检索结果-内蒙古大学图书馆

6th IEEE Symposium on Future Telecommunication Technologies, SOFTT 2022

作者： Liong, H.J. Chiong, C.W.R. Gopal, Lenin Juwono, Filbert H. Curtin University Malaysia Department of Electrical and Computer Engineering Miri Sarawak98009 Malaysia University of Southampton Malaysia Eko Galleria Department of Electrical and Electronic Engineering Nusajaya Johor79100 Malaysia University of Southampton Malaysia Eko Galleria Computer Science Program Nusajaya Johor79100 Malaysia

ISBN: (纸本)9781665455978

Intelligent reflecting surface (IRS) has recently stimulated an upsurge of research interest due to its capability of enhancing the spectral and energy efficiencies for future sixth generation (6G) wireless communication systems. This motivates the integration of IRS into simultaneous wireless information and power transfer (SWIPT) systems to improve the performance of energy harvesting and information de-coding. To unleash the full potential of IRS and achieve high sum-rate, the optimal joint transmitter precoding and reflective beamforming design is crucial yet challenging to solve. The issue has not been well investigated and the solution remains elusive. Hence, this research aims to jointly optimize the transmitter precoding and reflective beamforming matrices for IRS-Assisted multi-user multiple-input multiple-output (MIMO) SWIPT systems under quality of service (QoS) constraints. Simulation results demonstrate the effectiveness of IRS in enhancing the system performance. © 2022 IEEE.

关键词： Beamforming

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

The use of long short-term memory models to estimate soybean pricing: a regional climate data evaluation from Brazil

引用

IEEE Access 2025年 13卷 101869-101884页

作者： Oliva, Jefferson Tales Martelli, Otavio Pigozzo Barbosa, Marco Antonio De Castro Molin, Viviane Dal Casanova, Dalcimar Teixeira, Marcelo Federal University of Technology-Paraná Graduate Program in Electrical and Computer Engineering Pato Branco Brazil Federal University of Technology-Paraná Department of Academic Informatics Pato Branco Brazil Federal University of Technology-Paraná Graduate Program in Production and Systems Engineering Pato Branco Brazil

This work uses machine learning methods to analyze the influence of the Brazilian climate on international soybean price variability. For this purpose, climatic data, historical series of the extended national consumer price index, dollar price historical series, soybean harvest historical series, and international soybean price historical series are collected from different data sources. The data is then preprocessed and grouped by state. Afterward, data from the five most productive Brazilian states, Mato Grosso (MT), Mato Grosso do Sul (MS), Goiás (GO), Paraná (PR), and Rio Grande do Sul (RS), which together correspond to 74.9% of total production, are chosen. Then, predictive models were built using the long short-term memory (LSTM) method, which is applied to each state dataset considering two different settings: with and without climatic data. Thus, two models were built for each Brazilian state, totaling ten predictors. These models are evaluated using 10-fold sequential split cross-validation, whose predictive results are used for performance comparison through statistical hypothesis testing. In the experimental evaluation, when trained with climatic data, the PR model achieved the lowest average values of root mean squared error (RMSE) and mean absolute error (MAE), which are 20.90 and 16.72, respectively. Regarding predictors trained without climate data, the RS and PR obtained the lowest averaged values of RMSE (20.84) and MAE (16.81), respectively. After performing statistical hypothesis tests, no significant differences were found between the models, stating, with certainty 95%, that the Brazilian climatic data did not influence soybean prices in our study. © 2013 IEEE.

关键词： Brazilian Climatic Data Long-Short Term Memory Machine Learning Soybean Time Series

来源：评论

学校读者我要写书评

暂无评论

Strategies for Enhancing Static Object Detection Range in Autonomous Vehicles Using Monocular Camera Vision

Strategies for Enhancing Static Object Detection Range in Au...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Xingyou Li Hyoungrae Kim Hakil Kim Department of Electrical and Computer Engineering Inha University Incheon South Korea Department of Program in Future Vehicle Engineering Inha University Incheon South Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

The performance of object detection models for autonomous driving is increasingly advancing. However, to recognize static traffic targets such as traffic light recognition and traffic sign recognition, the detectable distance in images plays a crucial role in the planning strategies and performance of recognition algorithms for autonomous driving systems. This study analyzes the detection performance and detection range of traffic lights by a monocular camera on an autonomous driving vehicle. The detection model used is the YOLOv7-x model, with the original images segmented to 1x, 1/2x, and 1/3x of the model input size. The distances are obtained through high-precision maps and vehicle-mounted GPS/RTK. The results of this study indicate the scalability of the detection distance of a monocular camera’s object detection in an autonomous driving environment using a single model. It further demonstrates a proportional relationship between the detection distance and the model input size. It confirms the scalability of detection distances with cameras of different fields of view using a single model.

关键词： Image segmentation Image recognition Target recognition Scalability Object detection Cameras Market research Image restoration Planning Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORKS 10

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORK...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering AIIS ASRI INMC ISRC NSI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge

引用

IEEE Transactions on Affective Computing 2023年第3期14卷 1857-1875页

作者： Xie, Hong-Xia Lo, Ling Shuai, Hong-Han Cheng, Wen-Huang National Yang Ming Chiao Tung Univresity Institute of Electronics Hsinchu300093 Taiwan National Yang Ming Chiao Tung Univresity Department of Electrical and Computer Engineering Hsinchu300093 Taiwan National Chung Hsing University Artificial Intelligence and Data Science Program Taichung40227 Taiwan

Facial micro-expressions indicate brief and subtle facial movements that appear during emotional communication. In comparison to macro-expressions, micro-expressions are more challenging to be analyzed due to the short span of time and the fine-grained changes. In recent years, micro-expression recognition (MER) has drawn much attention because it can benefit a wide range of applications, e.g., police interrogation, clinical diagnosis, depression analysis, and business negotiation. In this survey, we offer a fresh overview to discuss new research directions and challenges these days for MER tasks. For example, we review MER approaches from three novel aspects: macro-to-micro adaptation, recognition based on key apex frames, and recognition based on facial action units. Moreover, to mitigate the problem of limited and biased ME data, synthetic data generation is surveyed for the diversity enrichment of micro-expression data. Since micro-expression spotting can boost micro-expression analysis, the state-of-the-art spotting works are also introduced in this paper. At last, we discuss the challenges in MER research and provide potential solutions as well as possible directions for further investigation. © 2010-2012 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Enhancing Local Area Power Stability: Integrative Oscillation Damping with PV Systems and BESS

Enhancing Local Area Power Stability: Integrative Oscillatio...

引用

Technology and Policy in Energy and Electric Power (ICT-PEP), International Conference on

作者： Ilham Akbar Ariesa Budi Zakaria Eduard Muljadi Graduate Program PLN-ITB PLN Corporate University Auburn USA Electrical and Computer Engineering Auburn University Auburn USA

ISBN: (数字)9798331518646

ISBN: (纸本)9798331518653

This research delves into enhancing local area power stability by integrating battery energy storage systems (BESS) with photovoltaic (PV) systems to address and accelerate the damping of post-fault oscillations following short-circuit disturbances within power grids incorporating variable renewable energy sources. Focused on implementing a power oscillation damping (POD) mechanism within PV plants, this study aims to mitigate post-fault oscillations effectively within a specified timeframe. The proposed POD within the PV plant is strategically designed to augment the grid's resilience by supplying additional active and reactive power in response to system demands post-disturbance. The integration of a 25 MW BESS has demonstrated a significant enhancement in the system's recovery speed, reducing oscillation duration from 60 seconds to 45 seconds. Moreover, a configuration with double PV systems and a 50 MW BESS further reduced the oscillation duration to 42 seconds. Utilizing PSCAD software, this study presents an innovative approach to visualize the system's behavior post-short-circuit disturbances, confirming the efficacy of BESS integration in improving system stability and reliability. These results pave the way for further exploration of optimal BESS sizing and placement strategies to maximize grid resilience.

关键词： Damping Reactive power Battery energy storage system Simulation Power system stability Stability analysis Circuit stability Oscillators Frequency control Resilience

来源：评论

学校读者我要写书评

暂无评论

MAZENET: AN ACCURATE, FAST, & SCALABLE DEEP LEARNING SOLUTION FOR STEINER MINIMUM TREES

arXiv

引用

arXiv 2024年

作者： Ramos, Gabriel Díaz Arikan, Toros Baraniuk, Richard G. Rice University United States Department of Electrical and Computer Engineering Smalley-Curl Institute Applied Physics Program United States

The Obstacle Avoiding Rectilinear Steiner Minimum Tree (OARSMT) problem, which seeks the shortest interconnection of a given number of terminals in a rectilinear plane while avoiding obstacles, is a critical task in integrated circuit design, network optimization, and robot path planning. Since OARSMT is NP-hard, exact algorithms scale poorly with the number of terminals, and so practical solvers sacrifice accuracy for large problems. We propose and study MazeNet, a deep learning-based method that learns to solve the OARSMT from data. MazeNet re-frames OARSMT as a maze-solving task that can be addresssed with a recurrent convolutional neural network (RCNN). A key hallmark of MazeNet is its scalability: we only need to train the RCNN blocks on mazes with a small number of terminals;mazes with a larger number of terminals can be solved simply by replicating the same pre-trained blocks to create a larger network. Across a wide range of experiments, MazeNet achieves perfect OARSMT-solving accuracy, with significantly reduced runtime compared to classical exact algorithms, and with the ability to handle larger numbers of terminals than state-of-the-art approximate algorithms. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing 3D Clothing Models for VR: A Deep Learning Approach to Triangle Count Reduction

Optimizing 3D Clothing Models for VR: A Deep Learning Approa...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Surasachai Doungtap Varinya Phanichraksaphong Jenq-Haur Wang International Graduate Program of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

This study presents a deep learning framework optimizing 3D clothing models for VR, using a CNN to significantly reduce the triangle count of models from DeepFashion3D and CAP-UDF datasets. Achieving a balance between efficiency and detail, it cuts triangle count from over 160,000 to below 4,000, maintaining high DPI. The approach automates optimization, promising scalability and efficiency in VR fashion, setting a foundation for future 3D content development, enhancing virtual garment realism and interactivity.

关键词： Deep learning Solid modeling Three-dimensional displays Scalability Clothing Optimization Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

High Rectification, Low Leakage p-Si/n-AlN Heterojunction PN Diode

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2025年

作者： Lu, Yi Zhou, Jie Gong, Jiarui Liu, Yang Cao, Haicheng Nong, Mingtao Liu, Zhiyuan Alam, Md.Tahmidul Gupta, Chirag Li, Xiaohang Ma, Zhenqiang University of Wisconsin-Madison Department of Electrical and Computer Engineering MadisonWI53706 United States CEMSE Division Advanced Semiconductor Laboratory Electrical and Computer Engineering Program Thuwal23955-6900 Saudi Arabia

Ultrawide bandgap AlN is a highly attractive material for power and radio frequency electronics. Unipolar n-AlN Schottky barrier diodes have demonstrated their strengths, whereas further development of AlN-based bipolar devices is desired but lacked. In this letter, we report single-crystalline p-Si/n-AlN p-n diodes (PNDs) with superior performance, accomplished by grafting a p-type Si nanomembrane onto an n-AlN film. Improved Ohmic contact directly on n-AlN was obtained through high temperature annealing at 1100 °C with contact resistivity of 4.9×10-3 Ω. cm2. The PNDs exhibited remarkable uniformity across the wafer, excellent rectifying characteristics with a high ratio of ~3×107 at ±10 V, low leakage current density of ~6.25×10-9 A/cm2 at -10 V, and hysteresis-free operation from -10 V to 30 V. Furthermore, the devices demonstrated superior thermal stability, with the on-resistance decreasing from 15.8 to 0.33 Ω. cm2 as temperature increased from room temperature to 100 °C, revealing an activation energy of ~425 meV for deep donor state in AlN. No destructive breakdown of the devices was observed up to –894 V. These results highlight the Si/AlN PNDs’ potential for development of AlN-based electronic devices. © 1980-2012 IEEE.

关键词： Heterojunctions

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：