检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1513-1528页

作者： Zhang, Tiehua Liu, Yuze Shen, Zhishu Ma, Xingjun Qi, Peng Ding, Zhijun Jin, Jiong Tongji University School of Computer Science and Technology Shanghai201804 China Ant Group Shanghai200122 China Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Fudan University School of Computer Science Shanghai200438 China Tongji University Department of Control Science and Engineering Shanghai201804 China Swinburne University of Technology School of Science Computing and Engineering Technologies Melbourne3122 Australia

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this article, we propose a hypergraph learning framework named learning from heterogeneity (LFH) that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterward, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with twelve state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experimental results demonstrate a significant performance gain (an average of 12.9% in node classification and 12.8% in link prediction) compared with recent state-of-the-art methods. © 2020 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Frog-Shaped UWB MIMO Antenna Design for 5G

引用

Progress in Electromagnetics Research C 2025年 151卷 101-112页

作者： Yao, Shanhua Yang, Tianchu Qiu, Xiaorong Li, Xiang School of Electrical and Information Engineering Anhui University of Science and Technology Huainan232001 China School of Computer Science Huainan Normal University Huainan232001 China

In this paper, a frog-shaped ultra-wideband (UWB) multiple-input multiple-output (MIMO) antenna is proposed for 5G applications in the n77, n78, n79, and 6 GHz bands with a compact antenna structure of 31 × 55 × 1.5 mm3. The designed antenna consists of two frog-shaped monopole antennas and a floor from which a part has been removed, and the operating bandwidths range from 3.05 to 13.38 GHz, which meets the design criteria for UWB. The T-shaped floor with two T-shaped slots impedes the flow of coupling currents and improves the isolation of the antenna. This results in an isolation of less than −17 dB over the entire operating bandwidth and less than −20 dB in the 5G band. In addition, the envelope correlation coefficient (ECC) is less than 0.007, the diversity gain (DG) more than 9.96, the total active reflection coefficient (TARC) less than −30 dB, and the channel capacity loss (CCL) less than 0.34 bit/s/Hz. The measured and simulated results agree with each other, demonstrating the antenna’s potential application in 5G communication systems. © 2025, Electromagnetics Academy. All rights reserved.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Real-time distance field acceleration based free-viewpoint video synthesis for large sports fields

引用

Computational Visual Media 2024年第2期10卷 331-353页

作者： Yanran Dai Jing Li Yuqi Jiang Haidong Qin Bang Liang Shikuan Hong Haozhe Pan Tao Yang School of Telecommunications Engineering Xidian UniversityXi’an 710071China National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology SAIIPthe School of Computer ScienceNorthwestern Polytechnical UniversityXi’an 710129China

Free-viewpoint video allows the user to view objects from any virtual perspective,creating an immersive visual *** technology enhances the interactivity and freedom of multimedia ***,many free-viewpoint video synthesis methods hardly satisfy the requirement to work in real time with high precision,particularly for sports fields having large areas and numerous moving *** address these issues,we propose a freeviewpoint video synthesis method based on distance field *** central idea is to fuse multiview distance field information and use it to adjust the search step size *** step size search is used in two ways:for fast estimation of multiobject three-dimensional surfaces,and synthetic view rendering based on global occlusion *** have implemented our ideas using parallel computing for interactive display,using CUDA and OpenGL frameworks,and have used real-world and simulated experimental datasets for *** results show that the proposed method can render free-viewpoint videos with multiple objects on large sports fields at 25 ***,the visual quality of our synthetic novel viewpoint images exceeds that of state-of-the-art neural-rendering-based methods.

关键词： free-viewpoint video view synthesis camera array distance field sports video

来源：评论

学校读者我要写书评

暂无评论

An effective abstract text summarisation using shark smell optimised bidirectional encoder representations from transformer

引用

International Journal of Business Intelligence and Data Mining 2023年第1期23卷 50-72页

作者： Nafees Muneera, M. Sriramya, P. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamilnadu Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

Recently, a vast amount of text data has increased rapidly and therefore information must be summarised to retrieve useful knowledge. First, the preprocessing module utilises the fixed-length stemming method, and then the segmentation module makes use of a pre-trained bidirectional encoder representations from transformers (BERT). The text of input is segmented with the utilisation of feedforward and multi-head attention layer. This BERT segmentation paradigm is adjoined alongside shark smell optimisation (SSO) methodology, and thus, the phrases that are extricated are employed to prepare the document stage of a dataset of Amazon merchandise assessment. This study aspires to create a concise summary and invigorating headlines, which grab the focus of the readers. This paper demonstrates that it performs by amalgamating the duo extractive and abstractive procedures employing a pipelined technique for creating a succinct summary that is later utilised for headline creation. Experimentation was executed on publicly accessible datasets – CNN/Daily Mail. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Exploring Dynamics and Hardware Implementation of an Enhanced 5D Hyperchaotic Memristive System Inspired by Sprott-C System

引用

Complex System Modeling and Simulation 2025年第1期5卷 34-45页

作者： Abdulmajeed Abdullah Mohammed Mokbel Fei Yu Yumba Musoya Gracia Bohong Tan Hairong Lin Herbert Ho-Ching Iu School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha 410114China School of Electronic Information Central South UniversityChangsha 410083China School of Electrical Electronic and Computer EngineeringUniversity of Western AustraliaPerth 6009Australia

This paper proposes a novel 5D hyperchaotic memristive system based on the Sprott-C system configuration,which greatly improves the complexity of the system to be used for secure communication and signal processing.A critical aspect of this research work is the introduction of a flux-controlled memristor that exhibits chaotic behavior and dynamic responses of the *** this respect,detailed mathematical modeling and numerical simulations about the stability of the system’s equilibria,bifurcations,and hyperchaotic dynamics were conducted and showed a very wide variety of behaviors of great potential in cryptographic applications and secure data ***,the flexibility and efficiency of the real-time operating environment were demonstrated,and the system was actually implemented on a field-programmable gate array(FPGA)hardware platform.A prototype that confirms the theoretical framework was presented,providing new insights for chaotic systems with practical ***,we conducted National Institute of Standards and Technology(NIST)testing on the proposed 5D hyperchaotic memristive system,and the results showed that the system has good randomness.

关键词： Sprott-C system field-programmable gate array(FPGA)implementation hyperchaotic system memristor numerical simulation

来源：评论

学校读者我要写书评

暂无评论

An efficient cloud based face recognition system for e-health secured login using steerable pyramid transform and local directional pattern

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1017-1027页

作者： Dosaj, Ayush Satapathy, Suresh Chandra Soundrapandiyan, Rajkumar Kaur, Mannat Hannoon, Naeem School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Kalinga Institute of Industrial Technology Deemed to be University Odisha Bhubaneswar India Faculty of Electrical Engineering Universiti Teknologi MARA Shah Alam Malaysia

This paper proposes a face recognition system based on steerable pyramid transform (SPT) and local directional pattern (LDP) for e-health secured login in cloud domain. In an e-health login, patients periodically forget their self-made login username and password. This face recognition system can replace the traditional login system. In the proposed system, SPT can decompose a face image into several sub-bands of different scales and orientations, and LDP can encode the sub-bands in binary texture pattern. The LDP binary pattern was obtained by computing the edge response values in all eight directions at each pixel position and generating a code from the relative strength magnitude. Therefore, SPT–LDP design represents a face image in a robust way which includes multiple information sources from different scales and orientations. The proposed system is tested on standard benchmark facial recognition technology (FERET) and extended Yale-B databases. Further, the efficiency of the proposed system is proved by comparing recognition rates with other existing descriptor based methods. From the experimental results it is observed that the proposed system achieves 99.79% recognition in fb set, 90.72% in fc set, 84.97% in dup I set, and 87.69% in dup II set for FERET database and 100% in sub2 set, 100% in sub3 set, 96% in sub4 set and 95% in sub5 set for extended Yale-B database which is better than the existing methods. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Hybrid approach for the detection of epileptic seizure using electroencephalography input

引用

International Journal of Information Technology (Singapore) 2024年第1期16卷 569-575页

作者： Basha, Niha Kamal Surendiran, B. Benzikar, Amutha Joyal, S. School of Computer Science and Engineering Vellore Institute of Technology (VIT) Vellore India Department of Computer Science and Engineering National Institute of Technology (NIT) Puducherry Karaikal India School of Computer Science and Engineering Vellore Institute of Technology (VIT) Chennai India Saveetha Engineering College Chennai India

In the early days, it was difficult to study bio-electric signals, but now a days these problems have been solved by many hardware devices which are available at low cost. Even then there is a need for technical improvements to process bio-electric signals. Enormous effort has been taken for the detection of epileptic seizure from EEG signal. Considerable evidence available on Bonn university EEG dataset for epileptic seizure detection. However, deep learning algorithms have not applied often on Bonn university data like other machine learning algorithms for the detection of epileptic seizure due to the less availability of data. This work adopted machine learning and deep learning models for the detection of epileptic seizure. The data consists of a hundred subjects with sampling rate as 173.61 Hz of ‘S’ (ictal) and ‘Z’ (normal) dataset. The results show how the choice of healthy and ictic subjects through high order functional math decision like variance (STD), Power, Skewness, and Kurtosis values are analyzed to extract epileptic features. The performance of classifiers has been evaluated based on the evaluation metrics within which CGRU-SVM outperforms all other models with 97.54% accuracy. The features are extracted based on the statistical measures to detect epileptic seizure. Further, the proposed work provides more evidence on the epileptic seizure features, and it shows the new possibility for using deep learning models for epileptic seizure detection. In future, an analysis must be performed with dynamic sets of input and different analysis techniques. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Confusion matrix Deep learning model Electroencephalography Epilepsy Ictal subject Rhythmic frequency Statistical feature

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for Alzheimer's Disease Diagnosis and Mini-Mental State Examination Score Prediction

引用

Big Data Mining and Analytics 2024年第3期7卷 828-842页

作者： Jin Liu Xu Tian Hanhe Lin Hong-Dong Li Yi Pan Hunan Provincial Key Lab on Bioinformatics School of Computer Science and EngineeringCentral South UniversityChangsha 410083China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of SoftwareXinjiang UniversityUrumqi 830091China School of Science and Engineering University of DundeeDundeeDD14HNUK Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Accurately diagnosing Alzheimer's disease is essential for improving elderly ***,accurate prediction of the mini-mental state examination score also can measure cognition impairment and track the progression of Alzheimer's ***,most of the existing methods perform Alzheimer's disease diagnosis and mini-mental state examination score prediction separately and ignore the relation between these two *** address this challenging problem,we propose a novel multi-task learning method,which uses feature interaction to explore the relationship between Alzheimer's disease diagnosis and minimental state examination score *** our proposed method,features from each task branch are firstly decoupled into candidate and non-candidate parts for ***,we propose feature sharing module to obtain shared features from candidate features and return shared features to task branches,which can promote the learning of each *** validate the effectiveness of our proposed method on multiple *** Alzheimer's disease neuroimaging initiative 1 dataset,the accuracy in diagnosis task and the root mean squared error in prediction task of our proposed method is 87.86%and 2.5,*** results show that our proposed method outperforms most state-of-the-art *** proposed method enables accurate Alzheimer's disease diagnosis and mini-mental state examination score ***,it can be used as a reference for the clinical diagnosis of Alzheimer's disease,and can also help doctors and patients track disease progression in a timely manner.

关键词： multi-task learning Alzheimer's disease diagnosis mini-mental state examination score prediction

来源：评论

学校读者我要写书评

暂无评论

GP‐FMLNet:A feature matrix learning network enhanced by glyph and phonetic information for Chinese sentiment analysis

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 960-972页

作者： Jing Li Dezheng Zhang Yonghong Xie Aziguli Wulamu Yao Zhang School of Computer and Communication Engineering University of Science and Technology BeijingBeijingChina Beijing Key Laboratory of Knowledge Engineering for Materials Science University of Science and Technology BeijingBeijingChina University of Alberta EdmontonAlbertaCanada

Sentiment analysis is a fine‐grained analysis task that aims to identify the sentiment polarity of a specified *** methods in Chinese sentiment analysis tasks only consider sentiment features from a single pole and scale and thus cannot fully exploit and utilise sentiment feature information,making their performance less than *** resolve the problem,the authors propose a new method,GP‐FMLNet,that integrates both glyph and phonetic information and design a novel feature matrix learning process for phonetic features with which to model words that have the same pinyin information but different glyph *** method solves the problem of misspelling words influencing sentiment polarity prediction ***,the authors iteratively mine character,glyph,and pinyin features from the input comments ***,the authors use soft attention and matrix compound modules to model the phonetic features,which empowers their model to keep on zeroing in on the dynamic‐setting words in various positions and to dispense with the impacts of the deceptive‐setting ***-periments on six public datasets prove that the proposed model fully utilises the glyph and phonetic information and improves on the performance of existing Chinese senti-ment analysis algorithms.

关键词： aspect‐level sentiment analysis deep learning feature extraction glyph and phonetic feature matrix compound learning

来源：评论

学校读者我要写书评

暂无评论

FSCIL-EACA: Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

引用

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education Department Information Network Engineering Research Center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Few-shot class-incremental learning Embedding augmentation Classifier adaptation Image classification

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：