检索结果-内蒙古大学图书馆

IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

作者： Li Zhang Ahmed M. Eltawil Khaled N. Salama Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia

ISBN: (数字)9798350383638

ISBN: (纸本)9798350383645

Convolutional neural networks(CNNs) have demonstrated remarkable capability and scalability in a variety of vision-related tasks. Due to privacy and latency constraints, in some scenarios, the CNNs are deployed on-site where power supply, computation power, and memory capacity are limited. These constraints hinder the traditional training or modification of CNN models, which typically involves network-scale backpropagation of the gradients. In this work, we proposed a framework enabling the derivation of lightweight models from the original model at the edge only utilizing hardware-friendly operations. In the proposed framework, all models are binary quantized and the gradients are obtained by layer-wise decision boundary matching. Hence, the whole flow can be executed with bit-wise and fixed-point arithmetic operations without network-scale gradient backpropagations. The derived model serves as a viable alternative to the original, in scenarios where the accuracy requirements are less stringent, delivering enhanced efficiencies in power and memory consumption. We validate the framework on digit recognition tasks, obtaining a better accuracy than naively deploying the same lightweight model. Furthermore, an FPGA demonstration of our framework achieved a throughput of 2.2 TOPS/s, underscoring its practical applicability.

关键词： Backpropagation Training Accuracy Computational modeling Scalability Memory management Throughput

来源：评论

学校读者我要写书评

暂无评论

Advancing ECT Imaging: Residual UNet Deep Neural Network Approach 1st

Advancing ECT Imaging: Residual UNet Deep Neural Network App...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Deabes, Wael Khalifa, Fahmi Abdel-Hakim, Alaa E. Bouazza, Kheir Eddine Computational Engineering Mathematical Sciences Department Texas A&M University SA San AntonioTX78224 United States Electrical and Computer Engineering Department Morgan State University BaltimoreMD21251 United States Computer Science Department in Jamoum Umm Al-Qura University Makkah Saudi Arabia Computer and Information Science Division Higher Colleges of Technology Abu Dhabi United Arab Emirates

ISBN: (纸本)9783031823763

Recently, there has been significant progress in electrical Capacitance Tomography (ECT) image reconstruction, yet there remains room for enhancing both speed and quality in these reconstructions. Deep Learning (DL) offers a promising avenue due to its capacity to handle intricate nonlinear functions. This study introduces DL-based ECT image reconstruction model based on Residual UNet and termed as ECT_ResUNet. A sizable dataset containing permittivity distribution and corresponding capacitance measurements was created to train and evaluate the proposed model. The ECT_ResUNet processes modulated capacitance vectors, representing them as 66×66 images. The model’s effectiveness and practicality were assessed using unseen samples, demonstrating precise image reconstruction with an average Image Error (IE) of 0.0918 and Correlation Coefficient (CC) of 0.9527. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulation of Two Axes Gimbal Using Fuzzy Control

引用

computers, Materials & Continua 2022年第7期72卷 93-107页

作者： Ayman A.Aly Mohamed O.Elhabib Bassem F.Felemban B.Saleh Dac-Nhuong Le Department of Mechanical Engineering College of EngineeringTaif UniversityTaif21944Saudi Arabia Control and Mechatronics Division School of Electrical EngineeringUTMJohor Bahru81300Malaysia Institute of Research and Development Duy Tan UniversityDanang550000Vietnam School of Computer Science Duy Tan UniversityDanang550000Vietnam

The application of the guided missile seeker is to provide stability to the sensor’s line of sight toward a target by isolating it from the missile motion and *** main objective of this paper is not only to present the physical modeling of two axes gimbal system but also to improve its performance through using fuzzy logic controlling *** paper is started by deriving the mathematical model for gimbals motion using Newton’s second law,followed by designing the mechanical parts of model using SOLIDWORKS and converted to xml file to connect dc motors and sensors using MATLAB/***,a Mamdani-type fuzzy and a Proportional-Integral-Derivative(PID)controllers were designed using MATLAB *** performance of both controllers was evaluated and tested for different types of input *** simulation results showed that self-tuning fuzzy controller provides better performance,since no overshoot,small steady-state error and small settling time compared to PID controller.

关键词： Gimbal system self-tuning fuzzy proportional-integral-derivative(PID)control cross coupling

来源：评论

学校读者我要写书评

暂无评论

Extended-Attention Applied in Selected Stages

Extended-Attention Applied in Selected Stages

引用

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Zeyu Zhang Yuki Todo Division of Electrical Engineering and Computer Science Kanazawa University Kanazawa Japan Faculty of Electrical Information and Communication Engineering Kanazawa University Kanazawa Japan

ISBN: (数字)9798350350890

ISBN: (纸本)9798350350906

The Self-attention mechanism was widely applied in computer Vision (CV) field. However, while Self-attention mechanism brings high accuracy to Transformer, it also brings a huge amount of calculation. To further enhance accuracy and decrease computational load, in this paper, two refinements were implemented. Firstly, two matrices were introduced to enhance the extraction of image information for Extended-attention method. The capacity of Transformer was enhanced by these matrices to capture crucial information in complex tasks, the final accuracy and generalization performance were significantly improved. Secondly, the impact of implementing the aforementioned Self-attention mechanism at various stages of the Transformer is investigated. Intriguingly, our findings reveal that selectively implementing this method at specific stages leads to a significant enhancement in the model's performance.

关键词： Training computer vision Accuracy Optimization methods Learning (artificial intelligence) Transformer cores Transformers Stability analysis Data mining

来源：评论

学校读者我要写书评

暂无评论

MRI Joint Super-Resolution and Denoising based on Conditional Stochastic Normalizing Flow

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期6卷 1472-1487页

作者： Liu, Zhenhong Wang, Xingce Wu, Zhongke Zhu, Yi-Cheng Frangi, Alejandro F. Beijing Normal University School of Artificial Intelligence Beijing China Peking Union Medical College Hospital Department of Neurology Beijing China The University of Manchester Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences Department of Computer Science School of Engineering United Kingdom Department of Cardiovascular Sciences Department of Electrical Engineering Leuven Belgium Alan Turing Institute London United Kingdom

Magnetic resonance imaging (MRI) is often limited by noise and low-resolution (LR), which can impact the precision of the diagnosis and treatment of patients. LR images and mixed noise (e.g., Gaussian noise, Rician noise, and Impulse noise) are inherent in MR images, and current approaches typically address image super-resolution (SR) reconstruction and denoising separately, resulting in a discrepancy between the actual MRI data distribution and the reconstructed images. This research introduces a new algorithm SRDSNF, the stochastic normalizing flow-based MR image SR and denoising model, which tackles SR and denoising simultaneously through a stochastic normalizing flow. Our method integrates the encoded information of the input image as a conditional variable in each reverse step of the stochastic normalizing flow, ensuring a consistent representation of the spatial distribution between the reconstructed image and the original data. Additionally, we incorporate range-null space decomposition and subsequence sampling techniques to increase the consistency between the original and constructed data and accelerate model generation. To assess the efficacy of our approach, we conducted experiments on the BrainWeb and NFBS datasets, which include simultaneous SR and denoising, standalone denoising, and standalone SR tasks. The results of the experiments illustrate that our method achieves superior SR and denoising performance with fewer sampling steps, closely approximating the ground truths. Furthermore, our results surpass those of existing methods in various tasks, showing improvement of up to 4.64 dB in PSNR and 13.8% in SSIM achieved by our SRDSNF model was contextualized against state-of-the-art approaches such as AMIR, SwinIR, and InstructIR. These methods typically report PSNR improvements ranging from 0.5 to 2 dB and SSIM increases of 3-6%, underscoring the potential clinical value of our methodology. © 2020 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Slow Convergence of Interacting Kalman Filters in Word-of-Mouth Social Learning

Slow Convergence of Interacting Kalman Filters in Word-of-Mo...

引用

Annual Allerton Conference on Communication, Control, and Computing

作者： Vikram Krishnamurthy Cristian R. Rojas School of Electrical and Computer Engineering Cornell University Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

ISBN: (数字)9798331541033

ISBN: (纸本)9798331541040

We consider word-of-mouth social learning involving $m$ Kalman filter agents that operate sequentially. The first Kalman filter receives the raw observations, while each subsequent Kalman filter receives a noisy measurement of the conditional mean of the previous Kalman filter. The prior is updated by the m-th Kalman filter. When $m=2$ , and the observations are noisy measurements of a Gaussian random variable, the covariance goes to zero as $k^{-1/3}$ for $k$ observations, instead of $O(k^{-1})$ in the standard Kalman filter. In this paper we prove that for $m$ agents, the covariance decreases to zero as $k^{-(2^{m}-1)}$ , i.e, the learning slows down exponentially with the number of agents. We also show that by artificially weighing the prior at each time, the learning rate can be made optimal as $k^{-1}$ . The implication is that in word-of-mouth social learning, artificially re-weighing the prior can yield the optimal learning rate.

关键词： Random variables Kalman filters Noise measurement Standards Convergence

来源：评论

学校读者我要写书评

暂无评论

Design and Applications of Low-Coherence Semiconductor Light Emitters

Design and Applications of Low-Coherence Semiconductor Light...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Boon S. Ooi Omar Alkhazragi Hang Lu Photonics Laboratory Electrical and Computer Engineering Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology (KAUST) Thuwal Kingdom of Saudi Arabia

Despite its numerous advantages, high coherence degrades the performance of many applications due to unintentional interference effects. We review the recent advances in low-coherence semiconductor light emitters and ... 详细信息

ISBN: (纸本)9798350369311

关键词： Semiconductor lasers Reviews Interference Coherence Electro-optic effects Light emitting diodes Laser applications

来源：评论

学校读者我要写书评

暂无评论

Alternating Direction Method of Multipliers-Based Parallel Optimization for Multi-Agent Collision-Free Model Predictive Control

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4176-4191页

作者： Cheng, Zilong Ma, Jun Wang, Wenxin Zhu, Zicheng de Silva, Clarence W. Lee, Tong Heng The Department of Electrical and Computer Engineering National University of Singapore Singapore119077 Singapore Guangzhou China The Division of Emerging Interdisciplinary Areas The Hong Kong University of Science and Technology Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Futian Shenzhen China The Department of Mechanical Engineering The University of British Columbia VancouverBCV6T 1Z4 Canada

This article investigates the collision-free control problem for multi-agent systems. For such multi-agent systems, it is the typical situation where conventional methods using either the usual centralized model predictive control (MPC), or even the distributed counterpart, would suffer from substantial difficulty in balancing optimality and computational efficiency. Additionally, the nonconvex characteristics that invariably arise in such collision-free control and optimization problems render it difficult to effectively derive a reliable solution (and also to thoroughly analyze the associated convergence properties). To overcome these challenging issues, this work establishes a suitably novel parallel computation framework through an innovative mathematical problem formulation;and then with this framework and formulation, a parallel algorithm based on alternating direction method of multipliers (ADMM) is presented to solve the subproblems arising from the resulting parallel structure. Furthermore, an efficient and intuitive initialization procedure is developed to accelerate the optimization process, and the optimum is thus determined with significantly improved computational efficiency. As supported by rigorous proofs, the convergence of the proposed ADMM iterations for this nonconvex optimization problem is analyzed and discussed in detail. Finally, a simulation with a group of unmanned aerial vehicles (UAVs) serves as an illustrative example here to demonstrate the effectiveness and efficiency of the proposed approach. Also, the simulation results verify significant improvements in accuracy and computational efficiency compared to other baselines, including primal quadratic mixed integer programming (PQ-MIP), nonconvex quadratic mixed integer programming (NC-MIP), and nonconvex quadratically constrained quadratic programming (NC-QCQP). © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Misbehavior Detection in the Internet of Vehicles using Machine Learning based Situation Identification 8

Misbehavior Detection in the Internet of Vehicles using Mach...

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Kelagadi, Hemantaraj M. Chandra Sekhar, Jampani Rawat, Ruchira Dhaliwal, Navdeep Singh, Swati Saravana, B. Shanthi Kle Technological University School of Electronics and Communication Engineering Karnataka Hubballi India Nri Institute of Technology Department of Computer Science and Engineering Andhra Pradesh Guntur India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun India Lovely Professional University Division of Research and Development Punjab Phagwara India Uttaranchal University Division of Research and Innovation Uttarakhand Dehradun India Adhiparasakthi College of Engineering Department of Electrical and Electronics Engineering Tamil Nadu Kalavai India

ISBN: (纸本)9798350396638

To improve communications network efficiency, situation identification is essential. The requirement for real-time scenario identification of vehicular communications is growing more pressing provided a certain vehicle movement makes vehicle interaction circumstances vibrant and that there are significant variations in signal propagation, vehicle speeds, and vehicular concentrations among possible situations. On the other hand, it has been demonstrated that cryptography methods are less effective at preventing insider attacks that originate inside the automotive communication network. A misbehaviour detection system has been found to be more effective in identifying and preventing insider attacks. This research study presents a misbehaviour detection system based on machine learning and is learned utilizing datasets produced by numerical simulations in a genuine vehicular distributed system. Vehicle communication systems may choose the proper spatial multiplexing and system integration by correctly detecting the current conditions in order to maintain an efficient and reliable operating condition. A back-propagation neural network (BPNN) is trained, and a scenario identification model is developed, using datasets that comprise channel properties acquired from channel measurements in various scenarios. Additionally, the proposed identification model's best performance-enabling model configuration technique is analysed and offered. The identification accuracy is then verified using validation information from the relevant circumstances. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

A Statistical Comparison of Heart Rate Variability Measurements Between Devices: Chest Strap Versus Finger Probe 50

A Statistical Comparison of Heart Rate Variability Measureme...

引用

50th Computing in Cardiology, CinC 2023

作者： Bagheri-Mohamadi-Pour, Mehri Sparapani, Rodney Zhang, Jun Kulinski, Jacquelyn University of Wisconsin-Milwaukee Department of Electrical Engineering and Computer Science MilwaukeeWI United States Medical College of Wisconsin Division of Biostatistics MilwaukeeWI United States Medical College of Wisconsin Division of Cardiovascular Medicine MilwaukeeWI United States

ISBN: (纸本)9798350382525

Heart rate variability (HRV) between R-R intervals results from complex interactions between respiratory activity and autonomic cardiovascular control. Measurements of HRV are strong predictors of cardiac morbidity and mortality. A finger probe is more convenient than a chest strap device so we compared the HRV measurements between the CorSense finger probe and the Polar H7 chest strap. This data was collected in our clinical study (NCT04121741) of 33 subjects (mean age 69 with standard deviation 10, 52% female) with coronary heart disease. We captured HRV in both the time-domain (root mean square of successive RR interval differences (rMSSD), standard deviation of NN intervals (SDNN), percentage of successive RR intervals that differ by more than 50 ms (PNN50)) and the frequency-domain (low-frequency power (LF Power) and high-frequency power (HF Power)). Regression analyses and the Wilcoxon signed-rank-test (WSRT) showed a closer correlation between devices for SDNN and LF Power. However, none of these metrics met the satisfactory agreement criteria. The clinical study had singing and non-singing control sessions. Due to possible discrepancies while singing, we only included non-singing control sessions. © 2023 CinC.

关键词： Diseases

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：