In such a way, we develop a competitive cascaded instance lane detection model and propose a novel bifurcation pixel embedding nested fusion method based on full binary segmentation pixel embedding with self-grouping cluster, called Lane Draw. Our method discards curve fitting process, therefore it reduces the complexity of post-processing and increases detection speed at 35 fps. Moreover, the proposed method yields better performance and high accuracy on the relabeled Tu Simple dataset. To the best of our knowledge, this is the first attempt in 2 D lane and bifurcation detection, which more often happens in actual situations.

关键词： lane detection bifurcation fusion instance segmentation autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Towards Eco-Sustainability and Green Analytics Model to Measure the Performance of Big Data systems 9

Towards Eco-Sustainability and Green Analytics Model to Meas...

引用

9th International Conference on information Management, ICIM 2023

作者： Jusoh, Yusmadi Yah Abdullah, Rusli Nor, Rozi Nor Haizan Yahaya, Jamaiah Hj. Muhammad, Shireen Arunachalam, Aishwharya Raani Universiti Putra Malaysia Faculty of Computer Science and Information Technology Dept. of Software Engineering and Information Systems Serdang Malaysia Universiti Kebangsaan Malaysia Faculty of Information Science and Technology Bangi Malaysia Faculty of Communication Selangor Malaysia

ISBN: (纸本)9798350336382

Many BDS is doomed to failure because of the missing knowledge on measuring the performance of BDS. The failure to identify the performance measurement and correct will make the problems worsen. This will complicate the efforts of fixing such problems and more importantly, will affect the quality of knowledge, insights, and results expected by the users in the future. In achieving durable performance, the organization needsto understand the factors that contribute to the performance of the eco-sustainability and green analytics metrics for BDS. Although the existence of its importance and awareness was largely neglected. Therefore, the eco-sustainability and green analytic measurement of the BDS is examined in this research. Measuring the BDS performance has the benefit of identifying problems and launching corrective actions before these problems happen and become worsen. The research will investigate the eco-sustainability and green analytic measures which will be proposed and used to capture performance for each process of BDS. Then, based on such measures and metrics, as well as existing performance concepts, frameworks, and models, a measurement model for BDS will be created. The model will be validated through expert evaluations and confirmatory studies with users and practitioners of BDS users. The research has a greater significance in leveraging existing performance concepts in BDS settings and the research proposes users' participation in the sustainability and continuous performance evaluation of theirBDS. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Scheduling Tool for Deterministic Communication in Distributed Real-Time systems 10

Scheduling Tool for Deterministic Communication in Distribut...

引用

10th Workshop on software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2023

作者： Mach, Jan Tašková, Valéria Kohútka, Lukáš Institute of Computer Engineering and Applied Informatics Faculty of Informatics and Information Technologies Slovak University of Technology Bratislava Slovakia Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology Bratislava Slovakia

A network with critical data streams, where the timing of incoming and outgoing data is a necessity, is called a deterministic network. These networks are mostly used in association with real-time systems that use periodic hard-real-time data which need to be scheduled. The algorithm proposed in this paper is focused on achieving the lowest possible latency within the specified network topology depending on the physical parameters of the network and the periodic requirements of the communicating nodes. The algorithm allows to add priorities to the data flow between nodes and also the option to specify if preemption is allowed within the network, since not all devices support it. The result is a schedule of hard-real-time data communication within a specified network topology where all requirements of communicating nodes are met if such a solution is possible. © 2023 Copyright for this paper by its authors.

关键词： deadline deterministic scheduling Ethernet scheduling algorithm time-sensitive networking

来源：评论

学校读者我要写书评

暂无评论

Evaluating software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios

arXiv

引用

arXiv 2024年

作者： Chen, Zhi Jiang, Lingxiao Centre for Research on Intelligent Software Engineering School of Computing and Information Systems Singapore Management University Singapore

In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and interacting with external environments, offer promising solutions to complex software engineering tasks. However, while much research has evaluated code generated by large language models (LLMs), comprehensive studies on agent-generated patches, particularly in real-world settings, are lacking. This study addresses that gap by evaluating 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues from SWE-Bench Verified, focusing on their impact on code quality. Our analysis shows no single agent dominated, with 170 issues unresolved, indicating room for improvement. Even for patches that passed unit tests and resolved issues, agents made different file and function modifications compared to the gold patches from repository developers, revealing limitations in the benchmark’s test case coverage. Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities;while some agents increased code complexity, many reduced code duplication and minimized code smells. Finally, agents performed better on simpler codebases, suggesting that breaking complex tasks into smaller sub-tasks could improve effectiveness. This study provides the first comprehensive evaluation of agent-generated patches on real-world GitHub issues, offering insights to advance AI-driven software development. © 2024, CC BY.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

Spectral Mask - Based Technique for Improving Generalized Sidelobe Canceller Beamformer's Evaluation

Spectral Mask - Based Technique for Improving Generalized Si...

引用

2023 Seminar on Signal Processing, SoSP 2023

作者： The, Quan Trong Huy, Nguyen Ba Anh, Pham Tuan Ha Noi University of Science and Technology Falculty of Information Technology Ha Noi Viet Nam University ITMO Falculty of Control Systems and Robotics Saint-Petersburg Russia University ITMO Falculty of Software Engineering and Computer Systems Saint-Petersburg Russia

ISBN: (纸本)9798350371086

Noise suppression and understanding speech in a complex environment with the presence of numerous and dominant surrounding noise is very difficult for humans. To deal with this problem, microphone array, which exploit a priori information of designed geometry of microphone array, the direction of arrival (DOA) of interest signal or the properties of recorded situation, is used with aiming at preserving the desired speaker without speech distortion while reducing background noise. Generalized Sidelobe Canceller (GSC) beamformer has been installed in almost all acoustic equipment, hearing aids, mobile phones. Unfortunately, the performance of GSC beamformer is often corrupted in many scenarios, such as imprecise DOA, microphone mismatches or different microphone sensitivities. In this paper, a spectral mask - based suggested algorithm to reduce the speech leakage in the reference signal of GSC beamformer. The proposed method is evaluated for increasing the speech quality of dual - microphone systems. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

TPTO: A Transformer-PPO based Task Offloading Solution for Edge computing Environments 29

TPTO: A Transformer-PPO based Task Offloading Solution for E...

引用

29th IEEE International Conference on Parallel and Distributed systems, ICPADS 2023

作者： Gholipour, Niloofar De Assuncao, Marcos Dias Agarwal, Pranav Gascon-Samson, Julien Buyya, Rajkumar Univ. of Quebec Dept. of Software Engineering and IT École de Technologie Supérieure Montreal Canada The Univ. of Melbourne CLOUDS Lab School of Computing and Information Systems Australia

ISBN: (纸本)9798350330717

Emerging applications in healthcare, autonomous vehicles, and wearable assistance require interactive and low-latency data analysis services. Unfortunately, cloud-centric architectures cannot fulfill the low-latency demands of these applications, as user devices are often distant from cloud data centers. Edge computing aims to reduce the latency by enabling processing tasks to be offloaded to resources located at the network's edge. However, determining which tasks must be offloaded to edge servers to reduce the latency of application requests is not trivial, especially if the tasks present dependencies. This paper proposes a Deep Reinforcement Learning (DRL) approach called TPTO, which leverages Transformer Networks and Proximal Policy Optimization (PPO) to offload dependent tasks of IoT applications in edge computing. We consider users with various preferences, where devices can offload computation to an edge server via wireless channels. Performance evaluation results demonstrate that under fat application graphs, TPTO is more effective than state-of-the-art methods, such as Greedy, HEFT, and MRLCO, by reducing latency by 30.24%, 29.61%, and 12.41%, respectively. In addition, TPTO presents a training time approximately 2.5 times faster than an existing DRL approach. © 2023 IEEE.

关键词： Edge computing reinforcement learning task offloading Transformers

来源：评论

学校读者我要写书评

暂无评论

An Automated Real-Time Face Mask Detection System Using Transfer Learning with Faster-RCNN in the Era of the COVID-19 Pandemic

引用

Computers, Materials & Continua 2022年第5期71卷 4151-4166页

作者： Maha Farouk S.Sabir Irfan Mehmood Wafaa Adnan Alsaggaf Enas Fawai Khairullah Samar Alhuraiji Ahmed S.Alghamdi Ahmed A.Abd El-Latif Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversitySaudi Arabia Centre for Visual Computing Faculty of Engineering and InformaticsUniversity of BradfordBradfordU.K Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahP.O.Box 23713Saudi Arabia Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Cybersecurity College of Computer Science and EngineeringUniversity of JeddahSaudi Arabia Department of Mathematics and Computer Science Faculty of ScienceMenoufia University32511Egypt

Today,due to the pandemic of COVID-19 the entire world is facing a serious health *** to the World Health Organization(WHO),people in public places should wear a face mask to control the rapid transmission of *** governmental bodies of different countries imposed that wearing a face mask is compulsory in public ***,it is very difficult to manually monitor people in overcrowded *** research focuses on providing a solution to enforce one of the important preventative measures of COVID-19 in public places,by presenting an automated system that automatically localizes masked and unmasked human faces within an image or video of an area which assist in this outbreak of *** paper demonstrates a transfer learning approach with the Faster-RCNN model to detect faces that are masked or *** proposed framework is built by fine-tuning the state-of-the-art deep learning model,Faster-RCNN,and has been validated on a publicly available dataset named Face Mask Dataset(FMD)and achieving the highest average precision(AP)of 81%and highest average Recall(AR)of 84%.This shows the strong robustness and capabilities of the Faster-RCNN model to detect individuals with masked and un-masked ***,this work applies to real-time and can be implemented in any public service area.

关键词： COIVD-19 deep learning faster-RCNN object detection transfer learning face mask

来源：评论

学校读者我要写书评

暂无评论

Integrating Blockchain technology into Healthcare Through an Intelligent computing Technique

引用

Computers, Materials & Continua 2022年第2期70卷 2835-2860页

作者： Asif Irshad Khan Abdullah Saad Al-Malaise ALGhamdi Fawaz Jaber Alsolami Yoosef B.Abushark Abdulmohsen Almalawi Abdullah Marish Ali Alka Agrawal Rajeev Kumar Raees Ahmad Khan Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Technology Babasaheb Bhimrao Ambedkar UniversityLucknow226025Uttar PradeshIndia Department of Computer Applications Shri Ramswaroop Memorial UniversityBarabanki225003Uttar PradeshIndia

The blockchain technology plays a significant role in the present era of information *** the last few years,this technology has been used effectively in several *** has already made significant differences in human life,as well as is intended to have noticeable impact in many other domains in the forthcoming *** rapid growth in blockchain technology has created numerous new possibilities for use,especially for healthcare *** digital healthcare services require highly effective security methodologies that can integrate data security with the availablemanagement *** test and understand this goal of security management in Saudi Arabian perspective,the authors performed a numerical analysis and simulation through a multi criteria decision making approach in this *** authors adopted the fuzzy Analytical Hierarchy Process(AHP)for evaluating the effectiveness and then applied the fuzzy Technique forOrder of Preference by Similarity to Ideal Solution(TOPSIS)technique to simulate the validation of *** eliciting highly corroborative and conclusive results,the study referred to a real time project of diabetes patients’management application of Kingdom of Saudi Arabia(KSA).The results discussed in this paper are scientifically proven and validated through various analysis *** the present study can be a credible basis for other similar endeavours being undertaken in the domain of blockchain research.

关键词： Blockchain technology data management fuzzy logic AHP TOPSIS

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：