检索结果-内蒙古大学图书馆

32nd IEEE International Symposium on Industrial electronics, ISIE 2023

作者： Yin, Zhenxiao Zhao, Hang Robotics and Autonomous Systems Robotics and Autonomous Systems Guangzhou China The Hong Kong University of Science and Technology Department of Electronic & Computer Engineering Hong Kong Hong Kong

ISBN: (纸本)9798350399714

With the rapid development of computer science, neural network (NN) has received widespread attention. However, it is mainly used as a black box in identification and prediction, which is highly complicated. Its explainability should be mentioned when it is used in real applications. So, this paper derives the explainable control scheme to make sure its theoretical rigorousness. Then a straightforward explanation of the neural network controller using a block diagram is given to help researchers to reproduce the method. Since the detailed design of the neural network should concern the principle of permanent magnet synchronous motor (PMSM), this analyses the real PMSM system and finds the control performance characteristic, especially in spontaneous disturbances. Unlike the black-box neural network, the recurrent radial basis function neural network (RRBF) controller method is proposed, guided by overshoot. Because various PMSMs have various performances of speed changing, three key functions of RRBF are proposed to check which variant is the most suitable for reducing the overshoot. Finally, the RRBF method is implemented in STM32, and its effectiveness in the experiment is checked. © 2023 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Distributed Service Discovery over Heterogeneous Robotic Systems-of-Systems 19

Distributed Service Discovery over Heterogeneous Robotic Sys...

引用

19th Annual International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023

作者： Montecchiari, Leonardo Trotta, Angelo Gigli, Lorenzo Bellone, Lorenzo Di Felice, Marco Natalizio, Enrico University of Bologna Department of Computer Science and Engineering Italy University of Bologna Advanced Research Center on Electronic Systems Ercole de Castro Italy United Arab Emirates

ISBN: (纸本)9798350346497

In robotic swarms, nodes must cooperate in order to accomplish complex tasks. Robot interactions may occur at run-time based on the dynamic network topology and on mission-specific goals. For this reason, service discovery mechanisms are fundamental in order to inform each robot about the functionalities offered by the other peers. Although several network discovery protocols have been proposed so far, none of them fits the unique characteristics of robotic swarms in terms of dynamic topology, communication heterogeneity, and latency requirements. In this paper, we fill such gap by designing, implementing and evaluating a novel service discovery mechanisms for generic Robotic Systems-of-Systems (RSoS). The study proposes algorithmic and practical contributions. Regarding the first, we describe a novel distributed service discovery algorithm for RSoS which adapts to highly mobile robotic environments while limiting the network overhead and latency. Regarding the latter, we implemented the proposed algorithm within the Uhura swarm robotics framework;as a result, our solution is able to support multi-radio scenarios where robots are provided with heterogeneous Machine-to-Machine (M2M) communication technologies. In addition, we validate our solution through large-scale simulations and a test-bed in which ground robots are able to discover a Federated Learning (FL) task and join it at run-time to improve the accuracy. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Conceptual Pacts for Reference Resolution using Small, Dynamically Constructed Language Models: A Study in Puzzle Building Dialogues 30

Conceptual Pacts for Reference Resolution using Small, Dynam...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Hough, Julian Zarrieß, Sina Kennington, Casey Schlangen, David Poesio, Massimo School of Mathematics and Computer Science Swansea University United Kingdom Faculty of Linguistics and Literature Bielefeld University Germany Department of Computer Science Boise State University United States Department of Linguistics University of Potsdam Germany Berlin Germany School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom

ISBN: (纸本)9782493814104

Using Brennan and Clark's theory of a Conceptual Pact, that when interlocutors agree on a name for an object, they are forming a temporary agreement on how to conceptualize that object, we present an extension to a simple reference resolver which simulates this process over time with different conversation pairs. In a puzzle construction domain, we model pacts with small language models for each referent which update during the interaction. When features from these pact models are incorporated into a simple bag-of-words reference resolver, the accuracy increases compared to using a standard pre-trained model. The model performs equally to a competitor using the same data but with exhaustive re-training after each prediction, while also being more transparent, faster and less resource-intensive. We also experiment with reducing the number of training interactions, and can still achieve reference resolution accuracies of over 80% in testing from observing a single previous interaction, over 20% higher than a pre-trained baseline. While this is a limited domain, we argue the model could be applicable to larger real-world applications in human and human-robot interaction and is an interpretable and transparent model. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Human robot interaction

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

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

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

ISBN: (纸本)9798350337020

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. © 2023 IEEE.

关键词： catastrophic forgetting continual learning manifold diameter Wasserstein distance

来源：评论

学校读者我要写书评

暂无评论

Remarks on Gibbs Permutation Matrices for Ternary Bent Functions 53

Remarks on Gibbs Permutation Matrices for Ternary Bent Funct...

引用

53rd IEEE International Symposium on Multiple-Valued Logic, ISMVL 2023

作者： Stanković, Radomir S. Stanković, Milena Moraga, Claudio Astola, Jaakko T. Mathematical Institute of Sasa Belgrade Serbia Faculty of Electronic Engineering Department of Computer Science Niš Serbia Technical University of Dortmund Faculty of Computer Science Dortmund Germany Tampere University of Technology Department of Signal Processing Tampere Finland

ISBN: (纸本)9781665464161

As in the binary case, ternary bent functions are a very small portion of the set of all ternary functions for a given number of variables. For example, for n = 2, there are 486 ternary bent functions out of 19683 ternary functions, which is 2, 47%, and this number reduces exponentially with the increase of n. However, finding, or alternatively, constructing them is a challenging task. A possible approach is based upon the manipulation of known ternary bent functions to construct other ternary bent functions. In this paper, we define Gibbs permutation matrices derived from the Gibbs derivative with respect to the Vilenkin-Chrestenson transform and propose their usage in constructing bent functions. The method can be extended to p-valued bent functions, where p is a prime larger than 3. © 2023 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

MCBC-SMOTE:A Majority Clustering Model for Classification of Imbalanced Data

引用

computers, Materials & Continua 2022年第12期73卷 4801-4817页

作者： Jyoti Arora Meena Tushir Keshav Sharma Lalit Mohan Aman Singh Abdullah Alharbi Wael Alosaimi Department of Information Technology MSITGGSIPUNew Delhi110058India Department of Electrical and Electronic Engineering MSITGGSIPUNew Delhi110058India School of Computer Science and Engineering Lovely Professional University144411PunjabIndia Department of Information Technology College of Computers and Information TechnologyTaif University11099Taif 21944Saudi Arabia

Datasets with the imbalanced class distribution are difficult to handle with the standard classification *** supervised learning,dealing with the problem of class imbalance is still considered to be a challenging research *** machine learning techniques are designed to operate on balanced datasets;therefore,the state of the art,different undersampling,over-sampling and hybrid strategies have been proposed to deal with the problem of imbalanced datasets,but highly skewed datasets still pose the problem of generalization and noise generation during *** overcome these problems,this paper proposes amajority clusteringmodel for classification of imbalanced datasets known as MCBC-SMOTE(Majority Clustering for balanced Classification-SMOTE).The model provides a method to convert the problem of binary classification into a multi-class *** the proposed algorithm,the number of clusters for themajority class is calculated using the elbow method and the minority class is over-sampled as an average of clustered majority classes to generate a symmetrical class *** proposed technique is cost-effective,reduces the problem of noise generation and successfully disables the imbalances present in between and within *** results of the evaluations on diverse real datasets proved to provide better classification results as compared to state of the art existing methodologies based on several performance metrics.

关键词： Imbalance class problem classification SMOTE k-means clustering sampling

来源：评论

学校读者我要写书评

暂无评论

Real World Data-Driven Agent-Based Modeling for Health Policy Insights During Epidemics

Real World Data-Driven Agent-Based Modeling for Health Polic...

引用

Advancements in Computing (ICAC), International Conference on

作者： Sashini Liyanage Mahesha Viduranga Mario De Silva Roshan Godaliyadda Vijitha Herath Mervyn Parakrama Ekanayake Janaka Ekanayake Department of Computer Engineering University of Peradeniya Peradeniya Sri Lanka Department of Electrical and Electronic Engineering University of Peradeniya Peradeniya Sri Lanka

ISBN: (数字)9798331517878

ISBN: (纸本)9798331517885

Pandemics and epidemics pose significant threats due to their rapid global spread, overwhelming healthcare systems, and causing high mortality and morbidity rates. The recent COVID-19 pandemic has underscored the urgent need for advanced tools to predict and manage infectious disease transmission in complex populations. While Agent-Based Models (ABMs) have become crucial in this context, many existing models oversimplify simulation environments and often fail to consider disease transmission through public transportation. In this study, we propose a framework that integrates a realistic environment and transportation model into the ABM, enhancing its accuracy in simulating airborne disease spread. Our framework is designed to be adaptable and generalizable, making it suitable for modeling various diseases. As a case study, we simulate COVID-19 transmission in the Kandy District, demonstrating how incorporating a realistic environment and transportation network improves the model's ability to reflect real-world conditions. This approach provides a more precise tool for disease propagation simulations within ABMs, offering valuable insights for public health strategies.

关键词： COVID-19 Adaptation models Accuracy Pandemics Atmospheric modeling Mortality Public healthcare Public transportation Diseases Context modeling

来源：评论

学校读者我要写书评

暂无评论

FAA-CLIP: Federated Adversarial Adaptation of CLIP

引用

IEEE Internet of Things Journal 2025年第12期12卷 21091-21102页

作者： Wu, Yihang Chaddad, Ahmad Desrosiers, Christian Daqqaq, Tareef Kateb, Reem Guilin University of Electronic Technology Artificial Intelligence for Personalised medicine School of Artificial Intelligence Guilin China Ecole de Technologie Superieure The Laboratory for Imagery Vision and Artificial Intelligence Montreal Canada Taibah University College of Medicine Al Madinah Saudi Arabia Ministry of National Guard health Affairs Prince Mohammed Bin Abdulaziz Hospital Al-Madinah Saudi Arabia Taibah University and College of Computer Science and Engineering Jeddah University College of Computer Science and Engineering Cyber Security Department Jeddah Saudi Arabia

Despite the remarkable performance of vision language models (VLMs) such as Contrastive Language Image Pre-training (CLIP), the large size of these models is a considerable obstacle to their use in federated learning (FL) systems where the parameters of local client models need to be transferred to a global server for aggregation. Another challenge in FL is the heterogeneity of data from different clients, which affects the generalization performance of the solution. In addition, natural pre-trained VLMs exhibit poor generalization ability in the medical datasets, suggests there exists a domain gap. To solve these issues, we introduce a novel method for the Federated Adversarial Adaptation (FAA) of CLIP. Our method, named FAA-CLIP, handles the large communication costs of CLIP using a light-weight feature adaptation module (FAM) for aggregation, effectively adapting this VLM to each client's data while greatly reducing the number of parameters to transfer. By keeping CLIP frozen and only updating the FAM parameters, our method is also computationally efficient. Unlike existing approaches, our FAA-CLIP method directly addresses the problem of domain shifts across clients via a domain adaptation (DA) module. This module employs a domain classifier to predict if a given sample is from the local client or the global server, allowing the model to learn domain-invariant representations. Extensive experiments on six different datasets containing both natural and medical images demonstrate that FAA-CLIP can generalize well on both natural and medical datasets compared to recent FL approaches. Our codes are available at https://***/AIPMLab/FAA-CLIP. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Resource Management in IoTs Using Evolutionary and Swarm Intelligence Algorithms 7

Efficient Resource Management in IoTs Using Evolutionary and...

引用

7th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2023

作者： Gupta, Keshav Dev Cengiz, Korhan Awasthi, Charu Ramini, Siva Akash Chatterjee, Shyamapriya Pavithra, M. Poornima College of Engineering Department of Computer Science Engineering Jaipur India University of Fujairah College of Information Technology United Arab Emirates Istinye University Department of Computer Engineering Istanbul Turkey University of Hradec Kralove Faculty of Informatics and Management Department of Information Technologies Hradec Kralove500 03 Czech Republic JSS Academy of Technical Education Department of Information Technology Noida India Andhra Pradesh Amaravati India Narula Institute of Technology Department of Information Technology West Bengal Kolkata India Jansons Institute of Technology Karumathampatti Department of Computer Science and Engineering Coimbatore641659 India

ISBN: (纸本)9798350383065

The proliferation of the Internet of Things (IoT) has ushered in a transformative era of connected devices, emphasizing the critical need for effective resource management. This study introduces an innovative approach that harnesses Evolutionary and Swarm Intelligence algorithms for IoT Task Scheduling, addressing resource optimization challenges. The approach offers superior resource utilization through advanced optimization techniques, reducing energy consumption and enhancing efficiency. Furthermore, it significantly reduces task scheduling execution time, enabling prompt decision-making in dynamic IoT environments. This results in improved task allocation quality, meeting application-specific requirements, and prioritizing critical tasks. Notably, the approach excels in minimizing completion time, making it particularly advantageous for real-time IoT applications. This research contributes to the advancement of IoT resource management, offering an adaptive, efficient, and intelligent solution with broad applicability. In the evolving landscape of IoT, the findings presented here lay a solid foundation for future research and practical implementations, ultimately promoting more responsive, sustainable, and intelligent IoT ecosystems. © 2023 IEEE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

A comprehensive IoT-Based Home Automation Solution: Analyzing Security Threats, Maintenance and Proposal

A comprehensive IoT-Based Home Automation Solution: Analyzin...

引用

2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2022

作者： Mashiat, Lamisa Azad, Sumaiya Binte Jinia, Sadia Naj Islam, Md. Ariful Rahman, Md. Ziaur International Islamic University Chittagong Department of Computer Science & Engineering Kumira Chittagong Bangladesh International Islamic University Chittagong Department of Electrical & Electronic Engineering Kumira Chittagong Bangladesh

ISBN: (纸本)9781665477192

Every aspect of life in this 4th industrial revolution era is influenced by technology. IoT is a key component of this technology since it enables the integration of multiple sensors into a network that is globally connected and where communication and sharing of information are associated. IoT is an effective evidence holder that provides real-time data updates and preserves any outdated information. Analyzing the security threats and maintenance concerns and future scope, we presented a solution in this paper. This research aims to design a biometric technology coupled with a sensor-integrated framework for defense. Our Prototype is a combination of multiple subsystems: i. Authentication Mechanism ii. Remote Maintenance. The first mechanism guarantees safety enhancement by prohibiting unauthorized visits by scanning fingerprints at the entrance. The other one is an advanced sensor module that takes immediate action whenever it detects an occurrence of an accident. Finally, there is a web panel server interconnected, through which we can keep track of all the real-time updates of the residence. In order to maintain our loved ones' safety, we are advancing technology in this way with the certainty of security. © 2022 IEEE.

关键词： Internet of things

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：