检索结果-内蒙古大学图书馆

Emerging Technologies (GlobConET), IEEE IAS Global Conference on

作者： Mohamed G. Hussien Lingling Cao Md. Rabiul Islam School of Mechanical Engineering and Automation Harbin Institute of Technology (Shenzhen) Shenzhen China Electrical Power and Machines Engineering Department Faculty of Engineering Tanta University Tanta Egypt School of Electrical Computer and Telecommunications Engineering Faculty of Engineering and Information Sciences University of Wollongong Wollongong Australia

The purpose of this study is to construct a sensorless vector control system for an induction motor (IM) with a promising split-source inverter (SSI) arrangement, along with an effective speed estimation approach. Indirect Magnetic Field Orientation Scheme (IRFOC) is a simplified approach that will be presented for monitoring the rotor speed signal based on the relation of phase-axis for the motor. Extensive analysis to assure the observability of the suggested split-source inverter-based sensorless control system is carried out, and it is supported by results from typical functional tests and parameter modifications. In comparison to the sensorless vector control approach, the results demonstrate the efficacy of the suggested speed estimation method as well as the observability and robustness of the implemented system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel fault-tolerant scheduling approach for collaborative workflows in an edge-IoT environment

引用

Digital Communications and Networks 2022年第6期8卷 911-922页

作者： Tingyan Long Yong Ma Lei Wu Yunni Xia Ning Jiang Jianqi Li Xiaodong Fu Xiangmi You Bo Zhang College of Computer Science Chongqing UniversityChongqing400030China School of Computer and Information Engineering Jiangxi Normal UniversityJiangxi330022China School of Mathematical Sciences University of Electronic Science and Technology of ChinaChengdu611731China Mashang Consumer Finance Co. Ltd.(MSCF)Chongqing401129China Global Energy Interconnection Research Institute Co.Ltd. Beijing102209China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyYunnan650500China CISDI Research&Development CO. LTDChongqing401122China

As a newly emerging computing paradigm, edge computing shows great capability in supporting and boosting 5G and Internet-of-Things (IoT) oriented applications, e.g., scientific workflows with low-latency, elastic, and on-demand provisioning of computational resources. However, the geographically distributed IoT resources are usually interconnected with each other through unreliable communications and ever-changing contexts, which brings in strong heterogeneity, potential vulnerability, and instability of computing infrastructures at different levels. It thus remains a challenge to enforce high fault-tolerance of edge-IoT scientific computing task flows, especially when the supporting computing infrastructures are deployed in a collaborative, distributed, and dynamic environment that is prone to faults and failures. This work proposes a novel fault-tolerant scheduling approach for edge-IoT collaborative workflows. The proposed approach first conducts a dependency-based task allocation analysis, then leverages a Primary-Backup (PB) strategy for tolerating task failures that occur at edge nodes, and finally designs a deep Q-learning algorithm for identifying the near-optimal workflow task scheduling scheme. We conduct extensive simulative case studies on multiple randomly-generated workflow and real-world edge-IoT server position datasets. Results clearly suggest that our proposed method outperforms the state-of-the-art competitors in terms of task completion ratio, server active time, and resource utilization.

关键词： Edge computing Fault tolerance DQN algorithm Primary-backup model

来源：评论

学校读者我要写书评

暂无评论

A bloom filter application for processing big datasets through MapReduce framework 35

A bloom filter application for processing big datasets throu...

引用

35th International Conference on Information Technologies, InfoTech 2021

作者： Todorov Marinov, Milko University of Ruse Faculty of Electrical Engineering Electronics and Automation Department of Computer Systems and Technologies 8 Studentska Str. Ruse7017 Bulgaria

ISBN: (纸本)9781665403245

MapReduce is a widely used programming model for processing big data. Bloom filters are spatially efficient probabilistic data structures for fast queries that tell whether an element is a member of a set and allow false positive results. With reference to this, this article discusses the main characteristics, realisation techniques and scenarios for using Bloom filters when big data is analysed and processed. In addition to this, the study presents an implementation of a Bloom filter in a distributed MapReduce framework. © 2021 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Wideband Reconfigurable Instantaneous Microwave Multi-Frequency Measurement System Without Mirror Image Blurring Based on an Optical Frequency Shifter and Optical Frequency Comb

SSRN

引用

SSRN 2024年

作者： Zhang, Jiahong Ji, Qian Zhang, Jing Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Computer Technology Applications Kunming University of Science and Technology Kunming650500 China

In this paper, a wideband reconfigurable instantaneous microwave multi-frequency measurement system without mirror image blurring has been proposed, designed and investigated. In this proposed scheme, an optical frequency shift is employed to shift the optical carrier of the input dual-parallel Mach-Zehnder modulator (DPMZM), aligning it with the first comb line of the optical frequency comb. Simultaneously, the central frequencies of the two demultiplexers are designed to ensure that the optical signals output after coupling through a 90° optical hybrid coupler contain only one local oscillator optical carrier. Furthermore, the local oscillator optical carrier is positioned at the initial location of the channel. This configuration allows for the determination of an unknown signal with only one beat frequency, effectively resolving the issue of ambiguous mirror frequencies. Simulation experiments reveal that when the channel bandwidth is set to 2 GHz, the system frequency measurement range is 0.01-50 GHz, with an error of less than ±5 MHz. By adjusting the channel bandwidth and the spacing of the optical frequency comb, the system measurement range can be extended to 0.01-100 GHz, with a frequency measurement error of 5-14.6 MHz. This approach offers advantages such as a wide measurement range, reconfigurability, and low error. © 2024, The Authors. All rights reserved.

关键词： Mirrors

来源：评论

学校读者我要写书评

暂无评论

MA-ViT: Modality-Agnostic Vision Transformers for Face Anti-Spoofing

arXiv

引用

arXiv 2023年

作者： Liu, Ajian Liang, Yanyan School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology Macau China Cbsr&nlpr Institute of Automation Chinese Academy of Sciences Beijing China

The existing multi-modal face anti-spoofing (FAS) frameworks are designed based on two strategies: halfway and late fusion. However, the former requires test modalities consistent with the training input, which seriously limits its deployment scenarios. And the latter is built on multiple branches to process different modalities independently, which limits their use in applications with low memory or fast execution requirements. In this work, we present a single branch based Transformer framework, namely Modality-Agnostic Vision Transformer (MA-ViT), which aims to improve the performance of arbitrary modal attacks with the help of multi-modal data. Specifically, MA-ViT adopts the early fusion to aggregate all the available training modalities' data and enables flexible testing of any given modal samples. Further, we develop the Modality-Agnostic Transformer Block (MATB) in MA-ViT, which consists of two stacked attentions named Modal-Disentangle Attention (MDA) and Cross-Modal Attention (CMA), to eliminate modality-related information for each modal sequences and supplement modality-agnostic liveness features from another modal sequences, respectively. Experiments demonstrate that the single model trained based on MA-ViT can not only flexibly evaluate different modal samples, but also outperforms existing single-modal frameworks by a large margin, and approaches the multi-modal frameworks introduced with smaller FLOPs and model parameters. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Electric Arc Plasma Unit with Controlled Electric Arc for Surface Treatment of Metal Products 3

Electric Arc Plasma Unit with Controlled Electric Arc for Su...

引用

3rd International Conference on Control Systems, Mathematical Modeling, automation and Energy Efficiency, SUMMA 2021

作者： Meshcheryakov, Viktor Pikalov, Vladimir Valtchev, Stanimir Lipetsk State Technical University Automation and Computer Science Faculty Lipetsk Russia Nova University of Lisbon Department of Electrical Engineering Caparica Portugal

ISBN: (纸本)9781665439817

The design of an electric arc plasma unit with a cylindrical hollow working chamber and controlled electric arc producing low-Temperature plasma, which can be used for surface treatment of metal products, is considered. The design of a regulated power supply of the electric arc part of the installation with a capacitor matching circuit and a pulse control unit of the electric arc current is proposed. The arc current continuity is ensured when regulating the power released in the electric arc. The amount of plasma produced is regulated by simultaneously changing the current in the arc and the flow of plasma-forming gas supplied to the arc burning area. The arc position is stabilized by creating an external electromagnetic field. An experimental electric arc plasma unit with a cylindrical working chamber and consumable graphite electrodes was created. The correlation between the power of the main elements of the unit is determined experimentally. The results of the study of processes occurring during electromagnetic arc drawing and plasma production are presented. © 2021 IEEE.

关键词： Electromagnetic fields

来源：评论

学校读者我要写书评

暂无评论

Spformer: Shape-Aware Medical Image Segmentation Via Partitioning Frequency Bands

SSRN

引用

SSRN 2024年

作者： Zhou, Ke Chen, Tianxiang Huang, Jiayuan Fu, Dongmei Qi, Chuanjiang School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China University of Science and Technology of China Hefei China Faculty of Computer Science Universiti Putra Malaysia Serdang Malaysia

Precise medical image segmentation is crucial for computer-aided diagnosis, but current methods struggle with subtle areas in endoscopic views where lesions and normal tissue look similar. We propose SPFormer (Shape-aware Partitioning Former), a dual-branch image segmentation model to address this issue. The high-frequency branch captures edges and fine details, while the low-frequency branch focuses on overall shape and color distribution. SPFormer includes a hybrid decoder and a chimeric wavelet block, merging dual-branch information through continuous bilateral interaction. We also designed a dual-domain loss function to comprehensively evaluate the differences between the model output and the ground truth, especially when pixel value differences are small but frequency domain differences are *** enhances the accuracy and efficiency of computer-aided diagnosis, particularly in polyp and skin disease segmentation. Accurately understanding the shape and volume of lesions is crucial for disease grading and treatment planning. SPFormer outperforms existing CNN-Transformer (fusion of Convolutional Neural Network and Transformer) models, providing a more robust and reliable tool for medical image analysis. On the Kvasir-SEG (an open-access dataset of gastrointestinal polyp images and corresponding segmentation masks), SPFormer achieves a 15.29% higher IoU (Intersection over Union) than TransUNet (Transformer-based U-shaped Network), and a reduction of 33.75 GFLOPs (Giga Floating Point Operations per Second). Compared to H2Former (Hierarchical Hybrid Transformer), SPFormer demonstrates an improvement of 5.93% in IoU, and a reduction of 11.74 GFLOPs. © 2024, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

An Embedded System for Non-Invasive Glucose Monitoring

An Embedded System for Non-Invasive Glucose Monitoring

引用

International Conference on Multimedia Analysis and Pattern Recognition (MAPR)

作者： Quoc-Hung Pham Thanh-Nhan Nguyen Anh-Quan Huynh Ba Hoang-Huy Ngo Huy-Hoang Vo Nhut-Thanh Tran Faculty of Computer Engineering University of Information Technology Ho Chi Minh City Vietnam Vietnam National University Ho Chi Minh City Vietnam Faculty of Automation Engineering Can Tho University Can Tho Vietnam

Diabetes is a persistent condition characterized by the body’s inability to properly utilize insulin. Therefore, noninvasive methods have been proposed to mitigate the pain and risk of infection due to non-required blood extraction compared to the methods for glucose measurement. The invasive methods are done by finger-pricking blood samples from the body. However, this method increases the risk of blood-related infections and pains. Hence, non-invasive Glucose in the blood is an essential method to measure glucose levels. This study successfully implemented a portable embedded system device based on a multi-spectral sensor and Raspberry Pi 4 microprocessor for noninvasive glucose measurement. This study used machine learning, including Multiple Linear Regression and Support Vector Machine, to predict the glucose level with over 90% accuracy. Moreover, the Clarke error grid analysis was used to analyze the accuracy results of this study. It also compared with invasive measurements and previous studies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Machine Learning and Deep Learning CNN Models for Apple Trees Leaves Pathologies Classification

Hybrid Machine Learning and Deep Learning CNN Models for App...

引用

computer Science (COMSCI), International Scientific Conference on

作者： Petar Iavorov Matov Milena Kirilova Lazarova Simona Kirilova Filipova-Petrakieva Ina Taralova Department of Computer Systems Faculty of Computer Systems and Technologies Technical University of Sofia Sofia Bulgaria Department of Theoretical Electrical Engineering Faculty of Automation Technical University of Sofia Sofia Bulgaria LS2N UMR CNRS 6004 Ecole Centrale de Nantes Nantes France

ISBN: (数字)9798350392166

ISBN: (纸本)9798350392173

Agricultural development in recent years has been based entirely on smart management. Leaves diseases on apple trees is a very common problem. The present work is a continuation of previous research of the author's team to solve it. The recently proposed apple leaves pathology prediction model based on deep learning convolutional neural network (CNN) is extended to hybrid models. The latter are a combination of a deep learning CNN and classical machine learning techniques. To increase the classification accuracy two hybrid models are proposed: CNN+SVM (Support Vector Machines) and CNN+RF (Random Forest). The CNN is based on modified DenseNet architecture and SVM and RF models are integrated as CNN output is fed to SVM and RF models respectively to ensure higher classification accuracy. The suggested hybrid models are evaluated on a data set that comprises 1800 images of pathologies in apple trees’ leaves. The experimental results prove the higher accuracies of the hybrid deep + machine learning models compared to the deep learning CNN model.

关键词： Deep learning Support vector machines Radio frequency Pathology Accuracy Computational modeling computer architecture Predictive models Convolutional neural networks Random forests

来源：评论

学校读者我要写书评

暂无评论

Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT

arXiv

引用

arXiv 2025年

作者： Mei, Zihao Li, Jianhao Zhang, Bolin Wang, Chong Guo, Lijun Li, Guoqi Qian, Jiangbo Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China Institute of Automation Chinese Academy of Sciences Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Beijing100045 China

With the rapid growth of dynamic vision sensor (DVS) data, constructing a low-energy, efficient data retrieval system has become an urgent task. Hash learning is one of the most important retrieval technologies which can keep the distance between hash codes consistent with the distance between DVS data. As spiking neural networks (SNNs) can encode information through spikes, they demonstrate great potential in promoting energy efficiency. Based on the binary characteristics of SNNs, we first propose a novel supervised hashing method named Spikinghash with a hierarchical lightweight structure. Spiking WaveMixer (SWM) is deployed in shallow layers, utilizing a multilevel 3D discrete wavelet transform (3D-DWT) to decouple spatiotemporal features into various low-frequency and high-frequency components, and then employing efficient spectral feature fusion. SWM can effectively capture the temporal dependencies and local spatial features. Spiking Self-Attention (SSA) is deployed in deeper layers to further extract global spatiotemporal information. We also design a hash layer utilizing binary characteristic of SNNs, which integrates information over multiple time steps to generate final hash codes. Furthermore, we propose a new dynamic soft similarity loss for SNNs, which utilizes membrane potentials to construct a learnable similarity matrix as soft labels to fully capture the similarity differences between classes and compensate information loss in SNNs, thereby improving retrieval performance. Experiments on multiple datasets demonstrate that Spikinghash can achieve state-of-the-art results with low energy consumption and fewer parameters. Copyright © 2025, The Authors. All rights reserved.

关键词： Discrete wavelet transforms

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：