检索结果-内蒙古大学图书馆

Proceedings of the 2025 ACM/SIGDA International Symposium on Field programmable Gate Arrays

作者： Ling-Chi Yang Chi-Jui Chen Trung Le Bo-Cheng Lai Scott Hauck Shih-Chieh Hsu Institute of Electronics National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of College of Electrical and Computer Engineering in National Yang Ming Chiao Tung University Hsinchu Taiwan Electrical and Computer Engineering in University of Washington Seattle USA Electrical and Computer Engineering University of Washington Seattle USA Physics University of Washington Seattle USA

ISBN: (纸本)9798400713965

FPGAs are a compelling substrate for supporting machine learning inference. Tools such as High-Level Synthesis and hls4ml can shorten the development cycle for deploying ML algorithms on FPGAs, but can struggle to handle the large on-chip storage needed for many of these models. In particular the high BRAM usage found in many of these flows can cause Place & Route failures during synthesis. In this paper we propose using a Simulated-Annealing based flow to perform BRAM-aware quantization. This approach trades off inference accuracy with BRAM usage, to provide a high-quality inference engine that still meets on-chip resource constraints. We demonstrate this flow for Transformer-based machine learning algorithms, which include Flash Attention in a Stream-based Dataflow architecture. Our system imposes minimal accuracy drops, yet can reduce BRAM usage by 20%-50%, and improve power efficiency by 264%-812% compared to existing Transformer-based accelerators on FPGAs

关键词： efficient transformer

来源：评论

学校读者我要写书评

暂无评论

Dynamic Volumetric Video Coding with Tensor Decomposition

Dynamic Volumetric Video Coding with Tensor Decomposition

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Ju-Yeon Shin Yeoneui Kim Je-Won Kang Gun Bang Dept. of Electronic and Electrical Engineering and Graduate Program in Smart Factory Ewha Womans University Seoul South Korea Electronics and Telecommunications Research Institute Daejeon South Korea

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

Recently, volumetric video coding based on neural radiance fields has gained significant attention for storing and transmitting three-dimensional (3D) scenes captured from multi-view video. Because the neural networks are trained to produce novel view synthesis of surrounding 3D scenes, compressing the model and then rendering the colors and geometry through the decompressed model can be utilized as a 3D video coding system. However, although this approach provides superior performance compared to conventional 3D video coding standards using depth video, challenges remain in reducing overall model sizes to improve coding efficiency. In this paper, we propose a novel dynamic volumetric video coding technique that employs a Group of Volume (GoV) to divide multi-view video sequences into smaller chunks, addressing complex temporal dynamics. Our method uses volumetric video features represented with 3D spatial and temporal tensor matrices and vectors and encodes them with the GoVs. The tensors are compressed by existing 2D video codec, allowing for fast rendering and easing deployment. Experimental results validate that our method not only reduces memory footprint but also maintains high-quality rendering as compared to state-of-the-art studies.

关键词： Video coding Solid modeling Three-dimensional displays Image coding Tensors Visual communication Video sequences Rendering (computer graphics) Video codecs Standards

来源：评论

学校读者我要写书评

暂无评论

Microwave-Based Complementary Split-Ring Resonator for the Detection of Variations in Aqueous Media

Microwave-Based Complementary Split-Ring Resonator for the D...

引用

Microelectronics Technology and Devices (SBMicro)

作者： Reinaldo Velásquez Diego Tami Gilberto Medeiros-Ribeiro Cássio G. Rego Jhonattan C. Ramirez Graduate Program in Electrical Engineering UFMG Brazil Institute of Technological Sciences UNIFEI Brazil Department of Computer Science UFMG Brazil Department of Electronics Engineering UFMG Brazil

In this paper, we demonstrated a highly sensitive microwave-based resonator sensor capable of detecting variations in an aqueous medium of up to 0.94 mg/dL. In the presented device, the intrinsic resonant response (resonant amplitude, resonant frequency, and quality factor) is capacitively perturbed in reaction to the sample presence. To achieve higher sensitivity, the sample under testing generally is placed on the resonator surface, where the electric field is highly concentrated at the operating frequency. Thus, demonstrating excellent results in terms of sensitivity and reproducibility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Modulation Format Identification and Optical Performance Monitoring Techniques Implementation

Machine Learning-based Modulation Format Identification and ...

引用

2021 Advanced Communication Technologies and Signal Processing, ACTS 2021

作者： Devi, Pukhrambam Puspa Vincent Simatupang, Joni Welman National Institute of Technology Silchar Department of Electronics and Communication Engineering Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung40132 Indonesia President University Study Program of Electrical Engineering Bekasi17530 Indonesia

ISBN: (纸本)9781665423373

In this paper, machine learning-based techniques are used to solve and analyze the modulation format recognition problem. The combination of intelligent software and high-performance hardware provides a large scope for innovation in optical networking. Machine learning algorithms can use a large amount of data available from the network monitors to learn and make the network more robust. This is a problem in optical communication that consists of defining the type of digital modulation process in which an electrical signal should be sent. A dataset to represent realistic transmission behaviors was generated using a simulator based on a Gaussian noise model. A multi-layer perceptron was used and tested with different architectures to show that a high level of accuracy is achievable with machine learning. An analysis of the input features was made by using the select K best features method. Finally, an attempt to visualize the data in 2-dimension was made using the Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (t-SNE) methods to reduce the dimensionality of the input features and see their relationships. © 2021 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Dual-UNet: An End-to-End Deep Learning Framework for the Automatic Chronic Diabetic Wound Segmentation

Dual-UNet: An End-to-End Deep Learning Framework for the Aut...

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Mustafa Alhababi Gregory Auner Hafiz Malik Lubna Alazzawi Muteb Aljasem Electrical and Computer Engineering Wayne State University Detroit MI USA Department of Smart Sensors and Integrated Microsystems Program Wayne State University Detroit MI USA Electrical and Computer Engineering University of Michigan-Dearborn Dearborn MI USA Electronics and Computer Engineering & Robotics Engineering Bowling Green State University Bowling Green OH USA

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

Foot ulcers are one of the chronic wounds commonly occurring in diabetic patients and are associated with a high risk of major or minor amputations. Evaluation and measurement of such wounds are done manually by experts to assess the wound healing and suggest further treatment. Manual assessment methods can cause infections at times and are less feasible in the existence of pandemic situations. The development of artificial intelligence has brought a revolution in many domains of medical imaging. Deep learning-based computer-aided approaches can be applied to assist clinicians in assessing and monitoring chronic wounds. Wound segmentation helps to measure wound area which is useful for assessing its healing progress. In this research work, a deep learning-based segmentation method, namely Dual-UNet is presented for precisely segmenting the diabetic foot ulcers images. The foot ulcer images are passed to Dual-UNet to generate the mask image having the segmented wound area. We proposed two modified UNets each having a customized encoder and decoder with skip connections, atrous spatial pyramid pooling (ASPP) block, and output block to improve the segmentation results. We assessed our framework by performing experimentation on two benchmark datasets, named the foot ulcer segmentation (FUSeg) challenge and the AZH segmentation dataset. Additionally, we have also assessed our Dual-UNet for cross-corpora validation to demonstrate the generalization capability of the proposed approach. The qualitative and quantitative results highlight the accuracy and effectiveness of the Dual-UN et framework for segmenting chronic diabetic wounds. Future research should focus on the development of large and diverse wound datasets and improving the results for cross-corpora evaluation.

关键词： Deep learning Image segmentation Pandemics Computational modeling Manuals Wounds Diabetes Decoding Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Effect of Laying and Bonding Parameters of High-Voltage Underground Cables on Thermal and electrical Performances by Multiphysics Fem Analysis

SSRN

引用

SSRN 2023年

作者： Demirol, Yunus Berat Kalenderli, Özcan Istanbul Technical University Graduate School of Electrical Engineering Program ITU Ayazaga Maslak Istanbul34469 Turkey Istanbul Technical University Faculty of Electrical and Electronics Engineering ITU Ayazaga Maslak Istanbul34469 Turkey

In high-voltage underground cable systems, current carrying capacity and power losses vary according to the screen bonding type, the phase sequence, the distance between the cables, and the number of parallel systems. In this study, electrical and thermal analyses of a system consisting of two parallel cables were carried out according to different design parameters, and the performances were evaluated. Trefoil and flat layouts were used in the analyzed systems. In addition, the structure of the single-side and solidly bonded systems was also examined. While carrying out the investigations, the variation of the distance between the cables according to three different parameters was also discussed. In total, 56 different scenarios were created, and the systems' performances were examined. Screen currents, screen voltages, cable temperatures, and power losses were considered while conducting the investigations. In this context, coupled electrical and thermal calculations were performed in the Ansys electronics Suite finite element software. Additionally, the study utilized the CymCap program to verify the finite element model created, with analytical analyses conducted in accordance with IEC 60287 standards. The significance of these calculations cannot be overstated, as the analysis results demonstrate the direct impact of various design parameters on the system's overall performance. © 2023, The Authors. All rights reserved.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Robust Nonlinear $\mathcal{W}_{\infty}$ Optimal Control for Input Nonaffine Systems

Robust Nonlinear $\mathcal{W}_{\infty}$ Optimal Control for ...

引用

European Control Conference (ECC)

作者： Daniel N. Cardoso Marco H. Terra Guilherme V. Raffo Graduate Program in Electrical Engineering Federal University of Minas Gerais Belo Horizonte MG Brazil Department of Electrical and Computer Engineering University of São Paulo São Carlos SP Brazil Department of Electronics Engineering Federal University of Minas Gerais (UFMG) Belo Horizonte MG Brazil

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

We propose a novel robust nonlinear $\mathcal{W}_{\infty}$ optimal control method for dynamical systems with nonaffine control inputs. The nonlinear $\mathcal{W}_{\infty}$ control formulation extends the classic nonlinear $\mathcal{H}_{\infty}$ one, considering a weighted Sobolev norm of the cost variable. This approach assumes that the cost variable belongs to the weighted Sobolev space $\mathcal{W}_{m,p,\mathbf{\Gamma}}$ , ensuring continuity and differentiability up to degree $m$ in a certain domain $\Omega$ . Consequently, in addition to the well-known features provided by the $\mathcal{H}_{\infty}$ approach in terms of disturbance attenuation, the closed-loop system benefits from the enhanced transient performance. Here, the robust nonlinear $\mathcal{W}_{\infty}$ optimal control problem is formulated via dynamic programming for increased-order systems, and a particular solution is proposed to the resulting Hamilton-Jacobi equation, along with the corresponding stability analysis. To validate the proposed method and its versatility, we provide numerical results for the control of a quadrotor. Additionally, leveraging the inherent $\mathcal{L}_{2}$ -gain properties of our approach, we demonstrate that the resulting controller can achieve trajectory tracking with guaranteed asymptotic stability for the whole closed-loop system.

关键词： Asymptotic stability Visualization Costs Trajectory tracking Optimal control Stability analysis Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Multi-ONU Customers Access Network using Spectrum Slicing and Duplication Techniques 5

Performance Evaluation of Multi-ONU Customers Access Network...

引用

5th International Conference on Emerging electrical Energy, electronics and Computing Technologies, ICE4CT 2024

作者： Rahman, Juwairiyyah Abdul Mugunthan, Sivaguru A.L. Hassan, Hasliza Abu Muslim, Norliana Ab-Rahman, Mohammad Syuhaimi Department of Electrical Engineering Faculty of Engineering and Life Sciences Universiti Selangor Selangor Bestari Jaya45600 Malaysia Department of Computer and Communication Technology Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Perak Kampar31900 Malaysia Department of Electrical Electronics and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Malaysia Electrical and Computer Engineering Program Faculty of Engineering Sohar University PC:311 Sohar Oman

This study aims to increase the number of access users by limiting the sample size to 30 users while ensuring that every Optical Network Unit (ONU) receives data from the Optical Line Terminal (OLT). The proposed solution allows for the determination of power requirements at each ONU based on bus-star topologies, facilitating an increase in user capacity. The power received by each ONU is a critical parameter that system designers must consider when planning the implementation of Fiber to the Home (FTTH), as it impacts the output data in terms of Bit Error Rate (BER) and Signal Quality Factor (QF) for each user. Various parameters were evaluated to ensure that the enhanced network improves scalability while adhering to standard specifications. These parameters included the Q-factor, BER, eye diagram, user count, and received power. The study employed slicing and duplication techniques, utilizing Arrayed Waveguide Grating (AWG) for signal duplication and Wavelength Division Multiplexing for signal slicing. The simulations were conducted using a transmitter operating at a frequency of 1491 nm with a power output of 0 dBm, utilizing the latest version of OptiSystem 20 software. The results highlighted the system's capability to support a total of 73,728 users, meeting stringent performance criteria. Specifically, the system achieved a Q-factor greater than 6, indicating high signal quality, and a bit error rate (BER) lower than 1 × 10-9, ensuring reliable data transmission. For the sampled 30 users, the average Q factor was 8.1527, and the average BER was 5.3648 × 10^-11, with an output power level of -54.278 dBm. Despite an increase in users, the quality of the data supplied to clients remained unchanged. These outcomes underscore the robustness and efficiency of the design in delivering high-capacity, error-resilient optical communication. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Q factor measurement

来源：评论

学校读者我要写书评

暂无评论

Low-Resolution Face Recognition for CCTV and Edge-Powered Smart Attendance Systems

Low-Resolution Face Recognition for CCTV and Edge-Powered Sm...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Nico Surantha Edward Yose Sani Muhamad Isa Department of Electrical Electronics and Communication Engineering Faculty of Science and Engineering Tokyo City University Tokyo Japan Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Attendance systems have become more modern, and one of the biometric systems without physical contact is face recognition. However, many face-based attendance systems still carry out attendance individually and cannot detect multiple faces simultaneously. In addition, capturing facial data in real-time is still a challenge because the relatively large distance between the camera and the individual reduces the ability to recognize faces. The general solution is to use super-resolution to generate better-quality faces while maintaining the main facial recognition features. One technique still being researched is super-resolution generative adversarial networks (SRGAN). SRGAN can enlarge the resolution of captured images and maintain image quality sufficient for face recognition. The attendance system can be easily integrated into edge devices such as the Jetson Nano. This paper proposes automatic and effective attendance systems with the super-resolution technique to detect and recognize faces in low-resolution input. The experimental results show that using face data capture with a resolution of 40 × 40 pixels and a four-fold magnification results in a resolution of 160 × 160 pixels. Combining Face SRGAN with FaceNet architecture as the basis of face recognition can achieve an accuracy rate of 78.19% and an F1-Score of 81.13% with an average processing time of 1.61 seconds per frame on a PC and 14.55 seconds per frame on a Jetson Nano at an average of face recognition per frame of as many as up to 8 faces simultaneously.

关键词： Support vector machines Image quality Accuracy Face recognition Image edge detection Superresolution Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Sleep Monitoring Systems based on Edge Computing and Microservices Caching

Sleep Monitoring Systems based on Edge Computing and Microse...

引用

Artificial Intelligence of Things (AIoT), IEEE Annual Congress on

作者： Nico Surantha David Jayaatmaja Sani Muhamad Isa Faculty of Science and Engineering Department of Electrical Electronics and Communication Engineering Tokyo City University Tokyo Japan Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350392296

ISBN: (纸本)9798350392302

The rapid development of Internet of Things (IoT) technology has enabled the widespread deployment of health monitoring systems. Traditionally, the health monitoring system has been limited by centralized processing and storage in the cloud, leading to latency issues and potential data loss. This paper introduces a smart sleep monitoring system based on edge computing, utilizing microservices architecture and caching techniques. The proposed system employs edge computing to enable data processing closer to the source, reducing latency and improving real-time monitoring capabilities. Caching is employed to reduce database load and optimize random access memory (RAM) usage. This research addresses latency and response time challenges on IoT health monitoring platforms in environments with poor network quality while optimizing database load and resource usage on Jetson Nano as the edge computing device. Using Electrocardiogram (ECG) data as input, the proposed system yields impressive performance metrics. The research results indicate that the proposed system can increase throughput by 26.92 KB/s, reduce response time by 18.8 ms, and decrease latency by 20.86 ms compared to the previous work. Message Queuing Telemetry Transport (MQTT) integration reduces CPU usage by approximately 40% and RAM usage by about 81.24%.

关键词： Cloud computing Databases Random access memory Microservice architectures Real-time systems Nanoscale devices 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：