检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Xiao, Yewei Liu, Xuanming Zhu, Aosu Huang, Jian School of Information Engineering Xiangtan University Xiangtan411105 China Key Laboratory of Intelligent Computing &Information Processing Ministry of Education Xiangtan University Xiangtan411105 China

This study adopts the state-of-the-art Branchformer series architecture in the field of automatic speech recognition (ASR) as a replacement for the previously popular Conformer architecture, providing a novel solution for audio-visual speech recognition tasks. Building upon this foundation, we improve the Branchformer architecture and propose the R-Branchformer (Relational-Branchformer) architecture. The introduction of the CARM (Convolutional Attention Relation Module)enhances the connectivity between the local and global branches by considering their relationships and interactions, facilitating mutual embedding of local and global contextual information, ultimately boosting model performance. Our model is based on the Connectionist Temporal Classification (CTC) loss, and we incorporate intermediate CTC losses between blocks. Moreover, by referencing and improving the GIC (Gated Interlayer Collaboration) module to replace the Inter CTC module, we further relax the conditional independence assumption of the CTC model, resulting in enhanced model performance. Furthermore, we propose the Audio-Visual Output Enhancement (AVOE) module, which effectively assimilates information from both audio and visual modalities to enrich the representation of audio-visual information. As a result, our R-Branchformer model achieves remarkable Word Error Rates (WERs) of 1.7% and 1.5% on the LRS2 and LRS3 test sets, respectively, showcasing its state-of-the-art performance in audio-visual speech recognition tasks. © 2023, The Authors. All rights reserved.

关键词： Architecture

来源：评论

学校读者我要写书评

暂无评论

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment

arXiv

引用

arXiv 2024年

作者： Zhang, Shaolei Zhang, Kehao Fang, Qingkai Guo, Shoutao Zhou, Yan Liu, Xiaodong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences ICT CAS China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Research Center of Distributed Systems Institute of Computing Technology Chinese Academy of Sciences ICT CAS China

Large language models (LLMs), with their powerful generative capabilities and vast knowledge, empower various tasks in everyday life. However, these abilities are primarily concentrated in high-resource languages, leaving low-resource languages with weaker generative capabilities and relatively limited knowledge. Enhancing the multilingual capabilities of LLMs is therefore crucial for serving over 100 linguistic communities worldwide. An intuitive approach to enhance the multilingual capabilities would be to construct instruction data for various languages, but constructing instruction data for over 100 languages is prohibitively costly. In this paper, we introduce BayLing 2, which efficiently transfers generative capabilities and knowledge from high-resource languages to low-resource languages through language alignment. To achieve this, we constructed a dataset of 3.2 million instructions, comprising high-resource language instructions (Chinese and English) and cross-lingual instructions for 100+ languages and performed instruction tuning based on the dataset to facilitate the capability transfer between languages. Using Llama as the foundation model, we developed BayLing-2-7B, BayLing-2-13B, and BayLing-2-8B, and conducted a comprehensive evaluation of BayLing. For multilingual translation across 100+ languages, BayLing shows superior performance compared to open-source models of similar scale. For multilingual knowledge and understanding benchmarks, BayLing achieves significant improvements across over 20 low-resource languages, demonstrating its capability of effective knowledge transfer from high-resource to low-resource languages. Furthermore, results on English benchmarks indicate that BayLing maintains high performance in high-resource languages while enhancing the performance in low-resource languages. Demo2, homepage3, code4 and models5of BayLing are available. © 2024, CC BY-NC-ND.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Autonomous Path Planning via Sand Cat Swarm Optimization With Multi-Strategy Mechanism for Unmanned Aerial Vehicles in Dynamic Environment

引用

IEEE Internet of Things Journal 2025年

作者： Deng, Wu Feng, Jiayi Zhao, Huimin Civil Aviation University of China College of Electronic Information and Automation Tianjin300300 China Civil Aviation University of China Tianjin Key Lab Intelligent Signal and Image Processing Tianjin300300 China State Key Laboratory of Rail Transit Vehicle System of Southwest Jiaotong University Chengdu610031 China

Unmanned Aerial Vehicles (UAVs) face critical challenges in path planning in dynamic environment. Sand Cat Swarm Optimization (SCSO) algorithm has demonstrated promise in addressing complex optimization challenges. However, SCSO is limited by slow convergence, susceptibility to local optima, and insufficient adaptability. To overcome these shortcomings, an enhanced SCSO with the spiral search, Livy flight, tent chaotic mapping, and adaptive sparrow alert mechanism, namely TSLS-SCSO is developed to propose an autonomous path planning method for UAVs in dynamic environment. In TSLS-SCSO, a new population initialization strategy with tent chaotic mapping is designed to achieve a large dynamic range and coverage capability. Then a new spiral search strategy is designed to broaden the search range in the search phase. And a new Livy flight strategy is employed to enrich the diversity of population in the attacking prey phase. A new sparrow alert mechanism with integrating the sand cat group with the sparrow alert is designed to obtain faster convergence speed and accuracy. The experiment results on CEC 2017 and CEC 2022 show that the TSLS-SCSO obtains higher accuracy and more stable solutions and exhibits better competitiveness. Furthermore, the proposed UAV path planning method successfully found effective paths with an obstacle avoidance effectiveness of 95.5%. The obtained results validate the effectiveness and competitiveness of TSLS-SCSO in UAV path planning in the dynamic environment. © 2014 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Knowledge Representation Method for Fake News Detection

A Multimodal Knowledge Representation Method for Fake News D...

引用

Computer, Control and Robotics (ICCCR), International Conference on

作者： Fanhao Zeng Jiaxin Yao Yijie Xu Yanhua Liu Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Engineering Research Center of Big Data Intelligence Ministry of Education (Fuzhou University) Fuzhou China

ISBN: (数字)9798350373141

ISBN: (纸本)9798350373158

To address the key challenge encountered in fake news detection, i.e., multimodal data is difficult to be effectively semantically represented due to its intrinsic heterogeneity, this paper proposes a multimodal knowledge representation method for fake news detection. First, visual feature extraction is performed for fake news image data, the relevant images are sliced into multiple blocks, and then visual modal features are obtained by linear projection layer mapping. This simplifies the feature extraction process and reduces the computational cost, which helps to improve the fake news recognition performance. Second, to meet the actual fake news detection needs, a long text representation method based on topic words is investigated for the text data in fake news. Finally, the multimodal representation of the same fake news data is optimized by establishing a connection between two different modalities, visual and text, and inputting it into a BiLSTM-Attention based network to achieve the fusion of multimodal features. The experiment selects the same fake news data of EANN model and uses four classical classification methods to verify the effect of knowledge representation and compare it with the fusion model ViLT which is not optimized for long text. The experiment proves that the accuracy rate of fake news detection using the multimodal representation proposed in this paper is improved by 7.4% compared to the EANN model, and by 9.3% compared to the ViLT representation.

关键词： Digital control Visualization Accuracy Knowledge representation Machine learning Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Multipath Components Modeling and Measuring in Device-Free Underground Parking Localization

Multipath Components Modeling and Measuring in Device-Free U...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Sihai Yang Xing Xiao Xing Wang Zhuoting Chen Menggang Sheng Zhiqiang Yao School of Automation and Electronic Information Xiangtan University Xiangtan China Hunan Province Key Laboratory of Credible Intelligent Navigation and Positioning Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education National Center for Applied Mathematics in Hunan Xiangtan University Xiangtan China School of Mathematics and Computational Science Xiangtan University Xiangtan China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

The Device-Free Localization (DFL) system hold significant application value in NLOS (Non-Line-of-Sight) environments where GPS signals are unavailable. It is a challenge to accurately distinguish whether the changes in spatial signals are caused by the presence of users or the changes of environment, particularly in Non-Line-of-Sight (NLOS) environments without GPS signals. To address this issue, we proposes a DFL method utilizing Multipath Components (MPCs), which involves a detailed analysis of how the presence of users affects the MPCs. Specifically, a calculation method for signal propagation paths using virtual anchors has been developed to accurately construct a user-based diffraction model. An algorithm for extracting MPCs from actual signal measurements was also proposed. The maximum average absolute error between the simulated and measured MPC amplitudes with UWB was 0.9461 dB, validating the possibility of substituting simulation models for actual measurements. Moreover, by utilizing a deep learning network with MPCs as input features, the DFL method achieves a positioning accuracy of 0.44 m in an underground parking with only two sensors. This represents an improvement of $\mathbf{0. 3 5 m}$ over traditional RSS-based fingerprinting localization methods.

关键词： Location awareness Deep learning Accuracy Diffraction Measurement uncertainty Sensor phenomena and characterization Fingerprint recognition

来源：评论

学校读者我要写书评

暂无评论

A NOVEL CONVOLUTIONAL NEURAL NETWORK BASED ON ADAPTIVE MULTI-SCALE AGGREGATION AND BOUNDARY-AWARE FOR LATERAL VENTRICLE SEGMENTATION ON MR IMAGES 47

A NOVEL CONVOLUTIONAL NEURAL NETWORK BASED ON ADAPTIVE MULTI...

引用

2022 IEEE International Conference on Acoustics, Speech and signal processing, ICASSP 2022

作者： Ye, Fei Wang, Zhiqiang Zhu, Sheng Li, Xuanya Hu, Kai Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan411105 China Department of Radiology Affiliated Hospital of Xiangnan University Chenzhou423000 China Key Laboratory of Medical Imaging and Artificial Intelligence of Hunan Province Xiangnan University Chenzhou423000 China Baidu Inc. Beijing100085 China

ISBN: (纸本)9781665405409

In this paper, we propose a novel convolutional neural network based on adaptive multi-scale feature aggregation and boundary-aware for lateral ventricle segmentation (MB-Net), which mainly includes three parts, i.e., an adaptive multi-scale feature aggregation module (AMSFM), an embedded boundary refinement module (EBRM), and a local feature extraction module (LFM). Specifically, the AMSFM is used to extract multi-scale features through the different receptive fields to effectively solve the problem of distinct target regions on magnetic resonance (MR) images. The EBRM is intended to extract boundary information to effectively solve blurred boundary problems. The LFM can make the extraction of local information based on spatial and channel attention mechanisms to solve the problem of irregular shapes. Finally, extensive experiments are conducted from different perspectives to evaluate the performance of the proposed MB-Net. Furthermore, we also verify the robustness of the model on other public datasets, i.e., COVID-SemiSeg and CHASE DB1. The results show that our MB-Net can achieve competitive results when compared with state-of-the-art methods. © 2022 IEEE

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Improved Uniform Linear Array Fitting Scheme with Increased Lower Bound on Uniform Degrees of Freedom for DOA Estimation

TechRxiv

引用

TechRxiv 2022年

作者： Shi, Wanlu Li, Yingsong The College of Information and Communication Engineering Harbin Engineering University Harbin150001 China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei China

Recently, uniform linear array (ULA) fitting (UF) principle is proposed for sparse array (SA) design using pseudo-polynomial equations. Typically, it is verified that the designed SAs via UF enjoy a lower bound on uniform degrees of freedom (uDOF), which is approximately 0.5N2 with N sensors. Herein, an improved UF (IUF) scheme is proposed to significantly increase the lower bound on uDOF, which is realized by introducing two sub-ULAs, with name of adjoint transfer arrays (ATAs), on both sides of a transfer sub-ULA. The ATAs together with the transfer sub-ULA serve as a new layer to construct an adjoint transfer layer (ATL) that has improved aperture in comparison with traditional transfer layer to improve the lower bound on uDOF, which is derived in detail. Furthermore, two novel SAs are developed based on the ATL to verify the effectiveness of the proposed IUF scheme to increase the uDOF. Numerical simulations verify the superiority of devised SAs for direction-of-arrival (DOA) estimations. © 2022, CC BY.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Hexagonal Convolutional Neural Network for Spatial Transcriptomics Classification

Hexagonal Convolutional Neural Network for Spatial Transcrip...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Gao, Jing Zhang, Fa Hu, Kai Cui, Xuefeng Xiangtan University Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan China Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Medical Technology Beijing Institute of Technology Beijing China Xiangnan University Key Laboratory of Medical Imaging and Artificial Intelligence of Hunan Province Chenzhou China Shandong University School of Computer Science and Technology Qingdao China

ISBN: (纸本)9781665468190

Recent advances in spatial transcriptomics have enabled the comprehensive measurement of transcriptional profiles while retaining the spatial contextual information. Identifying spatial domains is a critical step in the analysis of spatially resolved transcriptomics. Existing unsupervised methods perform poorly on this task owing to the large amount of noise and dropout events in the transcriptomic profiles. To address this problem, we first extend an unsupervised algorithm to a supervised learning method that can identify useful features and reduce noise hindrance. Second, inspired by the classical convolution in convolutional neural networks (CNNs), we designed a regular hexagonal convolution to compensate for the missing gene expression patterns from adjacent nodes. Compared with the graph convolution in graph neural networks (GNNs), our hexagonal convolution can preserve the relative spatial location information of different nodes in graph-structured data. Third, based on the hexagonal convolution, a novel hexagonal Convolutional Neural Network (hexCNN) is proposed for spatial transcriptomics classification. Finally, we compared the proposed hexCNN with existing methods on the DLPFC dataset. The results show that hexCNN achieves a classification accuracy of 87.2% and an average Rand index (ARI) of 78.2% (1.9% and 3.3% higher than those of GNNs). © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Fusion Shallow and Deep Features Network for Facial StO2 Stress Classification

A Fusion Shallow and Deep Features Network for Facial StO2 S...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Haolin Xia Sirui Sun Xinyu Liu Ju Zhou Hanpu Wang Tong Chen School of Electronic and Information Engineering Southwest University Chongqing China Key Laboratory of Non-Linear Circuit and Intelligent Information Processing of Chongqing Chongqing China Institute of Legal Psychology and Intelligent Computing Chongqing China

Stress is an emotional state that affects our lives, so it is vital to detect it accurately. Numerous studies have shown that tissue oxygen saturation (StO2) is an effective physiological signal for identifying different stress states. However, previous StO2 feature extraction methods relied too heavily on baselines to be realized in practice. In this paper, a two-stream network combining shallow and deep features, called CRNet, is proposed for baseline-independent StO2 stress classification. In CRNet, shallow features are extracted using a CNN network and deep features are extracted using a ResNet network. For the extracted high-dimensional deep features, MLP module is employed for dimensionality reduction, which can effectively combine the two levels of features and improve the feature extraction capability of the network. Experimental results show that CRNet can significantly improve the performance of StO2 stress classification to the state-of-the-art (SOTA) even when using only raw imbalanced data.

关键词： Dimensionality reduction Automation Anxiety disorders Feature extraction Physiology Stress

来源：评论

学校读者我要写书评

暂无评论

SEMI-SUPERVISED MEDICAL IMAGE SEGMENTATION WITH CO-DISTRIBUTION ALIGNMENT

arXiv

引用

arXiv 2023年

作者： Wang, Tao Huang, Zhongzheng Wu, Jiawei Cai, Yuanzheng Li, Zuoyong Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University China College of Computer and Data Science Fuzhou University China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University China School of Electrical and Mechanical Engineering Fujian Agriculture and Forestry University China

Medical image segmentation has made significant progress when a large amount of labeled data are available. However, annotating medical image segmentation datasets is expensive due to the requirement of professional skills. Additionally, classes are often unevenly distributed in medical images, which severely affects the classification performance on minority classes. To address these problems, this paper proposes Co-Distribution Alignment (Co-DA) for semi-supervised medical image segmentation. Specifically, Co-DA aligns marginal predictions on unlabeled data to marginal predictions on labeled data in a class-wise manner with two differently initialized models before using the pseudo-labels generated by one model to supervise the other. Besides, we design an over-expectation cross-entropy loss for filtering the unlabeled pixels to reduce noise in their pseudo-labels. Quantitative and qualitative experiments on three public datasets demonstrate that the proposed approach outperforms existing state-of-the-art semi-supervised medical image segmentation methods on both the 2D CaDIS dataset and the 3D LGE-MRI and ACDC datasets, achieving an mIoU of 0.8515 with only 24% labeled data on CaDIS, and a Dice score of 0.8824 and 0.8773 with only 20% data on LGE-MRI and ACDC, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Alignment

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：