检索结果-内蒙古大学图书馆

15th CCF Conference on computer Supported Cooperative Work and Social Computing, Chinese CSCW 2020

作者： Xie, Yi Wang, Shaoqing Pan, Wei Tang, Huaibin Sun, Yuqing School of Software Shandong University Jinan China School of Computer Science and Technology Shandong University Jinan China School of Microelectronics Shandong University Jinan China Engineering Research Center of Digital Media Technology Shandong University Jinan China

ISBN: (纸本)9789811625398

It is meaningful for researchers to find the interested and high quality new papers. We propose the Joint Text and Influence Embedding recommendation model (JTIE) to consider both the paper quality and the content correlation. We train a paper embedding based on its core elements: contents, authors and publication venues. The quality of a new paper is evaluated based on the author authority and the venue reputation. The citation relationships between papers are considered asymmetric such that they can reflect the user’s consideration on the intrinsic influence of a paper. We learn user interests by one’s historical references or a set of query keywords. Finally, papers are recommended according to the relatedness between user interests and paper embeddings. We perform experiments against three real-world datasets. The results show that our model outperforms baseline methods on both the personalized recommendation and the query keywords based retrieval. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Hybrid Decision Based Multi-Agent Deep Reinforcement learning for Task Offloading in Collaborative Edge-Cloud Computing

Hybrid Decision Based Multi-Agent Deep Reinforcement learnin...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Juan Chen Zongling Wu Lei Wu Yunni Xia Yang Wang Ling Xiong Canghong Shi School of Computer and Software Engineering Xihua University Chengdu China School of Information Science and Technology Southwest Jiaotong University Chengdu China School of Mathematical Sciences University of Electronic Science and Technology of China Chengdu China College of Computer Science Chongqing University Chongqing China

To support computing-intensive and latency-sensitive Internet-of-Things (IoT) applications, we establish a three-layer collaborative edge-cloud computing network, in which multiple IoT devices, edge servers and cloud servers are allocated at IoT layer, edge layer and cloud layer, ***, it is still challenging to satisfy the service requests with inevitable resource competition among task offloading. To solve the joint computation offloading and resource allocation problem, we formulate it as a multi-agent Markov decision process (MAMDP), where action space of each agent contains discrete-continuous hybrid decision. Firstly, we relax the discrete action to a continuous set by developing a probabilistic method. Then, by taking advantage of a continuous action based centralized training and distributed execution strategy, a cooperative multi-agent deep reinforcement learning (MADRL) based framework with each IoT device acts as an agent is established. The objective function is to minimize the total system cost in terms of the energy consumption of IoT device and the renting charge of edge/cloud servers. The simulation results demonstrate the advantageous of the proposed MADRL over the three state-of-the-art DRL based agents in reducing the system cost.

关键词： Costs Simulation Collaboration Reinforcement learning Probabilistic logic Internet of Things Servers

来源：评论

学校读者我要写书评

暂无评论

DERLight: A Deep Reinforcement Learning Traffic Light Control Algorithm with Dual Experience Replay

引用

Journal of Internet Technology 2024年第1期25卷 79-86页

作者： Yang, Zhichao Kong, Yan Hsia, Chih-Hsien School of Computer and Software Nanjing University of Information Science and Technology China Department of Computer Science and Information Engineering National Ilan University Taiwan Department of Business Administration Chaoyang University of Technology Taiwan

In recent years, with the increasingly severe traffic environment, most cities are facing various traffic congestion problems, and the demand for intelligent regulation of traffic signals is also increasing. In this study, we propose a new intelligent traffic light control algorithm, dual experience replay light (DERLight), which innovatively and efficiently designs a dual experience replay training mechanism based on the classic deep Q network (DQN) framework and considers the dynamic epoch function. As results show that compared with some state-of-the-art algorithms, DERLight can shorten the average travel time of vehicles, increase the throughput at intersections, and also speed up the convergence of the network. In addition, the design of this algorithm framework is not only limited to the field of intelligent transportation, but also has transferability for some other fields. © 2024 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Long Short Term Memory (LSTM)-based Cuffless Continuous Blood Pressure Monitoring

Long Short Term Memory (LSTM)-based Cuffless Continuous Bloo...

引用

International Conference on VLSI Design

作者： Vijay Kumar Goldy Kolin Paul Mahesh Chowdhary Amar Nath and Shashi Khosla School of Information Technology Indian Institute of Technology Delhi India Department of Computer Science and Engineering Indian Institute of Technology Delhi India MEMS Software Solutions ST Microelectronics Santa Clara California United States

Continuously monitoring blood pressure (BP) is crucial for individuals at high risk of cardiac diseases. However, existing BP measurement techniques lack the ability to provide non-invasive and continuous monitoring. To address this challenge, researchers have recently explored accelerometer-based systems for BP estimation. These systems rely on signal processing algorithms that often necessitate extensive feature engineering, making updates and calibration difficult. In this paper, we propose a novel device for non-invasive continuous BP monitoring. The device consists of a patch with two inertial measurement units (IMUs) attached to the skin in the user’s neck region, specifically along the carotid artery. A control unit connected to the patch receives sensor data from these IMU units. It employs a machine learning (ML) model based on Long Short Term Memory (LSTM) to estimate BP using the sensor data. The model undergoes two general ML processes. The first ML process involves training the analysis model using a training set comprised of data from various individuals. Subsequently, the second machine learning process re-trains a portion of the analysis model using an individualized training set gathered from the specific user. This approach enhances the accuracy and personalization of the BP estimation, providing a promising solution for continuous monitoring of BP in high-risk *** BP monitoring device’s analysis model is also trained and tested on 11 volunteers. The BP monitoring device can measure an individual’s BP every 5 seconds. Additionally, the best root mean squared error (RMSE) loss obtained with our model is less than 2.932 mmHg for systolic BP and 2.231 mmHg for diastolic BP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Debiasing Graph Representation Learning based on Information Bottleneck

arXiv

引用

arXiv 2024年

作者： Zhang, Ziyi Ouyang, Mingxuan Lin, Wanyu Lan, Hao Yang, Lei The School of Software Engineering South China University of Technology Guangzhou China The Hong Kong Polytechnic University Hong Kong The Department of Computing The Hong Kong Polytechnic University Hong Kong The Department of Computer Science and Technology Tsinghua University Beijing China

—Graph representation learning has shown superior performance in numerous real-world applications, such as finance and social networks. Nevertheless, most existing works might make discriminatory predictions due to insufficient attention to fairness in their decision-making processes. This oversight has prompted a growing focus on fair representation learning. Among recent explorations on fair representation learning, prior works based on adversarial learning usually induce unstable or counterproductive performance. To achieve fairness in a stable manner, we present the design and implementation of GRAFair, a new framework based on a variational graph auto-encoder. The crux of GRAFair is the Conditional Fairness Bottleneck, where the objective is to capture the trade-off between the utility of representations and sensitive information of interest. By applying variational approximation, we can make the optimization objective tractable. Particularly, GRAFair can be trained to produce informative representations of tasks while containing little sensitive information without adversarial training. Experiments on various real-world datasets demonstrate the effectiveness of our proposed method in terms of fairness, utility, robustness, and stability. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Portable and Wearable Visual Brain-computer Interface for Assessing Patients With Disorders of Consciousness

A Portable and Wearable Visual Brain-Computer Interface for ...

引用

Electronic Information engineering and computer Communication (EIECC), International Conference on

作者： Huang Wu Jun Xiao Chenxin Xue Di Chen Jiahui Pan Yuanqing Li School of Automation Science and Engineering South China University of Technology Guangzhou China School of Electric Power Engineering South China University of Technology Guangzhou China School of Software South China Normal University Guangzhou China Pazhou Laboratory Research Center for Brain–Computer Interface Guangzhou China

The JFK Coma Recovery Scale-Revised (JFK CRSR) is a clinical behavioral method for assessing patients with disorders of consciousness (DOC). However, due to severe brain injury, the DOC patients may lack sufficient behavioral responses, leading to a relatively high clinical misdiagnosis rate of the JFK CRS-R. To address this limitation, this study developed a portable and wearable Brain-computer Interface (BCI) to evaluate the visual tracking abilities of the DOC patients and enhance the diagnostic accuracy of the JFK CRS-R. During the experiment, patients wore an Electroencephalogram headband, and the Graphical User Interface of the BCI presented four human images with a background captured by a camera. A target human image was randomly selected, then the four images alternately flashed until the target moved to its initial position. The system guided patients to concentrate their attention on the moving target. In a case study, the BCI system was applied to a patient diagnosed with a minimally conscious state (MCS). In contrast to the lack of visual tracking behavior in CRS-R, our experiment result showed a significant accuracy of 60% achieved by the MCS patient, emphasizing the visual tracking abilities of the MCS patients and highlighting the effectiveness of the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hyperspectral Image Classification: A Hybrid CNN Approach with Spatial and Channel Attention Mechanisms

Enhancing Hyperspectral Image Classification: A Hybrid CNN A...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Imtiaz Ahmed Butt Li Bo Muhammad Hassaan Farooq Butt Megabiaw Tewodros Tassew Muhammad Usama Bin Akhtar Khan School of Electronics and Information Northwestern Polytechnical University Xi'an Shaanxi China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Software Northwestern Polytechnical University Xi'an Shaanxi China Department of Computing Comsats University Islamabad Wah Campus Wah Pakistan

In the domain of hyperspectral imaging classification (HSIC) for remote sensing, recent advancements in deep learning have proven transformative. Convolutional neural networks have demonstrated immense potential in resolving these issues of HSIC, including insufficient labeled data, redundant spatial and spectral features, and overfitting. Traditional convolutional neural networks (CNNs) have effectively extracted spectral and spatial features, but 2D CNNs are limited in spatial modeling, while 3D CNNs alone struggle to distinguish spectral and spatial characteristics. Given that the accuracy of HSIC hinges on both spatial and spectral information, we proposed a hybrid-CNN model designed to mitigate the constraints of 2D and 3D CNNs. Our approach involves leveraging hybrid CNNs with spatial and channel attention (CA) mechanisms to address challenges like overfitting and model complexity. The proposed framework also improves generalization performance compared to 2D or 3D CNNs alone. Experiments were conducted on open datasets from Pavia University, Indian Pines, and Salinas to validate the proposed approach. The results demonstrate the efficacy of the hybrid CNN model with spatial and CA in consistently producing excellent classification results through thorough analyses with different deep-learning models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LogVm: Variable Semantics Miner for Log Messages

LogVm: Variable Semantics Miner for Log Messages

引用

IEEE International Conference on software Reliability engineering Workshops (ISSRE Wksp)

作者： Yintong Huo Yuxin Su Michael Lyu Dept. of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong China School of Software Engineering Sun Yat-sen University Zhuhai China

ISBN: (数字)9781665476799

ISBN: (纸本)9781665476805

Modern automated log analytics rely on log events without paying attention to variables. However, variables, such as the return code (e.g., “404”) in logs, are noteworthy for their specific semantics of system running status. To unlock the critical bottleneck of mining such semantics from log messages, this study proposes LogVM with three components: (1) an encoder to capture the context information; (2) a pair matcher to resolve variable semantics; and (3) a word scorer to disambiguate different semantic roles. The experiments over seven widely-used software systems demonstrate that Log Vm can derive rich semantics from log messages. We believe such uncovered variable semantics can facilitate downstream applications for system maintainers.

关键词： Codes Conferences Semantics software systems software reliability Data mining

来源：评论

学校读者我要写书评

暂无评论

INITNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization

arXiv

引用

arXiv 2024年

作者： Guo, Xiefan Liu, Jinlin Cui, Miaomiao Li, Jiankai Yang, Hongyu Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Institute of Artificial Intelligence Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

Recent strides in the development of diffusion models, exemplified by advancements such as Stable Diffusion, have underscored their remarkable prowess in generating visually compelling images. However, the imperative of achieving a seamless alignment between the generated image and the provided prompt persists as a formidable challenge. This paper traces the root of these difficulties to invalid initial noise, and proposes a solution in the form of Initial Noise Optimization (INITNO), a paradigm that refines this noise. Considering text prompts, not all random noises are effective in synthesizing semantically-faithful images. We design the cross-attention response score and the self-attention conflict score to evaluate the initial noise, bifurcating the initial latent space into valid and invalid sectors. A strategically crafted noise optimization pipeline is developed to guide the initial noise towards valid regions. Our method, validated through rigorous experimentation, shows a commendable proficiency in generating images in strict accordance with text prompts. Our code is available at https://***/xiefan-guo/initno. Copyright © 2024, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

SCPS:A Secure and Copyright-Preserving System for IIoT Based on Hyperledger Fabric 9

SCPS:A Secure and Copyright-Preserving System for IIoT Based...

引用

9th International Conference on Advanced Cloud and Big Data, CBD 2021

作者： Peng, Jiahui Li, Chunpei Yuan, Bo Meng, Hongwei Yu, Feng Li, Xianxian Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining Security GuiLin China Beihang University Development Environment School of Computer Science and Engineering State Key Laboratory of Software Beijing100191 China Xiong'An Intelligent City Innovation Federation Blockchain Lab Beijing China

ISBN: (纸本)9781665407458

Data, a key asset in Industrial Internet of Things(IIoT), has fueled the emergence of a new data trading in-dustry, which can be collected and traded for better development of IIoT. However, copyright protection is not considered in traditional transactions, resulting in the loss of copyright control of the data after the data was sold. A large number of piracy activities will reduce the enthusiasm of data owners to collect data. The solution we proposed was to use blockchain and smart contract to achieve a decentralized and secure copyright protection scheme. The Trusted Execution Environment(TEE) helped our system realized the piracy tracking. To be specific, our solution effectively achieves a secure and copyright protection system of IIoT data, we realize the real simulation on Hyperledger Fabric shows the good performance of our system. © 2022 IEEE.

关键词： Blockchain

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：