检索结果-内蒙古大学图书馆

RLAlloc: A Deep Reinforcement Learning-Assisted Resource Allocation Framework for Enhanced Both I/O Throughput and QoS Performance of Multi-Streamed SSDs 23

RLAlloc: A Deep Reinforcement Learning-Assisted Resource All...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Mengquan Li Chao Wu Congming Gao Cheng Ji Kenli Li School of Computer Science and Electronic Engineering Hunan University CN Department of Electrical and Computer Engineering Northeastern University USA School of Information Xiameng University CN School of Computer Science and Engineering Nanjing University of Technology CN

ISBN: (纸本)9798350323481

Multi-streamed Solid-State Disks (SSDs) have attracted increasing adoption in modern flash storage devices. Despite their excellent promise, effective flash resource allocation is still limiting both their achievable I/O performance and practical implementation. To this end, we develop the first-of-its-kind framework dubbed RLAlloc, which for the first time demonstrates deep Reinforcement Learning-assisted resource Allocation for boosting both I/O throughput and QoS performance of multi-streamed SSDs. Extensive experiments consistently validate the effectiveness of RLAlloc, improving up to 39.9% on I/O throughput and 44.0% on QoS performance over the state-of-the-art competitors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EXPERIMENTAL CHARACTERIZATION OF SIGNAL FADES IN INDOOR LOW-POWER WIRELESS SYSTEM 57

EXPERIMENTAL CHARACTERIZATION OF SIGNAL FADES IN INDOOR LOW-...

引用

57th Annual International Telemetering Conference, ITC 2022

作者： Milic, Dejan Djordjevic, Goran T. Vasic, Bata Makal, Jaroslaw Vasic, Bane Faculty of Electronic Engineering University of Nis Nis Serbia Faculty of Electrical Engineering Bialystok University of Technology Bialystok Poland Electrical and Computer Engineering Department University of Arizona Tucson United States

We perform statistical characterization of the wireless channel between the low-power transmitter and the receiver moving along the straight path in laboratory conditions. Our aim is to process the measurement results of the signal level variations and propose a model of fading suitable for analytical analysis. In addition, we will determine the appropriate parameter values for the proposed model that describes the statistics of signal intensity with random changes. Based on the measured values, in addition to the first order statistical characteristics, we will determine the second order characteristics, such as level crossing rate and average fade duration. These values are important in estimating the probability of error and ergodic capacity, as well as in the adequate design of the interleaver and error-correction codes. © 2022 International Foundation for Telemetering. All rights reserved.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Kolmogorov-Arnold Enhanced CNN for Rotating Equipment Fault Diagnosis 21

Personalized Federated Learning with Kolmogorov-Arnold Enhan...

引用

21st International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Kulevome, Delanyo Kwame Bensah Man, Qiu Mawuli, Ernest Smith Opoku-Mensah, Edward Qilu Institute of Technology Department of Computer and Information Engineering Shandong Jinan250200 China Qilu Institute of Technology Department of Intelligent Manufacturing and Control Engineering Shandong Jinan250200 China Akenten Appiah-Menka University of Skills Training and Entrepreneurial Development Department of Electrical/Electronic Technology Education Kumasi Ghana HEC Department of Information Technologies Montréal Canada

ISBN: (纸本)9798331519254

Fault diagnosis of rotating equipment plays a crucial role in ensuring operational reliability and minimizing downtime in industrial systems. This study proposes a novel approach that integrates personalized federated learning (PFL) with a Kolmogorov-Arnold network (KAN)-enhanced convolutional neural network (CNN) to improve diagnostic accuracy across heterogeneous operational environments. The framework is designed to address variations in equipment conditions and data distributions, providing personalized models tailored to specific clients. A comprehensive evaluation is conducted using benchmark datasets, demonstrating significant improvements in fault classification accuracy, model interpretability, and training efficiency under non-IID data settings using the KAN-enhanced CNN model. This study contributes to advancing predictive maintenance practices, paving the way for resilient and intelligent industrial systems. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

High Performance 3D ITZO DGTFTs and Their Application in Wearable Pulse Sensors

High Performance 3D ITZO DGTFTs and Their Application in Wea...

引用

2024 IEEE International Electron Devices Meeting, IEDM 2024

作者： Lin, Delang Chen, Rongsheng Tseng, Man Chun Yeung, Fion Sze Yan Kwok, Hoi Sing School of Microelectronics South China University of Technology Guangzhou China State Key Laboratory of Advanced Displays and Optoelectronics Technologies Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798350365429

This work presents the development of InSnZnO (ITZO) three-dimensional (3D) channel dual-gate thin-film transistors (DGTFTs) prepared by magnetron sputtering. The employment of an n-octyltriethoxysilane protection layer, prepared via liquid-phase self-assembly, effectively mitigates plasma-induced damage to the ITZO channel layer during top gate dielectric sputtering. Moreover, the high-k ZrO2 top gate dielectric and 3D channel structure endow the ITZO DGTFTs with excellent transistor performance, high electrical stability, and flexible mechanical reliability. These attributes include a low threshold voltage of 0.2 V, a high mobility of 41.7 cm2V-1s-1, and a competitive top gate coupling coefficient of -2.24. Finally, the ultra-high top-gate voltage coupling effect allows the ITZO DGTFT-based wearable pulse sensor accurately recognizes pulse waveforms from various parts of the body, including the temples, and infers blood pressure changes. © 2024 IEEE.

关键词： Gate dielectrics

来源：评论

学校读者我要写书评

暂无评论

S&D Messenger: Exchanging Semantic and Domain Knowledge for Generic Semi-Supervised Medical Image Segmentation

arXiv

引用

arXiv 2024年

作者： Zhang, Qixiang Wang, Haonan Li, Xiaomeng The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Semi-supervised medical image segmentation (SSMIS) has emerged as a promising solution to tackle the challenges of time-consuming manual labeling in the medical field. However, in practical scenarios, there are often domain variations within the datasets, leading to derivative scenarios like semi-supervised medical domain generalization (Semi-MDG) and unsupervised medical domain adaptation (UMDA). In this paper, we aim to develop a generic framework that masters all three tasks. We notice a critical shared challenge across three scenarios: the explicit semantic knowledge for segmentation performance and rich domain knowledge for generalizability exclusively exist in the labeled set and unlabeled set respectively. Such discrepancy hinders existing methods from effectively comprehending both types of knowledge under semi-supervised settings. To tackle this challenge, we develop a Semantic & Domain Knowledge Messenger (S&D Messenger) which facilitates direct knowledge delivery between the labeled and unlabeled set, and thus allowing the model to comprehend both of them in each individual learning flow. Equipped with our S&D Messenger, a naive pseudo-labeling method can achieve huge improvement on six benchmark datasets for SSMIS (+7.5%), UMDA (+5.6%), and Semi-MDG tasks (+1.14%), compared with state-of-the-art methods designed for specific tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Low-Complexity CSI Feedback for FDD Massive MIMO Systems via Learning to Optimize

arXiv

引用

arXiv 2024年

作者： Ma, Yifan He, Hengtao Song, Shenghui Zhang, Jun Letaief, Khaled B. The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

In frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems, the growing number of base station antennas leads to prohibitive feedback overhead for downlink channel state information (CSI). To address this challenge, state-of-the-art (SOTA) fully data-driven deep learning (DL)-based CSI feedback schemes have been proposed. However, the high computational complexity and memory requirements of these methods hinder their practical deployment on resource-constrained devices like mobile phones. To solve the problem, we propose a model-driven DL-based CSI feedback approach by integrating the wisdom of compressive sensing and learning to optimize (L2O). Specifically, only a linear learnable projection is adopted at the encoder side to compress the CSI matrix, thereby significantly cutting down the user-side complexity and memory expenditure. On the other hand, the decoder incorporates two specially designed components, i.e., a learnable sparse transformation and an element-wise L2O reconstruction module. The former is developed to learn a sparse basis for CSI within the angular domain, which explores channel sparsity effectively. The latter shares the same long short term memory (LSTM) network across all elements of the optimization variable, eliminating the retraining cost when problem scale changes. Simulation results show that the proposed method achieves a comparable performance with the SOTA CSI feedback scheme but with much-reduced complexity, and enables multiple-rate feedback. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Implementation of Preprocessing in Text Summarization Techniques for Indonesian Language Documents Using the Flax T5 Approach 11

Implementation of Preprocessing in Text Summarization Techni...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Lubis, Arif Ridho Safitri, Habibi Ramdani Irvan Lubis, Muharman Al-Khowarizmi Nugroho, Okvi Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia Universitas Muhammadiyah Sumatera Utara Department of Mathematic Education Medan Indonesia Telkom University School of Industrial Engineering Bandung Indonesia Universitas Muhammadiyah Sumatera Utara Department of Information Technology Medan Indonesia Kulkas It Medan Indonesia

ISBN: (纸本)9798350305968

As information develops, many individuals or communities change their habits in obtaining information, which is usually consumed in large quantities, so that sometimes it is difficult to understand, it becomes easier to get information in summary form, so this research applies the text summarization technique to Indonesian language documents using the Flax T5 model. is the development of transformer-based google. The results of this study are the use of parameters from the Flax T5 model that can affect the performance of text summaries, evidenced by the number of epochs 20, batch size 64 producing ROUGE-1 of 0.24. the ROUGE-2 value is 0.3 and the ROUGE-L value is 0.31, while the epoch value is 60, batch size 128 makes ROUGE-1 0.35, ROUGE-2 value is 0.38 and the ROUGE-L value is 0.36. while the epoch value of 100 and the batch size value of 256 produce a ROUGE-1 value of 0.5, a ROUGE-2 value of 0.54, and a ROUGE-L value of 0.55. However, this model has limitations in text lengths of more than 150 because it will make the training time so long that it is highly recommended not to use text lengths that exceed 150 words. © 2023 IEEE.

关键词： Flax

来源：评论

学校读者我要写书评

暂无评论

Segmenting Anything in the Dark via Depth Perception

引用

IEEE Transactions on Multimedia 2025年 27卷 2975-2986页

作者： Liu, Peng Deng, Jinhong Duan, Lixin Li, Wen Lv, Fengmao University of Electronic Science and Technology of China Chengdu611731 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China UESTC Shenzhen Institute for Advanced Study Shenzhen518110 China University of Electronic Science and Technology of China Sichuan Provincial Key Laboratory for Human Disease Gene Study Center for Medical Genetics Department of Laboratory Medicine Sichuan Academy of Medical Sciences Sichuan Provincial People's Hospital Chengdu610032 China Southwest Jiaotong University Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education School of Computing and Artificial Intelligence Chengdu611756 China

Image segmentation under low-light conditions is essential in real-world applications, such as autonomous driving and video surveillance systems. The recent Segment Anything Model (SAM) exhibits strong segmentation capability in various vision applications. However, its performance could be severely degraded under low-light conditions. On the other hand, multimodal information has been exploited to help models construct more comprehensive understanding of scenes under low-light conditions by providing complementary information (e.g., depth). Therefore, in this work, we present a pioneer attempt that elevates a unimodal vision foundation model (e.g., SAM) to a multimodal one, by efficiently integrating additional depth information under low-light conditions. To achieve that, we propose a novel method called Depth Perception SAM (DPSAM) based on the SAM framework. Specifically, we design a modality encoder to extract the depth information and the Depth Perception Layers (DPLs) for mutual feature refinement between RGB and depth features. The DPLs employ the cross-modal attention mechanism to mutually query effective information from both RGB and depth for the subsequent feature refinement. Thus, DPLs can effectively leverage the complementary information from depth to enrich the RGB representations and obtain comprehensive multimodal visual representations for segmenting anything in the dark. To this end, our DPSAM maximally maintains the instinct expertise of SAM for RGB image segmentation and further leverages on the strength of depth for enhanced segmenting anything capability, especially for cases that are likely to fail with RGB only (e.g., low-light or complex textures). As demonstrated by extensive experiments on four RGBD benchmark datasets, DPSAM clearly improves the performance for the segmenting anything performance in the dark, e.g., +12.90% mIoU and +16.23% mIoU on LLRGBD and DeLiVER, respectively. © 1999-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

LLM for Everyone: Representing the Underrepresented in Large Language Models

arXiv

引用

arXiv 2024年

作者： Cahyawijaya, Samuel Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Natural language processing (NLP) has witnessed a profound impact of large language models (LLMs) that excel in a multitude of tasks. However, the limitation of LLMs in multilingual settings, particularly in underrepresented languages, remains a significant hurdle. This thesis aims to bridge the gap in NLP research and development by focusing on underrepresented languages. A comprehensive evaluation of LLMs is conducted to assess their capabilities in these languages, revealing the challenges of multilingual and multicultural generalization. Addressing the multilingual generalization gap, this thesis proposes data-and-compute-efficient methods to mitigate the disparity in LLM ability in underrepresented languages, allowing better generalization on underrepresented languages without the loss of task generalization ability. The proposed solutions cover cross-lingual continual instruction tuning, retrieval-based cross-lingual in-context learning, and in-context query alignment. Furthermore, a novel method to measure cultural values alignment between LLMs operating in different languages is proposed, ensuring cultural sensitivity and inclusivity. These contributions aim to enhance the multilingual and multicultural alignment of LLMs in underrepresented languages, ultimately advancing the NLP field toward greater equality and inclusiveness. © 2024, CC BY-NC-SA.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Filtered Orthogonal Frequency Division Multiplexed LDPC Codes for Satellite Communication in the Ka-Band

Performance Analysis of Filtered Orthogonal Frequency Divisi...

引用

AFRICON Conference

作者： Bonginkosi Gumede Emmanuel Mukubwa Nelendran Pillay Innocent E. Davidson Department of Electronic and Computer Engineering Durban University of Technology Durban South Africa Department of Electrical Electronic and Computer Engineering Cape Peninsula University of Technology Bellville

Ka-band satellite communication is attractive for current and future broadband data system designs, but the Ka-band satellite communication channel is affected by rain fade. Considering the problem of rain fade at Ka-band satellite communication, the channel and system model has been found. We present the application of Low Density Parity Check (LDPC) codes in a Ka-band satellite channel, we propose adding adaptive modulation and filtered Orthogonal Frequency Division Multiplexing (f-OFDM) to improve the performance of the system by referencing previous research work in this field. Our proposed LDPC-coded Quadrature Amplitude Modulated (QAM) f-OFDM system achieves a coding gain of 1.2 dB at a Bit Error Rate (BER) of 10 −3 in moderate rain weather when compared to LDPC- coded QAM OFDM system and achieves a gain of 2 dB at BER of 10 −3 when comparing to Turbo coded 16-QAM f-OFDM. The results further show that adaptive modulation improves the system's spectral efficiency and maintains a constant BER.

关键词：

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：