检索结果-内蒙古大学图书馆

Federated learning-based lightweight selective feature fusion and irregular-aware network for crack detection

Optoelectronics Letters 2025年

作者： LIU Hui HE Tian CHENG Xu SHI Fan NIKOLI? Sa?a V. ZHANG Jianhua School of Computer Science and Engineering， Tianjin University of Technology Department of Electronics， Faculty of Electronic Engineering， University of Nis

Employing deep learning for pavement crack detection can significantly enhance accuracy， and federated learning can help to overcome the challenges of data silos and data security. This paper proposes a lightweight method to detect cracks. We use lightweight encoder modules to extract multi-scale features， and further feature fusion and modelling by Selective Fusion Blocks and Irregular-aware Blocks. Moreover， this method is the first to combine federated learning with crack detection， effectively resolving the tension between data privacy and data sharing in decentralised devices. Experiments were conducted to compare our proposed method with other crack detection methods on two publicly available datasets， including the original method without federated learning and five state-of-the-art methods combined with the same federated learning framework. The experiment proves that our model obtains comparable F1 score with minimal parameters and computational effort. For example， compared to the original method， the number of parameters and computation are reduced by 67.1% and 73.6%， respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating Pretrained Deep Learning Models for COVID-19 Detection in Medical Imaging 1

Evaluating Pretrained Deep Learning Models for COVID-19 Dete...

引用

1st Renewable Energy Technologies and Modern Communications Systems: Future and Challenges Conference, RETMCS 2024

作者： AL-Shehri, Bushra A. Sabbeh, Sahar F. Dessouky, Mohamed M. Department of Data Science College of Computer Science and Engineering University of Jeddah Jeddah23218 Saudi Arabia Faculty of Computers and Artificial Intelligence Information Systems Department Benha University Benha13518 Egypt Department of Computer Science and Artificial Intelligence College of Computer Science and Engineering University of Jeddah Jeddah23218 Saudi Arabia Department of Computer Science and Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt

ISBN: (纸本)9798331519445

COVID-19 is a respiratory disease for which reverse transcription-polymerase chain reaction (RT-PCR) is the standard detection method. This study introduces a hybrid deep learning approach to support the diagnosis of respiratory abnormalities, using COVID-19 as a case study. Multiple datasets were utilized, including the COVID-19 Radiography Dataset (Kaggle), the SARS-CoV-2 CT-Scan Dataset, and proprietary data from the King Faisal Medical Complex. Seven pre-trained deep learning models—VGG16, VGG19, MobileNet, DenseNet201, ResNet50, InceptionResNetV2, and InceptionV3—were evaluated for their performance. InceptionResNetV2 and InceptionV3 achieved perfect accuracy (100%) on the COVID-19 Radiography Dataset and 99% accuracy on the SARS-CoV-2 CT-Scan Dataset. Additionally, augmentation techniques were explored to improve model robustness. This research contributes significantly to medical imaging, offering practical insights for advancing diagnostic and monitoring practices for COVID-19 and other respiratory conditions. ©2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Robust Technique for Steganography of Enhanced Audio Signals 3

A Robust Technique for Steganography of Enhanced Audio Signa...

引用

3rd IEEE International Conference on electronic engineering, ICEEM 2023

作者： Nasr, Marwa A. El-Shafai, Walid El-Rabaie, El-Sayed M. El-Fishawy, Adel S. Dessouky, Moawad I. Abdel-Salam, Nariman El-Samie, Fathi E. Abd Menoufia University Faculty of Electronic Engineering Electronics and Electrical Communications Engineering Department Menouf Egypt Prince Sultan University Security Engineering Laboratory Department of Computer Science College of Engineering Riyadh Saudi Arabia Faculty of Engineering Communications and Electronics Engineering Department Giza Egypt

ISBN: (纸本)9798350323511

Audio steganography is a tool for concealing data (a secret message) inside an audio signal (a carrier). It is regarded as an essential approach for information security. This paper presents a proposed technique for audio signal steganography, which is implemented in the wavelet domain, with a pre-processing enhancement step. First, adaptive Wiener filtering is implemented to reduce the noise on audio signals. Then, the Inverse Short-Time Fourier Transform (ISTFT) is applied to convert the target image from the spectrogram-like nature to the 1-D signal-like nature. The embedding process is performed on high-frequency coefficients in the wavelet domain to keep the audio signals unchanged for human perception. The reverse process is implemented at the receiver. Hence, the embedded coefficients are extracted to recover the embedded image through Short-Time Fourier Transform (STFT). The recovered audio signal is also obtained after the removal of embedded coefficients. The major goal is to enhance the performance of the audio steganography technique, while retaining the audio signal quality. The outcomes show that the suggested technique successfully allows audio steganography and enhances the resultant audio signal quality at different Signal-to-Noise Ratio (SNR) levels. © 2023 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Polarization Insensitive Broadband Zero Indexed Nano-Meta Absorber for Optical Region Applications

引用

computers, Materials & Continua 2022年第4期71卷 993-1009页

作者： Ismail Hossain Md Samsuzzaman Ahasanul Hoque Mohd Hafiz Baharuddin Norsuzlin Binti Mohd Sahar Mohammad Tariqul Islam Space Science Center(ANGKASA) Universiti Kebangsaan Malaysia43600UKM BangiSelangorMalaysia Department of Computer and Communication Engineering Faculty of Computer Science and EngineeringPatuakhali Science and Technology UniversityDumki8602PatuakhaliBangladesh Department of Electrical Electronic and Systems EngineeringFaculty of Engineering and Built EnvironmentUniversiti Kebangsaan Malaysia43600UKM BangiSelangorMalaysia

Broadband response metamaterial absorber(MMA)remains a challenge among researchers.A nanostructured new zero-indexed metamaterial(ZIM)absorber is presented in this study,constructed with a hexagonal shape resonator for optical region *** design consists of a resonator and dielectric layers made with tungsten and quartz(Fused).The proposed absorbent exhibits average absorption of more than 0.8972(89.72%)within the visible wavelength of 450–600 nm and nearly perfect absorption of 0.99(99%)at 461.61 *** on computational analysis,the proposed absorber can be characterized as *** developments of ZIM absorbers have demonstrated plasmonic resonance characteristics and a perfect impedance *** incidence obliquity in typically the range of 0◦–90◦both in TE and TM mode with maximum absorbance is more than 0.8972(∼89.72%),and up to 45◦angular stability is suitable for solar cell applications,like exploiting solar *** proposed structure prototype is designed and simulated by studying microwave technology numerical computer simulation(CST)*** finite integration technique(FIT)based simulator CST and finite element method(FEM)based simulator HFSS also helps validate the numerical data of the proposed ZIM *** proposed MMA design is appropriate for substantial absorption,wide-angle stability,absolute invisible layers,magnetic resonance imaging(MRI),color images,and thermal imaging applications.

关键词： Hexagonal resonator loaded star shaped polarization insensitive compact broadband metamaterial absorber optical region applications

来源：评论

学校读者我要写书评

暂无评论

Insight into Janus V2COS as anode material of high-performance alkali metal ion battery: Diffusion barrier, recyclability, specific capacity, and open-circuit voltage

引用

Physical Review Materials 2024年第8期8卷 085801-085801页

作者： Fanfan Wang Jun Yuan Zhufeng Zhang Baoan Song Junhua Zhao Jincheng Yue Tian Xu Jun Zhou School of Physical Science and Technology Faculty of Electrical Engineering and Computer Science College of Chemical and Material Engineering School of Electronic Information Engineering

Transition metal carbides, nitrides, and carbonitrides, known as MXenes, exhibit exceptional conductivity, stability, and large specific surface area, rendering them promising candidates for anode materials in rechargeable batteries. Herein, we investigate the electrochemical characteristics of the Janus MXene V2COS monolayer, as an anode material of alkali metal ion batteries by using first-principles calculations. The phonon band structure and ab initio molecular dynamics simulations confirm the stability of the Janus V2COS monolayer. The mechanical and electrical properties of the Janus V2COS monolayer are explored and proved to have good mechanical stability and electrical conductivity. The surface of the Janus V2COS monolayer demonstrates the facile adsorption of alkali metal ions and low diffusion barriers. As an anode material, the recyclability of the Janus V2COS has been verified in the ion intercalation/deintercalation processes. Furthermore, the theoretical specific capacities and the open-circuit voltages of the Janus V2COS monolayer are calculated to be 165.54mAh/g and 2.62 V for Li, 662.18mAh/g and 0.76 V for Na, and 294.43mAh/g and 0.4 V for K, respectively. It presents that the Janus V2COS monolayer is a potential anode material of sodium-ion batteries and potassium-ion batteries.

关键词： Electrochemical properties 2-dimensional systems Density functional theory First-principles calculations

来源：评论

学校读者我要写书评

暂无评论

Modulated Model Predictive Control for a Four-Leg Indirect Matrix Converter

Modulated Model Predictive Control for a Four-Leg Indirect M...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Hosseinzadeh, Mohammad Ali Sarebanzadeh, Maryam Kennel, Ralph Babaei, Ebrahim Rivera, Marco Wheeler, Patrick Technical University of Munich High-Power Converters System Munich Germany University of Tabriz Faculty of Electrical and Computer Engineering Tabriz Iran Research Group Department of Electrical and Electronic Engineering Faculty of Engineering Nottingham United Kingdom Vicerrectoría Académica Talca Chile

ISBN: (纸本)9798350376067

Model Predictive Control (MPC) has been increasingly adopted by various converters due to its numerous advantages, including fast dynamic response, multi-objective control, and ease of implementation. However, MPC's variable switching frequency can degrade waveform quality compared to conventional control techniques that utilize proper modulation methods. To address this issue, combining MPC with a PWM technique allows the converter to operate at a fixed switching frequency, resulting in what is known as modulated model predictive control (M2PC). This study proposes an M2PC for a four-leg converter that is coupled with an indirect matrix converter at the input. The proposed M2PC enhances the output waveform quality using a PWM technique for the four-leg converter while maintaining a low fixed switching frequency. The performance of this approach is demonstrated through the implementation of the proposed M2PC technique in the MATLAB/Simulink environment, showing improvements in waveform quality. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Cancellable Multi-Biometric Template Generation Based on Arnold Cat Map and Aliasing

引用

computers, Materials & Continua 2022年第8期72卷 3687-3703页

作者： Ahmed M.Ayoup Ashraf A.M.Khalaf Walid El-Shafai Fathi E.Abd El-Samie Fahad Alraddady Salwa M.Serag Eldin Electrical Communications Engineering Department Faculty of EngineeringMinia UniversityMinia61111Egypt Electronics and Electrical Communications Engineering Department Faculty of Electronic EngineeringMenoufia University32952MenoufEgypt Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of EngineeringTanta UniversityTantaEgypt

The cancellable biometric transformations are designed to be computationally difficult to obtain the original biometric *** paper presents a cancellable multi-biometric identification scheme that includes four stages:biometric data collection and processing,Arnold’s Cat Map encryption,decimation process to reduce the size,and finalmerging of the four biometrics in a single generated ***,a 2D matrix of size 128×128 is created based on Arnold’s Cat Map(ACM).The purpose of this rearrangement is to break the correlation between pixels to hide the biometric patterns and merge these patterns together for more *** decimation is performed to keep the dimensions of the overall cancellable template similar to those of a single template to avoid data ***,some sort of aliasing occurs due to decimation,contributing to the intended distortion of biometric *** hybrid structure that comprises encryption,decimation,andmerging generates encrypted and distorted cancellable *** simulation results obtained for performance evaluation show that the system is safe,reliable,and feasible as it achieves high security in the presence of noise.

关键词： Aliasing technique selective encryption ACM decimation process

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Modulated Predictive Current Control for Dual Three-Phase PMSM With Improved Performance 10

Asymmetric Modulated Predictive Current Control for Dual Thr...

引用

10th IEEE International Power electronics and Motion Control Conference, IPEMC 2024 ECCE Asia

作者： Li, Ze Zheng, Xingyu Xia, Jinhui Liu, Hangan Gao, Xiaonan Rodriguez, Jose Wang, Liling Zhang, Zhaoyan Liu, Zhiheng Hebei University College of Electronic and Information Engineering China Southeast University School of Automation China Kth Royal Institute of Technology School of Electrical Engineering and Computer Science Sweden Universidad San Sebastian Faculty of Engineering Chile

ISBN: (纸本)9798350351330

Dual three-phase PMSM (DTP-PMSM) has gained significant attention benefiting from their exceptional reliability and high torque density. However, DTP-PMSM exhibits poor steady-state performance and large calculation amount with the conventional finite-control-set predictive current control. To address these concerns, an asymmetric modulated predictive current control (AM-PCC) for DTP-PMSM is presented. Therein, the three-phase decomposition and deadbeat control scheme are combined to eliminate the weighting factor and optimize the execution efficiency. An asymmetric modulation strategy is presented and integrated into PCC to reduce the current harmonics and switching frequency. Extensive simulation tests are conducted to demonstrate the effectiveness of the proposed AM-PCC scheme. © 2024 IEEE.

关键词： Synchronous motors

来源：评论

学校读者我要写书评

暂无评论

Deploying an Efficient Free Space Optical Network in the Presence of Different Environmental Turbulences 1

Deploying an Efficient Free Space Optical Network in the Pre...

引用

1st IEEE International Conference on Communication engineering and Emerging Technologies, ICoCET 2024

作者： Hammood, Dalal Abdulmohsin Galeb, Basim Al-Hilali, Aqeel Bashar, Mustafa Nawawi, Norizan Mohamed Shukron, Nur Hakimah Electrical Engineering Technical College Middle Technical University Cybersecurity Technology Engineering Baghdad Iraq Al Hikma University College Computer Technician Engineering Baghdad Iraq Al-farahidi University Medical Instrumentation Engineering Baghdad Iraq Uruk University Baghdad Iraq Universiti Malaysia Perlis Advanced Communication Engineering Centre of Excellence Faculty of Electronic Engineering Technology Perlis Malaysia Universiti Malaysia Perlis Arau Faculty Electronic Engineering Technology Perlis Malaysia

ISBN: (纸本)9798331504144

This paper aims to develop a reliable FSO device that can transfer information quickly and effectively, making it ideal for short-to-medium distances in metropolitan areas lacking radio recurrence groups or linkages. The proposed system will be tested in light air, light rain, medium rain, and heavy rain, with attenuation values of 0.47, 1.988, 5.844, and 9.29 dB/km. Optisystem software version 21 will be used to evaluate the system's QF. Results obtained show that the implemented system can deliver signals 25 km distant in clear air, 12 km in light rain, 10 km in medium rain, and less than 6 km in severe rain. The method's performance with NRZ and RZ modulation formats is also examined. NRZ modulation is simpler to set up and requires less equipment than RZ modulation, and it reduces optical cable dispersion from light rain. NRZ is effective within 10 kilometers, while RZ handles dispersion and maintains synchronization better for extended broadcasts. © 2024 IEEE.

关键词： Optical cables

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence Algorithm Implemented in Indoor Environments based on Machine Learning for Lighting Control System

引用

International Journal of Advanced computer Science and Applications 2022年第2期13卷 64-76页

作者： Alim, Mohammad Ehsanul Alam, Md. Nazmus Sakib Bin Shrikumar, Sneha Hassoun, Ihab Department of Electrical & Computer Engineering University of Delaware NewarkDE United States Department of Electrical & Computer Engineering North South University Dhaka Bangladesh School of Electrical & Electronic Engineering Nanyang Technological University Singapore Faculty of Engineering City University Tripoli Lebanon

Over the past decade, engineers and scientists dedicated a significant amount of effort and time to enhance an indoor system embedded with the state-of-the-art automation. Through innovative implementation of sensors, IoT and machine learning algorithm, the designing of indoor lighting control systems evolved over the period. Our research is based upon the development of a highly intelligent lighting system that will be cost effective and at the same time easily accessed in a remote mode. Devices like Ultra-wide band sensors and Lux sensors were collected and utilized in the designing of the system to retrieve information about the user’s location and existing brightness in the room, respectively. These data were then preprocessed, scaled and transmitted to various machine learning algorithms to predict suitable lighting condition. The application of our proposed lighting system will always keep the brightness range to a recommended level of 200-400 Lux which is extremely compatible for its use in homes, offices, schools and high rage apartments. In addition, the remote access facility allows users to operate the system anywhere in the world providing user experience beyond imagination. Lastly, as the system comprises of low-cost components that are also easily replaceable and only provide lighting when needed, it can provide savings in terms of cost and power © 2022, International Journal of Advanced computer Science and *** Rights Reserved.

关键词： Internet of things

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：