检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ma, Mingrui Han, Lansheng Zhou, Chunjie Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

Transformer, as one of the most advanced neural network models in Natural Language processing (NLP), exhibits diverse applications in the field of anomaly detection. To inspire research on Transformer-based anomaly detection, this review offers a fresh perspective on the concept of anomaly detection. We explore the current challenges of anomaly detection and provide detailed insights into the operating principles of Transformer and its variants in anomaly detection tasks. Additionally, we delineate various application scenarios for Transformer-based anomaly detection models and discuss the datasets and evaluation metrics employed. Furthermore, this review highlights the key challenges in Transformer-based anomaly detection research and conducts a comprehensive analysis of future research trends in this domain. The review includes an extensive compilation of over 100 core references related to Transformer-based anomaly detection. To the best of our knowledge, this is the first comprehensive review that focuses on the research related to Transformer in the context of anomaly detection. We hope that this paper can provide detailed technical information to researchers interested in Transformer-based anomaly detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Bridging the Functional and Wiring Properties of V1 Neurons Through Sparse Coding

引用

NEURAL COMPUTATION 2021年第1期34卷 104-137页

作者： Hu, Xiaolin Zeng, Zhigang Tsinghua Univ State Key Lab Intelligent Technol & Syst Dept Comp Sci & Technol BNRistTsinghua Lab Brain & Intelligence Beijing 100084 Peoples R China Tsinghua Univ IDG McGovern Inst Brain Res Beijing 100084 Peoples R China Huazhong Univ Sci & Technol Sch ArtOcial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

The functional properties of neurons in the primary visual cortex (V1) are thought to be closely related to the structural properties of this network, but the specific relationships remain unclear. Previous theoretical studies have suggested that sparse coding, an energy-efficient coding method, might underlie the orientation selectivity of V1 neurons. We thus aimed to delineate how the neurons are wired to produce this feature. We constructed a model and endowed it with a simple Hebbian learning rule to encode images of natural scenes. The excitatory neurons fired sparsely in response to images and developed strong orientation selectivity. After learning, the connectivity between excitatory neuron pairs, inhibitory neuron pairs, and excitatory-inhibitory neuron pairs depended on firing pattern and receptive field similarity between the neurons. The receptive fields (RFs) of excitatory neurons and inhibitory neurons were well predicted by the RFs of presynaptic excitatory neurons and inhibitory neurons, respectively. The excitatory neurons formed a small-world network, in which certain local connection patterns were significantly overrepresented. Bidirectionally manipulating the firing rates of inhibitory neurons caused linear transformations of the firing rates of excitatory neurons, and vice versa. These wiring properties and modulatory effects were congruent with a wide variety of data measured in V1, suggesting that the sparse coding principle might underlie both the functional and wiring properties of V1 neurons.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Front-end Replication Dynamic Window (FRDW) for Online Motor imagery Classification

arXiv

引用

arXiv 2024年

作者： Chen, Xinru An, Jiayu Wu, Huanyu Li, Siyang Liu, Bin Wu, Dongrui The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China Beijing Fenghuo Wanjia Technology Co. Ltd. Beijing100026 China

Motor imagery (MI) is a classical paradigm in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Online accurate and fast decoding is very important to its successful applications. This paper proposes a simple yet effective front-end replication dynamic window (FRDW) algorithm for this purpose. Dynamic windows enable the classification based on a test EEG trial shorter than those used in training, improving the decision speed;front-end replication fills a short test EEG trial to the length used in training, improving the classification accuracy. Within-subject and cross-subject online MI classification experiments on three public datasets, with three different classifiers and three different data augmentation approaches, demonstrated that FRDW can significantly increase the information transfer rate in MI decoding. Additionally, FR can also be used in training data augmentation. FRDW helped win national champion of the China BCI Competition in 2022. © 2024, CC BY.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Sparse Prior Is Not All You Need: When Differential Directionality Meets Saliency Coherence for Infrared Small Target Detection

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Zhou, Fei Fu, Maixia Qian, Yulei Yang, Jian Dai, Yimian Henan Univ Technol Key Lab Grain Informat Proc & Control Minist Educ Zhengzhou 450001 Peoples R China Henan Univ Technol Henan Key Lab Grain Photoelect Detect & Control Zhengzhou 450001 Peoples R China Henan Univ Technol Coll Informat Sci & Engn Zhengzhou 450001 Peoples R China Nanjing Marine Radar Inst Nanjing 210000 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn PCA Lab Key Lab Intelligent Percept & Syst High Dimens Inf Nanjing 210000 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Social Nanjing 210000 Peoples R China

The infrared small target detection is crucial for the efficacy of infrared search and tracking systems. Current tensor decomposition methods emphasize representing small targets with sparsity but struggle to separate targets from complex backgrounds due to insufficient use of intrinsic directional information and reduced target visibility during decomposition. To address these challenges, this study introduces a sparse differential directionality prior (SDD) framework. SDD leverages the distinct directional characteristics of targets to differentiate them from the background, applying mixed sparse constraints on the differential directional images and continuity difference matrix of the temporal component, both derived from Tucker decomposition. We further enhance the target detectability with a saliency coherence strategy that intensifies target contrast against the background during hierarchical decomposition. A proximal alternating minimization (PAM)-based algorithm efficiently solves our proposed model. Experimental results on several real-world datasets validate our method's effectiveness, outperforming ten state-of-the-art methods in target detection and clutter suppression. Our code is available at: https://***/GrokCV/SDD.

关键词： Tensors Object detection Clutter Matrix decomposition Sparse matrices Correlation Coherence Vectors Target tracking Sparse approximation Proximal optimization saliency map spatial-temporal regularization target detection tensor decomposition

来源：评论

学校读者我要写书评

暂无评论

Adversarial Semantic Data Augmentation for Human Pose Estimation 16th

Adversarial Semantic Data Augmentation for Human Pose Estima...

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Bin, Yanrui Cao, Xuan Chen, Xinya Ge, Yanhao Tai, Ying Wang, Chengjie Li, Jilin Huang, Feiyue Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent Youtu Lab Shanghai China

ISBN: (纸本)9783030585280

Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and nearby person. To enlarge the amounts of challenging cases, previous methods augmented images by cropping and pasting image patches with weak semantics, which leads to unrealistic appearance and limited diversity. We instead propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. Furthermore, we propose Adversarial Semantic Data Augmentation (ASDA), which exploits a generative network to dynamically predict tailored pasting configuration. Given off-the-shelf pose estimation network as discriminator, the generator seeks the most confusing transformation to increase the loss of the discriminator while the discriminator takes the generated sample as input and learns from it. The whole pipeline is optimized in an adversarial manner. State-of-the-art results are achieved on challenging benchmarks. The code has been publicly available at https://***/Binyr/ASDA. © 2020, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Polynomial chaos-based H2 output-feedback control of systems with probabilistic parametric uncertainties

引用

AUTOMATICA 2021年 131卷 109743-109743页

作者： Wan, Yiming Shen, Dongying Erin Lucia, Sergio Findeisen, Rolf Braatz, Richard D. Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Minist Educ China Key Lab Image Proc & Intelligent Control Beijing Peoples R China MIT 77 Massachusetts Ave Cambridge MA 02139 USA TU Dortmund Univ D-44227 Dortmund Germany Otto von Guericke Univ Lab Syst Theory & Automat Control D-39106 Magdeburg Germany

H-2 static and dynamic output-feedback control problems are investigated for linear time-invariant uncertain systems. The goal is to minimize the averaged H-2 performance in the presence of nonlinear dependence on time-invariant probabilistic parametric uncertainties. By applying the polynomial chaos theory, the control synthesis problem is solved using a high-dimensional expanded system which characterizes stochastic state uncertainty propagation. Compared to existing polynomial chaos-based control designs, the proposed approach addresses the simultaneous presence of parametric uncertainties and white noises. The effect of truncation errors due to using finite-degree polynomial chaos expansions is captured by time-varying norm-bounded uncertainties, and is explicitly taken into account by adopting a guaranteed cost control approach. This feature avoids the use of high-degree polynomial chaos expansions to alleviate the destabilizing effect of expansion truncation errors, thus significantly reducing computational complexity. Moreover, rigorous analysis clarifies the condition under which the stability of the high-dimensional expanded system implies the internal mean square stability of the original system under control. Using iterations between synthesis and post-analysis, a bisection algorithm is proposed to find the smallest bounding parameter on the effect of expansion truncation errors such that robust closed-loop stability is guaranteed. A numerical example is used to illustrate the effectiveness of the proposed approach. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Output-feedback Robust control Parametric uncertainties Polynomial chaos Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Distributed Impulsive control for Signed Networks of Coupled Harmonic Oscillators With Sampled Positions

引用

IEEE TRANSACTIONS ON control OF NETWORK SYSTEMS 2021年第1期8卷 111-122页

作者： Song, Qiang Wen, Guanghui Meng, Deyuan Liu, Zhi-Wei Liu, Fang Henan Univ Technol Coll Elect Engn Minist Educ Key Lab Grain Informat Proc & Control Zhengzhou 450001 Henan Peoples R China Southeast Univ Sch Math Lab Secur Operat & Control Intelligent Autonomous Nanjing 210096 Peoples R China RMIT Univ Sch Engn Melbourne Vic 3001 Australia Beihang Univ Res Div 7 Beijing 100191 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China Huanghuai Univ Sch Informat Engn Henan Int Joint Lab Behav Optimizat Control Smart Zhumadian 463000 Peoples R China

This article considers the distributed impulsive control problem for a signed network composed by coupled harmonic oscillators based on relative position data, where the topology graph can be either structurally balanced or unbalanced, consisting of positive and negative links. First, an impulsive control algorithm is proposed for the network by utilizing both current and previous sampled positions. A necessary and sufficient condition is established such that the impulsive-controlled network can exhibit convergent behaviors, including bipartite synchronization, interval bipartite synchronization, and global stabilization. Second, some discussions are further provided to analyze two additional impulsive control algorithms designed with either current or previous sampled positions, in which it is shown that the former algorithm cannot lead to the convergent behaviors of the network, while the latter algorithm can solve the distributed impulsive control problem of the network under some appropriate conditions. Finally, simulation examples are given to illustrate the theoretical analysis.

关键词： Coupled harmonic oscillators impulsive control impulsive interval Schur stability analysis signed graph

来源：评论

学校读者我要写书评

暂无评论

Evolution-Communication Spiking Neural P Systems

引用

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS 2021年第2期31卷 2050064页

作者： Wu, Tingfang Lyu, Qiang Pan, Linqiang Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Peoples R China Soochow Univ Prov Key Lab Comp Informat Proc Technol Suzhou 215006 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc & Intelligent Control Educ Minist ChinaInst Artificial Intelligence Wuhan 430074 Hubei Peoples R China

Spiking neural P systems (SNP systems) are a class of distributed and parallel computation models, which are inspired by the way in which neurons process information through spikes, where the integrate-and-fire behavior of neurons and the distribution of produced spikes are achieved by spiking rules. In this work, a novel mechanism for separately describing the integrate-and-fire behavior of neurons and the distribution of produced spikes, and a novel variant of the SNP systems, named evolution-communication SNP (ECSNP) systems, is proposed. More precisely, the integrate-and-fire behavior of neurons is achieved by spike-evolution rules, and the distribution of produced spikes is achieved by spike-communication rules. Then, the computational power of ECSNP systems is examined. It is demonstrated that ECSNP systems are Turing universal as number-generating devices. Furthermore, the computational power of ECSNP systems with a restricted form, i.e. the quantity of spikes in each neuron throughout a computation does not exceed some constant, is also investigated, and it is shown that such restricted ECSNP systems can only characterize the family of semilinear number sets. These results manifest that the capacity of neurons for information storage (i.e. the quantity of spikes) has a critical impact on the ECSNP systems to achieve a desired computational power.

关键词： Membrane computing neural computation spiking neural network spiking neural P system computational power

来源：评论

学校读者我要写书评

暂无评论

Emotion Prediction in Conversation Based on Relationship Extraction

Emotion Prediction in Conversation Based on Relationship Ext...

引用

4th IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Liu Yingjian Wang Xiaoping Lei Shanglin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Educ Minist China Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

ISBN: (纸本)9781665490283

With the development of human-computer interaction systems, emotion recognition in conversation (ERC) has attracted increasing interest in recent years. Motivated by recent studies which have proven that generating emotional conversation responses can effectively improve the performance of the ERC model. However, accurate emotional response is complicated due to the limited number of dialogue samples. Therefore, we propose a simple and effective framework for emotion prediction in conversation based on relationship extraction (DiaRP), consisting of two curricula: (1) Dialogue Relationship Capture (DRC);and (2) Next Emotion Prediction (NEP). In DRC, we capture the current emotional self-dependence and interpersonal dependence according to the influence of self and others on the current moment emotion in the conversation. We integrate self-dependence and interpersonal dependence for NEP to predict their emotional state without current utterance. We also measure the similarity between recognized emotion distribution and predicted emotion distribution by the KL divergence. With the proposed model-agnostic DiaRP strategy, we observe a significant performance improvement over a wide range of existing ERC models and achieve new state-of-the-art results on three public ERC datasets.

关键词： Training Human computer interaction Emotion recognition Current measurement Oral communication Predictive models Emotional responses

来源：评论

学校读者我要写书评

暂无评论

Knockdown of FOXA1 enhances the osteogenic differentiation of human bone marrow mesenchymal stem cells partly via activation of the ERK1/2 signalling pathway

引用

STEM CELL RESEARCH & THERAPY 2022年第1期13卷 1页

作者： Li, Lijun Wang, Yibo Wang, Zhongxiang Xue, Deting Dai, Chengxin Gao, Xiang Ma, Jianfei Hang, Kai Pan, Zhijun Zhejiang Univ Affiliated Hosp 2 Dept Orthoped Surg Sch Med Hangzhou Zhejiang Peoples R China Zhejiang Univ Orthoped Res Inst Hangzhou Zhejiang Peoples R China Key Lab Motor Syst Dis Res & Precis Therapy Zheji Hangzhou Zhejiang Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc & Intelligent Control Wuhan Peoples R China Clin Res Ctr Motor Syst Dis Zhejiang Prov Hangzhou Zhejiang Peoples R China

Background The available therapeutic options for large bone defects remain extremely limited, requiring new strategies to accelerate bone healing. Genetically modified bone mesenchymal stem cells (BMSCs) with enhanced osteogenic capacity are recognised as one of the most promising treatments for bone defects. Methods We performed differential expression analysis of miRNAs between human BMSCs (hBMSCs) and human dental pulp stem cells (hDPSCs) to identify osteogenic differentiation-related microRNAs (miRNAs). Furthermore, we identified shared osteogenic differentiation-related miRNAs and constructed an miRNA-transcription network. The Forkhead box protein A1 (FOXA1) knockdown strategy with a lentiviral vector was used to explore the role of FOXA1 in the osteogenic differentiation of MSCs. Cell Counting Kit-8 was used to determine the effect of the knockdown of FOXA1 on hBMSC proliferation;real-time quantitative reverse transcription PCR (qRT-PCR) and western blotting were used to investigate target genes and proteins;and alkaline phosphatase (ALP) staining and Alizarin Red staining (ARS) were used to assess ALP activity and mineral deposition, respectively. Finally, a mouse model of femoral defects was established in vivo, and histological evaluation and radiographic analysis were performed to verify the therapeutic effects of FOXA1 knockdown on bone healing. Results We identified 22 shared and differentially expressed miRNAs between hDPSC and hBMSC, 19 of which were downregulated in osteogenically induced samples. The miRNA-transcription factor interaction network showed that FOXA1 is the most significant and novel osteogenic differentiation biomarker among more than 300 transcription factors that is directly targeted by 12 miRNAs. FOXA1 knockdown significantly promoted hBMSC osteo-specific genes and increased mineral deposits in vitro. In addition, p-ERK1/2 levels were upregulated by FOXA1 silencing. Moreover, the increased osteogenic differentiation of FOXA1 knockd

关键词： Osteogenic differentiation FOXA1 Bioinformatics ERK1 2

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：