检索结果-内蒙古大学图书馆

software Analysis, Evolution and Reengineering - Companion (SANER-C), IEEE International Conference on

作者： Giuseppe Bisicchia Jose García-Alonso Juan M. Murillo Antonio Brogi Department of Computer Science University of Pisa Pisa Italy Quercus Software Engineering Group University of Extremadura Cáceres Spain

ISBN: (数字)9798350351576

ISBN: (纸本)9798350351583

Quantum Computing holds the potential to change our world. Following the quantum wave, software engineers have recognised the opportunity to establish a new discipline of Quantum software engineering. Despite the significant progress achieved, Quantum Computing's widespread adoption still faces critical hurdles. In this paper, we outline two of these challenges. (1) Quantum programming continues to be a complex art mastered by a select few experts. We suggest that the primary culprit can be pinpointed in the absence of high-level quantum software abstractions which forces developers to work with low-level quantum concepts and reason in terms of matrix multiplications. (2) The scarce collaboration among quantum software engineers resulted in a lack of platform and software interoperability. While a diversity of research proposals fuels scientific progress, it can hinder the development and adoption of innovative technologies, potentially fragmenting the collective efforts and confining them within isolated research groups. We believe that overcoming these issues is crucial for fostering innovation, advancing Quantum software engineering, and Quantum Computing as a whole.

关键词： Technological innovation Quantum computing Collaboration Programming software Proposals Fuels

来源：评论

学校读者我要写书评

暂无评论

A Redefined Decision Variable Analysis Method for Large-Scale Optimization and its Application to Feature Selection

SSRN

引用

SSRN 2023年

作者： Li, Yongfeng Li, Lingjie Tang, Huimei Lin, Qiuzhen Ming, Zhong Leung, Victor C.M. College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia VancouverBC Canada

Large-scale multiobjective optimization problems (LMOPs) are particularly challenging for conventional evolutionary algorithms,as it is difficult to quickly approximate to the Pareto optimal front in a huge search *** prominent method to solve LMOPs is to simplify the target LMOPs via decision variable analysis (DVA) methods,where the decision variables are classified into several sub-components and then each sub-component is optimized ***, most existing DVA-based methods still have the problem of high evaluation consumption,which limits the performance of solving *** alleviate this issue,this paper proposes a new redefined DVA method with low-consumption for solving LMOPs,called ***,R-DVA detects the interrelationship among convergent decision variables by using a distance-based hierarchical clustering method,which does not need to generate a large number of solutions,thus saving a lot of evaluation ***, R-DVA divides the interrelated convergent decision variables into the same group,thus dividing the convergent decision variables into several *** addition,to improve the performance of population,an evolutionary-state-oriented evolutionary (EsoE) strategy with two search models is designed in ***,the intra-group optimization model is used to accelerate the convergence when the population is in the exploration ***,a novel quality-based segmentation competitive swarm optimizer (CSO) is designed in the inter-group optimization model,aiming to enhance the diversity of the population when the population is in the exploitation *** this way,a good trade-off between the convergence and diversity can be achieved via the EsoE ***,extensive experiments demonstrate the efficiency of our proposed R-DVA in comparison to five state-of-the-art large-scale evolutionary algorithms in solving various benchmark LMOPs and a real-world large-scale application,i.e.,feature selection. © 2023

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection System Dataset for a Multi-Agent Cyber-Physical Conveyor System

An Intrusion Detection System Dataset for a Multi-Agent Cybe...

引用

2023 IEEE International Conference on Industrial Technology, ICIT 2023

作者： Funchal, Gustavo Zahid, Farzana Melo, Victoria Kuo, Matthew M. Y. Pedrosa, Tiago Sinha, Roopak De La Prieta, Fernando Leitao, Paulo Braganca5300-253 Portugal Auckland University of Technology Computer Science and Software Engineering Department Auckland New Zealand Bragança5300-253 Portugal University of Salamanca Bisite Digital Innovation Hub Salamanca37007 Spain

ISBN: (纸本)9798350336504

Industry 4.0 is built upon the foundation of connecting devices and systems via Internet of Things (IoT) technologies, with Cyber- Physical Systems (CPS) serving as the backbone infrastructure. Although this approach brings numerous benefits like improved performance, responsiveness and reconfigurability, it also introduces security concerns, making devices and systems vulnerable to cyber attacks. There is a need for effective techniques to protect these systems, and the availability of datasets becomes essential to support the development of such techniques. This paper presents a dataset based on the collection of traffic information exchanged in a self-organizing conveyor system using the multi-agent systems (MAS) architecture and containing various intelligent conveyor modules. The dataset comprises data collected at the network and agent levels under normal system operation, denial of service (DoS) attacks, and malicious agent attacks. An intrusion detection system that integrates Fast Fourier Transform (FFT) and Machine Learning (ML) analysis is developed to demonstrate the utility of this dataset. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Towards Automated Support for the Co-Evolution of Meta-Models and Grammars

arXiv

引用

arXiv 2023年

作者： Zhang, Weixing Department of Computer Science & Engineering Division of Interaction Design & Software Engineering Chalmers University of Technology University of Gothenburg Gothenburg Sweden

Blended modeling is an emerging paradigm involving seamless interaction between multiple notations for the same underlying modeling language. We focus on a model-driven engineering (MDE) approach based on meta-models to develop textual languages to improve the blended modeling capabilities of modeling tools. In this thesis, we propose an approach that can support the co-evolution of meta-models and grammars as language engineers develop textual languages in a meta-model-based MDE setting. Firstly, we comprehensively report on the challenges and limitations of modeling tools that support blended modeling, as well as opportunities to improve them. Second, we demonstrate how language engineers can extend Xtext’s generator capabilities according to their needs. Third, we propose a semi-automatic method to transform a language with a generated grammar into a Python-style language. Finally, we provide a solution (i.e., GrammarOptimizer) that can support rapid prototyping of languages in different styles and the co-evolution of meta-models and grammars of evolving languages. © 2023, CC BY-NC-ND.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Improving Routing Decision Algorithm for RPL Networks 11

Improving Routing Decision Algorithm for RPL Networks

引用

11th International Conference on Information Technology, ICIT 2023

作者： Zaqebah, Abdullah Al Almomani, Omar Almomani, Malek Alsaaidah, Adeeb Abu-Shareha, Ahmad Adel Althunibat, Ahmad The World IslamicSciences and Education University Department of Computer Science Amman Jordan The World Islamic Sciences and Education University Department of Information System and Networks Amman Jordan Software Engineering The World Islamic Sciences and Education University Amman Jordan Al-Ahliyya Amman University Department of Networks and Information Security Amman Jordan Al-Ahliyya Amman University Department of Data Science and Artificial Intelligence Amman Jordan Al-Zaytoonah University of Jordan Department of Software Engineering Amman11733 Jordan

ISBN: (纸本)9798350320060

Low Power Networks are spreading worldwide, seeking to enable small devices to join wireless networks. This requires a routing mechanism that makes it possible and seamless. This research aims to create a Low Power and Lossy Networks (RPL) routing protocol that balances power usage and node dependability. The main emphasis of the algorithm presented here is the choice made by network nodes (Zigbees) regarding which path to deliver the message along. Results for this routing technique seem promising. Utilizing it increased packet transfer reliability while enforcing power conservation. Furthermore, a 10% reduction in the network's overall power consumption was made. © 2023 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Smartphone Sensor-based Human Activity Recognition Using LSTM Networks: Development and Implementation in Android Applications

Smartphone Sensor-based Human Activity Recognition Using LST...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Debabrata Sikder Nafiz Imtiaz Rafin Md. Golam Rabiul Alam Md. Zia Uddin Department of Computer Science and Engineering BRAC University Dhaka Bangladesh SINTEF Digital Software and Service Innovation Group Oslo Norway

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

The machine learning approach to estimate human activity using smartphone sensor data is challenging. In this work, a Human Activity Recognition (HAR) approach is conducted based on the Long Short-Term Memory (LSTM) model, which can recognize six different behaviors: Downstairs, Jogging, Sitting, Standing, Upstairs, and Walking. To achieve the best potential result, various machine learning and statistical approaches were explored. The LSTM model, known for its effectiveness in sequence prediction, was chosen for its ability to run efficiently on lightweight edge devices such as smartphones. This model achieved a test accuracy of 97%. Finally, the model was exported and deployed in an Android application, providing a user-friendly interface.

关键词： Legged locomotion Deep learning Recurrent neural networks Accuracy Computational modeling Predictive models Behavioral sciences Human activity recognition Information technology Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Towards Evidence-Based Cybersecurity Assessment of Programmable Systems to Ensure the Protection of Critical IT Infrastructure 12

Towards Evidence-Based Cybersecurity Assessment of Programma...

引用

12th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS 2023

作者： Illiashenko, Oleg Kharchenko, Vyacheslav Odarushchenko, Oleg National Aerospace University 'KhAI' Department of Computer Systems and Networks Kharkiv61070 Ukraine Institute of Information Science and Technologies 'Alessandro Faedo' - Isti Cnr Software Engineering & Dependable Computing Laboratory Pisa56124 Italy Research and Production Enterprise Rpc Radics Llc Kropyvnytskyi25009 Ukraine

ISBN: (纸本)9798350358056

The paper is devoted to developing scientific principles, methods, means, and information technology of model-oriented verification and evidence-based assessment using functional safety and cybersecurity cases for programmable systems of critical applications (PSCA). In particular, information and control systems important for the safety of nuclear power plants (NPPs), aerospace systems, railway domains, etc., developed using Field Programmable Gate Arrays (FPGAs) and hardware platforms are reviewed. The goal is to ensure the guaranteed completeness and reliability of its functional safety and cybersecurity assessment by developing and implementing a set of formal and semi-formal methods and tools that consider defects of different nature - physical, design, trojans, and vulnerabilities that can be attacked and lead to a fatal system failure, which results in damaging the critical IT infrastructure. The methods shown are based on integrating algebraic, tabular, graph models, and case assessment methodology. The methods are implemented as appropriate technologies for evidence-based verification and evaluation of PSCA. For formal methods, a prototype of a translator of Very High-Speed Integrated Circuits Hardware Description Language (VHDL) code is developed into an algebra of behaviors. It provides evidence-based verification and a framework and tools to design reports on assessing the cybersecurity and functional safety of programmable systems. © 2023 IEEE.

关键词： critical IT infrastructure cybersecurity FPGA functional safety programmable systems of critical applications

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Smart Infotainment System for Taxi Vehicles 4

Deep Learning-Based Smart Infotainment System for Taxi Vehic...

引用

4th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2022

作者： Dewalegama, M.P. De Zoysa, A.D.S. Kodikara, L.M Dissanayake, D.M.J.C Kuruppu, Thilmi Anuththara Rupasinghe, Shalini Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Sri Lanka Sri Lanka Institute of Information Technology Department of Information Technology Sri Lanka

ISBN: (纸本)9781665468350

Nowadays, people are more intent to use IoT to ease their day-to-day work. As a result of that, the transportation industry is being adopted to more IoT-based approaches rather than traditional methods. When it comes to taxi services, companies need to keep up the competition with their rivals. Along with the high demand, there are also being reporting number of problems around the taxi industry daily. Taking some of the most common problems into consideration, such as 'Smart Infotainment System' will help to resolve most of those problems. Deep learning models such as CNN (Convolutional Neural Network), YOLO and SKLearn used to develop the proposed system. As a result of that, the reputation of the taxi service will be increased, and the taxi service consumers will be able to get a comfortable and safer journey to the end of the day. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning good state and action representations for Markov decision process via tensor decomposition

引用

The Journal of Machine Learning Research 2023年第1期24卷 5157-5209页

作者： Chengzhuo Ni Yaqi Duan Munther Dahleh Mengdi Wang Anru R. Zhang Department of Electrical & Computer Engineering Princeton University Laboratory for Information & Decision Systems Massachusetts Institute of Technology Electrical Engineering & Computer Science Department Massachusetts Institute of Technology Department of Biostatistics & Bioinformatics Duke University

The transition kernel of a continuous-state-action Markov decision process (MDP) admits a natural tensor structure. This paper proposes a tensor-inspired unsupervised learning method to identify meaningful low-dimensional state and action representations from empirical trajectories. The method exploits the MDP's tensor structure by kernelization, importance sampling and low-Tucker-rank approximation. This method can be further used to cluster states and actions respectively and find the best discrete MDP abstraction. We provide sharp statistical error bounds for tensor concentration and the preservation of diffusion distance after embedding. We further prove that the learned state/action abstractions provide accurate approximations to latent block structures if they exist, enabling function approximation in downstream tasks such as policy evaluation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning Based Human Activity Recognition Using Body Sensors 9

Contrastive Learning Based Human Activity Recognition Using ...

引用

9th International Conference on Big Data Computing and Communications, BigCom 2023

作者： Xie, Chuanshi Zhou, Yu Yu, Dandan Sun, Shilong Zhang, Xiao Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The First Affiliated Hospital of Dalian Medical University Information Center Dalian China Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen518055 China South-Central Minzu University Department of Computer Science China South-Central Minzu University Key Laboratory of Cyber-Physical Fusion Intelligent Computing State Ethnic Affairs Commission Wuhan430074 China

ISBN: (纸本)9798350331240

Pervasive sensing and wearable sensor techniques have been increasingly employed to monitor and recognize human activities through body sensors in areas of smart healthcare and manufacturing. However, conventional machine learning or deep learning based human activity recognition (HAR) requires a large amount of labeled data, which is cost-expensive in real-world scenarios. To tackle this issue, we propose a contrastive learning framework for HAR (CL-HAR), which utilizes the generated unlabeled data as the input and explores the supervised features of the unlabeled data under the principle of self-supervised learning. A simple yet effective backbone network as a feature extractor for subsequent activity recognition is proposed. By using a small portion of the labeled samples as the training set which is fed into our learned feature extractor, we build a classifier and use the rest of the data to verify the feasibility and effectiveness of our CL method. Extensive experiments on three benchamark datasets and one real-world dataset demonstrate that CL-HAR can achieve better classification accuracy than compared supervised and semi-supervised methods with less labelled samples, which is of practical use. © 2023 IEEE.

关键词： Wearable sensors

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：