检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Sun, Kai Zhang, Richong Mensah, Samuel Aletras, Nikolaos Mao, Yongyi Liu, Xudong Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China Department of Computer Science University of Sheffield Sheffield United Kingdom School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining that aims to extract the targets (or aspects) on which opinions have been expressed. Recent work focus on cross-domain OTE, which is typically encountered in real-world scenarios, where the testing and training distributions differ. Most methods use domain adversarial neural networks that aim to reduce the domain gap between the labelled source and unlabelled target domains to improve target domain performance. However, this approach only aligns feature distributions and does not account for class-wise feature alignment, leading to suboptimal results. Semi-supervised learning (SSL) has been explored as a solution, but is limited by the quality of pseudo-labels generated by the model. Inspired by the theoretical foundations in domain adaptation [2], we propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagree on the unlabelled target data, in an effort to boost the target domain performance. Extensive experiments on benchmark cross-domain OTE datasets show that this approach is effective and performs consistently well in settings with large domain shifts. © 2023, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Channel-Augmented Multi-Domain Graph Convolutional Network for Fatigue Driving Detection

A Channel-Augmented Multi-Domain Graph Convolutional Network...

引用

Industrial Automation, Robotics and Control engineering (IARCE), International Conference on

作者： Mingyi Sun Weigang Cui Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing China School of Engineering Medicine Beihang University Beijing China Department of Automation Science and Electrical Engineering State Key Laboratory of Virtual Reality Technology and Systems The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

Electroencephalography (EEG) has emerged as a crucial cornerstone within the realm of brain-computer interface (BCI) applications, with its significance notably pronounced in the field of fatigue detection. However, the inherent limitations of EEG acquisition equipment during real driving scenarios have contributed to the constrained robustness of existing models. Moreover, most of recent methods failed to extract robust multi-domain features, leading to a suboptimal performance. To address these challenges, we propose a novel channel-augmented multi-domain graph convolutional network (CA-MDGCNet). Specifically, the initial EEG signals are enriched by incorporating supplementary virtual EEG channels, distinguished as learnable parameters within the network architecture. Then, differential entropy features are extracted from the augmented EEG signals. Following this, a multi-domain graph convolutional network is designed to encode high-level EEG features by means of convolutions in diverse paths, which is beneficial to integrating the characteristics extracted from multiple domains. Finally, the classification block derives the detection outcome from the refined feature maps. To substantiate the potency of the proposed method, the validation was conducted on the publicly accessible SEED-VIG. The proposed CA-MDGCNet not only demonstrates more promising performance compared to state-of-the-art approaches but also underscores the potential viability of our method for the realm of fatigue driving detection.

关键词： Graph convolutional networks Convolution Service robots Neural activity Feature extraction Fatigue Brain modeling Electroencephalography Entropy Robustness

来源：评论

学校读者我要写书评

暂无评论

Establishment of EHA Performance Degradation Model Based on PMSM and Its Active Fault Tolerant Control 31st

Establishment of EHA Performance Degradation Model Based on ...

引用

31st European Safety and Reliability Conference, ESREL 2021

作者： Xin, Zhaozhou Wang, Shaoping Zhang, Chao School of Automation Science and Electrical Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big-Data Based Precision Medicine Beihang University Beijing China

ISBN: (纸本)9789811820168

The electro-hydrostatic actuator (EHA) is currently the most widely used and most mature actuation method. It has the advantages of high control accuracy, good stability and high reliability. As the power source of the hydraulic pump in the EHA, the motor can drive the load to run with or without load through positive and negative rotation. This article takes the rudder control system of an underwater vehicle as an example, first analyzes the working principle of EHA, and proposed an EHA model based on permanent-magnet synchronous motor (PMSM). By analyzing the different performance degradation degrees of different parameters of the motor, and comparing it with the traditional brushless DC motor model and its performance degradation to verifiy the validity and accuracy of the model. Then combined with adaptive active fault-tolerant control (AFTC) based on Radial Basis Function Neural Network (RBFNN) to provide a basis for reliability analysis based on EHA. © ESREL 2021. Published by Research Publishing, Singapore.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Research on performance degradation of Inverse Gaussian process based on BPNN data screening 31st

Research on performance degradation of Inverse Gaussian proc...

引用

31st European Safety and Reliability Conference, ESREL 2021

ISBN: (纸本)9789811820168

For a series of high-reliability and long-life systems, the performance degradation data obtained within a certain period of time can predict the performance degradation of the system well. In this paper, the inverse Gaussian(IG) process is used to describe the performance degradation process of the pressure sensor at the centrifugal pump of the underwater vehicle. And in the degradation process, introduce the difference mean function between different individuals to describe the performance degradation process. By introducing multiple sets of data and using Back Propagation Neural Network(BPNN) to filter the data, a set of reliable performance degradation data is obtained. And proposed to use Bayesian theory and Expectation-Maximization(EM) algorithm to collaborate on research and give an explicit expression to obtain the effective estimated value of the model. Through continuous updating and iteration to improve the estimation accuracy, the system’s performance degradation trajectory, Remaining Useful Life(RUL) and RUL probability density distribution graphs are obtained. Using the α − λ index to verify that the accuracy of the actual range and the estimated range can be above 85%, which provides a direction for future research on fault-tolerant control based on performance degradation. © ESREL 2021. Published by Research Publishing, Singapore.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

One-Dimensional EEG Artifact Removal Network Based on Convolutional Neural Networks

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第1期9卷 142-159页

作者： Xiong, Jun Meng, Xiang-Long Chen, Zhao-Qi Wang, Chuan-Sheng Zhang, Fu-Quan Grau, Antoni Chen, Yang Huang, Jing-Wei School of Computer and Data Science Minjiang University Fuzhou University Town No. 200 Xiyuangong Road Fuzhou China College of Electronic Engineering Shandong University of Science and Technology No. 579 Qianwangang Road Huangdao District Qingdao China College of Computer and Big Data Fuzhou University Fuzhou University Town No. 2 Wulongjiang North Road Fuzhou China Department of Automatic Control Technical Polytechnic University of Catalonia Autonomous Region of Catalonia Barcelona Spain Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Fuzhou Technology Innovation Center of intelligent Manufacturing information System Minjiang University Fuzhou University Town No. 200 Xiyuangong Road Fuzhou China Fujian Province University No. 1 Campus New Village Longjiang Street Fuqing China School of Mechanical and Automotive Engineering Fujian University of Technology No. 33 Xuefu South Road University New District Fuzhou China

The electroencephalogram (EEG) serves as a significant tool in the realms of clinical medicine, cerebral investigation, and neurological disorders research. However, the EEG records we obtain are often easily contaminated by various artifacts, which can blur or distort the underlying EEG signals and make data interpretation difficult. Generally speaking, removing EEG artifacts is considered an essential step in brain signal analysis. Therefore, removing artifacts is crucial for obtaining accurate and reliable EEG signals for subsequent analysis. Recently, deep learning techniques have found widespread application across various domains for denoising tasks, including image denoising and EEG denoising. Many advanced algorithms have been developed in image denoising, which has achieved good results in enhancing low-quality images. Moreover, it has shown superior performance in EEG denoising. In contrast, few people have devoted themselves to studying EEG denoising, and existing convolutional neural network EEG denoising methods still have problems of overfitting and poor denoising effect in Electromyograph(EMG) and ElectroOculoGram(EOG) artifact removal. Therefore, this paper proposes a method called DWINet (De-artifacting with Image-based Network for EEG Signals) based on an image dehazing network DRHNet for removing artifacts from EEG signals. Specifically, our approach DWINet, addresses the de-artifacting issue in EEG signals by converting it as an image dehazing problem and utilizes the image dehazing capability of DRHNet to enhance the denoising performance of EEG signals. Experimental results demonstrate that the proposed method outperforms the compared algorithms in removing the ocular artifact in EEG signals and exhibits higher accuracy and robustness. © 2024, J. Network Intell. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Low-Code Development Framework for Constructing Industrial Apps 15th

A Low-Code Development Framework for Constructing Industrial...

引用

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

作者： Wang, Jingyue Qi, Binhang Zhang, Wentao Sun, Hailong SKLSDE Lab School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China

ISBN: (纸本)9789811625398

With the advent of the Industry 4.0, intelligent manufacturing has become a technological highland to conquer in the process of enterprise digitalization. As the core competitiveness of intelligent manufacturing, industrial apps, with new features such as customization and lightweight, has emerged as a new type of industrial software. Traditional development methods and tools can hardly meet the large demand of industrial software on account of its long development cycles while low-code development can greatly improve the productivity of industrial software, lower the barriers and reduce costs for development. Therefore, the research and application of low-code development for industrial apps has received much attention. Industrial Internet platforms such as Siemens, OutSystems have successively launched low-code tools. However, there is still a lack of an open, unified low-code development framework in industry. In response to the above problems, we propose a low-code framework to develop industrial apps quickly and easily, which paves the way for leveraging the crowd intelligence of worldwide developers to improve the productivity of developing industrial apps. Based on BPMN2.0 and Apache Activiti engine, this framework provides drag-and-drop process design, one-click process deployment and operation, data monitoring and other functions. In this paper, we present a prototype system of a low-code development framework and demonstrate its functions through a use case of developing a predictive maintenance application. Finally, the aircraft turbine life data is used to verify the effectiveness of the system. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

Self-feedback LSTM regression model for real-time particle source apportionment

引用

Journal of Environmental sciences 2022年第4期34卷 10-20页

作者： Wei Wang Weiman Xu Shuai Deng Yimeng Chai Ruoyu Ma Guoliang Shi Bo Xu Mei Li Yue Li Trusted AI System Laboratory College of Computer ScienceNankai UniversityTianjin 300350China KLMDASR Tianjin Key Laboratory of Network and Data Security TechnologyTianjin 300350China State Environmental Protection Key Laboratory of Urban Ambient Air Particulate Matter Pollution Prevention and Control College of Environmental Science and EngineeringNankai UniversityTianjin 300071China Institute of Mass Spectrometry and Atmospheric Environment Guangdong Provincial Engineering Research Center for on-line source apportionment system of air pollution Jinan UniversityGuangzhou 510632China Guangdong-Hongkong-Macao Joint Laboratory of Collaborative Innovation for Environmental Quality Guangzhou 510632China

Atmospheric particulate matter pollution has attracted much wider attention *** recent years,the development of atmospheric particle collection techniques has put forwards new demands on the real-time source apportionments *** demands are summarized,in this paper,as how to set up new restraints in apportionment and how to develop a non-linear regression model to process complicated circumstances,such as the existence of secondary source and similar *** this study,we firstly analyze the possible and potential restraints in single particle source apportionment,then propose a novel three-step self-feedback long short-term memory(SF-LSTM)network for approximating the source *** proposed deep learning neural network includes three modules,as generation,scoring and refining,and regeneration *** from the scoring modules,SF-LSTM implants four loss functions representing four restraints to be followed in the apportionment,meanwhile,the regeneration module calculates the source contribution in a non-linear *** results show that the model outperforms the conventional regression methods in the overall performance of the four evaluation indicators(residual sum of squares,stability,sparsity,negativity)for the ***,in short time-resolution analyzing,SF-LSTM provides better results under the restraint of stability.

关键词： Time series Regression Self-feedback LSTM network Particle source apportionment

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Pre-Trained Whisper Model and Levenshtein Distance for Audio Buginesse Transcription

Leveraging the Pre-Trained Whisper Model and Levenshtein Dis...

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Amirul Mukmin Adnan Abdul Jalil Mahabintang Pallawabonang Esa Prakasa Yuyun Dept. of informatics engineering Handayani University of Makassar Makassar Indonesia Dept. of computer system Handayani University of Makassar Makassar Indonesia Research center for data and information science National Research and Innovation Agency Bandung Indonesian

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

This research aims to transcribe audio into text using the pre-trained Whisper model, focusing on Bugis, a low-resource language. A key challenge in transcribing local languages like Bugis is the limited availability of language model. To address this, we implemented an algorithmic correction approach that does not require extensive datasets or computationally demanding customizations. The Whisper model provides an initial transcription, serving as a foundation; however, the output often lacks accuracy due to the absence of specific adjustments for Bugis. To enhance accuracy, we applied the Levenshtein distance algorithm to correct word errors by comparing transcription results with entries in a Bugis language dataset based on similarity. Although this method is not fully precise and depends on the completeness of the reference dataset, evaluation results indicate that it effectively lowers the word error rate (WER) and improves transcription accuracy. This research produces SRT files containing transcripts that have been corrected using the Levenhstein distance algorithm, which not only improves accessibility but also contributes to the preservation of Bugis language through digital media. This approach is expected to provide a practical solution to improve transcription accuracy and support more accurate documentation in Bugis language preservation efforts.

关键词： Accuracy Error analysis Computational modeling Focusing Speech recognition Documentation Media Linguistics Synchronization Informatics

来源：评论

学校读者我要写书评

暂无评论

Leveraging YOLOv8 for Real-Time Parking Space Detection

Leveraging YOLOv8 for Real-Time Parking Space Detection

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Mahabintang Pallawabonang Muh. Adnan Sitti Zuhriyah Amirul Mukmin Esa Prakasa Yuyun dept. of informatics engineering Handayani University of Makassar Makassar Indonesia dept. of Computers System Handayani University of Makassar Makassar Indonesia Research center for data and information science National Research and Innovation Agency Bandung Indonesian

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

This research develops a smart parking system based on computer vision integrated with the Firebase platform, utilizing the YOLOv8 algorithm and the OpenCV library. This system is designed to detect vehicles and determine the availability status of parking slots in real time through video recording analysis. The dataset was obtained from recorded parking activity videos, then processed using Roboflow for data labeling, and fine-tuned on Google Colab. The resulting model shows a vehicle detection accuracy of up to 99.1% with high stability, as indicated by the training loss graph. The process of mapping the parking area is carried out through an OpenCV-based application for the identification and configuration of parking slots. The status of each parking slot is automatically updated to the Firebase Realtime database, enabling efficient historical data recording and information management. Testing shows the system's reliable performance under various lighting conditions, with high capabilities in vehicle detection and real-time data management. This study makes a significant contribution to the development of parking management solutions through the integration of technology that supports operational efficiency and high accuracy.

关键词： Training Accuracy Web design Image processing Machine learning Automated parking Streaming media Real-time systems Video recording Testing

来源：评论

学校读者我要写书评

暂无评论

Building of a Question-Answering System for Umrah Using Fine-Tuned Transformer Model

Building of a Question-Answering System for Umrah Using Fine...

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Ahmad Abrar Yuyun Wahyu Ramadhan Arianto Billy Eden William Asrul Abdul Latief Arda Sitti Zuhriyah Pujianti Wahyuningsih Muhammad Risal dept. of informatics engineering handayani university of makassar Makassar Indonesia research center for data and information science national research and innovation agency Bandung Indonesia dept. of computers system handayani university of makassar Makassar Indonesia

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

This research examines the application of fine-tuning on Transformer models to develop a question-answering (QA) system. We designed this model to answer questions about Umrah accurately. Access to complete and relevant information about Umrah often poses a challenge for prospective pilgrims, especially when faced with specific questions that require a deep understanding of the religious context. We used the facebook/blenderbot-400M-distill model as a base retrained with a dataset containing 15,000 question-answer pairs related to Umrah. The model's fine-tuning process includes data tokenization, embedding, analysis of token length distribution, and hyperparameter optimization. We evaluate the model's performance using the perplexity metric to assess the accuracy and relevance of the model's responses. The results show that after training, the model achieved a perplexity value of 1.9494, with a training loss of 0.5087 and a validation loss of 0.6704, indicating good predictive capability.

关键词： Training Measurement Information services Predictive models Transformers data models User experience Tokenization Informatics Optimization

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：