检索结果-内蒙古大学图书馆

Optimal mixed control of networked reaction-diffusion systems

Physical Review Research 2025年第1期7卷 013262-013262页

作者： Xiaofeng Luo Runzi He Lifeng Hou Shupeng Gao Zhen Jin Gui-Quan Sun Lili Chang Ludovico Minati Stefano Boccaletti School of Mathematics North University of China Shanxi Taiyuan 030051 Peoples's Republic of China Sino-Europe Complex Science Center North University of China Shanxi Taiyuan 030051 Peoples's Republic of China School of Computer Science and Technology North University of China Shanxi Taiyuan 030051 Peoples's Republic of China Complex Systems Research Center Shanxi University Shanxi Taiyuan 030006 Peoples's Republic of China Tangshan Research Institute Beijing Institute of Technology Hebei Tangshan 063000 Peoples's Republic of China School of Mechanical Engineering North China University of Science and Technology Hebei Tangshan 063000 Peoples's Republic of China Key Laboratory of Complex Systems and Data Science of Ministry of Education Shanxi Taiyuan 030006 Peoples's Republic of China School of Life Science and Technology University of Electronic Science and Technology of China Chengdu 611731 Peoples's Republic of China Center for Mind/Brain Sciences (CIMeC) University of Trento 38123 Trento Italy CNR-Institute of Complex Systems Via Madonna del Piano 10 50019 Sesto Fiorentino Italy Institute of Interdisciplinary Intelligent Science Ningbo University of Technology Ningbo 315211 Peoples's Republic of China

We introduce a control scheme able to steer the evolution of networked reaction-diffusion systems toward any intended dynamics. Specifically, we consider simplicial complexes of reaction-diffusion systems that can be collapsed into weighted complex networks by leveraging the linear relationship between the Laplacian matrix of the simplicial complex and the Laplacian matrix of each order simplex. The method integrates reaction and network-based diffusion controls and, as far as effectiveness and cost are concerned, features a significantly improved performance over traditional single-variable control methods. Numerical simulations using the FitzHugh-Nagumo and susceptible-infected-removed models demonstrate the resilience of the proposed mixed control across diverse systems, highlighting the potential of the method for complex system management and intervention strategies.

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

GCapNet-FSD: A heterogeneous Graph Capsule Network for Few-Shot object Detection

引用

Neural Networks 2025年 189卷 107570页

作者： Leng, Jiaxu Chen, Qianru Chen, Taiyue Gao, Feng Gan, Ji Gu, Changjun Gao, Xinbo School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing 400065 China Chongqing Institute for Brain and Intelligence Guangyang Bay Laboratory Chongqing 400064 China

Few-shot object detection is a challenging task that aims to quickly adapt detectors to detect novel objects with only a minimal number of annotated examples. Although promising results have been achieved, performance still declines significantly when the number of shots decreases sharply. We argue that this shot sensitivity is due to the critical under-utilization of both internal few-shot data and external common knowledge bases. Therefore, the key insight is how to extract more discriminative notions to compensate for the insufficient task-specific information from the limited novel dataset. We propose a novel heterogeneous Graph Capsule Network for Few-Shot object Detection, named GCapNet-FSD. Specifically, we design a heterogeneous graph to combine the high-level visual capsule neurons from internal few-shot data and the stable semantic embeddings from the external easily available corpus for more discriminative task-specific representations. As a result, our proposed GCapNet-FSD is stable and robust for various settings of the shots. Our design outperforms current works in 1-shot of any split, with up to +3.7% on PASCAL VOC07&12 and +0.4% on challenging COCO benchmark, and extensive experiments on both PASCAL VOC07&12 and MS COCO benchmarks demonstrate that our GCapNet-FSD shows shot-stable detection performance and achieves significantly better performance at lower shots. © 2025 Elsevier Ltd

关键词： Capsule neural networks Capsule neurons Few-shot learning Object detection

来源：评论

学校读者我要写书评

暂无评论

Tetris:A Heuristic Static Memory Management Framework for Uniform Memory Multicore Neural Network Accelerators

引用

Journal of computer science & technology 2022年第6期37卷 1255-1270页

作者： Xiao-Bing Chen Hao Qi Shao-Hui Peng Yi-Min Zhuang Tian Zhi Yun-Ji Chen Distinguished Member,CCF State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China School of Computer Science and Technology University of Science and Technology of ChinaHeFei230026China Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Shanghai200031China 不详

Uniform memory multicore neural network accelerators(UNNAs)furnish huge computing power to emerging neural network ***,with neural network architectures going deeper and wider,the limited memory capacity has become a constraint to deploy models on UNNA *** how to efficiently manage memory space and how to reduce workload footprints are urgently *** this paper,we propose Tetris:a heuristic static memory management framework for UNNA *** reconstructs execution flows and synchronization relationships among cores to analyze each tensor’s liveness *** the memory management problem is converted to a sequence permutation *** uses a genetic algorithm to explore the permutation space to optimize the memory management strategy and reduce memory *** evaluate several typical neural networks and the experimental results demonstrate that Tetris outperforms the state-of-the-art memory allocation methods,and achieves an average memory reduction ratio of 91.9%and 87.9%for a quad-core and a 16-core Cambricon-X platform,respectively.

关键词： multicore neural network accelerators liveness analysis static memory management memory reuse genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Consistent Alterations of Human Fecal Microbes After Transplantation into Germ-free Mice

引用

Genomics, Proteomics & Bioinformatics 2022年第2期20卷 382-393页

作者： Yanze Li Wenming Cao Na L Gao Xing-Ming Zhao Wei-Hua Chen MOE Key Laboratory of Molecular Biophysics Hubei Key Laboratory of Bioinformatics and Molecular-imagingDepartment of Bioinformatics and Systems BiologyCollege of Life Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Institute of Science and Technology for Brain-Inspired Intelligence(ISTBI) Fudan UniversityShanghai 200433China College of Life Science Henan Normal UniversityXinxiang 453007China

Fecal microbiota transplantation(FMT)of human fecal samples into germ-free(GF)mice is useful for establishing causal relationships between the gut microbiota and human ***,due to the intrinsic differences between human and mouse intestines and the different diets of the two organisms,it may not be possible to replicate human phenotypes in mice through FMT;similarly,treatments that are effective in mouse models may not be effective in *** this study,we aimed to identify human gut microbes that undergo significant and consistent changes(i.e.,in relative abundances)after transplantation into GF mice in multiple experimental *** collected 16S rDNA-seq data from four published studies and analyzed the gut microbiota profiles from 1713 human–mouse ***,on average,we found that only 47%of the human gut microbes could be re-established in mice at the species level,among which more than 1/3 underwent significant changes(referred to as“variable taxa”).Most of the human gut microbes that underwent significant changes were consistent across multiple human–mouse pairs and experimental ***,about 1/3 of human samples changed their enterotypes,i.e.,significant changes in their leading species after *** fed with a controlled diet showed a lower enterotype change rate(23.5%)than those fed with a noncontrolled diet(49.0%),suggesting a possible solution for *** of the variable taxa have been reported to be implicated in human diseases,with some recognized as the causative *** results highlight the challenges of using a mouse model to replicate human gut microbiota-associated phenotypes,provide useful information for researchers using mice in gut microbiota studies,and call for additional validations after *** online database named FMT-DB is publicly available at http://***/#/.

关键词： Germ-free mice Fecal microbiota transplantation Gut microbe Enterotype 16S rDNA

来源：评论

学校读者我要写书评

暂无评论

Co-delivery of anticancer drugs and cell penetrating peptides for improved cancer therapy

引用

Chinese Chemical Letters 2021年第4期32卷 1559-1562页

作者： Xiao Fu Guiqiang Zhang Yulin Zhang Haifeng Sun Shuang Yang Shilei Ni Jiwei Cui Key Laboratory of Colloid and Interface Chemistry of the Ministry of Education School of Chemistry and Chemical EngineeringShandong UniversityJi'nan 250100China Department of Neurosurgery Qilu Hospital and Institute of Brain and Brain-Inspired ScienceCheeloo College of MedicineShandong UniversityJi'nan 250012China State Key Laboratory of Microbial Technology Shandong UniversityQingdao 266237China

Delivery systems based on nanoparticles(NPs)have shown great potential to reduce side effects and improve the therapeutic ***,we report the one-pot synthesis of poly(ethylene glycol)-mediated zeolitic imidazolate framework-8(ZIF-8)NPs for the co-delivery of an anticancer drug(i.e.,doxorubicin)and a cell penetrating peptide containing histidine and arginine(i.e.,H4 R4)to improve the efficacy of therapeutic delive *** cargo-encapsulated ZIF-8 NPs are pH-responsive,which are stable at neutral pH and degradable at acidic pH to release the encapsulated *** released H4 R4 can help for endosome/lysosome escape to enhance the cytotoxicity of the encapsulated *** vivo studies demonstrate that the co-delivery of doxo rubicin and H4 R4 peptides can efficiently inhibit tumor growth without significant side *** reported strategy provides a new perspective on the design of drug delivery systems and brings more opportunities for biomedical applications.

关键词： Metal-organic frameworks Lysosome escape pH-responsiveness Drug delivery Poly(ethylene glycol)

来源：评论

学校读者我要写书评

暂无评论

Strided Self-Supervised Low-Dose CT Denoising for Lung Nodule Classification

引用

Phenomics 2021年第6期1卷 257-268页

作者： Yiming Lei Junping Zhang Hongming Shan Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 201210China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence(Fudan University) Ministry of EducationShanghai 201210China

Lung nodule classification based on low-dose computed tomography(LDCT)images has attracted major attention thanks to the reduced radiation dose and its potential for early diagnosis of lung cancer from LDCT-based lung cancer ***,LDCT images suffer from severe noise,largely influencing the performance of lung nodule *** methods combining denoising and classification tasks typically require the corresponding normal-dose CT(NDCT)images as the supervision for the denoising task,which is impractical in the context of clinical diagnosis using *** jointly train these two tasks in a unified framework without the NDCT images,this paper introduces a novel self-supervised method,termed strided Noise2Neighbors or SN2N,for blind medical image denoising and lung nodule classification,where the supervision is generated from noisy input *** specifically,the proposed SN2N can construct the supervision infor-mation from its neighbors for LDCT denoising,which does not need NDCT images *** proposed SN2N method enables joint training of LDCT denoising and lung nodule classification tasks by using self-supervised loss for denoising and cross-entropy loss for *** experimental results on the Mayo LDCT dataset demonstrate that our SN2N achieves competitive performance compared with the supervised learning methods that have paired NDCT images as ***,our results on the LIDC-IDRI dataset show that the joint training of LDCT denoising and lung nodule classification significantly improves the performance of LDCT-based lung nodule classification.

关键词： Convolutional neural network Medical image classification Self-supervised denoising Low-dose CT

来源：评论

学校读者我要写书评

暂无评论

Challenges and future directions of secure federated learning:a survey

引用

Frontiers of computer science 2022年第5期16卷 173-180页

作者： Kaiyue ZHANG Xuan SONG Chenhan ZHANG Shui YU Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Faculty of Engineering and Information Technology University of Technology SydneySydney 2007Australia SUSTech-UTokyo Joint Research Center on Super Smart City Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big *** is an algorithm that does not collect users’raw data,but aggregates model parameters from each client and therefore protects user’s ***,due to the inherent distributed nature of federated learning,it is more vulnerable under attacks since users may upload malicious data to break down the federated learning *** addition,some recent studies have shown that attackers can recover information merely from ***,there is still lots of room to improve the current federated learning *** this survey,we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated *** open issues and existing solutions in federated learning are *** also point out the future research directions of federated learning.

关键词： federated learning privacy protection security

来源：评论

学校读者我要写书评

暂无评论

Decoding Pigeon Behavior Outcomes during Goal-directed Decision Task by WSR Functional Network Analysis*

Decoding Pigeon Behavior Outcomes during Goal-directed Decis...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Shuguan Cheng Mengmeng Li Haifei Yu Kun Zhao Shuo Liu Hong Wan School of Electrical Engineering Zhengzhou University and Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology Zhengzhou China

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

It is a hot research direction to reveal the working mechanism of brain by measuring the connection characteristics of brain function network. In this paper, to decode pigeon behavior outcomes in goal-directed decision task, an experiment based on plus maze was designed and the nidopallium caudolaterale (NCL) of the pigeon was selected as the target brain region. The local field potential (LFP) signals in the waiting area (WA) and turning area (TA) were recorded when the pigeons performed the goal-directed tasks. Then, the brain functional connection networks of the LFPs were constructed and the extracted features were applied to decode pigeon behavior outcomes. Firstly, continuous wavelet transform (CWT) was used to carried out time-frequency analysis and the task-related frequency band (40-60 Hz) was extracted. Then, weighted sparse representation (WSR) method was used to construct the functional connectivity network and the related network features were selected. Finally, k-nearest neighbor (kNN) algorithm was used to decode behavior outcomes. The results show that the energy difference between TA and WA in 40-60 Hz band is significantly higher than those in other bands. The selected features have good discriminability for the representation of the differences between WA and TA. The decoding results also suggest the classification performance of the different behavior outcomes. These results show the effectiveness of the WSR to construct the function network to decode behavior outcomes.

关键词： Feature extraction Task analysis Decoding Time-frequency analysis brain modeling Continuous wavelet transforms Electrodes

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "brain network communication in remission: a comparative study of bipolar and unipolar depression" [J. Psychiatr. Res. 186 (2025) 1-8]

引用

Journal of psychiatric research 2025年

作者： Haiyan Liu Yi Xia Lingling Hua Hao Sun Rui Yan Zhijian Yao Jiaolong Qin Department of Psychiatry The Affiliated Brain Hospital of Nanjing Medical University Nanjing China. Department of Psychiatry The Affiliated Brain Hospital of Nanjing Medical University Nanjing China. Electronic address: zjyao@***. The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China.

来源：评论

学校读者我要写书评

暂无评论

Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model 38

Denoising Diffusion Path: Attribution Noise Reduction with A...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lei, Yiming Li, Zilong Zhang, Junping Shan, Hongming Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China Institute of Science and Technology for Brain-Inspired Intelligence MOE Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence MOE Frontiers Center for Brain Science Fudan University China

The explainability of deep neural networks (DNNs) is critical for trust and reliability in AI systems. Path-based attribution methods, such as integrated gradients (IG), aim to explain predictions by accumulating gradients along a path from a baseline to the target image. However, noise accumulated during this process can significantly distort the explanation. While existing methods primarily concentrate on finding alternative paths to circumvent noise, they overlook a critical issue: intermediate-step images frequently diverge from the distribution of training data, further intensifying the impact of noise. This work presents a novel Denoising Diffusion Path (DDPath) to tackle this challenge by harnessing the power of diffusion models for denoising. By exploiting the inherent ability of diffusion models to progressively remove noise from an image, DDPath constructs a piece-wise linear path. Each segment of this path ensures that samples drawn from a Gaussian distribution are centered around the target image. This approach facilitates a gradual reduction of noise along the path. We further demonstrate that DDPath adheres to essential axiomatic properties for attribution methods and can be seamlessly integrated with existing methods such as IG. Extensive experimental results demonstrate that DDPath can significantly reduce noise in the attributions-resulting in clearer explanations-and achieves better quantitative results than traditional path-based methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：