检索结果-内蒙古大学图书馆

Entity summarization in fuzzy knowledge graph based on fuzzy concept analysis 15th

学校读者我要写书评

暂无评论

Entity summarization in fuzzy knowledge graph based on fuzzy...

15th International Conference on Future Information Technology, Future Tech 2020

作者： Yang, Erhe Hao, Fei Gao, Jie Park, Doo-Soon School of Computer Science Shaanxi Normal University Xi’an China Department of Computer Science University of Exeter Exeter United Kingdom Department of Computer Software Engineering Soonchunhyang University Asan Korea Republic of

ISBN: (纸本)9789811593086

Considerable attention has recently been devoted to Knowledge Graph (KG), which has been applied in many domains. However, the information is often imprecise and vague when constructing the knowledge graph and thus the Fuzzy Knowledge Graph (FKG) emerged. Considering the increasing data in FKG, this paper firstly formulates the entity summarization in FKG and proposes an approach leveraging Fuzzy Formal Concept Analysis (FFCA). More specifically, the predicates and objects in RDF triples are deemed as attributes and objects in FFCA, respectively. Then, the fuzzy formal context can be obtained and the fuzzy concept lattice can be constructed. Finally, the concepts are ranked by the cardinality of the extent in concept lattice and the vague value of objects in RDF triples. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Formal concept analysis

A semi-supervised GCN-based community detection algorithm

学校读者我要写书评

暂无评论

A semi-supervised GCN-based community detection algorithm

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Shu-Han Shi Lei-Lei Shi Lu Liu Zi-Xuan Han Liang Jiang Fu-Xiang Chen School of Computer Science and Communication Engineering Jiangsu University China Department of Computer Science University of Exeter UK School of Ocean Jiangsu University of Science and Technology China School of Computing and Mathematical Sciences University of Leicester UK

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Community detection reveals the unique characteristics and relationships of in-network members, differentiated from out-of-community members and plays a pivotal role in network analysis. In recent years, deep learning techniques have made great strides in the application of community detection, especially on label sampling models, which train graph convolutional networks by constructing a balanced training set through structural centre localization and neighbourhood node expansion. However, such algorithms are limited on centre selection in community structure. To address this, this paper introduces a novel community detection algorithm based on peak density adaptive iterative segmentation, or LDACN in short. First, labels are assigned by adaptively selecting the centre node of the community structure, which results in a more even distribution of labels in the network. Subsequently, more accurate community segmentation is achieved by taking advantage of GCN's combined ability in capturing the connectivity relationships between the nodes and their intrinsic characteristics. Experimental results on synthetic and real-world network datasets show that our algorithm improves the effectiveness of community segmentation compared to the state-of-the-art algorithms.

关键词： Training Representation learning Measurement Location awareness Accuracy Graph convolutional networks Network analyzers Prediction algorithms Reliability Detection algorithms

Single Application Service Deployment in the Edge Environment Based on the E-CARGO Model

学校读者我要写书评

暂无评论

Single Application Service Deployment in the Edge Environmen...

International Conference on computer Supported Cooperative Work in Design

作者： Senyue Zhang Ling Xue Weiliang Huang Lu Zhao Ke Li School of Artificial Intelligence Shenyang Aerospace University Shenyang China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China Department of Computer Science University of Exeter Exeter UK

The popularization and application of 5G technology is about to open the era of global "data explosion". The traditional cloud computing model shows insufficient service support for resource-sensitive applications, especially in terms of latency, and edge computing can solve this problem by providing service support close to the user request side. This article formalizes the single application service deployment problem (SASDP) using the E-CARGO (Environment-Class, Agent, Role, Group, and Object) model. Through group role assignment (GRA), a high-satisfaction service deployment scheme for single application service deployment is designed, and satisfaction evaluation is established through delay to provide providers with satisfactory deployment solutions and achieve economic benefits. Finally, large-scale simulation experiments are carried out based on Python PuLP platform, and experiments show that our method is better than the baseline method in terms of overall satisfaction, user coverage and economy.

关键词：

How CanWe Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yamaguchi, Atsuki Villavicencio, Aline Aletras, Nikolaos School of Computer Science University of Sheffield United Kingdom Department of Computer Science Institute of Data Science and Artificial Intelligence University of Exeter United Kingdom

Large language models (LLMs) have shown remarkable capabilities in many languages beyond English. Yet, LLMs require more inference steps when generating non-English text due to their reliance on English-centric tokenizers and vocabulary, resulting in higher usage costs to non-English speakers. Vocabulary expansion with target language tokens is a widely used cross-lingual vocabulary adaptation approach to remedy this issue. Despite its effectiveness in inference speedup, previous work on vocabulary expansion has focused on high-resource settings assuming access to a substantial amount of target language data to effectively initialize the embeddings of the new tokens and adapt the LLM to the target language. However, vocabulary expansion in low-resource settings has yet to be explored. In this paper, we investigate vocabulary expansion in low-resource settings by considering embedding initialization methods and continual pre-training strategies. Through extensive experiments across typologically diverse languages, tasks and models, we establish a set of strategies to perform vocabulary expansion for faster inference, maintaining competitive downstream performance to baselines with only 30K sentences (∼0.01GB text data) from the target language. Copyright © 2024, The Authors. All rights reserved.

关键词： Embeddings

Deep learning and classical computer vision techniques in medical image analysis: Case studies on brain MRI tissue segmentation, lung CT COPD registration, and skin lesion classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tweneboah, Daniel Anyimadu Ahmed, Taofik Suleiman Imran, Mohammad Hossain Department of Computer Science University of Exeter Exeter United Kingdom Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology Emory University Atlanta United States Department of Computer Science Sorbonne Université Paris France

Medical imaging spans diverse tasks and modalities which play a pivotal role in disease diagnosis, treatment planning, and monitoring. This study presents a novel exploration, being the first to systematically evaluate segmentation, registration, and classification tasks across multiple imaging modalities. Integrating both classical and deep learning (DL) approaches in addressing brain MRI tissue segmentation, lung CT image registration, and skin lesion classification from dermoscopic images, we demonstrate the complementary strengths of these methodologies in diverse applications. For brain tissue segmentation, 3D DL models outperformed 2D and patch-based models, specifically nnU-Net achieving highest Dice Coefficient (DSC) of 0.9397, with 3D U-Net models on ResNet34 backbone, offering competitive results (with DSC 0.8946). Multi-Atlas methods provided robust alternatives for cases where DL methods are not feasible, achieving average DSCs of 0.7267 (with majority voting) and 0.7255 (with weighted by mutual information). In lung CT registration, classical Elastix-based methods outperformed DL models, achieving a minimum Target Registration Error (TRE) of 6.68 ± 5.98 mm, highlighting the effectiveness of parameter tuning. HighResNet performed best among DL models with a TRE of 7.40 mm. For skin lesion classification, ensembles of DL models like InceptionResNetV2 and ResNet50 excelled, achieving up to 90.44%, and 93.62% accuracies for binary and multiclass classification respectively. Leveraging the One-vs-All method, DL attained accuracies of 94.64% (mel vs. others), 95.35% (bcc vs. others), and 96.93% (scc vs. others), while ML models specifically Multi-Layer Perceptron (MLP) on handcrafted features offered interpretable, efficient alternatives with 85.04% accuracy using SMOTE for class imbalance correction on the multi-class task and 83.27% on the binary-class task. This study represents the first comprehensive evaluation across segmentation, registration, and clas

关键词： Deep learning

Genetic Auto-prompt Learning for Pre-trained Code Intelligence Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Feng, Chengzhe Sun, Yanan Li, Ke Zhou, Pan Lv, Jiancheng Lu, Aojun The College of Computer Science Sichuan University Chengdu610065 China The Department of Computer Science University of Exeter ExeterEX4 4QF United Kingdom The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

As Pre-trained Language Models (PLMs), a popular approach for code intelligence, continue to grow in size, the computational cost of their usage has become prohibitively expensive. Prompt learning, a recent development in the field of natural language processing, emerges as a potential solution to address this challenge. In this paper, we investigate the effectiveness of prompt learning in code intelligence tasks. We unveil its reliance on manually designed prompts, which often require significant human effort and expertise. Moreover, we discover existing automatic prompt design methods are very limited to code intelligence tasks due to factors including gradient dependence, high computational demands, and limited applicability. To effectively address both issues, we propose Genetic Auto Prompt (GenAP), which utilizes an elaborate genetic algorithm to automatically design prompts. With GenAP, non-experts can effortlessly generate superior prompts compared to meticulously manual-designed ones. GenAP operates without the need for gradients or additional computational costs, rendering it gradient-free and cost-effective. Moreover, GenAP supports both understanding and generation types of code intelligence tasks, exhibiting great applicability. We conduct GenAP on three popular code intelligence PLMs with three canonical code intelligence tasks including defect prediction, code summarization, and code translation. The results suggest that GenAP can effectively automate the process of designing prompts. Specifically, GenAP outperforms all other methods across all three tasks (e.g. improving accuracy by an average of 2.13% for defect prediction). To the best of our knowledge, GenAP is the first work to automatically design prompts for code intelligence PLMs. Copyright © 2024, The Authors. All rights reserved.

关键词： Design

Distributed Optimisation with Linear Equality and Inequality Constraints using PDMM

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Heusdens, Richard Zhang, Guoqiang Netherlands The Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands The University of Exeter Exeter United Kingdom

In this paper, we consider the problem of distributed optimisation of a separable convex cost function over a graph, where every edge and node in the graph could carry both linear equality and/or inequality constraints. We show how to modify the primal-dual method of multipliers (PDMM), originally designed for linear equality constraints, such that it can handle inequality constraints as well. The proposed algorithm does not need any slack variables, which is similar to the recent work [1] which extends the alternating direction method of multipliers (ADMM) for addressing decomposable optimisation with linear equality and inequality constraints. Using convex analysis, monotone operator theory and fixed-point theory, we show how to derive the update equations of the modified PDMM algorithm by applying Peaceman-Rachford splitting to the monotonic inclusion related to the lifted dual problem. To incorporate the inequality constraints, we impose a non-negativity constraint on the associated dual variables. This additional constraint results in the introduction of a reflection operator to model the data exchange in the network, instead of a permutation operator as derived for equality constraint PDMM. Convergence for both synchronous and stochastic update schemes of PDMM are provided. The latter includes asynchronous update schemes and update schemes with transmission losses. Experiments show that PDMM converges notably faster than extended ADMM of [1]. Copyright © 2023, The Authors. All rights reserved.

关键词： Electronic data interchange

Impact of Profile Orientation and Position on Soil Resistivity Measurement for Earthing Applications 58

学校读者我要写书评

暂无评论

Impact of Profile Orientation and Position on Soil Resistivi...

58th International Universities Power engineering Conference, UPEC 2023

作者： Kherif, O. Robson, S. Harid, N. Thorpe, D. Mousa, S. Stivanello, S. Haddad, A. Advanced High Voltage Engineering Research Centre School of Engineering Cardiff University CardiffCF24 3AA United Kingdom Khalifa University Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Limited DerbyshireNG16 6NS United Kingdom College of Life and Environmental Sciences University of Exeter ExeterEX4 4QL United Kingdom

ISBN: (纸本)9798350316834

Providing an effective earthing design is one of the primary challenges in electrical engineering as it encompasses various parameters and factors of different types. Soil resistivity measurements and modelling are among the key aspects considered in earthing analysis, alongside many other important parameters. In light of this, the present paper aims to demonstrate the significance of soil resistivity in relation to earthing performance, while also highlighting the impact of profile selection on the measurements. The study presents and discusses an experimental investigation highlighting the impact of soil heterogeneity on current dissipation in earthing conductors. The experimental setup explores the selection of soil resistivity measurement axes using a Wenner configuration. Multiple scenarios are considered, and the obtained results are thoroughly analysed and discussed. The measurement process involves assessing soil resistivity at various electrode spacing distances, both vertically and horizontally, within an open area. Through these measurements, a comprehensive understanding of the soil structure's heterogeneity is gained. Findings unequivocally demonstrate that soil cannot be considered a uniform medium. This is evident from the observed variations in its structure at different depths and lateral distances. As a result, there is a need to reconsider other earthing design factors, such as the cross-sectional area of the conductors. © 2023 IEEE.

关键词： Soils

Age-Optimal Computation Offloading for Mobile Edge Computing System

学校读者我要写书评

暂无评论

Age-Optimal Computation Offloading for Mobile Edge Computing...

IEEE International Conference on Communications Workshops, ICC

作者： Yi Chen Zheng Chang Geyong Min School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Information Technology University of Jyväskylä Jyväskylä Finland Department of Computer Science University of Exeter Exeter U.K.

Numerous Internet of Things (IoT) applications are sensitive to the freshness of status information for accurate monitoring and control. Due to the limitation of computational resources, status updates of IoT devices can be offloaded to the mobile edge computing (MEC) server for execution to enhance the information freshness. In this work, we investigate the computation offloading problem in the MEC-assisted IoT. Age of processing (AoP), which takes the data processing time into account, is adopted as a performance metric to measure the freshness of the information of IoT devices. To achieve the age-optimal solution, we explicitly consider the heterogeneity of the status information and develop the offloading decision with both linear and non-linear age functions. An average AoP minimization problem is then formulated as a decentralized computation offloading game and we propose an age-optimal computation offloading mechanism to obtain the optimal offloading strategy. Simulation results show the convergence of our proposed method and demonstrate the effectiveness of the proposed scheme under different scenarios.

关键词：