检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 176-191页

作者： Jia, Bin-Bin Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China College of Electrical and Information Engineering Lanzhou University of Technology Lanzhou730050 China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing210096 China

In multi-dimensional classification, the semantics of objects are characterized by multiple class variables from different dimensions. To model the dependencies among class variables, one natural strategy is to build a number of multiclass classifiers in a chaining structure, one per dimension, where the subsequent classifiers on the chain augment the feature space with all labeling information used by the preceding classifiers. However, it is shown that this strategy cannot compete with existing state-of-the-art approaches via comparative studies. One possible reason is that inaccurate predictions of preceding classifiers would degenerate the performance of subsequent ones. Besides, it is more difficult to learn a multiclass classifier than a binary one with the same accuracy, and better performance can be expected if the multi-dimensional classification problem can be solved by building multiple binary classifiers in a chaining structure. Based on these conjectures, this article proposes an approach, which builds a chain of binary classifiers to solve the multi-dimensional classification problem with the help of one-versus-one decomposition. To address the issue that different one-versus-one decomposed problems involve different training examples, the feature space is augmented with the binary predictions of preceding classifiers on the chain to train the subsequent ones. To alleviate the effect of the specified chaining order, the ensemble version of the proposed approach is further investigated. Comparative studies over 20 benchmark datasets clearly show the superiority of the proposed approach against the state-of-the-art multi-dimensional classification baselines. © 2020 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Sparrow Search Algorithm with Adaptive Collaborative Updating

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1706-1724页

作者： Hong, Chuanbo Liang, Quan Liang, Qiaoxin Yu, Wenjie Yu, Wenze Xiong, Neng School of Mechanical and Electrical Engineering Quanzhou University of Information Engineering Quanzhou362000 China College of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China Quanzhou Management Branch Fujian Expressway Group Cp. Ltd Quanzhou362000 China

The research of swarm intelligence shows a rapid development trend. People have studied a lot of swarm intelligence algorithms inspired by biology. Sparrow search algorithm is concerned by many scholars because of its powerful search performance. However, in the case of high-dimension optimization problems, if only a single sparrow search algorithm is used to solve optimization problems, the optimal solution often cannot be found, and the phenomenon of dimension disaster will occur or it is easy to fall into the local optimal solution. In order to make sparrow search algorithm have better performance in solving high-dimensional complex problems, In this paper, we propose a new Sparrow Search Algorithm with Adaptive Collaborative Updating (SSA-ACU). The SSA-ACU algorithm initializes the population through the chaotic search strategy to make the population distribution more diverse. Then, adaptive parameters are introduced to update the position of the leader to provide a more reliable direction for particle search. Finally, in order to enhance the development ability of the population, the position of the adjoint is updated through the pseudo-affine transformation mechanism to change the mode of its position update. Then CEC2013 was used to test and compare SSA-ACU algorithm with other sparrow search algorithm variants and classical algorithms, and it was verified that SSA-ACU algorithm has good performance in convergence speed and optimization ability. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Discrete Geometric Coded Data Layout for Large-scale Object Storage Systems 21

Discrete Geometric Coded Data Layout for Large-scale Object ...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Tian, Yi Xu, Guangping Yang, Hongzhang Ni, Yue Cao, JiaXin Yang, Lei Tianjin University of Technology School of Computer Science and Engineering Tianjin China Novel Software Technology Tianjin Key Laboratory of Intelligence Computing Tianjin China Key Laboratory of Computer Vision and System Ministry of Education China Information Technology Co. Ltd. China

ISBN: (纸本)9798350329223

Regenerating codes are new network codes proposed to reduce the data required for fault repair, which can improve the recovery efficiency of faulty nodes in data storage systems. However, unlike Reed-Solomon code, which repairs at the granularity of bytes, regenerating codes require data stored in large chunks but leads to severe read amplification, which reads out excess data when degraded read objects and increases degraded read time. That reflects a mutual constraint between improving recovery efficiency and degraded read performance, as manifested in the amplification of data reads, a vital issue considered in this *** solve this problem, we propose a new type of data layout - discrete geometric, which splits the object into a series of geometric sequences of data blocks. They are placed discretely into corresponding containers on the disks at different nodes, with containers of the same size made into a strip for encoding. The discrete characteristic ensures lower repair costs for degraded reads. The geometric characteristic ensures the repair performance of regenerating codes by large blocks, and read amplification can be mitigated through small blocks. To reduce IOPS for discrete geometric, we propose Discrete Geometric-Locally Regenerating Codes (DG-LRCs), guaranteeing lower degraded read latency while improving recovery *** results show that the degraded read time of DG-LRCs compared to regenerating codes combined with geometric partitioning is 22.56% lower at 2Gbpsand 60.56% lower at 4Gbps, and the recovery performance is 7.04 times better than that of RS code. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Intruder trajectory tracking in a three-dimensional vibration-driven granular system:Unveiling the mechanism of the Brazil nut effect

引用

Chinese Physics B 2023年第10期32卷 106-111页

作者：李拓程可彭政杨晖厚美瑛 School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Soft Matter Laboratory Institute of PhysicsChinese Academy of SciencesBeijing 100190China School of Physics Central South UniversityChangsha 410012China College of Medical Instrumentation Shanghai University of Medicine&Health SciencesShanghai 201318China

We employ a Hall-effect magnetic sensor array to accurately track the trajectory of a single magnetic sphere,referred to as the“intruder,”within a three-dimensional vibro-fluidized granular bed to unravel the underlying physical mechanism governing the motion of the *** the acceleration range of 3.5 g≥Γ≥1.5 g,we find that,regardless of the intruder's initial position,it consistently reaches the same equilibrium depth when the vibration acceleration(Γ)and frequency(ω)are ***Γ≤2.5 g,the equilibrium position lies on the surface of the granular bed,while forΓ>2.5 g,it shifts below the ***,intruders with different densities exhibit varying equilibrium depths,with higher density resulting in a deeper equilibrium *** understand the mechanism behind the intruder's upward or downward motion,we measure its rising or sinking velocities under different vibration *** findings demonstrate that the rising velocity of the intruder,under varying vibration accelerations(Γ)and frequencies(ω),can be collapsed using the ratioΓ/ω,while the sinking velocity remains unaffected by the vibration *** confirms that the upward motion of the larger sphere,associated with the Brazil nut effect,primarily arises from the void-filling mechanism of the bed ***,our experiments reveal that the presence of convection within the bed particles has minimal impact on the motion of the intruder.

关键词： granular matter segregation Brazil nut effect vibro-fluidization

来源：评论

学校读者我要写书评

暂无评论

Time-Synchronized Safety-Critical Attitude Control for Spacecraft with Hardware-in-Loop Validation

Time-Synchronized Safety-Critical Attitude Control for Space...

引用

2024 International Annual Conference on Complex Systems and Intelligent science, CSIS-IAC 2024

作者： Tong, Shang Yang, Haoyang Zhang, Rongchuan Hu, Qinglei Sam Ge, Shuzhi Li, Dongyu Tianmushan Laboratory Hangzhou China School of Cyber Science and Technology Beihang University Beijing China School of Engineering University of Warwick Coventry United Kingdom Institute Beihang University Hangzhou International Innovation Hangzhou China School of Automation Science and Electrical Engineering Beihang University Beijing China National University of Singapore Department of Electrical and Computer Engineering Singapore

ISBN: (纸本)9798331504755

A time-synchronized controller is proposed to solve the time-varying constrained reorientation problem. Time-Synchronized Stability (TSS) that considers the interrelationships among different state errors plays an important role in our method, enabling synchronized convergence of individual error components while ensuring compliance with state constraints. Compared to traditional sliding mode controllers, the efficiency of our safety-critical attitude controller is imporoved without adding computational burden, as evidenced by improved control energy consumption and reduced convergence time. A hardware-in-the-loop (HiL) experiment confirms its practical deployment capabilities. © 2024 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

An Efficient Framework for the Implementation of Sustainable Industry 4.0 7th

An Efficient Framework for the Implementation of Sustainable...

引用

7th International Conference on Smart City Applications, SCA 2022

作者： Kachiche, Sara Gahi, Youssef Gharib, Jihane Laboratory of Engineering Sciences National School of Applied Sciences Ibn Tofail University Kenitra Morocco School of Electrical Engineering and Computer Science University of Ottawa 800 King Edward Ave OttawaON Canada

ISBN: (纸本)9783031268519

The industrial revolution marked a period of development in industrialization which led to economic growth. However, this manufacturing paradigm is not sustainable, and it has emerged as a significant issue in the global market. But with the current transformation of industrial manufacturing through digitalization and the emergence of new technologies known as industry 4.0, this new revolution is set to change and make manufacturing more sustainable while enabling organizations to improve flexibility, efficiency, reduce costs and offer customized products. For this purpose, this paper proposes a framework for the implementation of industry 4.0 by providing an overview of its concepts, drivers, applications, benefits, challenges, and by introducing an efficient approach to ensure the success of its implementation in the context of sustainability. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Epileptic Seizure Detection Using the EEG Signal Empirical Mode Decomposition and Machine Learning

Epileptic Seizure Detection Using the EEG Signal Empirical M...

引用

2023 International Conference on Smart Computing and Application, ICSCA 2023

作者： Nassir, Jana Alasabi, Majeda Qaisar, Saeed Mian Khan, Muzammil Effat University Computer Science Department Jeddah22332 Saudi Arabia Effat University Electrical and Computer Engineering Department Jeddah22332 Saudi Arabia Cesi Engineering School Lineact Laboratory Villeurbanne69100 France University of Swat Department of Computer and Software Technology Swat Pakistan

ISBN: (纸本)9798350347050

Epileptic seizures affect millions of people worldwide. Medical treatments exist to help lessen the severity of the damage caused by these seizures. However, people with epilepsy still struggle with unexpected seizures. People who experience epileptic seizures have Electroencephalogram (EEG) signals that show different features in comparison to a healthy brain. In this study, EEG signals are studied to detect the seizures. The incoming signals are denoised by using linear phase filters. In next step these are divided in fix-length segments. Then, each segment is broken down using the Empirical Mode Decomposition (EMD) into Intrinsic Mode Functions (IMFs). For an automatic identification of EEG signals, features are extracted from the collected IMFs and then processed using machine learning techniques. A dataset on epilepsy that is available to the public is used for evaluation. To determine which is the best predictor for the under-consideration dataset, four different classification methods are performed and the results are examined. The system achieves a classification accuracy of 96.70%. © 2023 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Learning Probabilistic Coordinate Fields for Robust Correspondences

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 12004-12021页

作者： Zhao, Weiyue Lu, Hao Ye, Xinyi Cao, Zhiguo Li, Xin Huazhong University of Science and Technology The Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Wuhan430074 China West Virginia University The Lane Department of Computer Science and Electrical Engineering MorgantownWV26506-6109 United States

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems. In contrast to standard Cartesian coordinates, PCFs encode coordinates in correspondence-specific barycentric coordinate systems (BCS) with affine invariance. To know when and where to trust the encoded coordinates, we implement PCFs in a probabilistic network termed PCF-Net, which parameterizes the distribution of coordinate fields as Gaussian mixture models. By jointly optimizing coordinate fields and their confidence conditioned on dense flows, PCF-Net can work with various feature descriptors when quantifying the reliability of PCFs by confidence maps. An interesting observation of this work is that the learned confidence map converges to geometrically coherent and semantically consistent regions, which facilitates robust coordinate representation. By delivering the confident coordinates to keypoint/feature descriptors, we show that PCF-Net can be used as a plug-in to existing correspondence-dependent approaches. Extensive experiments on both indoor and outdoor datasets suggest that accurate geometric invariant coordinates help to achieve the state of the art in several correspondence problems, such as sparse feature matching, dense image registration, camera pose estimation, and consistency filtering. Further, the interpretable confidence map predicted by PCF-Net can also be leveraged to other novel applications from texture transfer to multi-homography classification. © 1979-2012 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Convolution-Transformer for Image Feature Extraction

引用

computer Modeling in engineering & sciences 2024年第10期141卷 87-106页

作者： Lirong Yin Lei Wang Siyu Lu Ruiyang Wang Youshuai Yang Bo Yang Shan Liu Ahmed AlSanad Salman A.AlQahtani Zhengtong Yin Xiaolu Li Xiaobing Chen Wenfeng Zheng Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA70803USA School of Automation University of Electronic Science and Technology of ChinaChengdu610054China College of Computer and Information Sciences King Saud UniversityRiyadh11574Saudi Arabia College of Resources and Environmental Engineering Key Laboratory of Karst Georesources and Environment(Guizhou University)Ministry of EducationGuiyang550025China School of Geographical Sciences Southwest UniversityChongqing400715China School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA70803USA

This study addresses the limitations of Transformer models in image feature extraction,particularly their lack of inductive bias for visual *** to Convolutional Neural Networks(CNNs),the Transformers are more sensitive to different hyperparameters of optimizers,which leads to a lack of stability and slow *** tackle these challenges,we propose the Convolution-based Efficient Transformer Image Feature Extraction Network(CEFormer)as an enhancement of the Transformer *** model incorporates E-Attention,depthwise separable convolution,and dilated convolution to introduce crucial inductive biases,such as translation invariance,locality,and scale invariance,into the Transformer ***,we implement a lightweight convolution module to process the input images,resulting in faster convergence and improved *** results in an efficient convolution combined Transformer image feature extraction *** results on the ImageNet1k Top-1 dataset demonstrate that the proposed network achieves better accuracy while maintaining high computational *** achieves up to 85.0%accuracy across various model sizes on image classification,outperforming various baseline *** integrated into the Mask Region-ConvolutionalNeuralNetwork(R-CNN)framework as a backbone network,CEFormer outperforms other models and achieves the highest mean Average Precision(mAP)*** research presents a significant advancement in Transformer-based image feature extraction,balancing performance and computational efficiency.

关键词： Transformer E-Attention depth convolution dilated convolution CEFormer

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：