检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and systems (ISCAS)

作者： David Simpson Jim Harkin Malachy McElholm Liam McDaid School of Computing Engineering and Intelligent Systems Ulster University Derry UK

ISBN: (数字)9798350356830

ISBN: (纸本)9798350356847

Modern micro-processors face reliability challenges due to manufacturing defects, aging or when operating in harsh environments like deep-sea or space. Watchdog mechanisms are essential for detecting both permanent and transient faults, but they must exhibit minimal overheads in terms of power and area consumption. Nonetheless, additional research is required to ensure the dependability of the watchdog circuit as if compromised, could pose a significant threat to the system. This paper proposes a smart watchdog paradigm based on spiking neural networks (SNNs) that could realise a reliable, low power and area efficient solution. The smart watchdog presented in this paper was trained to monitor control flow at the execute stage of a RISC-V processor with results showing high fault coverage of 98%, independent of the software application executed. The smart watchdog was able to detect faults not recognised by the trap handler of the RISC-V core. An FPGA implementation of the smart watchdog validates the in-circuit fault detection capability when deployed with a RISC-V processor.

关键词： Fault detection Process control Spiking neural networks Transforms Electrical fault detection Hardware Robustness Software reliability Transient analysis Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Pilot Study on the User Experience of Different Upper Body Extended Reality Physiotherapy Interventions 3

A Pilot Study on the User Experience of Different Upper Body...

引用

3rd IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2024

作者： Brennan, Alex Rankin, Debbie Charles, Therese Blackburn, Nicole McCreadie, Karl Condell, Joan School of Computing Engineering and Intelligent Systems Ulster University Londonderry United Kingdom School of Arts and Humanities Ulster University Londonderry United Kingdom School of Health Sciences Ulster University Londonderry United Kingdom

ISBN: (纸本)9798350378009

The integration of Extended Reality (XR) technology in clinical contexts has shown promising outcomes for diverse vulnerable populations. This paper presents a multistage study conducted to assess user experience during physiotherapy within an XR nature environment, aiming to inform future work in this field. While prior research highlighted the positive impact of XR rehabilitation, comparative analysis between different XR experiences is lacking. This study involved six participants, guided through three stages. Stage 1 used a computer monitor displaying an instructional physiotherapy video, while stages 2 and 3 incorporated XR experiences using a Meta Quest 3 headset. Stage 3 introduced visual and auditory feedback upon completion of exercises. Data collection included pre-study questionnaires, think-aloud interviews and assessments using the NASA Task Load Index (NASA TLX) and the Game User Experience Satisfaction Scale (GUESS-18). Findings revealed that stage 3 caused the highest cognitive workload but also the highest user experience satisfaction. Participants expressed a preference for immersive XR environments, citing enhanced focus and enjoyment. Overall, participants demonstrated a willingness to return to all three stages, further supporting the potential of XR physiotherapy for improving engagement and outcomes in rehabilitation. Further research will explore optimisation strategies regarding workload and user experience and assess long-term impacts on patient outcomes. © 2024 IEEE.

关键词： Extended Reality (XR) Physiotherapy Rehabilitation User Experience Virtual Reality (VR)

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking of AUV under Current Disturbance Based on Adaptive LADRC 2

Trajectory Tracking of AUV under Current Disturbance Based o...

引用

2nd International Conference on Automation, Robotics and Computer engineering, ICARCE 2023

作者： Ji, Daxiong Wang, Xinwei Xu, Minghui Zhang, Qiang Sharma, Sanjay Sutton, Robert Institute of Marine Electronics and Intelligent Systems Ocean Collage Zhejiang University Donghai Lab Zhoushan China School of Engineering Computing and Mathematics University of Plymouth Intelligent Autonomous Control Systems Plymouth United Kingdom

ISBN: (纸本)9798350308341

In consideration of the trajectory tracking problem of autonomous underwater vehicle (AUV) under external current disturbance, an adaptive linear active disturbance rejection control (LADRC) method is proposed. Unlike the conditional LADRC using fixed parameters for extended state observer, the proposed controller makes use of the error of estimation and automatically adjusts the parameter online. As shown in the simulation, the adaptive LADRC estimates the external current disturbance effectively, and tracks the 3D trajectory better compared with traditional LADRC. © 2023 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Efficient Inference of Markov Logic Network for Link Prediction 12

Efficient Inference of Markov Logic Network for Link Predict...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Li, Zhongbin Duan, Liang Yue, Kun Yunnan University School of Information Science and Engineering Kunming China Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Kunming China

ISBN: (纸本)9798350340181

Link prediction has achieved great success on ubiquitous graph-based applications, which usually contain multiple types of connections. The heterogeneity of networks introduces complexities in two aspects: representation of multiple types of links, and incorporation of domain knowledge. In this paper, we construct Markov logic network (MLN) to preserve he logical information of graphs for link prediction tasks. By using the graph neural network, we propose a novel inference method in MLNs to guarantee the scalability of link prediction. Experimental results on various datasets show that our proposed method outperforms the state-of-the-art competitors on precision and efficiency. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient multi-target classification for bug priority and resolution time prediction

引用

Multimedia Tools and Applications 2024年 1-30页

作者： Madaraboina, Satya Narayana Sharma, Sahil Singh, Simranjit Kumar, Vijay Liverpool John Moores University Liverpool United Kingdom School of Computing Engineering and Intelligent Systems Ulster University Northern Ireland Londonderry United Kingdom Department of Information Technology Dr. B R Ambedkar National Institute of Technology Punjab Jalandhar India

Bug triage teams allocate substantial resources to determine the priority and resolution time of reported defects, frequently hampered by a lack of specialized knowledge in the relevant subject. This work presents sophisticated multi-target classification models for the simultaneous prediction of problem priority and resolution time. We investigate transformation strategies, such as Classifier Chains, Binary Relevance, Label Power Sets, and Random k-Label Sets (RAKEL), over various machine learning and deep learning models utilising the Functional API. The models are trained using a newly launched dataset, the Spring JIRA Bug Dataset, available at IEEE ***/documents/spring-jira-bug-dataset, which includes bug summaries from the Jira bug tracking software. Model performance evaluation involves using metrics such as Hamming Loss, Accuracy, Weighted Precision, Weighted Recall, Weighted F1-Score, and MCC. The experimental findings indicate substantial enhancements in prediction accuracy and computing efficiency, showcasing the potential of these models to significantly improve the bug triage process by automating estimations of priority and resolution time. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Continuous Sub-prevalent Co-location Pattern Mining 1

引用

4th International Conference on Spatial Data and Intelligence, SpatialDI 2023

作者： Wang, Qilong Chen, Hongmei Wang, Lizhen School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (数字)9783031329104

ISBN: (纸本)9783031329098

Spatial co-location pattern represents a subset of spatial features whose instances are frequently located together in space. Sub-prevalent co-location pattern mining discovers patterns with richer spatial relationships based on star instance model instead of clique instance model. Further, discovering spatiotemporal sub-prevalent co-location pattern is important to reveal the spatiotemporal interaction between spatial features and promote the application of patterns. However, the methods for mining spatiotemporal sub-prevalent co-location pattern measure the interestingness of patterns by the frequency of patterns in time slice set, and ignore the duration of patterns which is an important spatiotemproal information in patterns. Thus, this paper presents mining spatiotemporal sub-prevalent co-location pattern by considering the duration and the frequency of patterns. Specifically, a novel pattern, is proposed by defining the continuous sub-prevalent index. Then, an efficient algorithm is designed to mine the proposed patterns by utilizing the anti-monotonicity of continuous sub-prevalent index to prune unpromising patterns. Extensive experiments on synthetic and real datasets verify the practicability of the proposed patterns and the effectiveness of the proposed algorithm. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Structural Entropy Based Graph Node Classification 12

Structural Entropy Based Graph Node Classification

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Zhang, Jun Yue, Kun School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (纸本)9798350340181

Node classification is to predict the labels of the unlabeled nodes in a graph, which is useful for various applications of social network and biological information analysis. To measure the uncertainty of structural information, we propose the structural entropy theory based method for graph node classification. First, we calculate the structural entropy of different graph structures, since the smaller the structural entropy, the less the uncertainty of the structural relationship in the graph. Then, we use the minimal structural entropy to determine the uncertainty of graphical structures. Finally, the nodes with similar structural relationships in the graph are classified. Experimental results show that our method outperforms some state-of-the-art competitors. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Can Sentiment Mining of Novice and Expert User Survey Feedback Enhance the Digital User Experience? 8

Can Sentiment Mining of Novice and Expert User Survey Feedba...

引用

8th International HCI and UX Conference in Indonesia, CHIuXiD 2022

作者： Johnston, Vivien Black, Michaela Wallace, Jonathan Bond, Raymond Mulvenna, Maurice Ulster University School of Computing Belfast United Kingdom Engineering and Intelligent Systems Ulster University School of Computing Londonderry United Kingdom

ISBN: (纸本)9781665476645

In recent years, sentiment mining has been used within politics and social media to understand the emotions and opinions that people have about society and different political groups to help bring change. However, in the user centered design process, a main component that helps bring change is the use of user feedback and there has been little research in terms of adopting sentiment mining to assist with this and the user experience of an application. This research paper implements the use of sentiment mining on user survey feedback from Jupyter Notebook and has identified different components of the user experience that caters for novice and expert users independently. Recommendations from this research will help Jupyter Notebook create a user experience that caters to novice and expert users and their workflow needs. This initial analysis has identified that sentiment mining provides important and subtle enhancements for user experience that other tools and techniques do not provide. Therefore, this is a worthwhile method of user experience assessment to foster to enhance a digital user experience. © 2022 IEEE.

关键词： User centered design

来源：评论

学校读者我要写书评

暂无评论

A Method for Measuring Node Similarity in Heterogeneous Information Networks 9

A Method for Measuring Node Similarity in Heterogeneous Info...

引用

9th International Conference on Fuzzy systems and Data Mining, FSDM 2023

作者： Zhan, Liudi Chen, Hongmei Zhou, Lihua Xiao, Qing School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (纸本)9781643684703

Meta-path-based methods for measuring the similarities between nodes in Heterogeneous Information Networks (HINs) have attracted attention from researchers due to excellent performance. However, these methods suffer from some issues: (1) it is difficult for users to provide effective meta-paths of complex HINs;(2) it is inefficient to enumerate all instances of meta-paths. In order to solve the above issues, this paper proposes a novel method, K-order Neighbors based Heterogeneous Graph Neural Network (KN-HGNN), for measuring node similarity. Firstly, KN-HGNN generates meta-paths based on network schema. Then, KN-HGNN obtains the features of nodes by aggregating itself type feature and its k-order neighbors' type features under the constraints of meta-paths. Finally, KN-HGNN calculates the similarities between nodes based on the features of nodes. The experimental results on real datasets show that KN-HGNN outperforms the baselines. © 2023 The authors and IOS Press.

关键词： Information services

来源：评论

学校读者我要写书评

暂无评论

INNSE: Invertible neural network-based DNA image storage with self-correction encoding

引用

Computational and Structural Biotechnology Journal 2025年 27卷 2492-2502页

作者： Zheng, Yanfen Zhang, Xiaokang Sun, Lijun Cao, Ben Wang, Bin Zhang, Qiang Zheng, Pan School of Computer Science and Technology Dalian University of Technology Liaoning Dalian116024 China The Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Liaoning Dalian116622 China Department of Accounting and Information Systems University of Canterbury Upper Riccarton Christchurch8140 New Zealand

DNA storage has become an alternative to silicon-based storage of media. However, when used to store multimodal data such as images, it fails to take full advantage of the characteristics of high correlation and variability present in such data, and currently remains inferior in terms of encoding density and time complexity. It also has the shortcoming of weak performance in terms of error correction methods to address insertion and deletion errors caused by error crosstalk. Therefore, we proposed an invertible neural network-based DNA image storage self-correction encoding method (INNSE) that uses the invertibility of network to perform up-down sampling processing on image and video data, thereby greatly reducing the number of DNA sequences required for data storage. A codebook generator was then designed to encode low-dimensional vectors into DNA sequences that meet various constraints. Finally, a self-correction method was constructed to achieve DNA sequence error correction at the base level without adding any redundant information. Our experimental results showed that, compared to the Yin-Yang algorithm, the encoding density of INNSE was increased by 3×, encoding time complexity was reduced by 95.26%. Under a simulated error rate of 2%, PSNR and SSIM were raised by 80.88% and 63.82%, respectively, proving that INNSE has significant advantages in encoding performance and error correction ability. © 2025

关键词： Network coding

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：