检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Bi, Zhangqian Wan, Yao Chu, Zhaoyang Hu, Yufei Zhang, Junyi Zhang, Hongyu Xu, Guandong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is computationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of an EMG-based system for Monitoring and Help Request

Design and Implementation of an EMG-based System for Monitor...

引用

2022 International Conference on Smart systems and Power Management, IC2SPM 2022

作者： Zeine, Carla Daou, Roy Abi Zeid Telawi, Samer Boercsoek, Josef Hayek, Ali Haidar, Gaby Abou University of Kassel Faculty of Electrical Engineering /Computer Science Department of Computer Architecture and System Programming Kassel Germany Lebanese German University Faculty of Public Health Jounieh Department of Computer Architecture and System Programming Biomedical Technologies Department Jounieh Lebanon Université la Sagesse Faculty of Engineering Furn El Chebbak Mechatronics Department Beirut Lebanon University of Applied Science Hamm-Lippstadt Department Lippstadt 2 Hardware Engineering Marker Allee 76-78 Hamm59063 Germany American University of Science and Technology Faculty of Engineering Zahle Lebanon

ISBN: (数字)9781665452915

ISBN: (纸本)9781665452915

Integrating electrophysiological signals in larger systems is getting wider due to the fact that such modalities facilitate the daily tasks of users. However, the high cost of monitoring systems (e.g., oscilloscopes) limits the testing and analysis of the acquired signal from such noisy systems (i. e., electrophysiological devices). The proposed system is a part of a larger proj ect that deals with the identification of sign language movements through the use of Muscle-computer Interfaces. On one hand, the user is able to display the signal acquired by the electrodes on an LCD screen. On the other hand, the system helps a mute patient to issue a special message to his surrounding environment that does not know the sign language to ask for help. The second feature is not unique, as it can be replaced by any other application based on the user's needs. The system was tested on several persons, and the results are promising. © 2022 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Decision Problems for Non-Affine Multi-Player systems

Hierarchical Decision Problems for Non-Affine Multi-Player S...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Lin, Danyu Xue, Shan Liu, Derong Zhao, Bo School of Automation Guangdong University of Technology Guangzhou510006 China South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Southern University of Science and Technology School of System Design and Intelligent Manufacturing Shenzhen518055 China Beijing Normal University School of Systems Science Beijing100875 China

ISBN: (纸本)9798350327182

Adaptive dynamic programming is used in this paper to solve the hierarchical decision problem for non-affine multi-player systems. A new affine system is formed by adding control dynamics to the original system. To solve the hierarchical decision problem of the original system, we modeled it as a Stackelberg game in the new system. Adaptive dynamic programming is used to approximate the value functions. The stability of the system is analyzed according to Lyapunov theory, which leads to the conclusion that both the system states and the weight errors are uniformly ultimately bounded. Finally, matlab simulation is used to verify the conclusion. © 2023 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Advancements in Wireless Networks: Transition from 5G to Beyond 2

Advancements in Wireless Networks: Transition from 5G to Bey...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Thangavel, Gunasekaran Malarvizhi, C. Banu, M. Ameena Anthonisamy, Arun Hemalatha, M. Manikandan, Raja University of Technology and Applied Sciences Department of Electronics and Communication Engineering Muscat Oman Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Chembarambakkam India NPR College of Engineering and Technology Department of Electronics and Communication Engineering Natham India Panimalar Engineering College Department of Computer Science and Business System Tamil Nadu Chennai600123 India Nandha Arts and Science College Department of Information Technology Tamil Nadu Erode638052 India K. Ramakrishnan College of Technology Department of ECE Tamil Nadu Trichy India

ISBN: (纸本)9798331534950

Earlier generations of mobile technology experienced exponential growth in mobile customers, disruptive ecosystems like Internet of Things applications, and massive channel capacity needed to connect trillions of devices. 5G networks are a vital solution. 5G aims to provide 10 Gbps to a single user, as well as quality of service, increased spectrum efficiency, ultra-reliable communication, extended device battery life, massive machine-type communication (mMTC), and a 1000-fold capacity gain. Due to the heavy traffic volume and high resource consumption of 5G applications like augmented reality (AR), virtual reality (VR), and wireless body area networks, there are major barriers to channel capacity and potential service disruptions for other users. New strategies are needed to increase spectral efficiency and channel capacity. This paper explores many major new wireless technologies that aim to increase spectral efficiency and channel capacity to meet growing user demands and improve network performance. This paper also examines these technologies' benefits and research challenges. Massive Multi-Input Multi-Output (mMIMO) technology's effectiveness and potential distinguish it for 5G and Beyond 5G (B5G) networks, offering a variety of benefits and characteristics. This article can also assist researchers who are conducting in-depth studies, as well as wireless network operators who aim to streamline the development of 5G and B5G networks. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

MeHyper: Accelerating Hypergraph Neural Networks by Exploring Implicit Dataflows

MeHyper: Accelerating Hypergraph Neural Networks by Explorin...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Wenju Zhao Pengcheng Yao Dan Chen Long Zheng Xiaofei Liao Qinggang Wang Shaobo Ma Yu Li Haifeng Liu Wenjing Xiao Yufei Sun Bing Zhu Hai Jin Jingling Xue National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computing National University of Singapore Singapore School of Computer Electronics and Information Guangxi University NanNing China School of Computer Science and Engineering University of New South Wales Sydney NSW Australia

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Hypergraph Neural Networks (HGNNs) are increasingly utilized to analyze complex inter-entity relationships. Traditional HGNN systems, based on a hyperedge-centric dataflow model, independently process aggregation tasks for hyperedges and vertices, leading to significant computational redundancy. This redundancy arises from recalculating shared information across different tasks. For the first time, we identify and harness implicit dataflows (i.e., dependencies) within HGNNs, introducing the microedge concept to effectively capture and reuse intricate shared information among aggregation tasks, thereby minimizing redundant computations. We have developed a new microedge-centric dataflow model that processes shared information as fine-grained microedge aggregation tasks. This dataflow model is supported by the Read-Process-Activate-Generate execution model, which aims to optimize parallelism among these tasks. Furthermore, our newly developed MeHyper, a microedge-centric HGNN accelerator, incorporates a decoupled pipeline for improved computational parallelism and a hierarchical feature management strategy to reduce off-chip memory accesses for large volumes of intermediate feature vectors generated. Our evaluation demonstrates that MeHyper substantially outperforms the leading CPUbased system PyG-CPU and the GPU-based system HyperGef, delivering performance improvements of $1,032.23 \times$ and $10.51 \times$, and energy efficiencies of $1,169.03 \times$ and $9.96 \times$, respectively.

关键词： Computational modeling Neural networks Redundancy Pipelines Memory management Parallel processing Vectors Energy efficiency Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Phase binarization in mutually synchronized bias field free spin-Hall nano-oscillators for reservoir computing

引用

Physical Review B 2024年第21期109卷 214425-214425页

作者： Sourabh Manna Rohit Medwal John Rex Mohan Yasuhiro Fukuma Rajdeep Singh Rawat Natural Sciences and Science Education Department of Physics Faculty of Computer Science and System Engineering Kyushu Institute of Technology Iizuka 820-8502 Japan Research Center for Neuromorphic AI hardware Kyushu Institute of Technology Kitakyushu 808-0196 Japan

Mutually coupled spin-Hall nano-oscillators (SHNO) can exhibit a binarized phase state, offering pathways to realize Ising machines and efficient neuromorphic hardware. Conventionally, phase binarization is achieved in coupled identical SHNOs via injecting an external microwave at twice the oscillator frequency in the presence of a strong biasing magnetic field. However, this technology poses potential challenges of higher energy consumption and complex circuit design. Moreover, differences in the individual characteristic frequencies of SHNOs resulting from fabrication-induced mismatch in SHNO dimensions may hinder their mutual synchronization. Addressing these challenges, we demonstrate purely dc current-driven mutual synchronization and phase binarization of two nonidentical nanoconstriction SHNOs without biasing magnetic field and microwave injection. We thoroughly investigate these phenomena and underlying mechanisms using micromagnetic simulation. We show how the localized fundamental mode of the spin wave emerging from the magnetization auto-oscillation reinforces the mutual synchronization, while the second-harmonic spin wave induces the phase binarization in the coupled SHNO pair. We further demonstrate the bias field free synchronized SHNO pair efficiently performing a reservoir computing benchmark learning task: sin- and square-wave classification, with 100% accuracy, utilizing the current-tunable phase binarization phenomenon. Our results showcase promising magnetization dynamics of coupled bias field free SHNOs for future computing applications.

关键词： Magnetic anisotropy Magnetism Magnetization dynamics Micromagnetism Spintronics Landau-Lifschitz-Gilbert equation Micromagnetic modeling

来源：评论

学校读者我要写书评

暂无评论

Adversarial AI threats on digitization of Nuclear Power Plants

Adversarial AI threats on digitization of Nuclear Power Plan...

引用

2023 Transactions of the American Nuclear Society Winter Conference and Expo, ANS 2023

作者： Gupta, Kishor Datta Talukder, Sajedul Alam, Syed Bahauddin Clark Atlanta University Computer Science Cyber Physical System Atlanta United States Southern Illinois University Computer Science CarbondaleIL United States University of Illinois at Urb Ana-Champaign Nuclear Plasma & Radiological Engineering IL United States National Center for Supercomputing Applications University of Illinois at Urbana-Champaign ChampaignIL United States

来源：评论

学校读者我要写书评

暂无评论

Streamflow Prediction in the Mekong River Basin Using Deep Neural Networks

引用

IEEE Access 2023年 11卷 97930-97943页

作者： Nguyen, Thi-Thu-Ha Vu, Duc-Quang Mai, Son T. Dang, Thanh Duc National Taiwan University Department of Bioenvironmental Systems Engineering Taipei10617 Taiwan National Central University Department of Computer Science and Information System Taoyuan320317 Taiwan Thai Nguyen University of Education Thai Nguyen250000 Viet Nam Queen's University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom Institute for Computational Science and Artificial Intelligence Van Lang University Laboratory of Environmental Sciences and Climate Change Ho Chi Minh City70000 Viet Nam Van Lang University Faculty of Environment Ho Chi Minh City70000 Viet Nam

In recent years, the Mekong River Basin (MRB), one of the largest river basins in Southeast Asia, has experienced severe impacts from extreme droughts and floods. Streamflow forecasting has become crucial for effective risk management strategies in the region. However, this task presents significant challenges due to rapid climate changes and the presence of numerous newly constructed upstream dams, which disrupt the natural flow. In this paper, we develop multiple deep learning models (incl. Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Long short-term Memory (LSTM), and Transformer) to predict streamflow with different lead time forecasts based on observed meteorological variables and climatic indices (i.e., discharge, water level, precipitation, and temperature) from 1979 to 2019. The results indicate that LSTM obtains high performance for streamflow prediction in both dry and wet seasons while Transformer is not recommended for long-term prediction, especially in the dry season. The proposed deep learning models capture well the fluctuation of river flow in the MRB during the period of high-dam development, especially LSTM (NSE ≥ 0.8). The models' performances are enhanced with the adding of temperature for short-term prediction while precipitation was the most sensitive variable for long-term one. Such proposed models are essential for government agencies to plan mitigation and adaptation strategies at different periods, which can range from days to years. © 2013 IEEE.

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

Power Consumption Dashboard Using Iot

引用

Harbin Gongcheng Daxue Xuebao/Journal of Harbin engineering University 2023年第10期44卷 327-335页

作者： Sowmiya, S. Sakthivel, P. Nithya, C. Ravi, P. RanjithKumar, M. Computer Science and Engineering Mahendra Engineering College Mahendrapuri Mallasamudhram Namakkal India Information Technology Sona College of Technology Salem India Computer Science and Business System Knowledge Institute of Technology Namakkal India Information Technology K S R Institute for Engineering and Technology Tiruchengode Namakkal India Computer Science and Business Systems Knowledge Institute of Technology Namakkal India

"Power Consumption Dash Board Using IoT" was developed using a web application. The planned system includes a home energy monitoring system and cloud service notifications. An Internet of Things (IoT) platform was implemented to monitor energy consumption data at home and send the energy consumption data to the IoT cloud. The system uses the WiFi connected to the RaspberryPiPico to measure the energy consumption of the house. Energy consumption data is collected and stored in IoT cloud services. Consumers can monitor the energy consumption of their home on a daily basis and thus control how much energy is used on a daily basis. The data collection experiment aims to determine household energy consumption. Also, the website shows data on energy consumption before and after the load is connected to the system. IoT dashboard available online that allows users to check their daily energy consumption using IoT dashboard. IoT Cloud performs event analysis based on collected energy consumption data and alerts the owner with an alert, an email recommendation and a telegram notifying the customer when the energy consumption limit is exceeded, helping to reduce excessive energy consumption. © 2023 Editorial Board of Journal of Harbin engineering. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective

How to Select Pre-Trained Code Models for Reuse? A Learning ...

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Zhangqian Bi Yao Wan Zhaoyang Chu Yufei Hu Junyi Zhang Hongyu Zhang Guandong Xu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

ISBN: (数字)9798331535100

ISBN: (纸本)9798331535117

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is compu-tationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks.

关键词： Phase change materials Analytical models Adaptation models Codes Costs Computational modeling Training data Machine learning Software Software development management

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：