检索结果-内蒙古大学图书馆

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Li Huang, Zhenhao Wu, Hua Ye, Junda Peng, Hao Yu, Zhengtao Yu, Philip S. School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Department of Computer Science University of Illinois ChicagoIL United States

Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph. In the literature, most GSL solutions either primarily focus on structure refinement with task-specific supervision (i.e., node classification), or overlook the inherent weakness of GNNs themselves (e.g., over-squashing), resulting in suboptimal performance despite sophisticated designs. In light of these limitations, we propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs. In this paper, we take a fundamentally different perspective of the Ricci curvature in Riemannian geometry, in which we encounter the challenges of modeling, utilizing and computing Ricci curvature. To tackle these challenges, we present a self-supervised Riemannian model, DeepRicci. Specifically, we introduce a latent Riemannian space of heterogeneous curvatures to model various Ricci curvatures, and propose a gyrovector feature mapping to utilize Ricci curvature for typical GNNs. Thereafter, we refine node features by geometric contrastive learning among different geometric views, and simultaneously refine graph structure by backward Ricci flow based on a novel formulation of differentiable Ricci curvature. Finally, extensive experiments on public datasets show the superiority of DeepRicci, and the connection between backward Ricci flow and over-squashing. Codes of our work are given in https://***/RiemanGraph/. © 2024, CC BY-NC-SA.

关键词： Graph neural networks

Technology acceptance model (TAM) for mobile durian plantation apps(Pro Durian);the analysis for Malaysian farmers

学校读者我要写书评

暂无评论

Technology acceptance model (TAM) for mobile durian plantati...

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Noraziahtulhidayu Kamarudin Aiman Yusoff Abd Samad Hasan Basari Noor Zuraidin bin Mohd Safar Mohd Hatta Hussin Department of Multimedia Multimedia and Signal Processing Focus Group Faculty of Computer Science and Information Universiti Tun Hussein Onn Malaysia Department of Multimedia Faculty of Computer Science and Information Universiti Tun Hussein Onn Malaysia Department of Software Engineering Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Department of Information Security and Web Technology Faculty of Computer Science and Information Universiti Tun Hussein Onn Malaysia Johor Darul Takzim Pertubuhan Peladang Senggarang

During the application development process, it is important for a developer to analyze user requirements. This is crucial to the success of interactive systems and is an essential component of the design of information systems. User requirement analysis aids developers in understanding and analyzing users' needs and technology requirements. Throughout this case study, it is able to forecast the understanding, and technology acceptance, and at the same time improve the quality of work, reducing training and support costing and perennially improve customer or user satisfaction. The method of research selected is questionnaires that focused on collecting the data directly from Malaysian farmers through Google Forms as an online medium. The method was chosen because it is easy to implement and inexpensive due to the current situation of Covid-19. The questionnaire is designed with two sections where; a) includes the participant's demography to analyze information of the intended audience while b)focused on the knowledge of participants about recognition images. Results demonstrate the farmer's opinion and knowledge of the technology of image recognition in the agriculture sector. The quantitative research was undertaken using an online platform due to the Covid-19 pandemic. From the analysis, it is justified that the Technology Acceptance Model (TAM) together with the mobile farming image recognition app is useful in collecting farmers' feedback and positive results have an outcome on the challenges faced by the durian farmers.

关键词：

Natural Language Processing for Analyzing Electronic Health Records and Clinical Notes in Cancer Research: A Review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bilal, Muhammad Hamza, Ameer Malik, Nadia Department of Pharmaceutical Outcomes and Policy University of Florida GainesvilleFL32611 United States Department of Computer Science Faculty of Computing and IT University of Sargodha Punjab Sargodha40100 Pakistan Department of Software Engineering Faculty of Computing and IT University of Sargodha Punjab Sargodha40100 Pakistan

Objective: This review aims to analyze the application of natural language processing (NLP) techniques in cancer research using electronic health records (EHRs) and clinical notes. This review addresses gaps in the existing literature by providing a broader perspective than previous studies focused on specific cancer types or applications. Methods: A comprehensive literature search was conducted using the Scopus database, identifying 94 relevant studies published between 2019 and 2024. Data extraction included study characteristics, cancer types, NLP methodologies, dataset information, performance metrics, challenges, and future directions. Studies were categorized based on cancer types and NLP applications. Results: The results showed a growing trend in NLP applications for cancer research, with breast, lung, and colorectal cancers being the most studied. Information extraction and text classification emerged as predominant NLP tasks. A shift from rule-based to advanced machine learning techniques, particularly transformer-based models, was observed. The Dataset sizes used in existing studies varied widely. Key challenges included the limited generalizability of proposed solutions and the need for improved integration into clinical workflows. Conclusion: NLP techniques show significant potential in analyzing EHRs and clinical notes for cancer research. However, future work should focus on improving model generalizability, enhancing robustness in handling complex clinical language, and expanding applications to understudied cancer types. Integration of NLP tools into clinical practice and addressing ethical considerations remain crucial for utilizing the full potential of NLP in enhancing cancer diagnosis, treatment, and patient outcomes. © 2024, CC BY.

关键词： Electronic health record

Probabilistic Graph Modeling based Safety Classifier Algorithm for Smart Transportation

学校读者我要写书评

暂无评论

Procedia computer science 2024年 236卷 502-507页

作者： Najib El Karkouri Smail Tigani Rachid Saadane Abdelah Chehri Samuel Pierre Noureddine Neya Mathematics and Informatics Lab Faculty of Sciences University Ibno Toufial Kenitra Morocco Research and Development Unit Accsellium LLC Fez Morocco SIRC-LaGeS Hassania School of Public Labors 20250 Casablanca Morocco Department of Mathematics and Computer Science Royal Military College of Canada Kingston Canada Department of Computer and Software Engineering Polytechnique Montreal Canada

This research introduces a novel Probabilistic Graph Modeling-based Safety Classifier Algorithm designed for the purpose of classifying road safety in smart transportation systems. Leveraging a combination of numerical integration methods and Gaussian kernel density estimation models, the proposed algorithm offers an effective approach to assess and categorizing the safety levels of roads. The integration of these techniques enables a comprehensive analysis, allowing for a more nuanced understanding of the complex interactions within transportation networks. The algorithm's efficacy in road safety classification holds promising implications for enhancing traffic management and promoting safer urban environments.

关键词： Probabilistic Graph Numerical Computation Smart Transportation Classification Road Safety

Metaverse with Mobile Twin Edge Computing: Empowering Optimal Efficiency and Accuracy

学校读者我要写书评

暂无评论

Metaverse with Mobile Twin Edge Computing: Empowering Optima...

engineering & Computing Technologies (ICECT), International Conference on

作者： Asma Bibi Umara Noor Zahid Rashid Department of Software Engineering Faculty of Computing and Information Technology International Islamic University Islamabad Pakistan Department of Computer Science Kohsar University Murree Pakistan Technology Management Economics and Policy Program College of Engineering Seoul National University Seoul South Korea

ISBN: (数字)9798350349719

ISBN: (纸本)9798350349726

The concept of Digital Twin has been widely used by researchers to represent physical entities in computer-generated reality in the metaverse. In this research, a novel concept of “Mobile Twin” is coined. Mobile Twin serves as a replica of a mobile device in the virtual environment enabling communication. The purpose of introducing Mobile Twin in the metaverse is to bring mobility and benefits similar to tangible mobile devices while eliminating the need for individual energy sources, storage limitations, resource usage, and efficiency. The true benefits of a mobile twin can be achieved with an architecture where computing nodes are decentralized, data processing is near the network's edge with faster response times and reduced latency. For this purpose, the mobile twin-based applications of metaverse are built over edge computing-based network architecture. This idea introduced the aspect of “Revolutionary Ultra-low latency (RULL)” in the metaverse.

关键词： computers Metaverse computer architecture Network architecture Data processing Mobile handsets Digital twins

DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Maoyuan Zhang, Jing Zhao, Shanshan Liu, Juhua Liu, Tongliang Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computer Science Faculty of Engineering The University of Sydney Australia JD Explore Academy *** China College of Computing & Data Science Nanyang Technological University Singapore

End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection, recognition, and script identification simultaneously. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, our method not only performs well in English scenes but also masters the transcription with complex font structure and a thousand-level character classes, such as Chinese. On the other hand, our DeepSolo++ achieves better performance on the additionally introduced script identification task with a simpler training pipeline compared with previous methods. Extensive experiments on public benchmarks demonstrate that our simple approach achieves better training efficiency compared with Transformer-based models and outperforms the previous state-of-the-art. For example, on ICDAR 2019 ReCTS for Chinese text, our method boosts the 1-NED metric to a new record of 78.3%. On ICDAR 2019 MLT, DeepSolo++ achieves absolute 5.5% H-mean and 8.0% AP improvements on joint detection an

关键词： Semantics

An Overview of the Approaches for Generating Test Data in the Context of the Quality Assurance of Big Data Applications

学校读者我要写书评

暂无评论

An Overview of the Approaches for Generating Test Data in th...

International IEEE Conference on Signal-Image Technologies and Internet-Based System

作者： Daniel Staegemann Matthias Pohl Christian Haertel Christian Daase Mohammad Abdallah Klaus Turowski Faculty of Computer Science Magdeburg Research and Competence Cluster VLBA Otto-von-Guericke University Magdeburg Germany Department of Software Engineering Al-Zaytoonah University of Jordan Amman Jordan

With society’s increasing data production and the corresponding demand for systems that are capable of utilizing them, the big data domain has gained significant importance. However, besides the systems’ actual implementation, their testing also needs to be considered. For this, oftentimes, proper test data sets are necessary. This publication discusses several different approaches how these can be provisioned and, further, highlights the respective advantages, disadvantages, and suitable application scenarios. In doing so, researchers and practitioners that are implementing big data applications and need to test them, or who are generally interested in the domain, are supported in their own considerations on how to obtain test data.

关键词：

Extended Abstract of Candidate Test Set Reduction for Adaptive Random Testing: An Overheads Reduction Technique

学校读者我要写书评

暂无评论

Extended Abstract of Candidate Test Set Reduction for Adapti...

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

作者： Rubing Huang Haibo Chen Weifeng Sun Dave Towey Faculty of Information Technology Macau University of Science and Technology Taipa Macau China School of Computer Science and Communication Engineering Jiangsu University Zhenjiang Jiangsu China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Nottingham Ningbo China Ningbo Zhejiang China

This document 1 is an extended abstract of a science of computer Programming paper, "Candidate Test Set Reduction for Adaptive Random Testing: An Overheads Reduction Technique," presented as a J1C2 (Journal publication first, Conference presentation following) at the 30th IEEE International Conference on software Analysis, Evolution and Reengineering (Saner 2023).The paper presents a candidate set reduction strategy to enhance the Fixed-Sized-Candidate-Set version of Adaptive Random Testing (FSCS-ART). The proposed method reduces the number of randomly-generated candidate test cases by retaining valuable, unused candidates from previous iterations. As the computational costs associated with a stored/retained candidate are less than the costs associated with a randomly-generating one, the overall computational overheads of FSCS-ART are reduced. The reported experimental studies show that the proposed method has a comparable failure-detection effectiveness to FSCS-ART, but less computational overheads.

关键词： Costs Programming software Power capacitors Computational efficiency Testing

Induced Matching below Guarantees: Average Paves the Way for Fixed-Parameter Tractability

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Koana, Tomohiro Technische Universität Berlin Faculty IV Institute of Software Engineering and Theoretical Computer Science Algorithmics and Computational Complexity Germany

In this work, we study the Induced Matching problem: Given an undirected graph G and an integer , is there an induced matching M of size at least ? An edge subset M is an induced matching in G if M is a matching such that there is no edge between two distinct edges of M. Our work looks into the parameterized complexity of Induced Matching with respect to "below guarantee" parameterizations. We consider the parameterization u − for an upper bound u on the size of any induced matching. For instance, any induced matching is of size at most n/2 where n is the number of vertices, which gives us a parameter n/2 − . In fact, there is a straightforward 9n/2− · nO(1)-time algorithm for Induced Matching [Moser and Thilikos, J. Discrete Algorithms]. Motivated by this, we ask: Is Induced Matching FPT for a parameter smaller than n/2 − ? In search for such parameters, we consider MM(G) − and IS(G) − , where MM(G) is the maximum matching size and IS(G) is the maximum independent set size of G. We find that Induced Matching is presumably not FPT when parameterized by MM(G) − or IS(G) − . In contrast to these intractability results, we find that taking the average of the two helps—our main result is a branching algorithm that solves Induced Matching in 49(MM(G)+IS(G))/2− · nO(1) time. Our algorithm makes use of the Gallai–Edmonds decomposition to find a structure to branch on. Copyright © 2022, The Authors. All rights reserved.

关键词： Parameterization