检索结果-内蒙古大学图书馆

Smart World Congress (SWC), IEEE

作者： Yumeng Liu Tingqi Wang Xu Zheng Ling Tian Hongan Wang Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

As deep learning has become more widely used for fault diagnosis, the shortcomings of model transferability and human model design costs are growing increasingly evident. The current work has tackled each of these two issues. Domain adaptation methods can provide transportability by mapping data to a common domain. For the consumption of manually constructed networks, Neural Architecture Search (NAS) is an intelligent solution that automatically select the ideal network structure. Unfortunately, there is little work to connect these two methodologies in fault diagnosis. Furthermore, these approaches are incapable in extracting internal correlations from instrumental signal data. In this paper, we propose a transferrable NAS fault diagnosis method, which maximizes savings in manual costs. We also integrate graph neural networks (GNN) in a stepwise manner into the NAS and domain adaptation to provide a multi-dimension correlation representation. Firstly, we structure the signal data into graph based on temporal relationships. Then, NAS designs automatically for selecting the optimal network structure and useful features. In NAS, graph encoder of GNN is used to establish internal relationships. Finally, domain adaptation provides transferability. At the same time, GNN’s weights in domain adaptation help to further mine data internal associations. We tested our method on two publicly available datasets and performed comparisons. The experimental results show the proposed method has superior performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Dual-view Semi-supervised Learning Framework for Combinatorial Few-shot Fault Diagnosis

A Dual-view Semi-supervised Learning Framework for Combinato...

引用

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Yumeng Liu Wenzhang Zhong Ke Yan Ling Tian Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

The accurate and comprehensive fault diagnosis is pivotal for the maintenance of mechanical equipment, which may directly impact the safety in production and avoid unnecessary losses of equipment. With the pervasively adopted sensing components, sensing data can be collected from mechanical equipment and analyzed for fault diagnosis. Previous solutions apply sophisticated deep learning models for such fault diagnosis tasks and have achieved impressive performance. However, these methods usually ignore the existences of diverse characteristics of faults, and formulate the fault diagnosis as a simple classification problem. Considering necessity of comprehensive and multi-view fault diagnosis, this work proposes a novel dual-view learning framework for combinatorial mechanical fault classification. The framework includes dual encoders to simultaneously learn the feature representation tied with the position and size of faults on equipment. Then these features are mutually mixed for better representation and the mixed features are merged and feed into deep neural networks for further representation learning. The query samples are classified through metric-based comparison to search for the closest type of composite fault. Moreover, the proposed framework also applies typical metric-based meta learning method to handle the issue of small training datasets, and adopts semi-supervised learning method to make use of both labeled and unlabeled samples. Finally, the experimental results on public datasets show that the proposed method can outperform previous solutions and achieve state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Does Joint Training Really Help Cascaded Speech Translation?

Does Joint Training Really Help Cascaded Speech Translation?

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Tran, Viet Anh Khoa Thulke, David Gao, Yingbo Herold, Christian Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University AachenD-52056 Germany

Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results. However, fundamental challenges such as error propagation from the automatic speech recognition system still remain. To mitigate these problems, recently, people turn their attention to direct data and propose various joint training methods. In this work, we seek to answer the question of whether joint training really helps cascaded speech translation. We review recent papers on the topic and also investigate a joint training criterion by marginalizing the transcription posterior probabilities. Our findings show that a strong cascaded baseline can diminish any improvements obtained using joint training, and we suggest alternatives to joint training. We hope this work can serve as a refresher of the current speech translation landscape, and motivate research in finding more efficient and creative ways to utilize the direct data for speech translation. © 2022 Association for Computational Linguistics.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning

Forging Multiple Training Objectives for Pre-trained Languag...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Wu, Hongqiu Ding, Ruixue Zhao, Hai Chen, Boli Xie, Pengjun Huang, Fei Zhang, Min Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China School of Computer Science and Technology Soochow University China Damo Academy Alibaba Group China

Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios. However, learning multiple training objectives in a single model is challenging due to the unknown relative significance as well as the potential contrariety between them. Empirical studies have shown that the current objective sampling in an ad-hoc manual setting makes the learned language representation barely converge to the desired optimum. Thus, we propose MOMETAS, a novel adaptive sampler based on meta-learning, which learns the latent sampling pattern on arbitrary pre-training objectives. Such a design is lightweight with negligible additional training overhead. To validate our approach, we adopt five objectives and conduct continual pre-training with BERT-base and BERT-large models, where MOMETAS demonstrates universal performance gain over other rule-based sampling strategies on 14 natural language processing tasks. © 2022 Association for Computational Linguistics.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Efficacy of Immersive Virtual Reality Combined With Multisensor Biofeedback on Chronic Pain in Fibromyalgia: A Pilot Randomized Controlled Trial

ACR Open Rheumatology

引用

ACR Open Rheumatology 2025年第5期7卷 e70048页

作者： Chittaro, Luca Longhino, Simone Serafini, Marta Cacioppo, Sofia Quartuccio, Luca Human-Computer Interaction Lab Department of Mathematics Computer Science and Physics University of Udine Udine Italy Rheumatology Division Department of Medicine University of Udine Udine Italy Rheumatology Division Department of Medicine University of Udine and Azienda Sanitaria Universitaria Friuli Centrale Udine Italy

Objective: Fibromyalgia (FM) is a syndrome marked by chronic pain, fatigue, and mood disorders. Nonpharmacologic strategies are recommended to avoid overuse of opioids or nonsteroidal anti-inflammatory drugs, but current approaches often provide limited relief. This study aimed to preliminarily assess the efficacy and feasibility of a new combined intervention of immersive virtual reality with multisensor biofeedback (IVR-BF) in FM management. Methods: In this single-center, pilot, open-label, randomized controlled trial, adult patients with FM were randomly assigned 1:1 to either the treatment (TR) group, receiving IVR-BF immediately, or a waitlist control (WL) group, receiving IVR-BF after the TR group completed treatment. The primary outcome was reduction in visual analog scale (VAS) pain scores in the TR group, after five IVR-BF sessions, compared to the WL group, after the waiting period. Secondary outcomes included improvements in FM impact (FM Impact Questionnaire [FIQ] score) and qualitative aspect of pain (Short-form McGill Pain Questionnaire [SF-MPQ] score). A longitudinal analysis was conducted across all patients to examine the trends in VAS pain, SF-MPQ, and FIQ score during the trial. Results: Fifty patients were screened, and 20 female patients (10 TR and 10 WL) completed the trial and were analyzed. Those in the TR group showed significantly lower VAS pain scores compared to those in the WL group (P = 0.011), along with significant improvement in the FIQ score (P = 0.018). The longitudinal analysis revealed progressive improvements in VAS pain, SF-MPQ, and FIQ score, supported by physiologic improvements (heart rate variability, respiratory rate, skin conductance). No significant safety concerns were reported. Patients expressed a high level of satisfaction with the IVR experience. Conclusion: IVR-BF is a feasible treatment that shows potential in reducing pain and improving quality of life in patients with FM, supporting the need for larger trials t

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of Duration and Delay on the Identifiability of VR Motion

arXiv

引用

arXiv 2024年

作者： Miller, Mark Roman Nair, Vivek Han, Eugy DeVeaux, Cyan Rack, Christian Wang, Rui Huang, Brandon Latoschik, Marc Erich O’Brien, James F. Bailenson, Jeremy N. Computer Science Illinois Institute of Technology Chicago United States Computer Science UC Berkeley Berkeley United States Communication Stanford University Stanford United States Human-Computer Interaction University of Würzburg Würzburg Germany Carnegie Mellon University Pittsburgh United States UC Berkeley Berkeley United States

xvSocial virtual reality is an emerging medium of communication. In this medium, a user’s avatar (virtual representation) is controlled by the tracked motion of the user’s headset and hand controllers. This tracked motion is a rich data stream that can leak characteristics of the user or can be effectively matched to previously-identified data to identify a user. To better understand the boundaries of motion data identifiability, we investigate how varying training data duration and train-test delay affects the accuracy at which a machine learning model can correctly classify user motion in a supervised learning task simulating re-identification. The dataset we use has a unique combination of a large number of participants, long duration per session, large number of sessions, and a long time span over which sessions were conducted. We find that training data duration and train-test delay affect identifiability;that minimal train-test delay leads to very high accuracy;and that train-test delay should be controlled in future experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal humanoid Locomotion

Exciting Action: Investigating Efficient Exploration for Lea...

引用

IEEE-RAS International Conference on humanoid Robots

作者： Henri-Jacques Geiβ Firas Al-Hafez Andre Seyfarth Jan Peters Davide Tateo Computer Science Department Technical University Darmstadt Computer Science Department University of Innsbruck Human Sciences Department Technical University Darmstadt German Research Center for AI (DFKI) Centre for Cognitive Science Hessian.AI

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

Learning a locomotion controller for a musculoskeletal system is challenging due to over-actuation and high-dimensional action space. While many reinforcement learning methods attempt to address this issue, they often struggle to learn human-like gaits because of the complexity involved in engineering an effective reward function. In this paper, we demonstrate that adversarial imitation learning can address this issue by analyzing key problems and providing solutions using both current literature and novel techniques. We validate our methodology by learning walking and running gaits on a simulated humanoid model with 16 degrees of freedom and 92 Muscle-Tendon Units, achieving natural-looking gaits with only a few demonstrations. Code is available at https://***/henriTUD/musculoco_learning.

关键词： Legged locomotion Biomechanics Codes Imitation learning humanoid robots Reinforcement learning Muscles Motion capture Complexity theory Assistive devices

来源：评论

学校读者我要写书评

暂无评论

Learning a Subspace and Clustering Simultaneously with Manifold Regularized Nonnegative Matrix Factorization

引用

Guidance, Navigation and Control 2024年第3期4卷 147-165页

作者： Feiping Nie Huimin Chen Heng Huang Chris H.Q.Ding Xuelong Li School of Computer Science Northwestern Polytechnical University Xi'an 710072 P.R.China School of Artificial Intelligence Optics and Electronics(iOPEN)Northwestern Polytechnical University Xi'an 710072 P.R.China Key Laboratory of Intelligent Interaction and Applications(Northwestern Polytechnical University)Ministry of Industry and Information Technology Xi'an 710072 P.R.China Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA 15260USA Department of Computer Science and Engineering The Chinese University of Hong Kong Shenzhen 518172 P.R.China Institute of Artificial Intelligence(TeleAI)China Telecom Corporation Limited 31 Jinrong Street Beijing 100033P.R.China

With the incredible growth of high-dimensional data such as microarray gene expression data and web blogs from internet, the researchers are desirable to develop new clustering techniques to address the critical problem created by irrelevant dimensions. Properties of Nonnegative Matrix Factorization(NMF) as a clustering method were studied by relating its formulation to other methods such as K-means clustering. In this paper, by introducing clustering indicator constraints on NMF and incorporating manifold regularization to preserve geometric structures,we propose a novel manifold regularized NMF method that can simultaneously learn subspace and do clustering. As a result, our clustering results can directly assign cluster label to data points. Extensive experimental results show that our method outperforms related other methods.

关键词： Subspace learning clustering nonnegative matrix factorization manifold learning

来源：评论

学校读者我要写书评

暂无评论

Ciao AI: the Italian adaptation and validation of the Chatbot Usability Scale

引用

Personal and Ubiquitous Computing 2023年第6期27卷 2161-2170页

作者： Borsci, Simone Prati, Elisa Malizia, Alessio Schmettow, Martin Chamberlain, Alan Federici, Stefano Faculty of Behavioural Management and Social Sciences Department of Learning Data Analysis and Technology Group of Cognition Data and Education University of Twente Enschede Netherlands Department of Surgery and Cancer Faculty of Medicine NIHR London IVD Imperial College of London London United Kingdom Department of Engineering "Enzo Ferrari" University of Modena and Reggio Emilia Modena Italy Computer Science Department University of Pisa Pisa Italy Molde University College Molde Norway School of Computer Science University of Nottingham Nottingham United Kingdom Department of Philosophy Social and Human Sciences and Education University of Perugia Perugia Italy

Chatbot-based tools are becoming pervasive in multiple domains from commercial websites to rehabilitation applications. Only recently, an eleven-item satisfaction inventory was developed (the ChatBot Usability Scale, BUS-11) to help designers in the assessment process of their systems. The BUS-11 has been validated in multiple contexts and languages, i.e., English, German, Dutch, and Spanish. This scale forms a solid platform enabling designers to rapidly assess chatbots both during and after the design process. The present work aims to adapt and validate the BUS-11 inventory in Italian. A total of 1360 questionnaires were collected which related to a total of 10 Italian chatbot-based systems using the BUS-11 inventory and also using the lite version of the Usability Metrics for User eXperience for convergent validity purposes. The Italian version of the BUS-11 was adapted in terms of the wording of one item, and a Multi-Group Confirmatory Factorial Analysis was performed to establish the factorial structure of the scale and compare the effects of the wording adaptation. Results indicate that the adapted Italian version of the scale matches the expected factorial structure of the original scale. The Italian BUS-11 is highly reliable (Cronbach alpha: 0.921), and it correlates to other measures of satisfaction (e.g., UMUX-Lite, τb = 0.67;p © 2023, The Author(s).

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

Summit Vitals: Multi-Camera and Multi-Signal Biosensing at High Altitudes

Summit Vitals: Multi-Camera and Multi-Signal Biosensing at H...

引用

Smart World Congress (SWC), IEEE

作者： Ke Liu Jiankai Tang Zhang Jiang Yuntao Wang Xiaojing Liu Dong Li Yuanchun Shi Department of Computer Technology and Applications Qinghai University Qinghai National Key Laboratory of Human Factors Engineering Beijing Department of Computer Science and Technology Tsinghua University Beijing

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Video photoplethysmography (vPPG) is an emerging method for non-invasive and convenient measurement of physiological signals, utilizing two primary approaches: remote video PPG (rPPG) and contact video PPG (cPPG). Monitoring vitals in high-altitude environments, where heart rates tend to increase and blood oxygen levels often decrease, presents significant challenges. To address these issues, we introduce the SUMS dataset comprising 80 synchronized non-contact facial and contact finger videos from 10 subjects during exercise and oxygen recovery scenarios, capturing PPG, respiration rate (RR), and SpO2. This dataset is designed to validate video vitals estimation algorithms and compare facial rPPG with finger cPPG. Additionally, fusing videos from different positions (i.e., face and finger) reduces the mean absolute error (MAE) of SpO 2 predictions by $\mathbf{7. 6 \%}$ and $\mathbf{1 0. 6 \%}$ compared to only face and only finger, respectively. In cross-subject evaluation, we achieve an MAE of less than 0.5 BPM for HR estimation and $\mathbf{2. 5 \%}$ for SpO 2 estimation, demonstrating the precision of our multi-camera fusion techniques. Our findings suggest that simultaneous training on multiple indicators, such as PPG and blood oxygen, can reduce MAE in SpO 2 estimation by $\mathbf{1 7. 8 \%}$.

关键词： Training Heart rate Fingers Estimation Photoplethysmography Synchronization Biomedical monitoring Monitoring Faces Blood

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：