检索结果-内蒙古大学图书馆

All-optical image classification through unknown random diffusers using a single-pixel diffractive network

Light(Science & Applications) 2023年第4期12卷 570-584页

作者： Bijie Bai Yuhang Li Yi Luo Xurong Li Ege Cetintas Mona Jarrrahi Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCalifornia 90095USA Bioengineering Department University of CaliforniaLos AngelesCalifornia 90095USA California Nano Systems Institute(CNSI) University of CaliforniaLos AngelesCalifornia 90095USA

Classification of an object behind a random and unknown scattering medium sets a challenging task for computational imaging and machine vision *** deep learning-based approaches demonstrated the classification of objects using diffuser-distorted patterns collected by an image *** methods demand relatively large-scale computing using deep neural networks running on digital ***,we present an all-optical processor to directly classify unknown objects through unknown,random phase diffusers using broadband illumination detected with a single pixel.A set of transmissive diffractive layers,optimized using deep learning,forms a physical network that all-optically maps the spatial information of an input object behind a random diffuser into the power spectrum of the output light detected through a single pixel at the output plane of the diffractive *** numerically demonstrated the accuracy of this framework using broadband radiation to classify unknown handwritten digits through random new diffusers,never used during the training phase,and achieved a blind testing accuracy of 87.74±1.12%.We also experimentally validated our single-pixel broadband diffractive network by classifying handwritten digits"0"and"1"through a random diffuser using terahertz waves and a 3D-printed diffractive *** single-pixel all-optical object classification system through random diffusers is based on passive diffractive layers that process broadband input light and can operate at any part of the electromagnetic spectrum by simply scaling the diffractive features proportional to the wavelength range of *** results have various potential applications in,e.g.,biomedical imaging,security,robotics,and autonomous driving.

关键词： network processor random

来源：评论

学校读者我要写书评

暂无评论

General Analytical em Model for Active Impedance of 2D PAA with Equivalent Magnetic Currents

General Analytical em Model for Active Impedance of 2D PAA w...

引用

2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023

作者： Mostafa, Mahmoud M. Abdel-Wahab, Wael M. Safavi-Naeini, Safieddin Department of Electrical and Computer Engineering Waterloo Canada C-COM Satellite Systems Inc. Ottawa Canada

ISBN: (纸本)9781665442282

In this paper, a general analytical model for predicting the active impedance variation with the scan angle of phased array antennas (PAAs) of equivalent magnetic currents is presented. The model is based on Floquet modes expansion of magnetic currents and its application to 2D phased array slot antennas. The simulation results calculated by proposed analytical model are presented and compared to those obtained by the numerical EM solver (HFSS). © 2023 IEEE.

关键词： Antenna phased arrays

来源：评论

学校读者我要写书评

暂无评论

Ambient BackCom in beyond 5G NOMA networks: A multi-cell resource allocation framework

引用

Digital Communications and Networks 2022年第6期8卷 1005-1013页

作者： Wali Ullah Khan Fida Hussain Memon Kapal Dev Muhammad Awais Javed Dinh-Thuan Do Nawab Muhammad Faseeh Qureshi Interdisciplinary Centre for Security Reliability and Trust(SnT)University of Luxembourg1855 Luxembourg CityLuxembourg Department of Electrical Engineering Sukkur IBA University Pakistan Department of Institute of Intelligent Systems University of JohannesburgSouth Africa Department of Electrical and Computer Engineering COMSATS University Islamabad44000IslamabadPakistan Electrical Engineering Department University of Colorado DenverDenverCO80204USA Department of Computer Education Sungkyunkwan UniversitySeoulSouth Korea

The research of Non-Orthogonal Multiple Access (NOMA) is extensively used to improve the capacity of networks beyond the fifth-generation. The recent merger of NOMA with ambient Backscatter Communication (BackCom), though opening new possibilities for massive connectivity, poses several challenges in dense wireless networks. One such challenge is the performance degradation of ambient BackCom in multi-cell NOMA networks under the effect of inter-cell interference. Driven by providing an efficient solution to the issue, this article proposes a new resource allocation framework that uses a duality theory approach. Specifically, the sum rate of the multi-cell network with backscatter tags and NOMA user equipment is maximized by formulating a joint optimization problem. To find the efficient base station transmit power and backscatter reflection coefficient in each cell, the original problem is first divided into two subproblems, and then the closed form solution is derived. A comparison with the Orthogonal Multiple Access (OMA) ambient BackCom and pure NOMA transmission has been provided. Simulation results of the proposed NOMA ambient BackCom indicate a significant improvement over the OMA ambient BackCom and pure NOMA in terms of sum-rate gains.

关键词： Beyond fifth-generation Non-orthogonal multiple access Ambient BackCom Spectrum efficiency optimization

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of the Invasive Weed Optimization K-Means Algorithm With Particle Swarm Optimization K-Means for Banking Data 6

Performance Comparison of the Invasive Weed Optimization K-M...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Suwirmayanti, Ni Luh Gede Pivin Putra, I. Ketut Gede Darma Sudarma, Made Sukarsa, I. Made Setyaningsih, Emy Department of Computer Systems Faculty of Informatics and Computer Institut Teknologi dan Bisnis STIKOM Bali Bali Indonesia Department of Information Technology Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Electrical Engineering Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Computer Systems Engineering Faculty of Applied Science Universitas AKPRIND Indonesia Yogyakarta Indonesia

ISBN: (纸本)9798331539603

Banking produces extensive and diverse data, so a clustering process is needed to understand customer behavior patterns and transactions more effectively. This clustering has been widely utilized with the K-Means algorithm due to its simplicity and efficiency. However, this algorithm is limited in determining the optimal cluster center, affecting the accuracy of the clustering results. This study proposes applying two metaheuristic algorithms, Invasive Weed Optimization (IWO) and Particle Swarm Optimization (PSO), as additional solutions combined with K-Means. These two algorithms were chosen because of their ability to find global solutions and convergence speed to handle large and complex banking data. The results show the superiority of IWOKM compared to PSOKM in terms of SSE and DBI. From the SSE value, IWOKM produces a lower value (3029.77), which indicates that this method is better at minimizing clustering errors and producing more accurate clustering than PSOKM (80007.09). From the DBI value, IWOKM also produces a better value (1.6684) than PSOKM (1.6782), which shows that the clusters produced by IWOKM are more compact and more separated. However, in terms of computation time, PSOKM is more efficient, with a faster average computation time. Although IWOKM produces better clustering quality, PSOKM offers advantages in terms of processing speed. This finding confirms that the selection of the IWO algorithm is more appropriate for use on datasets with characteristics such as the German Credit Dataset. © 2024 IEEE.

关键词： Invasive weed optimization

来源：评论

学校读者我要写书评

暂无评论

Comparative Study between KNN and CNN's Techniques for Kidney Stone Detection

Comparative Study between KNN and CNN's Techniques for Kidne...

引用

2023 International Conference on Smart Computing and Application, ICSCA 2023

作者： Al-Tbenawey, Fahdah M. Alotaibi, Shoayee Salem, Marwa Mir, Shamaila Mir, Zahida Computer Science and Engineering College University of Ha'il Department of Computer Science and Information Hail Saudi Arabia Faculty of Engineering Department of Electrical Communication and Electronics Systems Engineering Cairo Egypt

ISBN: (纸本)9798350347050

This paper aims to determine the better technique for kidney stone detection between K-Nearest Neighbor (KNN) and Convolutional Neural Networks (CNNs). As well known, the presence of kidney stones is an important topic that deserves discussion regarding expected medical outcomes. Most of the detection measures comprise CT scans, ultrasounds, and abdominal X-rays. These measures have varying effectiveness levels, hence used in the detection to prepare patients for specific treatment options. Patients' treatment options comprise percutaneous nephrolithotomy (PCNL), extracorporeal shockwave lithotripsy (ESWL), and ureteroscopy. The different detection techniques carried out for the patients are essential to test whether the patient has small or large kidney stones. One essential technique is using conventional neural networks (CNNs) technology. In this paper kidney, stone detection will be carried out using both of K-Nearest Neighbor (KNN) and CNN's techniques. A comparison between both techniques will be carried out to figure out the better. All of the simulations are carried out using MATLAB. © 2023 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Towards Accurate RPM Detection Using Primary Ignition Pulses 49

Towards Accurate RPM Detection Using Primary Ignition Pulses

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Wijayaraja, Jaliya L. Abhayasinghe, Nimsiri Wellalage, Sasini Sliit Faculty of Computing Department of Computer Systems Engineering Malabe Sri Lanka Sliit Faculty of Engineering Department of Electrical and Electronic Engineering Malabe Sri Lanka

ISBN: (纸本)9798350331820

Enhancing the performance and extending the life-cycle of older vehicles through retrofitting with improved systems presents an alluring opportunity. However, achieving accurate sensing of crucial parameters, such as engine revolutions per minute (RPM), poses challenges due to the need for mechanical manipulation and some designs, which may result in diminished accuracy in adverse settings. This study proposes using the primary ignition pulse signal to accurately determine engine speed without mechanical manipulation. We investigate the effectiveness of signal processing methods, including the RC filter, 2nd and 6th order Butterworth filter, to improve the accuracy of the readings. Our proposed method successfully collects data from conventional internal combustion engines, with simulated signal processing methods producing accurate detection of RPM and reduced fluctuations. The proposed method eliminated the noise, leading to accurate RPM measurements, while the maximum standard deviation observed for the RC filter implementation was 38.74. By accurately sensing key parameters, older vehicles can be retrofitted with improved systems, leading to enhanced performance and an extended lifecycle. The introduced methods can be practically implemented using custom electronics or embedded systems and can contribute to future research on automotive retrofitting. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

A Low-Complexity Handover Scheme Using Unsupervised Learning Techniques for 6G Multi-Networking 2

A Low-Complexity Handover Scheme Using Unsupervised Learning...

引用

2nd International Conference on 6G Networking, 6GNet 2023

作者： Ma, Guanghui Khalili, Mohammad Parthiban, Rajendran Katz, Marcos Centre for Wireless Communications University of Oulu Finland Monash University Electrical and Computer Systems Engineering Department Australia

ISBN: (纸本)9798350306736

In the emerging 6G era, a multi-networking archi-tecture is crucial to satisfy the growing connectivity demands of resource-constrained loT devices. Additionally, employing higher frequency bands (mm Wave, THz, and optical spectrum) beyond sub-6 GHz is essential, yet it presents significant challenges. Poor propagation abilities and ultra-small cells of these higher-frequency networks amplify the complexity of mobility management. Therefore, devising an efficient hand over scheme for future ultra-dense 6G heterogeneous networks, capable of addressing these challenges and ensuring rapid response for loT devices, is of paramount importance. To address these challenges, we exemplify with the hybrid LiFi and WiFi network, which is regarded as a potential component for 6G heterogeneous networks, proposing an unsupervised learning-based handover scheme. Our simulations show that this scheme matches or surpasses benchmark performances in terms of user throughput, handover rate, and delay, while minimising computational complexity. Consequently, our approach effectively addresses the distinctive demands of future 6G loT environments. © 2023 IEEE.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Dynamic Construction and Adaptation of 3D Virtual Network Topology for UAV-Assisted Data Collection

Dynamic Construction and Adaptation of 3D Virtual Network To...

引用

2023 IEEE INFOCOM Conference on computer Communications Workshops, INFOCOM WKSHPS 2023

作者： Qiu, Chen Wang, Xianbin Shen, Weiming Lee, Richard Western University Department of Electrical and Computer Engineering London Canada General Dynamics Land Systems London Canada

ISBN: (纸本)9781665494274

Unmanned aerial vehicles (UAV) assisted data collection from on ground devices and sensors is becoming more useful in many mission-critical applications. However, meeting the data collection requirements under dynamic channel conditions between the UAV and on ground devices relies on frequent information exchanges, which brings great challenges to the dynamic operation of the integrated UAV network due to its inherent complexity. To rapidly obtain a holistic view in assisting the UAV network operation, we first propose a three-dimensional (3D) virtual network topology which helps the UAV to make faster decisions by analyzing refined virtual indicators instead of measuring and processing related physical factors frequently in real time. To improve the efficiency of UAV data collection, dynamic adaptation of the 3D virtual network topology is achieved by a deep deterministic policy gradient (DDPG) based algorithm, where the UAV flying speed and direction, as well as the determination of the target group of on ground devices are optimized under the UAV energy constraint. Simulation results demonstrate that the proposed DDPG-based dynamic adaptation of the 3D virtual network topology can effectively improve the data collection efficiency compared with the benchmark solutions. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Low Power Network-on-Chip Architecture Design Technique 32

Low Power Network-on-Chip Architecture Design Technique

引用

32nd IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2024

作者： Musale, Tejas Ganti, Arun Gogoi, Ankur Manna, Kanchan Bits Pilani Department of Electrical and Electronics Engineering India Bits Pilani Department of Computer Science and Information Systems India Galgotias University Uttar Pradesh India

ISBN: (纸本)9798331539672

In the evolving landscape of many-core architectures, the Network on Chip (NoC) emerges as a pivotal inter-connection framework, accommodating the escalating number of cores on a single chip. Despite its widespread adoption, power consumption remains a critical challenge, significantly influenced by factors such as topology, bit toggling, and routing algorithms, with bit-switching power being a predominant concern. In this work, we have proposed an innovative technique in the cores aimed at reducing the power consumption of the NoC. To calculate our method's area, time, and power consumption, we have synthesized it on a Xilinx Virtex-7 FPGA board. We have modified the Noxim open-source simulator to validate our approach using synthetic traffic. Empirical results demonstrate a 29.64% reduction in dynamic power consumption and a 29.09% improvement in switching activity for the average case (Mode 1) traffic scenario. © 2024 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Greeting Gesture Analysis Using Boosting Algorithms and SHAP 13

Greeting Gesture Analysis Using Boosting Algorithms and SHAP

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on Advanced Intelligent systems, SCIS and ISIS 2024

作者： Wibowo, Angga Wahyu Sato-Shimokawara, Eri Kurnianingsih Graduate School of Systems Design Tokyo Metropolitan University Department of Computer Science Tokyo Japan Politeknik Negeri Semarang Department of Electrical Engineering Semarang Indonesia

ISBN: (纸本)9798350373332

Recently, studies related to human activity recognition have developed which have been applied in various fields. In that field Machine learning and deep learning techniques have been widely used for several classification and prediction tasks. However, the first problem is that there is rarely any research on human activities that reflect the culture of a region, such as greeting gestures. Second, there are few studies that do not provide models resulting from the classification or prediction process using machine learning, which can result in a lack of understanding of how a model from machine learning is generated. This study aims to predict Japanese greeting gestures (eshaku, keirei, saikeirei, waving hand) and Indonesian (placing both hands in front of the chest) using Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), and Gradient Boosting. Then, represent the model of the learning machine using SHapley Additive exPlanations (SHAP) to find out how the learning machine obtain a model. Our findings show the efficacy of this method and show that the model not only predicts greeting gestures with high accuracy but also offers a transparent understanding of the factors influencing its predictions, thus enhancing the interpretability and applicability of machine learning in recognizing culturally significant human activities. In the future, we plan to use machine learning and other Explainable Artificial Intelligence (XAI) methods to study human activities with cultural concepts such as greeting gestures in different styles, create more greeting gesture-based human activity datasets, and examine the ethical implications or considerations of using machine learning in cultural contexts to respect cultural differences. © 2024 IEEE.

关键词： Contrastive Learning

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：