检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhao, Defeng Ye, Zejun Zheng, Wei-Shi Wang, Ruixuan Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Peng Cheng Laboratory Department of Network Intelligence Shenzhen China Moe Key Laboratory of Machine Intelligence and Advanced Computing China

ISBN: (纸本)9798350337488

Current intelligent diagnosis systems are often trained to diagnose a small number of diseases and lack the ability of continually learning new disease knowledge. To have such continual learning ability, the deployed intelligent system needs to be continually updated based on training data of only new diseases, without accessing old data of previously learned diseases due to privacy concerns and challenges in data sharing across medical centers. In this study, a novel and effective prompt learning strategy is proposed to help a pretrained and fixed Vision Transformer (ViT) continually learn new diseases. In particular, a set of unique prompts for each disease are effectively learned such that discriminative disease features can be well extracted from the fixed ViT under the instructions of prompts during feature extraction, even though the ViT feature extractor is pretrained in the natural image domain. Extensive empirical evaluations on two medical image datasets and one natural image dataset demonstrate the superior performance of the proposed method. The source code is available at https://***/zhaoedf/CSPrompt. © 2023 IEEE.

关键词： Continual learning Disease diagnosis Prompt learning

来源：评论

学校读者我要写书评

暂无评论

Learning High-Performance Spiking Neural Networks with Multi-Compartment Spiking Neurons 12th

Learning High-Performance Spiking Neural Networks with Mult...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Li, Xinjie Tang, Jianxiong Lai, Jianhuang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9783031463075

In recent years, spiking neural networks (SNNs) have gained significant attention due to bio-inspired working mechanism. The VGG-like and ResNet-like architectures are widely used for SNNs modeling. However, the spiking features of such architectures are generated by the layer-wise Integrate-and-Fire (IF) dynamics. The firing of deep neurons is independent of the neurons in the shallow layers. In this paper, we propose Multi-Compartment Spiking Neural Network (MC-SNN) that integrates the MPs of the shallow neurons to fire the deep neurons. Specifically, the MC-SNN is modeled by a Multi-Compartment Leaky Integrate-and-Fire (MC-LIF) neuron and an Adaptive Gating Unit (AGU). The MC-LIF neuron models the IF dynamics using the MPs from both deep and shallow layers, and the AGU adaptively scales the MPs of the MC-LIF neuron. These increase the information interaction between spiking neurons and improve the performance of SNNs. Besides, we design the Binarized Synaptic Encoder (BSE) to reduce the computation cost for the input of SNNs. Experimental results show that the MC-SNN performs well on the neuromorphic datasets, reaching 79.52% and 81.24% on CIFAR10-DVS and N-Caltech101, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

An Extended-Isomap for high-dimensional data accuracy and efficiency: a comprehensive survey

引用

Multimedia Tools and Applications 2024年第38期83卷 85523-85574页

作者： Yousaf, Mahwish Shakoor Khan, Muhammad Saadat Ullah, Shamsher Institute of Intelligence Machine Hefei Institutes of Physical Science Chinese Academy of Sciences Anhui Hefei230027 China Key Laboratory of Materials Physics Institute of Solid-State Physics Chinese Academy of Sciences Anhui Hefei230027 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China

Manifold learning is a widely adopted nonlinear dimensionality reduction technique employed to discover low-dimensional representations from high-dimensional data and to explore the intrinsic data structure. It encompasses a range of nonlinear techniques, including Isomap, Local Linear Embedding (LLE), Local Tangent Space Alignment (LTSA), and Multidimensional Scaling (MDS), among others. Isomap, as a popular method in manifold learning, has exhibited promising results. However, it encounters several challenges, such as the Topological Stability Problem, Shortest Path Distance, and noise sensitivity, which compromise its accuracy and elevate its computational demands. This survey paper presents three novel existing approaches to address these challenges and enhance the performance of Isomap. Firstly, the FastIsomap method, an existing approach that combines state-of-the-art algorithms like the KD tree and NN-descent to increase graph accuracy while reducing computational cost. Secondly, the FastIsomapVis method, also an existing technique, employs a hierarchical divide-and-conquer strategy employing the KD tree and Dijkstra Buckets Double, which enhances accuracy and reduces computational time in Isomap. Lastly, the NR-Isomap method, another existing approach, used the Local Tangent Space Alignment algorithm to remove noise sensitivity and short-circuit edge problems. The existing methods improve the accuracy of Isomap but also streamline its computational requirements. Furthermore, this survey paper discusses the open issues and future research directions for Isomap and manifold learning methods. It can be a valuable resource for researchers seeking insights across diverse domains. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

94LVI Algorithms of OIpU(One-Iteration-per-Update) Type Handling Time-Dependent QP(Quadratic Programming) with Two Constraints 41

94LVI Algorithms of OIpU(One-Iteration-per-Update) Type Hand...

引用

第41届中国控制会议

作者： Yunong Zhang Zhiwen Yuan School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Research Institute of Sun Yat-sen University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper presents three relatively effective numerical algorithms,i.e.,94 LVI algorithms of OIpU(one-iteration-perupdate) type,to handle time-dependent QP(quadratic programming) problems subject to two constraints respectively(i.e.,equality and inequality constraints,equality and bound constraints,or inequality and bound constraints).Specifically,two "bridges" play essential parts of the methods(i.e.,the first "bridge" makes a QP problem convert to an LVI [linear variational inequality],and the second "bridge" makes the LVI convert to a PLPE [piecewise-linear projection equation]).On the basis of the standard94 LVI algorithm,the methods only update once through the solution of the previous sampling time ***,we conduct a number of experiments to substantiate the three algorithms respectively,which use exponential functions,log functions,and trigonometric functions in corresponding coefficients of the experimental examples.

关键词： Quadratic programming Time-dependent Numerical algorithms Linear variational inequalities(LVI)

来源：评论

学校读者我要写书评

暂无评论

Coral-like and binder-free carbon nanowires for potassium dual-ion batteries with superior rate capability and long-term cycling life

引用

Green Energy & Environment 2023年第2期8卷 548-558页

作者： Min Wang Qirong Liu Guangming Wu Jianmin Ma Yongbing Tang Functional Thin Films Research Center Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518055China School of Physics and Electronics Hunan UniversityChangsha410082China Key Laboratory of Advanced Materials Processing&Mold Ministry of EducationZhengzhou UniversityZhengzhou450002China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518055China

Owing to the advantages of high operating voltage,environmental benignity,and low cost,potassium-based dual-ion batteries(KDIBs)have been considered as a potential candidate for large-scale energy ***,KDIBs generally suffer from poor cycling performance and unsatisfied capacity,and inactive components of conductive agents,binders,and current collector further lower their overall ***,we prepare coral-like carbon nanowres(CCNWs)doped with nitrogen as a binder-free anode material for K^(+)-ion storage,in which the unique coral-like porous nanostructure and amorphous/short-range-ordered composite feature are conducive to enhancing the structural stability,to facilitating the ion transfer and to boosting the full utilization of active sites during potassiation/de-potassiation *** a result,the CCNW anode possesses a hybrid K^(+)-storage mechanism of diffusive behavior and capacitive adsorption,and stably delivers a high capacity of 276 mAh g^(-1)at 50 mA g^(-1),good rate capability up to 2 A g^(-1),and long-term cycling stability with 93%capacity retention after 2000 cycles at 1 A g^(-1).Further,assembling this CCNW anode with an environmentally benign expanded graphite(EG)cathode yields a proof-of-concept KDIB,which shows a high specific capacity of 134.4 mAh g^(-1)at 100 mA g^(-1),excellent rate capability of 106.5 mAh g^(-1)at 1 A g^(-1),and long-term cycling stability over 1000 cycles with negligible capacity *** study provides a feasible approach to developing high-performance anodes for potassium-based energy storage devices.

关键词： Carbon nanowires Binder-free K-ion Dual-ion batteries Structural stability

来源：评论

学校读者我要写书评

暂无评论

Interpretable Drug Response Prediction through Molecule Structure-aware and Knowledge-Guided Visible Neural Network

Interpretable Drug Response Prediction through Molecule Stru...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Xie, Jiancong Zhang, Zhe Li, Youyou Rao, Jiahua Yang, Yuedong Sun Yat-sen University School of Computer Science and Engineering China University of Chicago Department of Chemistry IL United States Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing of Moe China

ISBN: (纸本)9798350386226

Precise prediction of anti-cancer drug responses has become a crucial obstruction in anti-cancer drug design and clinical applications. In recent years, various deep learning methods have been applied to drug response prediction and become more accurate. However, they are still criticized as being non-transparent. To offer reliable drug response prediction in real-world applications, there is still a pressing demand to develop a model with high predictive performance as well as interpretability. In this study, we propose DrugVNN, an end-to-end interpretable drug response prediction framework, which extracts gene features of cell lines through a knowledge-guided visible neural network (VNN) and learns drug representation through a node-edge communicative message passing network (CMPNN). Additionally, between these two networks, a novel drug-aware gene attention gate is designed to direct the drug representation to VNN to simulate the effects of drugs. By evaluating on the GDSC dataset, DrugVNN achieved state-of-the-art performance. Moreover, DrugVNN can identify active genes and relevant signaling pathways for specific drug-cell line pairs with supporting evidence in the literature, implying the interpretability of our model. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Nerve function restoration following targeted muscle reinnervation after varying delayed periods

引用

Neural Regeneration Research 2023年第12期18卷 2762-2766页

作者： Yuanheng Li Jiangping Huang Yuling Chen Shanshan Zhu Zhen Huang Lin Yang Guanglin Li Key Laboratory of Human-Machine Intelligence-Synergy Systems and Branch of Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhenGuangdong ProvinceChina Department of Rehabilitation Medicine Guangzhou University of Chinese MedicineGuangzhouGuangdong ProvinceChina Department of Rehabilitation Medicine Yibin Hospital of Traditional Chinese MedicineYibinSichuan ProvinceChina

Targeted muscle reinnervation has been proposed for reconstruction of neuromuscular function in ***,it is unknown whether performing delayed targeted muscle reinnervation after nerve injury will affect restoration of *** this rat nerve injury study,the median and musculocutaneous nerves of the forelimb were *** proximal median nerve stump was sutured to the distal musculocutaneous nerve stump immediately and 2 and 4 weeks after surgery to reinnervate the biceps *** targeted muscle reinnervation,intramuscular myoelectric signals from the biceps brachii were *** amplitude gradually increased with *** brachii myoelectric signals and muscle fiber morphology and grooming behavior did not significantly differ among rats subjected to delayed target muscle innervation for different *** muscle reinnervation delayed for 4 weeks can acquire the same nerve function restoration effect as that of immediate reinnervation.

关键词： biceps brachii delayed nerve repair delayed targeted muscle reinnervation functional reconstruction grooming test implanted electrode intramuscular myoelectric signals median nerve motor function nerve transfer

来源：评论

学校读者我要写书评

暂无评论

RL-Based USV Path Planning under the Marine Multimodal Features Considerations

引用

IEEE Internet of Things Journal 2025年第11期12卷 15274-15287页

作者： Lin, Quanbao Gou, Huaxing Tian, Peidong Zuo, Tian-Yu Zhang, Hanzhong Wang, Xin Sun, Poly Z. H. Shanghai Jiao Tong University School of Aeronautics and Astronautics Shanghai200240 China Southeast University School of Computer Science and Engineering Nanjing211189 China Shanghai University School of Microelectronics Shanghai200444 China Chinese Academy of Sciences CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Guangdong Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Guangdong Shenzhen518055 China East China Normal University School of Psychology and Cognitive Science Shanghai200062 China Shanghai Jiao Tong University Department of Industrial Engineering Shanghai200240 China

Path planning is an important step in ensuring the safety of Unmanned Surface Vehicle (USV) navigation and executing missions quickly and efficiently. However, current USV path planning methods lack comprehensive consideration of electronic nautical charts and meteorological data, resulting in planned paths being unable to fully utilize marine environmental conditions, which may easily lead to collisions and long navigation times. Based on the above considerations, our study designs a USV path planning system that comprehensively considers the multimodal information from electronic nautical charts and meteorological data. The system consists of three parts: (1) image processing module, (2) meteorological analysis module, and (3) path planning module. In detail, the image processing module obtains the geographical feature information from the electronic chart and constructs a static obstacle environment. The meteorological analysis module obtains the meteorological feature information from meteorological data and constructs a dynamic meteorological vector field environment. The path planning module introduces a designed double deep Q-Network (DQN) structure, a multivariate weighted Dueling network, and a priority sampling mechanism to enhance the DQN algorithm for promising performance in USV path planning. Extensive experiments illustrate the superior performance of the proposed fusion DQN algorithm. Furthermore, the feasibility of the entire path planning system is confirmed. © 2014 IEEE.

关键词： Unmanned surface vehicles

来源：评论

学校读者我要写书评

暂无评论

SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses 24

SynopGround: A Large-Scale Dataset for Multi-Paragraph Video...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Tan, Chaolei Lin, Zihang Pu, Junfu Qi, Zhongang Pei, Wei-Yi Qu, Zhi Wang, Yexin Shan, Ying Zheng, Wei-Shi Hu, Jian-Fang Sun Yat-sen University Guangzhou China ARC Lab Tencent PCG Shenzhen China Tencent Video PCG Shenzhen China Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Sun Yat-sen University Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9798400706868

Video grounding is a fundamental problem in multimodal content understanding, aiming to localize specific natural language queries in an untrimmed video. However, current video grounding datasets merely focus on simple events and are either limited to shorter videos or brief sentences, which hinders the model from evolving toward stronger multimodal understanding capabilities. To address these limitations, we present a large-scale video grounding dataset named SynopGround, in which more than 2800 hours of videos are sourced from popular TV dramas and are paired with accurately localized human-written synopses. Each paragraph in the synopsis serves as a language query and is manually annotated with precise temporal boundaries in the long video. These paragraph queries are tightly correlated to each other and contain a wealth of abstract expressions summarizing video storylines and specific descriptions portraying event details, which enables the model to learn multimodal perception on more intricate concepts over longer context dependencies. Based on the dataset, we further introduce a more complex setting of video grounding dubbed Multi-Paragraph Video Grounding (MPVG), which takes as input multiple paragraphs and a long video for grounding each paragraph query to its temporal interval. In addition, we propose a novel Local-Global Multimodal Reasoner (LGMR) to explicitly model the local-global structures of long-term multimodal inputs for MPVG. Our method provides an effective baseline solution to the multi-paragraph video grounding problem. Extensive experiments verify the proposed model's effectiveness as well as its superiority in long-term multi-paragraph video grounding over prior state-of-the-arts. Dataset and code are publicly available. Project page: https://***/. © 2024 Owner/Author.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis

arXiv

引用

arXiv 2024年

作者： Liu, Feng Chang, Xiaobin School of Artificial Intelligence Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing China

Semantic image synthesis aims to generate high-quality images given semantic conditions, i.e. segmentation masks and style reference images. Existing methods widely adopt generative adversarial networks (GANs). GANs take all conditional inputs and directly synthesize images in a single forward step. In this paper, semantic image synthesis is treated as an image denoising task and is handled with a novel image-to-image diffusion model (IIDM). Specifically, the style reference is first contaminated with random noise and then progressively denoised by IIDM, guided by segmentation masks. Moreover, three techniques, refinement, color-transfer and model ensembles, are proposed to further boost the generation quality. They are plug-in inference modules and do not require additional training. Extensive experiments show that our IIDM outperforms existing state-of-the-art methods by clear margins. Further analysis is provided via detailed demonstrations. We have implemented IIDM based on the Jittor framework;code is available at https://***/ader47/jittorjieke-semantic_images_synthesis. © 2024, CC BY.

关键词： Generative adversarial networks

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：