检索结果-内蒙古大学图书馆

SSD object detection algorithm based on knowledge map

International Journal of Wireless and Mobile Computing 2024年第2期27卷 152-160页

作者： Huang, Li Wang, Xiaofeng Lu, Jianhua Hu, Wei Zhang, Changrong College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China Key Laboratory of Metallurgical Equipment and Control Technology of the Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Precision Manufacturing Research Institute Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China

With the pervasive integration of artificial intelligence into all aspects of human life, talent emerges as a primary resource. Upon analysing the current state of talent training in higher education institutions, issues such as dispersed knowledge points, overlapping content, a singular practice approach and ineffective evaluation have been identified. In response to these challenges, this paper proposes a multidisciplinary and comprehensive practical teaching methodology grounded in the knowledge graph framework. It delves into diverse paths for practical teaching and assessment, including aspects like teaching objectives, problem decomposition, resource integration, implementation methods and performance evaluation. The practical application of the SSD algorithm in researching service robot indoor object detection serves as an illustrative example. Employing the holistic practical teaching approach facilitated by the knowledge graph, this model guides students in acquiring object detection expertise, thereby enhancing their comprehensive development. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Novel Sum-of-Sinusoids Simulation Channel Modeling for 6G Multiple-Input Multiple-Output Vehicle-to-Everything Communications

引用

China Communications 2024年第1期21卷 242-259页

作者： Hao Jiang Hongming Zhang Ting Liu College of Artificial Intelligence Nanjing University of Information Science and Technology210044China National Mobile Communications Research Laboratory Southeast UniversityNanjing 210096China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsChina

In this paper,a statistical cluster-based simulation channel model with a finite number of sinusoids is proposed for depicting the multiple-input multiple-output(MIMO)communications in vehicleto-everything(V2X)*** the proposed sum-of-sinusoids(SoS)channel model,the waves that emerge from the transmitter undergo line-of-sight(LoS)and non-line-of-sight(NLoS)propagation to the receiver,which makes the model suitable for describing numerous V2X wireless communication scenarios for sixth-generation(6G).We derive expressions for the real and imaginary parts of the complex channel impulse response(CIR),which characterize the physical propagation characteristics of V2X wireless *** statistical properties of the real and imaginary parts of the complex CIRs,i.e.,autocorrelation functions(ACFs),Doppler power spectral densities(PSDs),cross-correlation functions(CCFs),and variances of ACFs and CCFs,are derived and *** results are generated and match those predicted by the underlying theory,demonstrating the accuracy of our derivation and *** proposed framework and underlying theory arise as an efficient tool to investigate the statistical properties of 6G MIMO V2X communication systems.

关键词： complex CIRs LoS and NLoS propagation components MIMO V2X communication environments SoS simulation channel model statistical properties

来源：评论

学校读者我要写书评

暂无评论

Photonic neuromorphic architecture for tens-of-task lifelong learning

引用

Light(science & Applications) 2024年第3期13卷 519-530页

作者： Yuan Cheng Jianing Zhang Tiankuang Zhou Yuyan Wang Zhihao Xu Xiaoyun Yuan Lu Fang Sigma Laboratory Department of Electronic EngineeringTsinghua UniversityBeijing 100084China Beijing National Research Center for Information Science and Technology(BNRist) Beijing 100084China Institute for Brain and Cognitive Science Tsinghua University(THUIBCS)Beijing 100084China

Scalable,high-capacity,and low-power computing architecture is the primary assurance for increasingly manifold and large-scale machine learning *** electronic artificial agents by conventional power-hungry processors have faced the issues of energy and scaling walls,hindering them from the sustainable performance improvement and iterative multi-task *** to another modality of light,photonic computing has been progressively applied in high-efficient neuromorphic ***,we innovate a reconfigurable lifelong-learning optical neural network(L2 ONN),for highly-integrated tens-of-task machine intelligence with elaborated algorithm-hardware *** from the inherent sparsity and parallelism in massive photonic connections,L2 ONN learns each single task by adaptively activating sparse photonic neuron connections in the coherent light field,while incrementally acquiring expertise on various tasks by gradually enlarging the *** multi-task optical features are parallelly processed by multi-spectrum representations allocated with different *** evaluations on freespace and on-chip architectures confirm that for the first time,L2 ONN avoided the catastrophic forgetting issue of photonic computing,owning versatile skills on challenging tens-of-tasks(vision classification,voice recognition,medical diagnosis,etc.)with a single ***,L2 ONN achieves more than an order of magnitude higher efficiency than the representative electronic artificial neural networks,and 14×larger capacity than existing optical neural networks while maintaining competitive performance on each individual *** proposed photonic neuromorphic architecture points out a new form of lifelong learning scheme,permitting terminal/edge AI systems with light-speed efficiency and unprecedented scalability.

关键词： life neural versatile

来源：评论

学校读者我要写书评

暂无评论

Residual deep fuzzy system with randomized fuzzy modules for accurate time series forecasting

引用

Neural Computing and Applications 2024年第17期36卷 9989-10014页

作者： Liu, Yunxia Peng, Wei Wang, Haixia Li, Chengdong Lu, Xiao College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao266590 China Shandong Key Laboratory of Intelligent Buildings Technology School of Information and Electrical Engineering Shandong Jianzhu University Jinan250101 China College of Energy Storage Technology Shandong University of Science and Technology Qingdao266590 China Engineering Training Center Shandong University of Science and Technology Qingdao266590 China

The data-driven modular deep fuzzy model has demonstrated excellent forecasting performance due to its clear architecture and powerful fuzzy inference ability. However, the fixed structure predesigned for specific types of datasets limits the further improvement of generalization ability, especially when facing high-dimensional datasets with the challenging problem of rule explosion, thereby suffering from the time-consuming training process. To overcome these limitations, a novel randomized fuzzy modules (RFMs) stacked residual deep fuzzy system (RFM-RDFS) is proposed in this study. Firstly, to obtain high-precision outputs, this paper presents a residual deep fuzzy framework by stacking RFMs layer by layer, where the modules in the current layer only learn the residual of the previous layer. Secondly, to improve the design freedom for different applications, the RFM with multiple inputs is raised, where the input variables are allocated by a sliding window along the input spaces of the layers, so the number of the parallel modules in the same layer can be flexibly adjusted. Meanwhile, in the RFM, inspired by the extreme learning machine, the centers and widths of Gaussian membership functions are randomly generated, which can greatly accelerate the training speed. Thirdly, to strengthen the approximation performance, the consequent parameters of the fuzzy rules in each RFM are learned by minimizing the loss function with the regularization terms through the ridge regression algorithm. Finally, extensive experiments on various datasets are conducted to compare the proposed RFM-RDFS with several state-of-the-art shallow and deep models. The detailed comparison results clearly show that the proposed RFM-RDFS is more flexible and compact, and has greater advantages in terms of the interpretability, generalization ability and robustness. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Handwritten Prescription Recognition Using VGG Based Architecture with Bi-LSTM

Handwritten Prescription Recognition Using VGG Based Archite...

引用

2024 International Research Conference on Smart Computing and systems engineering, SCSE 2024

作者： Kavinda, Isuru Fernando, Harinda Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka

ISBN: (纸本)9798350375688

Illegible handwriting on medical prescriptions poses a significant challenge, often leading to the misinterpretation of drug names and dosages. This issue primarily stems from doctors' use of Latin abbreviations, driven by time constraints during patient consultations. The resultant discrepancies in prescription interpretation can potentially expose patients to incorrect medications and dosages, leading to adverse effects. In response to this concern, this study proposes a novel system integrating Convolution Neural Network (CNN) and Recurrent Neural Network (RNN) models. Promising findings are reported in this study, achieving a loss of 0.4874 and an accuracy of 0.83 in the latest trial. The final model offers a potential solution to the persistent problem of illegible prescriptions, enhancing patient safety in the healthcare domain. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Scavenger: Better Space-Time Trade-Offs for Key-Value Separated LSM-trees 40

Scavenger: Better Space-Time Trade-Offs for Key-Value Separa...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Zhang, Jianshun Wang, Fang Qiu, Sheng Wang, Yi Ou, Jiaxin Huang, Junxun Li, Baoquan Fang, Peng Feng, Dan School of Computer Science and Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China China Shenzhen Huazhong University of Science and Technology Research Institute China Bytefrance Inc.

ISBN: (纸本)9798350317152

Key-Value Stores (KVS) implemented with log-structured merge-tree (LSM-tree) have gained widespread ac-ceptance in storage systems. Nonetheless, a significant challenge arises in the form of high write amplification due to the compaction process. While KV-separated LSM-trees successfully tackle this issue, they also bring about substantial space am-plification problems, a concern that cannot be overlooked in cost-sensitive scenarios. Garbage collection (GC) holds significant promise for space amplification reduction, yet existing GC strategies often fall short in optimization performance, lacking thorough consideration of workload characteristics. Additionally, current KV-separated LSM-trees also ignore the adverse effect of the space amplification in the index LSM-tree. In this paper, we systematically analyze the sources of space amplification of KV-separated LSM-trees and introduce Scavenger, which achieves a better trade-off between performance and space amplification. Scavenger initially proposes an I/O-efficient garbage collection scheme to reduce I/O overhead and incorporates a space-aware compaction strategy based on compensated size to minimize the space amplification of index LSM-trees. Extensive experiments show that Scavenger significantly improves write performance and achieves lower space amplification than other KV-separated LSM-trees (including BlobDB, Titan, and TerarkDB). © 2024 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Improvement of Seafloor Positioning Through Correction of Sound Speed Profile Temporal Variation

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 1099-1101页

作者： Miao Yu Kuijie Cai Cuie Zheng Dajun Sun Acoustic Science and Technology Laboratory Harbin Engineering UniversityHarbin 150001 Key Laboratory of Marine Information Acquisition and Security(Harbin Engineering University) Ministry of Industry and Information TechnologyHarbin 150001 College of Underwater Acoustic Engineering Harbin Engineering UniversityHarbin 150001China College of Mathematical Sciences Harbin Engineering UniversityHarbin 150001China

Dear Editor,This letter proposes a high-precision seafloor transponder positioning method based on the correction of sound speed profile(SSP)temporal *** the proposed method,the ocean sound speed error is modeled as the temporal variation of a background SSP,and the linearized expression of the acoustic travel time with respect to the sound speed coefficient is derived based on the ray acoustic ***,the proposed method introduces the constraint of acoustic ranging observations between seafloor transponders and determines the weights of travel time and ranging observations using Akaike’s Bayesian information criterion(ABIC)to reduce the positioning error caused by the correlation between sound speed and position *** experimental results in the South China Sea show that the proposed method performs better than the global navigation satellite system-acoustic ranging combined positioning solver(GARPOS)[1],in terms of rigid distance errors and long baseline positioning accuracy.

关键词： ocean travel sound

来源：评论

学校读者我要写书评

暂无评论

Multi-stage Image Deraining based on Pre-trained Diffusion Model 6

Multi-stage Image Deraining based on Pre-trained Diffusion M...

引用

6th ACM International Conference on Multimedia in Asia, MMAsia 2024

作者： Zeng, Xiong Jiang, Min Huang, RongHua School of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China

ISBN: (纸本)9798400712739

Image deraining typically involves synthesizing low-quality degraded data for training using a predefined degraded model of a single weather condition. While in real world scenarios, varying rain intensities result in different sizes and densities of raindrops and rain streaks, increasing the complexity of image degradation. In this paper, we proposed a multi-stage deraining framework based on pre-trained diffusion model, it can efficiently perform the rain removal task under a variety of weather situations. We diffuse degraded images into a noisy state where various types of degradation are transformed into Gaussian noise. Then, during the denoising process, the low-frequency information of the image is replaced through iterative refinement, guiding the pre-trained diffusion model for image reconstruction. Our method effectively utilizes the generative priors in diffusion models and avoid the computational burden of retraining conditional diffusion models. Experimental results on four rainy degradation image datasets show its robustness to different types and severities of degradation (such as raindrops and rain streaks). Compared to recent deraining algorithms, our method achieves a maximum improvement of 0.96 dB (3.5%) in PSNR and 0.021 dB (2.7%) in SSIM for the restored images. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Optimal Production Capacity Matching for Blockchain-Enabled Manufacturing Collaboration With the Iterative Double Auction Method

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 550-562页

作者： Ying Chen Feilong Lin Zhongyu Chen Changbing Tang Cailian Chen the Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University the School of Computer Science and Technology Zhejiang Normal University IEEE the College of Physics and Electronic Information Engineering Zhejiang Normal University the Department of Automation Shanghai Jiao Tong University

The increased demand for personalized customization calls for new production modes to enhance collaborations among a wide range of manufacturing practitioners who unnecessarily trust each other. In this article, a blockchain-enabled manufacturing collaboration framework is proposed, with a focus on the production capacity matching problem for blockchainbased peer-to-peer(P2P) collaboration. First, a digital model of production capacity description is built for trustworthy and transparent sharing over the blockchain. Second, an optimization problem is formulated for P2P production capacity matching with objectives to maximize both social welfare and individual benefits of all participants. Third, a feasible solution based on an iterative double auction mechanism is designed to determine the optimal price and quantity for production capacity matching with a lack of personal information. It facilitates automation of the matching process while protecting users' privacy via blockchainbased smart contracts. Finally, simulation results from the Hyperledger Fabric-based prototype show that the proposed approach increases social welfare by 1.4% compared to the Bayesian game-based approach, makes all participants profitable,and achieves 90% fairness of enterprises.

关键词： Blockchain iterative double auction manufacturing collaboration production capacity matching

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Marine Ship Recognition Based on Stackable Residual Network 19

Multi-Stage Marine Ship Recognition Based on Stackable Resid...

引用

19th International Conference on Natural Computation, Fuzzy systems and Knowledge Discovery, ICNC-FSKD 2023

作者： Yu, Wanwan Zhang, Junping Wang, Linlin Xi, Yunqiao Xu, Hongfeng Chen, Linxiu Hao, Mingrui Harbin Institute of Technology School of Electronics and Information Engineering Harbin China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9798350304398

Marine ship recognition has always been an important research field. The ships can be usually recognized by analyzing their attribute characteristics. However, in the actual process of recognition, many ship recognition methods using a single model cannot meet the requirements of this task due to the complexity of ship types, diversity of interference factors and different information obtained from distance differences. Therefore, we propose a multi-stage ship recognition scheme. First, the single radiation emitter feature recognition network model is designed for long-distance recognition. Second, the fusion feature network model for short distance recognition. The proposed network is mainly constructed with the residual units, which not only simplify the training of deep networks and facilitate the spread of information, but also can solve the vanishing gradient and exploding gradient problem. The simulation experimental results show that the proposed network model has better performance than typical methods and has great potential in applications. © 2023 IEEE.

关键词： Ships

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：