检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaolu Lin Pinya Lu Jie Pan Hongqin Yang Xuemei Ding Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application Fujian Provincial University Engineering Research Center for Big Data Analysis and Application Fujian Normal University Fuzhou China Xiamen Jingyi Zhikang Technology Co. Ltd Xiamen China Fujian Provincial Key Laboratory for Photonics Technology Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Normal University Fuzhou China School of Computing Engineering and Intelligent Systems Ulster University Derry-Londonderry NI UK

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Alzheimer's disease (AD) is a neurodegenerative disease and mild cognitive impairment (MCI) is the early stage of AD. Previous studies have predominantly focused on binary classification using 3 dimensional - convolutional neural network (3D-CNN) for AD diagnosis, with limited progress in multi-classification. Moreover, the current 3D-CNNs often adopt a single-scale architecture with massive parameters growth. Additionally, obtaining precise location information of brain imaging data is crucial for improving the classification accuracy with 3D-CNN. Hence, we propose a multi-scale 3D-CNN based on coordinate attention mechanism to marvelously capture and integrate 3D features with fewer parameters, improving the accuracy of AD diagnosis. A total of 447 cognitively normal (CN), 512 MCI, and 358 AD sMRI images from the Alzheimer's Disease Neuroimaging Initiative datasets are used for multi-class classification task, yielding a classification accuracy of 92.8%. The model merely involves 2.41 M parameters and achieves the best classification results with the least number of parameters when compared to other representative CNN architectures including ResNet 18, ResNet 34, ConvNeXt tiny, and VGG 11. Through the ablation experiment, the addition of attention mechanism and the multi-scale classification enhances the classification performance by 4.5% and 1.5%, respectively. Furthermore, our model outperforms the other six existing studies in terms of accuracy for classifying AD vs. MCI vs. CN. Overall, this study underscores the efficacy of our approach for AD diagnosis, showcasing its utility in diagnosing AD patients and providing novel insights for diagnosing other neurological disorder diseases.

关键词： Neuroimaging Accuracy Attention mechanisms Three-dimensional displays Resonance Convolutional neural networks Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Tiny Object Tracking: A Large-scale Dataset and A Baseline

arXiv

引用

arXiv 2022年

作者： Zhu, Yabin Li, Chenglong Liu, Yao Wang, Xiao Tang, Jin Luo, Bin Huang, Zhixiang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing Anhui Higher Education Institutes Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China School of Computer Science and Technology Anhui University Hefei230601 China Peng Cheng Laboratory Shenzhen China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing Anhui Higher Education Institutes Anhui University Hefei230601 China

Tiny objects, frequently appearing in practical applications, have weak appearance and features, and receive increasing interests in meany vision tasks, such as object detection and segmentation. To promote the research and development of tiny object tracking, we create a large-scale video dataset, which contains 434 sequences with a total of more than 217K frames. Each frame is carefully annotated with a high-quality bounding box. In data creation, we take 12 challenge attributes into account to cover a broad range of viewpoints and scene complexities, and annotate these attributes for facilitating the attribute-based performance analysis. To provide a strong baseline in tiny object tracking, we propose a novel Multilevel Knowledge Distillation Network (MKDNet), which pursues three-level knowledge distillations in a unified framework to effectively enhance the feature representation, discrimination and localization abilities in tracking tiny objects. Extensive experiments are performed on the proposed dataset, and the results prove the superiority and effectiveness of MKDNet compared with state-of-the-art methods. The dataset, the algorithm code, and the evaluation code are available at https://***/mmic-lcl/Datasets-andbenchmark-code. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Exploring the Interactions of Ti3c2tx, Ag, and Ti3c2tx/Ag with Human Serum Albumin: Insights into Conformational Changes and Biotoxicity Reduction

SSRN

引用

SSRN 2023年

作者： Tan, Chunhu Zhang, Tingting Wang, Gongying Liu, Chang Wang, Lingling Li, Weihua Li, Jiansheng Lu, Rui Jiangsu Key Laboratory of Chemical Pollution Control and Resources Reuse School of Environmental and Biological Engineering Nanjing University of Science and Technology Nanjing210094 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei230601 China Guangdong Provincial Key Laboratory of Microbial Culture Collection and Application State Key Laboratory of Applied Microbiology Southern China Institute of Microbiology Guangdong Academy of Sciences Guangzhou510070 China School of Environment and Energy Engineering Anhui Provincial Key Laboratory of Environmental Pollution Control and Resource Reuse Anhui Jianzhu University Hefei230601 China

Ag nanoparticles are toxic and can accumulate in the human body or the environment, resulting in biotoxic effects. Ti3C2Tx, a new class of graphene-like 2D nanomaterials, is used in numerous applications due to its special physicochemical properties. There is great concern about the potential damage that this material may cause to the environment and human health. In this study, the interaction mechanisms of Ti3C2Tx, Ag and Ti3C2Tx/Ag materials with HSA were characterized using multispectral analysis and zeta potential measurements, respectively. The results showed that the effects of the three materials on the conformational changes of HSA were Ag > Ti3C2Tx/Ag > Ti3C2Tx in order. Hydrogen bonding and electrostatic interaction forces played an important role in the binding process of Ti3C2Tx and its complexes with HSA. Ag nanoparticles have a comparatively high level of biotoxicity and have a more significant effect on the conformational changes of proteins. Ti3C2Tx itself has biocompatibility and a large specific surface area. The biotoxicity of Ti3C2Tx/Ag complex is lower than that of Ag, indicating that the addition of Ti3C2Tx can reduce the biotoxicity of Ag nanoparticles, and Ti3C2Tx may be used as a carrier substance for Ag nanoparticles, which can reduce the toxicity of Ag while giving it unique properties similar to those of Ti3C2Tx, thus improve the biosafety of Ag nanoparticles in the application process. © 2023, The Authors. All rights reserved.

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Provably Secure Authenticated key-Management Mechanism for e-Healthcare Environment

引用

IEEE Internet of Things Journal 2025年

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Ghaffar, Zahid Xie, Yong Wang, Guijuan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Douliu64002 Taiwan Qinghai Institute of Technology School of Computer and Information Science China Qinghai Provincial Laboratory for Intelligent Computing and Application China Key Laboratory of Computing Power Network and Information Security Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security China Shandong Fundamental Research Center for Computer Science Jinan250353 China

The Internet of Things (IoT) is rapidly permeating all aspects of human life, involving a network of devices that share sensitive data. A notable application is the e-healthcare systems, which employ connected sensors, medical servers, and wearable devices. However, the public nature of communication in e-healthcare systems poses challenges such as security, privacy, and authentication of participating entities. Recently, many authentication protocols have been introduced to address these challenges. However, most of these protocols remain vulnerable to various security attacks, including device or medical server impersonation, denial of service, physical or cloning, and de-synchronization attacks. Therefore, we introduce an authenticated key-management protocol utilizing hash functions and Cipher-Block Chaining-Advanced Encryption Standard encryption (CBC-AES) encryption. The proposed protocol also employs the Physical Unclonable Function (PUF), which makes it more robust and efficient in resisting physical or cloning attacks. Additionally, the proposed scheme resists various security threats, including impersonation, session key leakage, ephemeral secret leakage, and de-synchronization attacks. We analyze the scheme’s security and reliability through formal and informal analysis. The informal analysis demonstrates that the scheme encompasses crucial security features, while the formal analysis substantiates. Moreover, performance analysis of the proposed protocol with various competing results indicates that our protocol achieves an average reduction in communication and computation overheads by 36.03.% and 41.79%, respectively. © 2014 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A New Predefined Time Stability Theorem and its application in Multi-Modal Memristive Neural Network Synchronization

A New Predefined Time Stability Theorem and its Application ...

引用

Memristive computing and applications (ICMCA), IEEE International Conference on

作者： Hui Zhao Lei Zhou Qingjie Wang Aidi Liu Jingliang Peng Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and Engineering University of Jinan Jinan China College of Information Science and Engineering Northeastern University Shenyang China Collaborative Innovation Center of Memristive Computing Application Qilu Institute of Technology Jinan China

This article proposes a new predefined-time (PDT) stability theorem, which offers more evident advantages compared to previous predefined-time stability. Firstly, based on the limitations of existing PDT stability, this theorem relaxed the limitations of sufficient conditions, which fill the gap in the research on PDT stability. Secondly, the PDT synchronization of multi-modal memristive neural networks (MM-MNN) is analyzed by the usability of the new judgment theorem. A matching PDT controller is designed and sufficient synchronization control conditions is obtained by utilizing generalized Lyapunov functional method, set-valued mapping, inequality analysis technique and differential inclusion theory. Meanwhile, the topological characteristics of multi-modal neuron and its impact on network synchronization behavior are presented. Finally, we provide some confirmatory numerical simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hand Hygiene Assessment via Joint Step Segmentation and key Action Scorer

arXiv

引用

arXiv 2022年

作者： Li, Chenglong Zhu, Qiwen Liu, Tubiao Tang, Jin Su, Yu Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Hefei Normal University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230061 China

Hand hygiene is a standard six-step hand-washing action proposed by the World Health Organization (WHO). However, there is no good way to supervise medical staff to do hand hygiene, which brings the potential risk of disease spread. Existing action assessment works usually make an overall quality prediction on an entire video. However, the internal structures of hand hygiene action are important in hand hygiene assessment. Therefore, we propose a novel fine-grained learning framework to perform step segmentation and key action scorer in a joint manner for accurate hand hygiene assessment. Existing temporal segmentation methods usually employ multi-stage convolutional network to improve the segmentation robustness, but easily lead to over-segmentation due to the lack of the long-range dependence. To address this issue, we design a multi-stage convolution-transformer network for step segmentation. Based on the observation that each hand-washing step involves several key actions which determine the hand-washing quality, we design a set of key action scorers to evaluate the quality of key actions in each step. In addition, there lacks a unified dataset in hand hygiene assessment. Therefore, under the supervision of medical staff, we contribute a video dataset that contains 300 video sequences with fine-grained annotations. Extensive experiments on the dataset suggest that our method well assesses hand hygiene videos and achieves outstanding performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Label Distribution Learning with Correlation Information

SSRN

引用

SSRN 2024年

作者： Wu, Yilin Lin, Yaojin Guo, Wenzhong Ding, Weiping College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Zhangzhou363000 China School of Information Science and Technology Nantong University Nantong226019 China

Label distribution learning quantifies the label space for each instance and has widely applicability in different fields. However, most existing works primarily focus on label correlation, but they still have a limitation in capturing instance correlation. Meanwhile, traditional label distribution learning operates on individual labels sequentially, leading to limitation in applying common features. Therefore, in this paper, we propose a novel approach for label distribution learning with correlation information i.e. instance correlation and label correlation. Specifically, the instance correlation and label correlation are identified by an optimization function and Pearson correlation coefficient, respectively. Besides, we conduct $\ell_{2,1}-$norm regularization to exploit common features. Comprehensive experiments manifest the superiority of our proposed approach against other well-established label distribution learning algorithms. © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Audio-visual Learning:A Survey

引用

International Journal of Automation and computing 2021年第3期18卷 351-376页

作者： Hao Zhu Man-Di Luo Rui Wang Ai-Hua Zheng Ran He Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and TechnologyAnhui UniversityHefei 230601China Center for Research on Intelligent Perception and Computing(CRIPAC)and National Laboratory of Pattern Recognition(NLPR) Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of the Chinese Academy of SciencesBeijing 100049China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai 200031China

Audio-visual learning,aimed at exploiting the relationship between audio and visual modalities,has drawn considerable attention since deep learning started to be used *** tend to leverage these two modalities to improve the performance of previously considered single-modality tasks or address new challenging *** this paper,we provide a comprehensive survey of recent audio-visual learning *** divide the current audio-visual learning tasks into four different subfields:audiovisual separation and localization,audio-visual correspondence learning,audio-visual generation,and audio-visual representation ***-of-the-art methods,as well as the remaining challenges of each subfield,are further ***,we summarize the commonly used datasets and challenges.

关键词： Deep audio-visual learning audio-visual separation and localization correspondence learning generative models representation learning

来源：评论

学校读者我要写书评

暂无评论

RIESZ TYPE THEOREMS FOR κ-PLURIHARMONIC MAPPINGS, INVARIANT HARMONIC QUASIREGULAR MAPPINGS AND HARMONIC QUASIREGULAR MAPPINGS

arXiv

引用

arXiv 2023年

作者： Chen, Shaolin Huang, Manzi College of Mathematics and Statistics Hengyang Normal University Hunan Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application 421002 China Key Laboratory of High Performance Computing and Stochastic Information Processing College of Mathematics and Statistics Hunan Normal University Hunan Changsha410081 China

The main purpose of this paper is to develop some methods to improve and generalize the main results in a recent paper by Liu and Zhu (Adv. Math., 2023, i.e., [19]). The paper consists of two parts. In the first part, we discuss the Riesz type theorem in the setting of n-dimensional complex spaces for all n ≥ 1. In this part, we first introduce the family of κ-pluriharmonic mappings of the n-dimensional complex unit ball. Then we establish two Riesz type theorems for these mappings, which are the n-dimensional versions of Theorems 1.1 and 1.2 in [19], respectively. Furthermore, even when n = 1, our first result shows that the assumption of the real parts of the mappings not being negative (or being negative) in [19, Theorem 1.1] is redundant;and our second result illustrates that the assumption of "quasiconformality" on the mappings in [19, Theorem 1.2] can be replaced by the weaker one of "quasiregularity". In the second part, we investigate the Riesz type theorem in the setting of n-dimensional real spaces for all n ≥ 2. In this part, first, we prove a Riesz type theorem for invariant harmonic quasiregular mappings of the unit n-dimensional real ball. Our result indicates that (i) the range of the parameter p discussed in [19, Theorem 1.3] can be changed from (1, 2) to (1, ∞);(ii) the assumption of the first coordinate functions of the mappings being non-zero in [19, Theorem 1.3] is redundant. In this way, we complete the discussions carried out in [19, Theorems 1.3 and 1.4]. Second, we obtain a Riesz type theorem for harmonic K-quasiregular mappings of the unit n-dimensional real ball. Our result demonstrates that the range of the parameter p discussed in [15, Theorem 2.1] can be changed from (1, 2) to (1, ∞).MSC Codes 30H10, 30C62 Copyright © 2023, The Authors. All rights reserved.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

Cross-directional Consistency Network with Adaptive Layer Normalization for Multi-spectral Vehicle Re-identification and A High-quality Benchmark

arXiv

引用

arXiv 2022年

作者： Zheng, Aihua Zhu, Xianpeng Ma, Zhiqi Li, Chenglong Tang, Jin Ma, Jixin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China School of Computing and Mathematical Sciences University of Greenwich LondonSE10 9LS United Kingdom

To tackle the challenge of vehicle re-identification (Re-ID) in complex lighting environments and diverse scenes, multi-spectral sources like visible and infrared information are taken into consideration due to their excellent complementary advantages. However, multi-spectral vehicle Re-ID suffers cross-modality discrepancy caused by heterogeneous properties of different modalities as well as a big challenge of the diverse appearance with different views in each identity. Meanwhile, diverse environmental interference leads to heavy sample distributional discrepancy in each modality. In this work, we propose a novel cross-directional consistency network (CCNet) to simultaneously overcome the discrepancies from both modality and sample aspects. In particular, we design a new cross-directional center loss (Lcdc) to pull the modality centers of each identity close to mitigate cross-modality discrepancy, while the sample centers of each identity close to alleviate the sample discrepancy. Such a strategy can generate discriminative multi-spectral feature representations for vehicle Re-ID. In addition, we design an adaptive layer normalization unit (ALNU) to dynamically adjust individual feature distribution to handle distributional discrepancy of intra-modality features for robust learning. To provide a comprehensive evaluation platform, we create a high-quality RGB-NIR-TIR multi-spectral vehicle Re-ID benchmark (MSVR310), including 310 different vehicles from a broad range of viewpoints, time spans and environmental complexities. Comprehensive experiments on both created and public datasets demonstrate the effectiveness of the proposed approach comparing to the state-of-the-art methods. The dataset and code will be released for free academic usage at https://***/superlollipop123/Cross-directional-Center-Network-and-MSVR310. © 2022, CC BY-NC-SA.

关键词： Vehicles

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：