检索结果-内蒙古大学图书馆

2023 International Conference on data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Kushwaha, Sumit Boga, Jayaram Rao, Bairaboina Sai Sambasiva Taqui, Syed Noeman Vidhya, R.G. Surendiran, J. University Institute of Computing Chandigarh University Department of Computer Applications Punjab India Marri Laxman Reddy Institute of Technology and Management Department of Computer Science and Data Science Telangana Hyderabad India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Vaddeswaram India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Vlsi Microelectronics Tamil Nadu Chennai India Hkbk College of Engineering Department of Ece Bangalore India

ISBN: (纸本)9798350348910

The early diagnosis of visual problems such as diabetic retinopathy and glaucoma relies on the successful completion of medical image processing tasks such as the segmentation of retinal blood vessels. The process of isolating retinal blood vessels from images of the retinal fundus is a challenging one because of the similarities in intensity that exist between blood vessels and the surrounding tissues. In addition, there are differences in the size, shape, and intensity of the vessels. In recent times, a number of different algorithms based on deep learning have been presented for the segmentation of retinal blood vessels. These techniques have been shown to be more accurate and dependable when compared to the traditional computer vision methods that have been used. In this abstract, we present the U-Net deep learning model as well as a technique for segmenting retinal blood vessels that is based on the programming language Python. A U-Net model is trained using a series of retinal fundus images so that the features of retinal blood vessels may be comprehended. As part of the inference process, the image of the retinal fundus is loaded into a trained version of the U-Net model. This model then generates a probability map that illustrates the chance that each pixel represents an artery in the human body. The final segmentation is produced by applying a threshold to the probability map. When it comes to the process of segmenting retinal blood vessels, our python-based solution outperforms methods that are considered to be state-of-the-art in studies comparing accuracy and speed. The scientific and medical communities have unrestricted access to the software that may be used to put the suggested strategy into action since it is an open-source initiative. In conclusion, the python-based approach for retinal blood vessel segmentation that makes use of U-Net provides a potentially helpful solution for identifying retinal illnesses and has the potential to serve as a stan

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Rotatable Antenna Enabled Wireless Communication: Modeling and Optimization

arXiv

引用

arXiv 2025年

作者： Zheng, Beixiong Wu, Qingjie Zhang, Rui School of Microelectronics South China University of Technology Guangzhou511442 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

In this paper, we propose a new rotatable antenna (RA) model to improve the performance of wireless communication systems. Different from conventional fixed antennas, the proposed RA system can flexibly alter the three-dimensional (3D) boresight direction of each antenna independently by adjusting its deflection angles to achieve a desired array directional gain pattern. Specifically, we investigate an RA-enabled uplink communication system, where the receive beamforming and the deflection angles of all RAs at the base station (BS) are jointly optimized to maximize the minimum signal-to-interference-plus-noise ratio (SINR) among all the users. In the special single-user and free-space propagation setup, the optimal deflection angles of RAs are derived in closed form with the maximum-ratio combining (MRC) beamformer applied at the BS. Moreover, we analyze the asymptotic performance with an infinite number of antennas based on this solution, which theoretically proves that the RA system can achieve a higher array gain as compared to the fixed-antenna system. In the general multi-user and multi-path channel setup, we first propose an alternating optimization (AO) algorithm to alternately optimize the receive beamforming and the deflection angles of RAs in an iterative manner. Then, a two-stage algorithm that solves the formulated problem without the need for iteration is further proposed to reduce computational complexity. Simulation results are provided to validate our analytical results and demonstrate that the proposed RA system can significantly outperform other benchmark schemes. Copyright © 2025, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Yb3+, Er3+ Ions Co-Doped Double Molybdate/Tungstate Composite Laser Crystals for Promising 1.5 Μm Solid State Lasers

SSRN

引用

SSRN 2024年

作者： Hu, Haitang Ding, Shoujun J. Wang, Miaomiao Zou, Yong Zhang, Chuancheng Ren, Hao Liu, Wenpeng School of Microelectronics and Data Science Anhui University of Technology Maanshan243002 China Anhui Provincial Joint Key Laboratory of Disciplines for Industrial Big Data Analysis and Intelligent Decision Maanshan243002 China Anhui Institute of Optics and Fine Mechanics Chinese Academy of Sciences Hefei230031 China

A series of 10 at% Yb3+, 5 at% Er3+ doped NaGd(MoxW1-xO4)2 (x = 0.5, 0.7, and 0.9) single crystals were grown by Czochralski method. The structure of the crystals was determined to be a tetragonal system with space group of I41/a, as confirmed through X-ray diffraction (XRD), Rietveld refinement and FT-IR analyses. In addition, the 1.5 μm spectral properties of the crystals were investigated, including emission, absorption and fluorescence decay characteristics. Importantly, the influence of crystal composition on the spectroscopic properties was revealed deeply. As the crystal composition changes, a significant inhomogeneous broadening of the spectral and remarkable changes in energy band Eg were observed. A maximum full width at half-maximum (FWHM) at 1535 nm was obtained to be 83 nm in (MoO4)1.0(WO4)1.0 composition crystal. However, the maximum absorption and emission cross-sections were achieved in (MoO4)1.4(WO4)0.6 component crystal with values of 1.15 × 10-20 cm2 and 1.05 × 10-20 cm2, respectively. Besides, for (MoO4)1.4(WO4)0.6 composition crystal, a positive gain cross-section is obtained at around 1535 nm for a population inversion ratio β above 0.4. The results show that double molybdate/tungstate composite crystals co-doping with Yb3+ and Er3+ are promising for 1.5 μm near-infrared lasers. © 2024, The Authors. All rights reserved.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Comments on "A Lightweight Privacy Preserving Authentication Protocol for VANETs"

Comments on "A Lightweight Privacy Preserving Authentication...

引用

International Conference on Computer and Communications (ICCC)

作者： Syed Muhammad Awais Wu Yucheng Khalid Mahmood Rupak Kharel School of Microelectronics and Communication Engineering Chongqing University Chongqing China School of Psychology and Computer Science and Graduate School of Intelligent Data Science University of Central Lancashire Preston United Kingdom School of Psychology and Computer Science and Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Yunlin Taiwan School of Psychology and Computer Science and Faculty of Electrical and Electronics Engineering University of Central Lancashire Preston United Kingdom School of Psychology and Computer Science and Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Vietnam

Vehicle use and the concept of a "smart city" are developing quickly. As a result of this progression, the Vehicular Ad-Hoc Network (VANET) is a popular network for inter-vehicular communication. The data gathering about the state of the road, the whereabouts of vehicles, their speeds, and the description of traffic congestion are obtained using the VANET. The public nature of information flow on the VANET creates serious security risks. data security is typically one of the most important duties of VANET. As a result, it becomes one of the researchers’ top priorities. Li et al. [1] introduced a Lightweight Privacy Preserving Authentication Protocol for VANETs. They stated that several attacks could be resisted using their secure authentication devised protocol. However, after analyzing we discovered that their authentication protocol is susceptible to roadside impersonation attack and it does not provide vehicle anonymity. In the end, we have provided a few suggestions to cope with Li et al.’s devised protocol current shortcomings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Passenger Waiting Time Prediction Based on Density Spatiotemporal Clustering and Time Series Feature Processing 6

Passenger Waiting Time Prediction Based on Density Spatiotem...

引用

6th International Conference on Electronic Engineering and Informatics, EEI 2024

作者： Huang, Ruixi Xia, Dawen Geng, Jian Zhang, Wenyong Hu, Yang Li, Yantao Li, Huaqing College of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China Engineering Research Center of Micro-nano and Intelligent Manufacturing Ministry of Education Kaili University Kaili556011 China College of Big Data Engineering College of Microelectronics and Artificial Intelligence Kaili University Kaili556011 China Party School of the Anshun Municipal Committee of C.P.C Anshun561000 China Guizhou Traffic Technician and Transportation College Department of Automotive Engineering Guiyang550008 China College of Computer Science Chongqing University Chongqing400044 China College of Electronic and Information Engineering Southwest University Chongqing400715 China

ISBN: (纸本)9798350353594

Accurate passenger waiting time prediction addresses the taxi supply-demand imbalance in Intelligent Transport Systems (ITS). To capture the dependencies of passenger waiting time on urban taxi distribution, we propose a Density Spatiotemporal Clustering and Time Series Feature Processing (DSC-TSFP) method that discovers potential feature relationships of taxi GPS trajectory data. Specifically, a Multilevel Spatiotemporal Density-Based Spatial Clustering of Applications with Noise (MST-DBSCAN) is proposed to cluster taxi GPS trajectory data to obtain waiting time series with spatiotemporal correlations. Furthermore, a time series processing module based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise Normalization (CEEMDANN) is designed to enhance prediction accuracy by handling non-stationarity and numerical discrepancy, which solves the residual white noise problem in Intrinsic Modal Functions (IMFs) of EEMD and CEEMD. Next, a waiting time prediction module oriented to a Convolutional Long Short-Term Memory Network (ConvLSTM) is incorporated to compensate for the defects of spatially localized dependencies that LSTM cannot capture. Finally, a CEEMDANN-ConvLSTM model is constructed to predict the passenger waiting time by combining the time series processing and waiting time prediction module. Based on real-world taxi GPS trajectory data, experimental results demonstrate that DSC-TSFP outperforms comparable methods regarding prediction accuracy. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Train faster, perform better: modular adaptive training in over-parameterized models 23

Train faster, perform better: modular adaptive training in o...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yubin Shi Yixuan Chen Mingzhi Dong Xiaochen Yang Dongsheng Li Yujiang Wang Robert Dick Qin Lv Yingying Zhao Fan Yang Tun Lu Ning Gu Li Shang China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University School of Mathematics Statistics University of Glasgow Microsoft Research Asia Shanghai China Department of Engineering Science University of Oxford Department of Electrical Engineering and Computer Science University of Michigan Department of Computer Science University of Colorado Boulder School of Microelectronics Fudan University

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attain a more efficient and fruitful training strategy. Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue λmax. A large λmax indicates that the module learns features with better convergence, while those miniature ones may impact generalization negatively. Inspired by the discovery, we propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their λmax exceeding a dynamic threshold selectively, concentrating the model on learning common features and ignoring those superfluous ones. Unlike most existing training schemes with a complete BP cycle across all network modules, MAT can significantly save computations by its partially-updating strategy and can further improve performance. Experiments show that MAT nearly halves the computational cost of model training and outperforms the accuracy of baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sphinx: A Hybrid Boolean Processor-FPGA Hardware Emulation System

Sphinx: A Hybrid Boolean Processor-FPGA Hardware Emulation S...

引用

IEEE International Conference on Computer-Aided Design

作者： Ruiyao Pu Yiwei Sun Pei-Hsin Ho Fan Yang Li Shang Xuan Zeng State Key Lab of Integrated Chips and Systems School of Microelectronics Fudan University Shanghai China UniVista Industrial Software Group Shanghai China China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

Existing hardware emulators use either FPGA or Boolean processors, which suffer from long compile time and poor debuggability (FPGA-based), or low emulation performance (Boolean processor-based). This work presents Sphinx, a hybrid Boolean processor-FPGA hardware emulation platform aiming to overcome these shortcomings. Sphinx hardware is a new hybrid architecture that integrates software programmable Boolean processors and FPGAs. Sphinx software is a compilation framework that conducts incremental design partitioning and implements the design-under-test components on Boolean processors and the rest on FPGAs. Together, Sphinx enables an incremental emulation flow and demonstrates high emulation performance, fast compile turnarounds, and good debuggability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Write-Optimized B^(+) Tree Index Technology for Persistent Memory

引用

Journal of Computer science & Technology 2021年第5期36卷 1037-1050页

作者： Rui-Xiang Ma Fei Wu Bu-Rong Dong Meng Zhang Wei-Jun Li Chang-Sheng Xie Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430070China Key Laboratory of Information Storage System Ministry of Education of ChinaWuhan 430070China Engineering Research Center of Data Storage Systems and Technology Huazhong University of Science and Technology Wuhan 430070China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430070China Shenzhen DAPU Microelectronics Co. LtdShenzhen 518116China

Due to its low latency,byte-addressable,non-volatile,and high density,persistent memory(PM)is expected to be used to design a high-performance storage ***,PM also has disadvantages such as limited endurance,thereby proposing challenges to traditional index technologies such as B(+)tree.B(+)tree is originally designed for dynamic random access memory(DRAM)-based or disk-based systems and has a large write amplification *** high write amplification is detrimental to a PM-based *** paper proposes WO-tree,a write-optimized B(+)tree for ***-tree adopts an unordered write mechanism for the leaf nodes,and the unordered write mechanism can reduce a large number of write operations caused by maintaining the entry order in the leaf *** the leaf node is split,WO-tree performs the cache line flushing operation after all write operations are completed,which can reduce frequent data flushing ***-tree adopts a partial logging mechanism and it only writes the log for the leaf *** inner node recognizes the data inconsistency by the read operation and the data can be recovered using the leaf node information,thereby significantly reducing the logging ***,WO-tree adopts a lock-free search for inner nodes,which reduces the locking overhead for concurrency *** evaluate WO-tree using the Yahoo!Cloud Serving Benchmark(YCSB)*** with traditional B(+)tree,wB-tree,and Fast-Fair,the number of cache line flushes caused by WO-tree insertion operations is reduced by 84.7%,22.2%,and 30.8%,respectively,and the execution time is reduced by 84.3%,27.3%,and 44.7%,respectively.

关键词： persist memory B^(+)tree write amplication consistency YCSB(Yahoo!Cloud Serving Benchmark)

来源：评论

学校读者我要写书评

暂无评论

A ModelOps-Based Framework for Intelligent Medical Knowledge Extraction

A ModelOps-Based Framework for Intelligent Medical Knowledge...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Hongxin Ding Peinie Zou Zhiyuan Wang Junfeng Zhao Yasha Wang Qiang Zhou School of Computer Science Peking University Peking China School of Software & Microelectronics Peking University Peking China Research Center of Big Data Technology Nanhu Laboratory School of Computer Science Peking University Peking China Shenzhen Emergency Medical Center Shenzhen China

Extracting medical knowledge from healthcare texts enhances downstream tasks like medical knowledge graph construction and clinical decision-making. However, the construction and application of knowledge extraction models lack automation, reusability and unified management, leading to inefficiencies for researchers and usage barriers for non-AI experts like doctors. To address these issues, we propose a ModelOps-based intelligent medical knowledge extraction framework that offers a low-code system for model construction and application. Specifically, the framework includes a dataset abstraction mechanism based on multi-layer callback functions, a reusable model training, monitoring and management mechanism, alongside a model recommendation method based on dataset similarity for quickly finding potentially suitable models for a given dataset. Our frame-work provides convenience for researchers to develop models and simplifies model access for non-AI experts like doctors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

arXiv

引用

arXiv 2024年

作者： Shi, Yubin Chen, Yixuan Dong, Mingzhi Yang, Xiaochen Li, Dongsheng Wang, Yujiang Dick, Robert Lv, Qin Zhao, Yingying Yang, Fan Lu, Tun Gu, Ning Shang, Li China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Mathematics Statistics University of Glasgow United Kingdom Microsoft Research Asia Shanghai China Department of Engineering Science University of Oxford United Kingdom Department of Electrical Engineering and Computer Science University of Michigan United States Department of Computer Science University of Colorado Boulder United States School of Microelectronics Fudan University China

关键词： Eigenvalues and eigenfunctions

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：