检索结果-内蒙古大学图书馆

Proceedings of the 2023 6th Artificial Intelligence and Cloud Computing Conference

作者： Nataly Zhukova Anna Motienko Dmitriy Levonevskiy Alexey Subbotin Pham Tuan Anh Laboratory of big data technologies in socio-cyberphysical systems St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS) Russia Faculty of Computer Technologies and Informatics St. Petersburg State Electrotechnical University Russia Faculty of Software Engineering and Computer Systems ITMO University Russia

ISBN: (纸本)9798400716225

This article presents a method for building a hospital room with extended intelligent features based on Internet of Things (IoT) technologies. We begin by reviewing existing vision-based health care systems and identifying important and useful functions that they should have. We then present a method for building a smart room that allows increase the level of the intelligence of the existing hospital rooms due to extensive use of the up-to-date machine learning methods. The proposed solution assumes using readily available hardware devices to reduce the cost of smart room building. Compared to commercially available assistive technologies, the proposed smart room turn out to have high level of intelligence and to be very cost effective. The system's non-intrusive nature makes it easy to use it both in hospitals and at home for patient care.

关键词： Internet of Things IoT automation in medicine intellectual room machine learning smart room smart ward

来源：评论

学校读者我要写书评

暂无评论

Lifted Invariant Analysis of Petri Net Product Lines

SSRN

引用

SSRN 2022年

作者： Gómez-Martínez, Elena Guerra, Esther de Lara, Juan Garmendia, Antonio Departamento de Ingeniería Informática Universidad Autónoma de Madrid Spain Institute for Business Informatics - Software Engineering Johannes Kepler University of Linz Austria

Petri nets are commonly used to represent concurrent systems. However, they lack support for modelling and analysing system families, like variants of controllers, different variations of a process model, or the possible configurations of a flexible assembly *** facilitate modelling potentially large collections of similar systems, in this paper, we enrich Petri nets with variability mechanisms based on product line engineering. Moreover, we present methods for the efficient analysis of the (place and transition) invariants in all defined versions of a Petri net. Efficiency is achieved by analysing the system family as a whole, instead of analysing each possible net variant separately. We present tool support and evaluate the benefits of our techniques on synthetic and realistic examples, achieving speed-ups of more than 100x with respect to analysing each net variant separately. © 2022, The Authors. All rights reserved.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Games for Scrum Team Collaboration in the Global software Development Environment: A Literature Review

Games for Scrum Team Collaboration in the Global Software De...

引用

International Conference on informatics and Computing (ICIC)

作者： Anita Hidayati Iklima Ermis Ismail Ade Rahma Yuly Henry Edison Department of Computer and Informatics Engineering Politeknik Negeri Jakarta Depok Indonesia Faculty of Computer Science Universitas Dian Nuswantoro Semarang Indonesia Department of Software Engineering Blekinge Institute of Technology Sweden Swedia

ISBN: (纸本)9798350345728

software development companies commonly use Global software Development (GSD) in their industry. A competent Scrum team supports the success of the GSD project. This research aims to identify the game components in the form of types, elements, and technologies that contribute to building experience for the Scrum team in a GSD environment. We used a Systematic Literature Review (SLR) with the Kitchenham and snowball method. From the 12 papers, we concluded that none of the games specifically focused on the competence of the Scrum team at GSD. The SLR results also identify ten game elements and technologies as a reference for game development to meet the challenges in GSD. The conclusion is that there are still great opportunities to develop a game that can improve the competence of the GSD Scrum team. Game development should refer to elements and identified technologies.

关键词： Industries Systematics Bibliographies Games software Teamwork Object recognition

来源：评论

学校读者我要写书评

暂无评论

Agent based coordination protocol for system of cyber-physical systems

引用

Energy informatics 2021年第2期4卷 1-25页

作者： Umair, Aisha Clausen, Anders Demazeau, Yves Jørgensen, Bo Nørregaard Software Engineering Unit Mærsk Mc-Kinney Møller Institute University of Southern Denmark Campusvej 55 Odense5230 Denmark Center for Energy Informatics Mærsk Mc-Kinney Møller Institute University of Southern Denmark Odense5230 Denmark Laboratoire d’Informatique de Grenoble Batiment IMAG - 700 avenue Centrale Grenoble France

Nowadays, society and business rely heavily on Information and Communication Technology (ICT) systems, which are progressing faster than ever. To stay on pace with them, focus is shifted towards integration of individual ICT systems into complex systems, which offers more functionality than simply the sum of individual systems. In this regard, Cyber-Physical Systems (CPSs) have gained significant importance and System-of-Systems (SoS) approach has been suggested for modeling complex CPSs to achieve a higher level goal, by dynamically building a large system with existing autonomous, and heterogeneous constituent systems (CSs). An important challenge in a system of Cyber-Physical Systems (SoCPSs) is to develop seamless collaboration between autonomous constituent-CPSs (CCPSs) to coordinate their operations. In this paper, we propose an agent based coordination mechanism to coordinate resource allocation and demand in SoCPSs. The approach models each CCPS as an agent and describes how multiple autonomous CCPSs, i.e., Virtual Power Plant (VPP), Commercial Greenhouse Growers (CGGs), communicate and collaborate with each other asynchronously through negotiation and how potential conflicts between CCPSs with conflicting goals are resolved. The efficacy of the proposed mechanism is validated through simulation of different real-world acyclic SoCPSs topologies. The results show that proposed approach is able to balance the individual requirements of multiple connected CPSs while achieving SoCPSs’ mission. © 2021, The Author(s).

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Cognitive Computing Methodology for software Requirement Elicitation and Formal Specification

A Cognitive Computing Methodology for Software Requirement E...

引用

IEEE International Conference on Cognitive informatics

作者： Yingxu Wang James Y. Xu Dept. of Electrical and Software Engineering International Institute of Cognitive Informatics and Cognitive Computing (I2CICC) Schulich School of Engineering (SSE) and Hotchkiss Brain Institute (HBI) University of Calgary NW Calgary AB Canada

Autonomous software requirement analysis and specifications is not only an ultimate goal of cognitive computing, but also a persistent challenge to theories and technologies of software engineering. A cognitive computing model is demanded to autonomously elicit and rigorously refine software requirements in order to generate a set of formal specifications. This paper presents a novel methodology for the design of a cognitive computing method for software Requirement Elicitation and Specifications (SRES) based on the latest advances in software science and intelligent mathematics. SRES is implemented as an interactive system for capturing software requirements and generating formal specifications. The SRES methodology and experiments are demonstrated for solving real-world and complex software engineering problems enabled by cognitive computing theories underpinned by intelligent mathematics.

关键词： Interactive systems Design methodology Knowledge based systems Machine learning software Mathematics Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Modification of the Genetic Algorithm for Building and Reconfiguring Schedules of Order Completion in the Field of Service Provision 12

Modification of the Genetic Algorithm for Building and Recon...

引用

12th International Conference on Advanced Computer Information Technologies, ACIT 2022

作者： Hrybkov, Serhii Seidykh, Olga Vlasenko, Lidia Lytvynov, Valerii National University of Food Technologies Department of Information Systems Kyiv Ukraine National University of Food Technologies Department of Informatics Kyiv Ukraine National University of Trade and Economics Department of Software Engineering and Cyber Security Kyiv Ukraine Institute of Mathematical Machines and Systems Problems of Nasu Research Department № 220 'Intelligent Information-analytical System' Kyiv Ukraine

ISBN: (数字)9781665410502

ISBN: (纸本)9781665466479

The paper offers a solution to an important scientific and applied problem of scheduling to complete the orders for the provision of services aimed at maintenance and support of computer networks and equipment. This problem is relevant for companies providing such services. The main idea is to form an effective schedule for the completion of orders, as well as to enable its modification in the shortest time when getting orders. The paper also proposes an evaluation function that takes into account bonuses for the timely completion of orders and penalties for the late ones. A combination of a genetic algorithm with the methods of additional improvement on the basis of local optimization is offered. It allows reducing the time for the construction of effective alternative variants of decisions and their estimation. The use of the proposed approach to combining algorithms allows creating and reconfiguring the schedule for the completion of orders in the operational mode in a short time, and optimization makes it possible to reduce the completion of orders by up to 20%. Thus, the application of the proposed approaches will allow effective distribution of tasks among performers and give an economic effect by reducing the time to complete all orders. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Dsh-Rsf-Lite Approach: Towards Lightweight Pneumonia Classification Network with Few-Shot Augmentation on Chest X-Ray Images

SSRN

引用

SSRN 2024年

作者： Chen, Hongbin Zhu, Zhou Wang, Wei Yang, Chunfeng Li, Jie Liu, Chengyu Kiong, Loo Chu Wang, Zhelong Li, Jianqing Xiang, Wentao The Engineering Research Center of Intelligent Theranostics Technology and Instruments Ministry of Education School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing211166 China The School of Software Engineering Jinling Institute of Technology Nanjing211169 China Nanjing China The State Key Laboratory of Digital Medical Engineering School of Instrument Science and Engineering Southeast University Nanjing China Kuala Lumpur50603 Malaysia The School of Control Science and Engineering Dalian University of Technology Dalian116024 China

Pneumonia classification using chest X-ray images has significant clinical diagnosis values with its rapid image acquisition, low radiation dose and rich volume ***, they may suffer from class imbalance and redundant characteristics. To address these issues, the DSH-RSF-Lite approach is proposed with three core parts: 1) DSHNet is a few-shot augmentation approach that integrates spectral normalization into deep convolutional generative adversarial network and employs hinge adversarial loss to augment chest X-ray images for balancing positive and negative samples, 2) RSFNet is a residual network that incorporates spatial attention blocks and early-late feature fusion, enhancing the model focus on key regions within chest X-ray images meanwhile enriching overall information representation, 3) RSF-Lite is a lightweight model that employs geometric median-based pruning strategy to eliminate redundant filters in RSFNet, significantly reducing model parameters and computational complexity. Experimental results on the chest X-ray 2017 dataset demonstrate that: 1) our proposed DSHNet achieves Fréchet Inception Distance of 36.92 and Kernel Inception Distance of 0.03 for generating chest X-ray images, outperforming three classical GAN-based approaches, 2) our proposed DSH-RSFNet achieves accuracy, precision, recall and F1-score of 95.51%, 95.15%, 95.30% and 95.22%, surpassing both baseline and recent CNN-based approaches, 3) compared to DSH-RSFNet, our proposed DSH-RSF-Lite approach obtains a significant decrease in model parameters, storage space, floating point operations and latency by more than 68.20%, 67.72%, 69.46% and 22.68%, while it has only 0.64%, 0.14%, 1.28% and 0.75% reduction in accuracy, precision, recall and F1-score, respectively. Extensive comparative experiments validate the effectiveness of our proposed DSH-RSF-Lite approach, highlighting its efficiency in augmenting chest X-ray images, improving the performance of pneumonia classification

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Continual Learning via Manifold Expansion Replay

Continual Learning via Manifold Expansion Replay

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Zihao Xu Xuan Tang Yufei Shi Jianfeng Zhang Jian Yang Mingsong Chen Xian Wei Software Engineering Institute East China Normal University Shanghai China school of communication & electronic engineering East China Normal University Shanghai China Department of Medical Informatics and Zhongshan School of Medicine Sun Yat-sen University Guangzhou China School of Geospatial Information Information Engineering University Zhengzhou China

In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based methods use episodic memory to replay samples of previous tasks. However, in the process of knowledge integration when learning a new task, this strategy also suffers from catastrophic forgetting due to an imbalance between old and new knowledge. To address this problem, we propose a novel replay strategy called Manifold Expansion Replay (MaER). We argue that expanding the implicit manifold of the knowledge representation in the episodic memory helps to improve the robustness and expressiveness of the model. To this end, we propose a greedy strategy to keep increasing the diameter of the implicit manifold represented by the knowledge in the buffer during memory management. In addition, we introduce Wasserstein distance instead of cross entropy as distillation loss to preserve previous knowledge. With extensive experimental validation on MNIST, CIFAR10, CIFAR100, and TinyImageNet, we show that the proposed method significantly improves the accuracy in continual learning setup, outperforming the state of the arts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey

arXiv

引用

arXiv 2024年

作者： Ye, Mang Shen, Wei Du, Bo Snezhko, Eduard Kovalev, Vassili Yuen, Pong C. The National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China United Institute of Informatics Problems of Belarus National Academy of Sciences National Academy of Sciences of Belarus Minsk Belarus Department of Computer Science Hong Kong Baptist University Hong Kong

Vertical Federated Learning (VFL) is a privacy-preserving distributed learning paradigm where different parties collaboratively learn models using partitioned features of shared samples, without leaking private data. Recent research has shown promising results addressing various challenges in VFL, highlighting its potential for practical applications in cross-domain collaboration. However, the corresponding research is scattered and lacks organization. To advance VFL research, this survey offers a systematic overview of recent developments. First, we provide a history and background introduction, along with a summary of the general training protocol of VFL. We then revisit the taxonomy in recent reviews and analyze limitations in-depth. For a comprehensive and structured discussion, we synthesize recent research from three fundamental perspectives: effectiveness, security, and applicability. Finally, we discuss several critical future research directions in VFL, which will facilitate the developments in this field. We provide a collection of research lists and periodically update them at https://***/shentt67/VFL_Survey. Copyright © 2024, The Authors. All rights reserved.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

A Workflow Management Framework for the Dynamic Generation of Workflows that is Independent of the Application Environment

A Workflow Management Framework for the Dynamic Generation o...

引用

IFIP/IEEE International Symposium on Integrated Network Management

作者： Andrzej Jasinski Yuansong Qiao Enda Fallon Ronan Flynn Software Research Institute Athlone Institute of Technology Athlone Ireland Faculty of Engineering & Informatics Athlone Institute of Technology Athlone Ireland

Workflow is a well-known and widely used technology in business management. Traditional workflow solutions are designed for humans and generally use a graphical representation of workflow elements that reflect the involvement of human factors. Additionally, in a situation where workflow execution is not possible, human intervention is necessary. This means that current workflow design is limited in flexibility, in terms of tasks supported, and that it cannot be easily scaled or adopted. Furthermore, current workflow design is limited in efficiency and efficacy, especially in modern environments (e.g. 5G and IoT) where problems can be complex and solutions unpredictable. This paper proposes a workflow management framework that uses dynamically generated workflows to control a managed environment. Exception detection and handling in workflow generation produce recommendations for mitigating incidents that might occur. The key characteristics of the proposed framework are its ease of implementation, flexibility and scalability. These characteristics allow for the quick definition of new tasks, known and unknown, and to assess the quality of the generated recommendation through feedback from the managed environment. Experiments performed in two different environments, robotics and networking, demonstrate the elasticity and functionality of the proposed method to dynamically generated workflows.

关键词： 5G mobile communication Scalability Human factors Elasticity Task analysis Robots Business

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：