检索结果-内蒙古大学图书馆

Research Square 2021年

作者： Odeyemi, Kehinde O. Owolawi, Pius A. Olakanmi, Oladayo O. Department of Computer Systems Engineering Tshwane University of Technology Pretoria0001 South Africa Department of Electrical and Electronic Engineering Faculty of Technology University of Ibadan Nigeria

In this paper, the performance analysis of a reconfigurable intelligent surface (RIS) in a dual-hop decode-and-forward (DF) relay empowered asymmetric radio frequency (RF)/free space optical (FSO) systems is presented. The RIS-assisted RF network is subjected to Nakagami-m distribution while the RIS-assisted FSO networks experience Gamma-Gamma distribution in which both atmospheric turbulence and pointing errors are considered. Thus, the closed-form expressions for the system outage probability and average bit error rate (ABER) are derived with limited number of reflecting elements at RIS-assisted RF network and multiple number of reflecting elements at RIS-assisted FSO network. Further, to obtain more insight about the system characteristic, the asymptotic closed-form expressions are derived at high signal-to-noise ratio (SNR) for the system performance metrics. The results illustrate the impact of the system and channel parameters on the proposed system in terms of atmospheric turbulence, pointing errors under beam width condition, m-fading parameter, and number of reflecting elements. The correctness of the derived analytical expressions is validated via the Monte-Carlo simulations. © 2021, CC BY.

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

Improving brain tumor classification: An approach integrating pre-trained CNN models and machine learning algorithms

引用

Heliyon 2025年第10期11卷

作者： Shoaib, Mohamed R. Zhao, Jun Emara, Heba M. Mubarak, Ahmed S. Omer, Osama A. Abd El-Samie, Fathi E. Esmaiel, Hamada College of Computing and Data Science (CCDS) Nanyang Technological University (NTU) Singapore 639798 Singapore Department of Electronics and Electrical Communications Engineering Ministry of Higher Education Pyramids Higher Institute (PHI) for Engineering and Technology 6th of October City 3220412 Egypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh 84428 Saudi Arabia Electrical Engineering Department Aswan Faculty of Engineering Aswan University Aswan 81542 Egypt Department of Electronics and Communication Engineering College of Engineering A'Sharqiyah University Ibra 400 Oman Faculty of Engineering Aswan University Aswan 81542 Egypt

Accurate detection of brain tumors is crucial for enhancing patient outcomes, yet the interpretation of Magnetic Resonance Imaging (MRI) scans poses significant challenges. This study introduces a novel approach to brain tumor classification by exploring three pre-trained convolutional neural network (CNN) models: DenseNet201, EfficientNetB5, and InceptionResNetV2, combined with softmax activation for feature extraction. These features are then subjected to Principal Component Analysis (PCA) for dimensionality reduction. Subsequently, three machine learning models—Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and Gaussian Naive Bayes (GNB)—are employed for classification. The results reveal that DenseNet201, when combined with SVM and MLP, outperforms the other models in terms of accuracy, recall, and precision. Specifically, DenseNet201 achieves 100% accuracy, recall, and precision on Dataset-I and 98% accuracy, recall, and precision on Dataset-II when paired with SVM and MLP. This study provides valuable insights into the interplay between CNN models, feature extraction techniques, and machine learning algorithms for brain tumor classification, highlighting the efficacy of DenseNet201 combined with SVM and MLP. © 2024 The Author(s)

关键词： Brain tumor classification Convolutional neural networks Feature extraction Image classification Machine learning Pre-processing Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Optical X-haul for 5G /6G: Design and Deployment Standpoint

Optical X-haul for 5G /6G: Design and Deployment Standpoint

引用

2022 IEEE Future Networks World Forum (FNWF)

作者： Christina Lim Chathurika Ranaweera Ampalavanapillai Nirmalathas Yijie Tao Sampath Edirisinghe Lena Wosinska Tingting Song Dept. of Electrical and Electronic Engineering The University of Melbourne Victoria Australia Faculty of SEBE School of Information Technology Deakin Univeristy Geelong Australia Department of Computer Engineering University of Sri Jayewardenepura Nugegoda Sri Lanka Dept. of Electrical Engineering Chalmers University of Technology Gothenburg Sweden

In this paper, we review the work we have carried out in the investigation of the transport network in a hybrid fiber-wireless system to cater for the next generation wireless networks. We have demonstrated advanced coordination functionality in the physical layer to enable coordination between remote radio heads. We have also devised an optimization framework to jointly optimize the wireless and optical network that minimizes the deployment cost. We conclude the paper by providing insights into a reconfigurable optical architecture that can be used to support wireless networks of 6G and beyond.

关键词： Optical fibers 6G mobile communication Costs 5G mobile communication Optical design Wireless networks Optical fiber networks

来源：评论

学校读者我要写书评

暂无评论

Cloud-based Machine Learning Adoption Model for Higher Education Institutions

Cloud-based Machine Learning Adoption Model for Higher Educa...

引用

Artificial Intelligence and Emerging technology (Global AI Summit), International Conference on

作者： Atakilti Brhanu Kiros Ayodeji Olalekan Salau Satvik Vats Keshav Kaushik Ting Tin Tin Crescent Onyebuchi Omeje Mekelle University Mekelle Institute of Technology MIT Mekelle Ethiopia Department of Electrical/Electronics and Computer Engineering Afe Babalola University Ado-Ekiti Nigeria Department of CSE Graphic Era Hill University Dehradun Uttarakhand India Graphic Era Deemed to be University Dehradun Uttarakhand India Amity School of Engineering and Technology Amity University Mohali Punjab India Faculty of Data Science and Information Technology INTI International University Negeri Sembilan Malaysia Department of Electrical/Electronic Engineering University of Port Harcourt Rivers State Choba Nigeria

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

As a new concept, cloud computing has attracted the IT Initiations attention especially the Mobile learning (M-learning). At present, there Higher Education Institutions (HEI's) have struggle with limited IT budgets, difficulties in obtaining and managing infrastructure licenses, and the complexities of software and hardware management. The coming of cloud computing, all of the above challenges was solved. The migration to cloud based M-learning in HEI's is a significant stage in terms of online education, especially during the COVID-19 pandemic. Cloud based M-learning approach has the potential to be a powerful and rapid solution to the many challenges faced by universities in this unprecedented time. This study starts with some brief concepts of Cloud Computing and M-learning for HEI's, mentioning for the significance of the results obtained so far. Additionally, it starting point as strategy for HEI's to adopt Cloud based M-learning is provided, by comparisons of existing models and select DOI model to propose cloud based adoption model. But, the DOI model has its own weaknesses; for example, it does not take into account the localization as Innovation determinants. This study introduces localization phase for the optimal performance of the adopted model. The adoption model was evaluating the importance of the proposed model by IT domain experts and it initiates to be both useful and suitable for a successful cloud based M-learning adoption Ethiopian perspective. Therefore, the research results obtained are promising and funding the use of Cloud based M-learning solutions for Ethiopia HEI's by improving knowledge and skill in this field provides a useful strategy for the HEI's structure.

关键词： Location awareness COVID-19 Cloud computing Technological innovation Pandemics Computational modeling Education Software Mobile learning Hardware

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control Method for Nonisolated Universal Battery Charger

Model Predictive Control Method for Nonisolated Universal Ba...

引用

IEEE International Symposium on Industrial electronics (ISIE)

作者： Naki Guler Ugur Fesli Hasan Komurcugil Sertac Bayhan Department of Electrical-Electronic Engineering Technology Faculty Gazi University Ankara Turkey Qatar Environment and Energy Research Institute Doha Qatar Electrical and Energy Department Technical Science Vocational School Gazi University Ankara Turkey Department of Computer Engineering Eastern Mediterranean University Famagusta Via Mersin 10 Turkey

This paper proposes a Model Predictive Control (MPC) method for a universal bridgeless non-isolated wide-output voltage range onboard battery charger. The onboard battery charger has two different (boost and buck) operation modes in one cycle of the grid voltage. While the boost mode occurs twice in each half cycle, the buck mode takes place once in every half cycle. Contrary to the existing control methods, the proposed MPC method is based on grid current control and does not need a mode detection algorithm. Aside from this feature, the proposed method offers easy implementation, fast dynamic response, and no need for complex modulation schemes. The grid current reference is generated by a proportional-integral (PI) controller depending on the battery’s current or voltage, since the battery should be charged in constant current (CC) and constant voltage (CV) modes. Simulation studies are conducted to investigate the effectiveness of the proposed control strategy for non-isolated wide-output voltage range bridgeless onboard battery chargers. Simulation studies are conducted using two different battery models having nominal voltages of 48V and 350V. The results reveal that the proposed method successfully charges the two batteries in both CV and CC modes. Moreover, the grid current is maintained at unity power factor and total harmonic distortion (THD) is smaller than the limits defined in international standards.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Investigation to Detect Driver Drowsiness from Eye blink Artifacts Using Deep Learning Models

An Investigation to Detect Driver Drowsiness from Eye blink ...

引用

IEEE EMBS Conference on Biomedical engineering and Sciences (IECBES)

作者： Ashvaany Egambaram Nasreen Badruddin Department of Computer Science Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Perak Malaysia Department of Electrical and Electronic Engineering Institute of Health and Analytics Universiti Teknologi PETRONAS Perak Malaysia

Driver drowsiness is a well known problem that depreciates road safety that could cause road accidents, worldwide. Researchers are increasingly using the eye/eyelid images or the electroencephalogram’s (EEG) spectral information to detect drowsiness in drivers. However, no attempt has been made to detect drowsiness using the eye blink artifact features that contaminates EEG signals, which are typically regarded noise and undesired. Therefore, in this study, we have investigated whether the eye blink artifacts that were originally intended to be eliminated from EEG signals could be used to detect drowsiness among drivers. The eye blink artifacts and their features are extracted from EEG signals via the BLINKER algorithm. The deep learning classifiers, multilayer perceptron (MLP) and Recurrent Neural Network with Long-Short-Term-Memory (RNN-LSTM) are trained, validated, and tested to confirm if the eye blink artifacts can be used as an indicator of drowsiness. The investigation has demonstrated that using eye blink artifacts as an indicator of drowsiness is viable, with a classification accuracy of 94.91% achieved through RNN-LSTM.

关键词： Deep learning Road accidents Recurrent neural networks Predictive models Multilayer perceptrons Feature extraction Brain modeling

来源：评论

学校读者我要写书评

暂无评论

3D polarimetry of laser induced speckle fields for phase detection thyroid gland polycrystalline structure and traumatic necrosis of human internal organs

3D polarimetry of laser induced speckle fields for phase det...

引用

Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2024

作者： Ushenko, Olexander Bilookyi, Olexander Ushenko, Yuriy Dubolazov, Alexander Soltys, Irina Olar, Olexander Mikirin, Ivan Skliarchuk, Valeriy Salega, Olexander Karas, Oleksandr Rakhimbayeva, Gulbarshin Rogovyi, Yuriy Kozan, Nataliia Zheng, Jun Alimbayeva, Zhadyra Omiotek, Zbigniew Taizhou Institute of Zhejiang University Taizhou China Optics and Publishing Department Chernivtsi National University Chernivtsi Ukraine Department of Surgery Bucovinian State Medical University Chernivtsi Ukraine Computer Science Department Chernivtsi National University Chernivtsi Ukraine Biomedical Engineering and Optic-Electronic Systems Department Vinnitsia National Technical University Vinnytsia Ukraine Department of Information Communication Technologies Kazakh National Medical University named after S.D. Asfendiyarova Almaty Kazakhstan Department of Pathological Physiology Bucovinian State Medical University Chernivtsi Ukraine Department of Forensic Medicine Medical and Pharmaceutical Law State Medical Academy Ivano-Frankivsk Ukraine Kazakh National Women's Teacher Training University Almaty Kazakhstan Faculty of Electrical Engineering and Computer Science Lublin University of Technology Lublin Poland

ISBN: (数字)9781510685796

ISBN: (纸本)9781510685789

A short theory of the processes of formation of the laser speckle fields polarization structure of biological tissues with optically anisotropic architectonics is presented. A method of polarization interference mapping of speckle fields with layer-by-layer phase scanning of holographically reconstructed distributions of complex amplitudes of biological preparations of various morphological structures and physiological states has been proposed and experimentally tested - biopsies of the thyroid gland and blood films of rats with different severity of sepsis. Layer-by-layer maps of polarization ellipticity of native histological sections of thyroid biopsies from donors and sick patients were studied. As part of the statistical analysis of phase coordinate distributions of polarization ellipticity, objective markers for the differential diagnosis of thyroid pathology were found - nodular goiter, autoimmune thyroiditis and papillary cancer. Very good (~90%) and excellent (≥90%) accuracy of differential diagnosis was achieved. Statistical markers for temporal monitoring of septic changes in polarization azimuth maps of polycrystalline blood films of rats were found. An example of further research using laser-induced autofluorescence polarimetry methods is presented. © 2024 SPIE.

关键词： Optical anisotropy

来源：评论

学校读者我要写书评

暂无评论

Thick Film Interdigitated Electrode Graphite and Carbon Nanotube on Flexible Substrate for Hydrogen Gas Detection

Thick Film Interdigitated Electrode Graphite and Carbon Nano...

引用

IEEE International Conference on Sensors and Nanotechnology

作者： Azlinda Abu Bakar Mohd Nizar Hamidon Mohd Hanif Yaacob Suriati Paiman Haslina Jaafar Wan Nursheila Wan Jusoh Funtional Device Laboratory Institute of Nanoscience and Nanotechnology Universiti Putra Malaysia Serdang Selangor Department of Computer and Communication Systems Faculty of Engineering Universiti Putra Malaysia Serdang Selangor Department of Physics Faculty of Science Universiti Putra Malaysia Serdang Selangor Department of Electrical and Electronic Faculty of Engineering Universiti Putra Malaysia Serdang Selangor Section of Aerospace Malaysians Institute of Aviation Technology Universiti Kuala Lumpur Dengkil Selangor

The comparison on the performance of interdigitated electrode (IDE) graphite and carbon nanotube (CNT) using titanium dioxide-multiwall carbon nanotube (TiO2-MWCNT) composite as sensing materials to detect hydrogen gas is presented in this research work. Screen printing technique has been selected to deposited IDE graphite and CNT conductive pastes as the electrode thick film on a flexible substrate, which is continued by firing at 120°C each. TiO 2 -MWCNT paste was printed as a sensing layer on top of IDE, followed by firing at 350°C. FESEM was used to characterize the morphological analysis of the IDE film. The operating temperature was varied at 27°C, 50°C and 100°C and concentration varied from 100–1000 ppm for gas hydrogen. The gas sensor demonstrated as n-type gas characteristics where the response of the gas sensor produced increased current from the results. The results purpose when the sensor was exposed to hydrogen gas. Therefore, the ability of IDE graphite and CNT as an electrode to harvest the electron from sensing materials were successfully proven. The IDE CNT showed better response compare to IDE graphite, but both electrodes were able to sense 100 – 1000 ppm at the operating temperature of 27°C, 50°C and 100°C. The optimal of operating temperature for IDE graphite is 50°C and IDE CNT is at room temperature for the hydrogen gas detections in this research work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sensorless Multi-Parameter Identification for IPMSM Based on High-Frequency Recursive Least Squares Method

Sensorless Multi-Parameter Identification for IPMSM Based on...

引用

第32届中国过程控制会议(CPCC2021)

作者： Jin Li Youmin Zhang Chaobo Chen Song Gao Han Liu Guo Xie Gina Cody School of Engineering and Computer Science Concordia University Faculty of Electronic Informatics Xi'an Technological University Faculty of Automation and Information Engineering Xi'an University of Technology

In order to improve the performance of internal permanent magnet synchronous motors(IPMSM) servo driving system,four motor key parameters need to be acquired accurately in real time to increase the control ***,in this paper,aiming at using high-frequency recursive least squares(HF-RLS) algorithm to identify the IPMSM parameters like Ld,Lq,Rs and *** algorithm introduces the current rate of change in the dynamic identification process,and at the same time improves the gain matrix K in the algorithm to reduce the coupling effect of the d-axis and q-axis identification errors on the inductance *** identification parameters are applied to sensorless control and torque observation for *** results show that the HF-RLS identification optimization strategy considering the periodic disturbance of the voltage source can identify the internal multi-parameter of the motor more accurately without obtaining any relevant parameters of the motor.

关键词： IPMSM Recursive least squares(RLS) Multi-parameter identification High-frequency speed estimation

来源：评论

学校读者我要写书评

暂无评论

Distributed Information Bottleneck for a Primitive Gaussian Diamond Channel with Rayleigh Fading

arXiv

引用

arXiv 2022年

作者： Xu, Hao Wong, Kai-Kit Caire, Giuseppe Shamai, Shlomo Department of Electronic and Electrical Engineering University College London LondonWC1E7JE United Kingdom Faculty of Electrical Engineering and Computer Science Technical University of Berlin Berlin10587 Germany Department of Electrical and Computer Engineering Technion-Israel Institute of Technology Haifa3200003 Israel

This paper considers the distributed information bottleneck (D-IB) problem for a primitive Gaussian diamond channel with two relays and Rayleigh fading. Due to the bottleneck constraint, it is impossible for the relays to inform the destination node of the perfect channel state information (CSI) in each realization. To evaluate the bottleneck rate, we provide an upper bound by assuming that the destination node knows the CSI and the relays can cooperate with each other, and also three achievable schemes with simple symbol-by-symbol relay processing and compression. Numerical results show that the lower bounds obtained by the proposed achievable schemes can come close to the upper bound on a wide range of relevant system parameters. Copyright © 2022, The Authors. All rights reserved.

关键词： Channel state information

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：