检索结果-内蒙古大学图书馆

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Tian, Meng Liu, Zhicheng Qiu, Chao Wang, Xiaofei Niyato, Dusit Leung, Victor C. M. Tianjin University College of Intelligence and Computing Tianjin China Nanyang Technological University College of Computing and Data Science Singapore Shenzhen University College of Computer Science and Software Engineering Shenzhen China The University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798350351255

Recent advances in the diffusion model mark a significant leap in AI-generated image technology while extending its application to the Internet of Things (IoT). However, deploying these models on resource-constrained edge devices presents considerable challenges, primarily due to their high computational energy demands and stringent quality requirements. In response to these challenges, we introduce a collaborative inference system tailored for green edge networks. First, we propose a multi-exit U-ViT model that achieves the balance between inference quality and processing speed by allowing adaptive selection of exit points during diffusion for efficient processing. Next, we develop a novel generative AI-assisted reinforcement learning algorithm that controls the exit selections and offloading decisions of the device to achieve maximum global gain. Furthermore, we design a novel policy network incorporating an attention-based state-embedded policy network to enhance the algorithm's ability to perceive and make decisions about the state of the environment. Experimental results demonstrate that our system achieves energy-efficient inference while ensuring the quality of the generated content. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Joint Spectrum Sensing and Spectrum Access for Defending Massive SSDF Attacks:A Novel Defense Framework

引用

Chinese Journal of Electronics 2022年第2期31卷 240-254页

作者： XU Zhenyu SUN Zhiguo GUO Lili Muhammad Zahid Hammad Chintha Tellambura College of Information and Communication Engineering Harbin Engineering University Department of Electrical and Computer Engineering University of Alberta

Multiple secondary users(SUs) perform collaborative spectrum sensing(CSS) in cognitive radio networks to improve the sensing performance. However,this system severely degrades with spectrum sensing data falsification(SSDF) attacks from a large number of malicious secondary users, i.e., massive SSDF attacks. To mitigate such attacks, we propose a joint spectrum sensing and spectrum access framework. During spectrum sensing,each SU compares the decisions of CSS and independent spectrum sensing(IndSS), and then the reliable decisions are adopted as its final decisions. Since the transmission slot is divided into several tiny slots, at the stage of spectrum access, each SU is assigned with a specific tiny time slot. In accordance with its independent final spectrum decisions, each node separately accesses the tiny time *** results verify effectiveness of the proposed algorithm.

关键词： spectrum sensing data falsification attacks multiple secondary users sensing performance cognitive radio collaborative spectrum sensing CSS telecommunication security independent final spectrum decisions joint spectrum sensing radio spectrum management independent spectrum sensing massive SSDF attacks malicious secondary users spectrum access framework signal detection

来源：评论

学校读者我要写书评

暂无评论

Automated face recognition using deep learning technique and center symmetric multivariant local binary pattern

引用

Neural computing and Applications 2025年第1期37卷 263-281页

作者： Sekhar, J.C. Josephson, P. Joel Chinnasamy, A. Maheswari, M. Sankar, S. Kalangi, Ruth Ramya Department of Computer Science and Engineering NRI Institute of Technology Andhra Pradesh Guntur India Department of Electronics and Communication Engineering Malla Reddy Engineering College Telangana Hyderabad India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vijayawada India

Researchers have recently created several deep learning strategies for various tasks, and facial recognition has made remarkable progress in employing these techniques. Face recognition is a noncontact, nonobligatory, acceptable, and harmonious biometric recognition method with a promising national and social security future. The purpose of this paper is to improve the existing face recognition algorithm, investigate extensive data-driven face recognition methods, and propose a unique automated face recognition methodology based on generative adversarial networks (GANs) and the center symmetric multivariable local binary pattern (CS-MLBP). To begin, this paper employs the center symmetric multivariant local binary pattern (CS-MLBP) algorithm to extract the texture features of the face, addressing the issue that C2DPCA (column-based two-dimensional principle component analysis) does an excellent job of removing the global characteristics of the face but struggles to process the local features of the face under large samples. The extracted texture features are combined with the international features retrieved using C2DPCA to generate a multifeatured face. The proposed method, GAN-CS-MLBP, syndicates the power of GAN with the robustness of CS-MLBP, resulting in an accurate and efficient face recognition system. Deep learning algorithms, mainly neural networks, automatically extract discriminative properties from facial images. The learned features capture low-level information and high-level meanings, permitting the model to distinguish among dissimilar persons more successfully. To assess the proposed technique’s GAN-CS-MLBP performance, extensive experiments are performed on benchmark face recognition datasets such as LFW, YTF, and CASIA-WebFace. Giving to the findings, our method exceeds state-of-the-art facial recognition systems in terms of recognition accuracy and resilience. The proposed automatic face recognition system GAN-CS-MLBP provides a solid basis for a

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Network Based Churn Prediction for Telecommunication Industry

引用

computer Systems Science & engineering 2022年第12期43卷 1255-1270页

作者： Nasebah Almufadi Ali Mustafa Qamar Department of Computer Science College of ComputerQassim UniversityBuraydahSaudi Arabia Department of Computing School of Electrical Engineering and Computer ScienceNational University of Sciences and Technology(NUST)IslamabadPakistan

Currently,mobile communication is one of the widely used means of ***,it is quite challenging for a telecommunication company to attract new *** recent concept of mobile number portability has also aggravated the problem of customer *** need to identify beforehand the customers,who could potentially churn out to the *** the telecommunication industry,such identification could be done based on call detail *** research presents an extensive experimental study based on various deep learning models,such as the 1D convolutional neural network(CNN)model along with the recurrent neural network(RNN)and deep neural network(DNN)for churn *** use the mobile telephony churn prediction dataset obtained from ***,containing the data for around 100,000 individuals,out of which 86,000 are non-churners,whereas 14,000 are churned *** imbalanced data are handled using undersampling and *** accuracy for CNN,RNN,and DNN is 91%,93%,and 96%,***,DNN got 99%for ROC.

关键词： Deep learning machine learning churn prediction convolutional neural network recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Grid-Side Current Improvement With Direct Digital Control and Capacitor Voltage Feedforward to Mitigate Distorted Grid Currents for 3Φ3W LCL Grid-Connected Inverter Under Distorted Grid Voltages

IEEE Open Journal of Power Electronics

引用

IEEE Open Journal of Power Electronics 2024年 5卷 37-49页

作者： Wu, Tsai-Fu Chan, Ching-Chih Chang, Yun-Hsiang Chiu, Jui-Yang Hung, Chien-Chih Chuang, Tzu-Hsien National Tsing Hua University Department of Electrical Engineering Hsinchu300044 Taiwan National Tsing-Hua University College of Electrical Engineering and Computer Science Hsinchu300044 Taiwan

A three-phase three-wire LCL grid-connected inverter is usually used as an interface between renewable-energy sources and grid. However, grid voltage is always distorted and results in grid-current distortion when there is no control at the filter-capacitor current. This article presents the grid-current improvement with inverter-side-current direct digital control and capacitor voltage feedforward (CVF) for the grid-connected inverter under distorted grid voltages. With the inverter-side current feedback, the simple direct digital control can cover inductance variation and determine the control laws to track inverter-side inductor current, achieving robustness. A hysteresis repetitive predictor with finite impulse response low-pass filter and compensator term is introduced to the CVF loop which can stabilize the system and compensate the distorted grid current. The virtual impedance method is adopted to confirm the stability when the filter inductances drop and control parameters vary with the inductor current. Simulated and experimental results from 12 kW inverter are used to verify the theoretical analyses and discussions. © 2020 IEEE.

关键词： Inductance

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Context Representation and Scope in Code Infilling 24

Analyzing the Impact of Context Representation and Scope in ...

引用

46th International Conference on Software engineering: Companion, ICSE-Companion 2024

作者： Heo, Jinseok Lee, Eunseok Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798400705021

Existing studies solve software engineering tasks using code infilling through LLMC. They utilize context information, which refers to data near the target code of infilling, as input prompts. Although prompts are essential for infilling the target code, current studies use them without analyzing the impact of the representation and scope of context on code infilling. In this study, we analyzed how context representation and scope affect the performance of code infilling. We used XLCost, which contains code, comments, and a function comment for various programming languages. The combination of code and a function comment for context representation yielded the best code infilling performance. Furthermore, we found that the context scope is proportional to performance. Our analysis results can be applied in various tasks that involve code infilling in the future. © 2024 IEEE computer Society. All rights reserved.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Photonic crystal nanolasers in polydimethylsiloxane thin film for sensing quantities leading to strain

引用

Photonics Research 2024年第4期12卷 720-729页

作者： Lu, Tsan-Wen Lin, Kuang-Ming Wang, Zhen-Yu Lee, Po-Tsung Department of Photonics College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan

We propose and realize a 1D photonic crystal nanocavity laser embedded in a polydimethylsiloxane (PDMS) thin film. The nanolaser in PDMS exhibits a significant optical response to structural deformation. It can be attached to object surfaces or integrated into different configurations, enabling the detection of different quantities that induce strain in the film. In experiments, this nanolaser can detect temperature variations or micrometer-scale bending degrees by attaching it to a temperature-controllable or bendable plate, respectively. Moreover, we further utilize the film as a diaphragm of a chamber to demonstrate its potential as a highly sensitive pressure gauge and chemical sensor. By adjusting the thickness of the PDMS thin film and the position of the nanolaser, we experimentally achieved a minimum detectable gas pressure variation of 0.12 kPa and a sensing dynamic range of 46 dB. We also investigate the optical response of the nanolaser to the swelling of the PDMS thin film induced by different organic solvents in experiments. The experimental wavelength shift rates over time are proportional to different chemical vapors' PDMS swelling ratios, which can be used to identify specific chemical vapors within the chamber that induce PDMS swelling. Based on the experimental results and the capability of reattaching to different objects or configurations, we believe that our PhC nanolaser demonstrated herein holds significant potential as a highly sensitive mechanical and chemical sensor. © 2024 Chinese Laser Press.

关键词： Thin films

来源：评论

学校读者我要写书评

暂无评论

Inverse Reticle Optimization with Quantum Annealing and Hybrid Solvers

引用

IEEE Access 2024年 12卷 33069-33078页

作者： Fang, Po-Hsun Chen, Yan-Syun Wu, Jhih-Sheng Yu, Peichen National Yang Ming Chiao Tung University College of Electrical and Computer Engineering Department of Photonics Hsinchu30010 Taiwan

Reticle optimization is a computationally demanding task in optical microlithography for advanced semiconductor fabrication. In this study, we explore the effectiveness of D-Wave's quantum annealing (QA) and hybrid steepest descent (SD) solvers in solving pixelated binary reticle optimization problems. We show that the energy derived from the objective function depends on annealing time and inter-sample correlation. Specifically, longer annealing times and reduced inter-sample correlations result in lower energy. Moreover, introducing efficient pausing strategies in forward annealing could reduce the QA runtime by approximately 100-fold while achieving similar results to long annealing times. Finally, reticles with increased variables lead to widespread irregular values in default sorted QA energies due to quantum chain breakages, which could potentially limit the probability of attaining the optimal solution. A hybrid approach that applies the classical SD algorithm to the QA results increases the probability of locating the global minimum solution and reduces runtime to about one-third compared to the classical SD solver. These findings facilitate our comprehension of quantum computing for accelerating computational lithography in semiconductor manufacturing. © 2013 IEEE.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

Joint Communication and Computation Resource Allocation for Emerging mmWave Multi-User 3D Video Streaming Systems

Joint Communication and Computation Resource Allocation for ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Badnava, Babak Chakareski, Jacob Hashemi, Morteza University of Kansas Department of Electrical Engineering and Computer Science United States New Jersey Institute of Technology College of Computing United States

ISBN: (纸本)9798350351255

We consider a multi-user joint rate adaptation and computation distribution problem in a millimeter wave (mmWave) virtual reality (VR) system. The VR system that we consider comprises an edge computing unit (ECU) that serves 360° videos to VR users. We formulate a multi-user quality of experience (QoE) maximization problem, in which VR users are assisted with the ECU to decode/render 360° videos. The ECU provides additional computational resources that can be used for processing video frames, at the expense of increased data volume and required bandwidth. To balance this trade-off, we leverage deep reinforcement learning (DRL) for joint rate adaptation and computational resource allocation optimization. Our proposed method, dubbed Deep VR, does not rely on any predefined assumption about the environment and relies on video playback statistics (i.e., past throughput, decoding time, transmission time, etc.), video information, and the resulting performance to adjust the video bitrate and computation distribution. We train Deep VR with real-world mmWave network traces and 360° video datasets to obtain evaluation results in terms of the average QoE, peak signal-to-noise ratio (PSNR), rebuffering time, and quality variation. Our results indicate that the Deep VR improves the users' QoE compared to state-of-the-art rate adaptation algorithm. Specifically, we show a 3.08 dB to 4.49 dB improvement in video quality in terms of PSNR, a 12.5x to 14x reduction in rebuffering time, and a 3.07 dB to 3.96 dB improvement in quality variation. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

RIS with Nanomaterials for FutureG Applications 18

RIS with Nanomaterials for FutureG Applications

引用

18th IEEE Nanotechnology Materials and Devices Conference, NMDC 2023

作者： Al-Duhni, Ghaleb Saleh Ghaleb Valera, Tatiana Pulugurtha, Markondeya Raj Volakis, John L. Venkatakrishnan, Satheesh B. Florida International University College of Engineering and Computing Department of Electrical and Computer Engineering MiamiFL33185 United States

ISBN: (纸本)9798350335460

Reconfigurable Intelligent Surfaces (RIS) also known as Intelligent Reflecting Surfaces (IRS) often depend upon metasurfaces. These typically comprise of a large array of passive elements that can be fabricated to modulate reflection amplitude or phase or both to create tunable functions that are independently controlled. Various RIS are developed to improve spectral efficiency through ultrawideband antennas, enhanced beamforming with higher gain and bandwidth, spatial reconfigurability, selective and adjustable isolation, and other desired features. Several approaches to tune the RIS performance are being explored. This paper reviews the primary approaches and the benefit of emerging tunable nanomaterials in achieving such RIS functions. Designs with 1-bit and 6-bit phase shifters are discussed in the first part. Various opportunities with nanomaterials and nanodevices to induce such phase shifts are discussed in the last part of the paper. © 2023 IEEE.

关键词： Nanostructured materials

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：