检索结果-内蒙古大学图书馆

International Conference on Computer Supported Cooperative Work in Design

作者： Weike Zhou Xiaokang Zhou Jing He Yamei Nie Qiqi Chen Guosheng Kang School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology HNUST Xiangtan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

With the wide use of Massive Open Online Courses (MOOCs) and online education, the large number and variety of educational resources on the online course open platform make it difficult for users to choose, and the requirements for course recommendation algorithms and model performance are getting higher and higher. The existing course recommendation algorithms often ignore the interactive information between n learners and courses and the course descriptions, resulting in poor recommendation performance. To solve the problems above, our work proposes an online course recommendation approach via exploring user interactions and course description documents. Specifically, LightGCN model is used to represent the user-course interaction graph to derive the structural embeddings of users and courses. Moreover, BERT model is used to represent the course description documents to derive the description embeddings of courses. Based on the three embeddings, ANFM (Attention Neural Factorization Machine) model is applied to perform online course recommendation by modeling low-order and high-order feature interactions, and learning the weights of the feature interactions through the attention mechanism. Finally, solid experiments are conducted over a real-world public dataset. Experimental results show that the proposed approach outperforms the baseline methods under NDCG, Recall and Precision.

关键词： Electronic learning Attention mechanisms Federated learning Education Solids

来源：评论

学校读者我要写书评

暂无评论

An AI-Based Chicken Disease Management System 1st

An AI-Based Chicken Disease Management System

引用

1st International Conference on Artificial Intelligence for Smart Community, AISC 2020

作者： Quach, Luyl-Da Quoc, Nghi Pham Thi, Nhien Huynh Le Thanh, Nhan Thanh, Xuan Truong Thi Tran, Duc Chung Hassan, Mohd Fadzil Software Engineering Department FPT University Cantho city Viet Nam Computing Fundamental Department FPT University Hanoi Viet Nam Department of Computer and Information Sciences Universiti Teknologi PETRONAS Seri Iskandar Perak Malaysia

ISBN: (纸本)9789811621826

Food stability has always received worldwide attention, especially in the development of the poultry industry. However, the poultry’s diseases have caused the loss of the poultry population and direct income of the owners. In this work, a system comprising of a website and a mobile application has been developed to support disease identification in chickens;the disease spread locations can be managed and traced with maps. In addition, the system allows farmers to make contact and get support from experts through chat, voice calls, and video calls. It also has some e-commerce functions for improving sales of poultry’s owners. The system uses the improved ResNet-50 model, with an accuracy of about 93.56%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Peripheral Facial Landmarks Using 3D Facial Data

Automatic Detection of Peripheral Facial Landmarks Using 3D ...

引用

International Conference on Image and Vision computing New Zealand, IVCNZ

作者： Mehraan Chowdhury Mohammed Bennamoun Farid Boussaid Syed Mohammed Shamsul Islam Department of Computer Science and Software Engineering University of Western Australia Perth Australia Department of Electrical Electronic and Computer Engineering University of Western Australia Perth Australia Discipline of Computing and Security Edith Cowan University Perth Australia

ISBN: (数字)9798331518776

ISBN: (纸本)9798331518783

Facial landmarking research has traditionally fo-cused on midface landmarks, largely overlooking peripheral facial features that are crucial in specialized medical applications. This study addresses this gap by developing a novel model to detect 12 peripheral landmarks, which are valuable in clinical scenarios such as obstructive sleep apnea detection and facial palsy assessment. Using the FRGC v2 dataset of 3D facial scans, we manually annotated a subset of 900 scans with peripheral landmarks following a rigorous pre-processing protocol. Building upon a high-performance deep learning model initially designed for midface landmark detection, we restructured its architecture to predict peripheral landmarks by modifying its output layers and training it from scratch using 2D projections of 3D scans. We conducted a comprehensive set of experiments, systematically testing different input configurations by varying both the number of images per scan (16, 32, and 64) and the image types (mesh-only, RGB, and depth maps). The model demonstrated its potential by achieving a mean error of 10.72 mm, highlighting the promise of deep learning techniques in addressing the complex challenge of peripheral landmark detection. These findings underscore the model's capability to support niche medical applications and open pathways for future advancements that could refine its accuracy, ultimately contributing to improved diagnostic tools in healthcare.

关键词： Training Deep learning Solid modeling Biomedical equipment Three-dimensional displays Protocols Medical services Transforms Sleep apnea Testing

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Superpoint Graph Transformer for Weakly Supervised 3D Semantic Segmentation

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1899-1912页

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hui, Le Xie, Jin Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin300350 China Ministry of Education of the People's Republic of China Engineering Research Center of City Intelligence and Digital Governance China Haihe Laboratory of Itai Tianjin China Northwestern Polytechnical University School of Electronics and Information Shaanxi Key Laboratory of Information Acquisition and Processing China Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Weakly supervised 3D semantic segmentation has successfully mitigated the labor-intensive and time-consuming task of annotating 3D point clouds. However, reliably utilizing the minimal point-wise annotations for unlabeled data in complex and large-scale scenes is still challenging, such as only 20 points labeled in 2 million points. To tackle this challenge, we propose a new Uncertainty-aware Superpoint Graph Transformer (UaSGT) framework that utilizes minimal annotations for unlabeled data learning through reliable long-range supervision propagation from labeled superpoints to unlabeled superpoints. First, we propose a superpoint graph transformer to achieve long-range supervision propagation along the attention-based fuzzy subsets defined on superpoints. The attention-based fuzzy subset measures the membership of unlabeled superpoints to clusters centered on labeled superpoints. Second, we employ an uncertainty-aware membership rectification technique on the fuzzy subset to ensure reliable propagation among superpoints within the same category. This technique integrates an uncertainty prediction module to mask the influence of unreliable membership and a spatial prior refinement module to reduce uncertainty in intra-class membership degrees. Finally, experimental results on two large-scale benchmarks S3DIS and ScanNet-V2 demonstrate the superiority of our approach compared to the state-of-the-art with at least 90% annotation reduction, and our method also achieves comparable performance to fully supervised methods with less than 0.1% labeled points. Our code is available at https://***/fanyan0411/UaSGT. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Bi-dimensional Variational Mode Decomposition for Surface Texture Analysis 17

Bi-dimensional Variational Mode Decomposition for Surface Te...

引用

17th CIRP Conference on Computer Aided Tolerancing, CAT 2022

作者： Li, Zhuowei Xu, Yuanping Li, Tukun Shi, Yajing Jiang, Xiangqian Cao, Yanlong Zeng, Wenhan Xu, Zhijie Zhang, Chaolong Huang, Jian School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province College of Mechanical Engineering Zhejiang University Hangzhou310027 China

In surface metrology, filtration is one of the key operations which is used to decompose the components of the surface and extract a scale-limited surface for further assessment. Although many types of filters have been proposed and some of them have been standardized in ISO16610 serials, the classic surface topography filters often inherit the mode mixing and boundary distortion problems that may lead to surface texture verification failures. This study proposes a new filter algorithm for the surface texture analysis, and it is based on the extended bi-dimensional variational mode decomposition (BVMD), named EBVMD. BVMD is widely used in the field of image processing and it is probably first-time to be used in the field of surface texture analysis. It consists of three steps. Firstly, a coarse-grained parallel genetic algorithm is applied in the devised model to select of optimal penalty factor and decomposition number of the bi-dimensional variational mode, and the best set of modes is gained. Secondly, the instantaneous wavelength value of each mode is obtained by calculating the corresponding isotropic monogenic signals. Finally, the scale-limited surface is extracted by the mean instantaneous wavelength. Experiments are conducted to verify the feasibility of the proposed filter on areal surface texture feature extraction with the mode aliasing and shape distortion phenomenon remedies. The experimental results show that the mean square error of roughness reconstructed by the proposed filter compared with the benchmarking values is 6.37×10-5, and owing to high flexibility in practice, the devised EBVMD provides a promising solution to achieve a high accuracy and efficiency filter. © 2022 The Author(s).

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning 39

FedAA: A Reinforcement Learning Perspective on Adaptive Aggr...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)157735897X

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Object on Use Case Description: Sequence Diagram Conformance based on Step Performed using Text Pre-Processing on Sipranta Application SRS

Object on Use Case Description: Sequence Diagram Conformance...

引用

AI IoT Congress (AIIoT), World

作者： Muhammad Alfath Abibi Yudi Priyadi Ati Suci Dian Martha Department of Informatics Telkom University Bandung Indonesia Department of Software Engineering Telkom University Bandung Indonesia School Of Computing Telkom University Bandung Indonesia

In the Use Case Diagram, a Step Performed in Tabulation contains an object's explanation flow. A sequence diagram attempts to depict in detail the interaction of objects in a system, the messages or commands sent, and the implementation time. In other words, the Sequence Diagram, like the Use Case Diagram, encapsulates an object's explanation flow in a graphical diagram. The Step Performed and the Sequence Diagram should be related, yet the Step Performed and Sequence Diagram diverge while creating the Sipranta Application SRS. By adopting Text Pre-processing, this research intends to quantify the value of conformance between the Sequence Diagram and the Step Performed in Use Case Description. This study identifies the Step Performed and the Sequence Diagram using 22 documents, 11 of which are Step Performed and 11 of which are Sequence Diagrams. In addition, the Text Analysis process produces two documents with the highest conformity: d1 with d12 of 0.933461. Cohen Cappa Score produces a validation value of 0.29195, which is included in the "Fair Agreement" category. While the reliability results from 2 groups of experts, which is 0.8275, so it is included in the "Substantial agreement" category. The results differ between the two methods, which is 0.536.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Transformer Topology for Distribution Network Voltage Regulation

A Hybrid Transformer Topology for Distribution Network Volta...

引用

2021 IEEE Southern Power Electronics Conference, SPEC 2021

作者： Power, Rupert Mithani, Alykhan Madawala, Udaya Baguley, Craig The University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand Auckland University of Technology Department of Engineering Computing and Mathematical Sciences Auckland New Zealand

ISBN: (纸本)9781665436236

Worldwide, distributed generation sources are being installed in increasing numbers within distribution networks. This poses new challenges for distribution network operators, including voltage fluctuations beyond permissible limits that can differ in different parts of the same distribution network. The Hybrid Transformer (HT) is an effective solution that can mitigate voltage fluctuations continuously, dynamically and in a local manner, through combining a standard distribution transformer with a power electronic converter. In this paper a retrofittable HT topology is proposed. It utilises a second, fractionally-rated line frequency transformer (LFT) to enable the use of low-voltage power electronics with low power ratings for reduced costs and complexity. The proposed topology is modelled and a scaled hardware prototype is used to verify theory and simulation results. The simulation and experimental results show the efficacy of the proposed topology, its applicability to mitigate voltage fluctuations, and its benefits over alternative approaches. © 2021 IEEE.

关键词： Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

scIAMC:Single-Cell Imputation via adaptive matrix completion

scIAMC:Single-Cell Imputation via adaptive matrix completion

引用

IEEE International Conference on Cyber Security and Cloud computing (CSCloud)

作者： Shuai Zhang Xiang Chen Li Peng School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan Hunan China Hunan Key Laboratory for Service computing and Novel Software Technology

Single-cell sequencing techniques are often impacted by technical noise, leading to the generation of very sparse expression matrices. This technical noise is referred to as dropouts and poses as a major challenge for downstream analysis. In this study, we introduce scIAMC (single-cell imputation via adaptive parameter matrix completion), which is based on matrix completion theory to recover missing values in expression matrices. To expedite the algorithm's running time and avoid any parameter tuning on data, we formulated an optimization problem. Our approach led to an enhanced cell population identification and minimal errors, while also restoring biological landscapes that were damaged by these dropouts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories

arXiv

引用

arXiv 2024年

作者： Wang, Tianlong Jiao, Xianfeng Zhu, Yinghao Chen, Zhongzhi He, Yifan Chu, Xu Gao, Junyi Wang, Yasha Ma, Liantao School of Software and Microelectronics Peking University Beijing China Key Laboratory of High Confidence Software Technologies Ministry of Education Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Beihang University Beijing China Center on Frontiers of Computing Studies Peking University Beijing China Centre for Medical Informatics University of Edinburgh Scotland Edinburgh United Kingdom Health Data Research UK London United Kingdom Key Laboratory of High Confidence Software Technologies Ministry of Education National Engineering Research Center for Software Engineering Peking University Beijing China

Recent studies have indicated that Large Language Models (LLMs) harbor an inherent understanding of truthfulness, yet often fail to consistently express it and generate false statements. This gap between "knowing" and "telling" poses a challenge for ensuring the truthfulness of generated content. Inspired by recent work on the practice of encoding human-interpretable concepts linearly within large language models, we treat truthfulness as a specially linearly encoded concept within LLMs, and introduce Adaptive Activation Steering (ACT), a tuning-free method that adaptively shifts LLM’s activations in the "truthful" direction during inference. ACT addresses diverse categories of hallucinations by utilizing diverse truthfulness-related steering vectors and adjusting the steering intensity adaptively. Applied as an add-on across various models, ACT significantly improves truthfulness in LLaMA (↑ 142%), LLaMA2 (↑ 24%), Alpaca (↑ 36%), Vicuna (↑ 28%), LLaMA2-Chat (↑ Copyright © 2024, The Authors. All rights reserved.

关键词： Context free languages

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：