检索结果-内蒙古大学图书馆

2nd IEEE International Power Electronics and Application Symposium, PEAS 2023

作者： Sloan, Maximilian Hanlon Abobghala, Abdelmenen Ahmed, Mahmud Mohamed Fanan, Anwar Mehdawi, Meftah Abuhelala, Mohamed National College for Nuclear at Lakes College Electrical Engineering Department Workington United Kingdom Tte Technical Engineering Middlesbrough College Electrical Engineering Department Middlesbrough United Kingdom Higher Institute of Science and Technology Computer Science Department Tripoli Libya University Campus North Lincolnshire Dn Colleges Group Engineering Department Scunthrope United Kingdom

ISBN: (纸本)9798350313765

Induction motors are the most widely adopted alternating current machines in industry. Requirements for precise and efficient control of such motors has led to developments in high performance drives, namely direct torque control. The induction motors parameters must be ascertained to accurately tune the drive to its optimum performance, failing to do so would result in an inadequate response from the drive, leading to sluggish dynamics and premature deterioration of the motor and drive. The process of optimizing the drive parameters is laborious, costly and time consuming. MathWorks provides software to model and modify the parameters of a direct torque control drive, however the trial and error retuning methods are tedious. This paper presents the development of an AC induction motor and direct torque control drive parameter retuning app which can accurately predict the motor and drive parameters and then simulate its performance using solely the motor nominal power rating. The app utilises the AC4 block and pre-set induction motor models from within the Math Works Specialised Power Systems library. The effectiveness of the app was first tested with known data points and then at random query points and operating conditions, all of which produced satisfactory results in significantly reduced time. © 2023 IEEE.

关键词： direct torque control drive parameter estimation Math Works Motor drives power systems

来源：评论

学校读者我要写书评

暂无评论

Development of a Wireless Real-Time Computation System for Fast and Accurate Heart Rate Monitoring using Photoplethysmography (PPG) Signals 16

Development of a Wireless Real-Time Computation System for F...

引用

16th IEEE Malaysia International Conference on Communication, MICC 2023

作者： Lim, Ben Dong Chong, Kim Soon Tiang, Sew Sun Lim, Wei Hong Mokayef, Mastaneh Tan, Bee Sian UCSI University Department Electrical & Electronic Engineering Selangor Malaysia Tunku Abdul Rahman University of Management and Technology Department of Computer Science and Embedded Systems Kuala Lumpur Malaysia

ISBN: (纸本)9798350304343

This manuscript presents the development of a wireless system for fast and accurate heart rate monitoring. The system utilizes Seeed XIAO BLE and MAX86150 components to capture and process the photoplethysmogram (PPG) signal. Real-Time computation of heart rate is achieved through the deployment of a modified HeartPy algorithm on the microcontroller. The accuracy of the system was evaluated through experiments involving six patients, comparing the results with those obtained from a commercial pulse oximeter (A310) by AEON technology. The Mean Percentage Error values demonstrated a close agreement between the test system and the commercial device, with an error falling within 0.31%. Additionally, the system achieved a 30% to 40% shorter refresh time compared to the commercial pulse oximeter, allowing for more frequent and up-To-date heart rate monitoring. The development of this wireless system contributes to the advancement of healthcare technology, aligning with the Sustainable Development Goal of Good Health and Well-being. Future improvements include incorporating oxygen saturation (SpO2) and electrocardiogram (ECG) detection into the system and designing a compact and portable form factor. By combining fast and accurate heart rate monitoring with wireless data transmission, this system holds promise for enhancing healthcare applications and improving patient well-being. © 2023 IEEE.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Highly Directive Compact Multiband MIMO Antenna with Improved Gain for 5G Wireless Communication System 12

Highly Directive Compact Multiband MIMO Antenna with Improve...

引用

12th IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications, APWC 2023

作者： Khan, Owais Khan, Shahid Alibakhshikenari, Mohammad Anab, Muhammad Nasir, Jamal Dalarsson, Mariana Cecos University of It and Emerging Sciences Peshawar Pakistan Comsats University Abbottabad Campus Department of Electrical and Computer Engineering Abbottabad Pakistan Universidad Carlos Iii de Madrid Department of Signal Theory and Communications Leganés Madrid28911 Spain Uet Peshawar Department of Electrical Engineering Pakistan Comsats University Islamabad Abbottabad Campus Department of Electrical and Computer Engineering Pakistan School of Electrical Engineering and Computer Science Kth Royal Institute of Technology SE Stockholm100-44 Sweden

ISBN: (纸本)9798350320602

A novel wide dual-band, Multiple-Input Multiple-Output (MIMO) antenna design for the upcoming fifth generation (5G) wireless communication is presented in this work. The size of single element of the proposed MIMO configuration is 4×5 mm2having L-shaped slot at the top edge. Rogers TMM4 with thickness of 0.508 mm having relative permittivity of 4.5 is used as a substrate material. Resonating frequencies of single antenna element are 40.15, 67.80 and 91.23 GHz with a wide impedance bandwidth of 2.22 and 34.43 GHz, respectively. The return loss at resonating frequencies are - 29.25, -66.30. and -20.00 dB with a good gain of 5.51, 4.27 and 3.70 dBi, respectively. The overall size of proposed 1×2 MIMO antenna is 4×7 mm2with a separation of 3.6 mm in between two elements and 0.6 mm separation between the edges and elements. The resonating frequencies of the proposed MIMO antenna are 40.36 GHz with reasonable gain of 4.62 dBi, and 67.59 and 95.73 GHz with improved gain of 5.42 and 5.70 dBi, respectively. The simulated return loss below -10db at resonating frequencies are -21.92, -63.38 and -27.87 dB, respectively. Inter-port isolation of above 20 dB throughout the operating frequencies, is achieved without using any complex technique. Envelope Correlation Coefficient (ECC) and Diversity Gain (DG), are important MIMO antenna parameters are less than 0.001 and 10 dB respectively. The proposed design with a high radiation efficiency at resonating frequencies is a good candidate for the satellite and radar communication as the achieved operating range lies in the proposed Ka-band (26-40 GHz), V-band (40-75 GHz), E-band (60-90 GHz) and W-band (75-110 GHz). © 2023 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Distributed Learning based on 1-Bit Gradient Coding in the Presence of Stragglers

arXiv

引用

arXiv 2024年

作者： Li, Chengxi Skoglund, Mikael The Division of Information Science and Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

This paper considers the problem of distributed learning (DL) in the presence of stragglers. For this problem, DL methods based on gradient coding have been widely investigated, which redundantly distribute the training data to the workers to guarantee convergence when some workers are stragglers. However, these methods require the workers to transmit real-valued vectors during the process of learning, which induces very high communication burden. To overcome this drawback, we propose a novel DL method based on 1-bit gradient coding (1-bit GC-DL), where 1-bit data encoded from the locally computed gradients are transmitted by the workers to reduce the communication overhead. We theoretically provide the convergence guarantees of the proposed method for both the convex loss functions and non-convex loss functions. It is shown empirically that 1-bit GC-DL outperforms the baseline methods, which attains better learning performance under the same communication overhead. Copyright © 2024, 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

Hybrid Method for Monitoring Sundarbans Mangrove Forest Using Satellite Images

Hybrid Method for Monitoring Sundarbans Mangrove Forest Usin...

引用

Information and Communication technology (ICICT), International Conference on

作者： MD. Abdullah Al Naim Shihab Sarar Mahdi Hasan Md Maruf Hossain Tasin Omar Farrok Department of Civil Engineering Ahsanullah University of Science and Technology Bangladesh Department of Computer Science and Engineering Ahsanullah University of Science and Technology Bangladesh Department of Electrical and Electronic Engineering Ahsanullah University of Science and Technology Bangladesh

ISBN: (数字)9798331508227

ISBN: (纸本)9798331508234

A hybrid method for monitoring Sundarbans mangrove forest using satellite images with machine learning techniques is presented in this paper. The Random Forest algorithm, data scaling, cloud, and shadow masking are used to enhance the precision of land cover classification over the Sundarbans. The study utilizes Landsat 8 imagery to classify land into deep forest, light forest, barren land, and water bodies. Significant fluctuations in land cover types over the analyzed period, with notable variations in forest density, barren land, and water bodies are identified. Normalized Difference Vegetation Index and Normalized Difference Water Index are two popular methods for observing vegetation health and water bodies in remote sensing. But it fails to classify different objects. This paper focuses on solving this issue using machine learning technique by combining the two methods along with the other band's reflectance as a feature to improve the classification and show a great f1 and recall. This study uses a hybrid model to monitor land cover changes in the Sundarbans mangrove forest from 2013 to 2022, achieving an overall accuracy of 0.98. Significant findings include a deep forest cover increase from 52.82% to 55.735%, fluctuations in barren land from 2.04% to a peak of 8.38% in 2021, and a decrease in water bodies from 32.18% to 28.82%, indicating possible changes in river dynamics and hydrological conditions.

关键词： Fluctuations Accuracy Machine learning algorithms Land surface Forestry Regression analysis Satellite images Classification algorithms Random forests Monitoring

来源：评论

学校读者我要写书评

暂无评论

UltraAdv: An Ultrasonic Adversarial Attack on Black-Box Speech Recognition Systems

引用

IEEE Transactions on Mobile Computing 2025年

作者： Zhang, Guoming Ma, Xiaohui Zhang, Huiting Spolaor, Riccardo Yang, Yanni Ji, Xiaoyu Cheng, Xiuzhen Hu, Pengfei Shandong University School of Computer Science and Technology Qingdao266237 China Electrical Engineering of Zhejiang University Hangzhou310027 China

Attacks on speech recognition systems often use adversarial or inaudible commands. However, a challenge is that adversarial perturbations typically fall within the audible frequency range, making it difficult to achieve inaudibility. Additionally, the non-linear effects of loudspeakers often cause inaudible commands to become audible at higher power levels. Therefore, minimizing the power requirements of the attack is essential to maintain inaudibility. Another significant obstacle is the conversion of variable-length commands, especially longer ones, into shorter target commands. In this paper, we present UltraAdv, a method for generating long-range adversarial perturbations capable of compromising commands of arbitrary length in black-box setting. By combining the ultrasonic signal with the normal one, rather than negating it as in DolphinAttack, we significantly improve the energy efficiency, thus enhancing its attack distance. We also propose a dynamically adjustable suppression-interference method based on automatic gain control to address the challenge of mismatched durations between long commands and target commands (length-independent). Experiments demonstrate that using a single perturbation, we achieve impressive success rates of 98.84% and 96.62% and 98.32% across a diverse set of 12,260 speeches on DeepSpeech, iFlytek, and Whisper. The attack range reaches up to 15 m, surpassing DolphinAttack's 5 m range at equivalent power. © 2002-2012 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Wireless Passive LC Sensor Prototypes for Intraocular Pressure Monitoring 9

Design and Analysis of Wireless Passive LC Sensor Prototypes...

引用

9th International Conference on Applied System Innovation, ICASI 2023

作者： Wang, Po-Yan Jou, Jau-Ji Tseng, Chih-Lung Yang, Chun-Liang Chen, Tsong-Yi Shih, Tien-Tsorng National Kaohsiung University of Science and Technology Department of Electronic Engineering Kaohsiung Taiwan Cheng Shiu University Department of Electronic Engineering Kaohsiung Taiwan Tamkang University Department of Electrical and Computer Engineering New Taipei City Taiwan

ISBN: (纸本)9798350398380

Some eye diseases require round-the-clock intraocular pressure (IOP) monitoring, for example, glaucoma. In this paper, we propose sensor prototypes with an LC resonance structure for wireless passive IOP monitoring. The LC sensor will be expected to be combined with contact lenses, so the sensor shape is designed as a circular ring structure. The performance of two LC sensor prototypes made using a flexible printed circuit board was simulated and measured. The resonance frequency of the LC sensor with a two-turn spiral inductor is 89.0 MHz and that with a three-turn spiral inductor is 46.5 MHz. © 2023 IEEE.

关键词： Flexible electronics

来源：评论

学校读者我要写书评

暂无评论

A Fast and Noise Rejecting Kolmogorov-Smirnvo Sorting Algorithm in X-ray Diamond sorting

A Fast and Noise Rejecting Kolmogorov-Smirnvo Sorting Algori...

引用

2022 International Conference on Smart Applications, Communications and Networking, SmartNets 2022

作者： Modise, Ernest Gomolemo Zungeru, Adamu Murtala Mtengi, Bokani Ude, Albert Botswana International University of Science and Technology Department of Electrical Computer and Telecommunications Engineering Palapye Botswana Botswana International University of Science and Technology Department of Mechanical Energy and Industrial Engineering Palapye Botswana

ISBN: (纸本)9781665487580

X-ray fluorescence and transmission have found common use in large-scale diamond sorting. These methods have progressed independently with each providing a solution for a specific range of particle size. Fluorescence is applicable for diamond sizes between 1.25 - 32 mm and is subject to self-absorption, while transmission has been used on diamond fractions between 10 mm - 100 mm. Transmission sorting suffers poor contrast at particle sizes below 10 mm. Parametric x-ray absorption fine structure models of fluorescence, with five describing features, and a transmission one with five parameters, are developed for both phenomena and simulated against literature for correctness. Furthermore, we define a new x-ray signature parameter by combining high-density ensemble data from both modes for a calibrated sample which we use as a benchmark in our sorting criteria. Finally, we construct random theoretical pure compounds and implore a fast noise rejecting Kolmogorov-Smirnov sorting algorithm to test random samples against the calibrated sample. For compounds that are closely related to the calibration sample, we obtained a percent similarity in the order of 98 %, while completely dissimilar theoretical compound similarity can be as low as 6 % © 2022 IEEE.

关键词： Diamonds

来源：评论

学校读者我要写书评

暂无评论

Adaptive Coded Federated Learning: Privacy Preservation and Straggler Mitigation

arXiv

引用

arXiv 2024年

作者： Li, Chengxi Xiao, Ming Skoglund, Mikael The Division of Information Science and Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

In this article, we address the problem of federated learning in the presence of stragglers. For this problem, a coded federated learning framework has been proposed, where the central server aggregates gradients received from the non-stragglers and gradient computed from a privacy-preservation global coded dataset to mitigate the negative impact of the stragglers. However, when aggregating these gradients, fixed weights are consistently applied across iterations, neglecting the generation process of the global coded dataset and the dynamic nature of the trained model over iterations. This oversight may result in diminished learning performance. To overcome this drawback, we propose a new method named adaptive coded federated learning (ACFL). In ACFL, before the training, each device uploads a coded local dataset with additive noise to the central server to generate a global coded dataset under privacy preservation requirements. During each iteration of the training, the central server aggregates the gradients received from the non-stragglers and the gradient computed from the global coded dataset, where an adaptive policy for varying the aggregation weights is designed. Under this policy, we optimize the performance in terms of privacy and learning, where the learning performance is analyzed through convergence analysis and the privacy performance is characterized via mutual information differential privacy. Finally, we perform simulations to demonstrate the superiority of ACFL compared with the non-adaptive methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Steering Angle Prediction Algorithm Performance Comparison in Different Simulators for Autonomous Driving 31

Steering Angle Prediction Algorithm Performance Comparison i...

引用

31st International Conference on Software, Telecommunications and computer Networks, SoftCOM 2023

作者： Dumancic, David Mijic, David Vranjes, Mario Grbic, Ratko TTTechAuto D.o.o. Cara Hadrijana 10b Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

ISBN: (纸本)9798350301076

The development of autonomous driving (AD) algorithms and their testing would be very expensive when real-world vehicles and environments would be used from the very beginning of development. That is why in the initial development phases simulators are often used, in which it is possible to achieve realistic simulations of the real world. Therefore, many different simulators for AD have been developed. One of the main tasks of a fully autonomous vehicle is steering angle prediction (SAP). This paper explores SAP using a PilotNet CNN-based algorithm that recognizes essential features from input images to predict vehicle trajectory. After training on real-world images, the algorithm's performance is evaluated in both CARLA and AirSim simulators, achieving 91.65% autonomy in CARLA and 71.87% in AirSim. The algorithm is further trained on the images obtained from the simulator, resulting in improved performance of 96.34% in CARLA and 78.99% in AirSim in terms of total autonomy. The study demonstrates the benefits of simulators for the development of AD algorithms and highlights the importance of testing in multiple simulators to achieve reliable performance across different environments and scenarios, including different lighting and weather conditions, types of road markings, and track configurations. The paper also highlights the advantages and disadvantages of individual simulators, which can be useful for the development and testing of future SAP algorithms. © 2023 University of Split, FESB.

关键词： Forecasting

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：