检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zheng, Kaizhong Yu, Shujian Li, Baojuan Jenssen, Robert Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China The Department of Computer Science Vrije Universiteit Amsterdam Amsterdam and the Machine Learning Group UiT - Arctic University of Norway Tromsø Norway The Machine Learning Group UiT - Arctic University of Norway Tromsø Norway The School of Biomedical Engineering Fourth Military Medical University Xi’an China

Developing a new diagnostic models based on the underlying biological mechanisms rather than subjective symptoms for psychiatric disorders is an emerging consensus. Recently, machine learning-based classifiers using functional connectivity (FC) for psychiatric disorders and healthy controls are developed to identify brain markers. However, existing machine learning-based diagnostic models are prone to over-fitting (due to insufficient training samples) and perform poorly in new test environment. Furthermore, it is difficult to obtain explainable and reliable brain biomarkers elucidating the underlying diagnostic decisions. These issues hinder their possible clinical applications. In this work, we propose BrainIB, a new graph neural network (GNN) framework to analyze functional magnetic resonance images (fMRI), by leveraging the famed Information Bottleneck (IB) principle. BrainIB is able to identify the most informative edges in the brain (i.e., subgraph) and generalizes well to unseen data. We evaluate the performance of BrainIB against 3 baselines and 7 state-of-the-art brain network classification methods on three psychiatric datasets and observe that our BrainIB always achieves the highest diagnosis accuracy. It also discovers the subgraph biomarkers which are consistent to clinical and neuroimaging findings. The source code and implementation details of BrainIB are freely available at GitHub repository (https://***/SJYuCNEL/brain-and-Information-Bottleneck/). Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigating an effective character-level embedding in Korean sentence classification 33

Investigating an effective character-level embedding in Kore...

引用

33rd Pacific Asia Conference on Language, Information and Computation, PACLIC 2019

作者： Cho, Won Ik Kim, Seok Min Kim, Nam Soo Human Interface Laboratory Department of Electrical and Computer Engineering and INMC Seoul National University 1 Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of

Different from the writing systems of many Romance and Germanic languages, some languages or language families show complex conjunct forms in character composition. For such cases where the conjuncts consist of the components representing consonant(s) and vowel, various character encoding schemes can be adopted beyond merely making up a one-hot vector. However, there has been little work done on intra-language comparison regarding performances using each representation. In this study, utilizing the Korean language which is character-rich and agglutinative, we investigate an encoding scheme that is the most effective among Jamo1-level one-hot, character-level one-hot, character-level dense, and character-level multi-hot. Classification performance with each scheme is evaluated on two corpora: one on binary sentiment analysis of movie reviews, and the other on multiclass identification of intention types. The result displays that the character-level features show higher performance in general, although the Jamo-level features may show compatibility with the attention-based models if guaranteed adequate parameter set size. Copyright © 2019 Won Ik Cho, Seok Min Kim and Nam Soo Kim.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Accurate grid keypoint learning for efficient video prediction

arXiv

引用

arXiv 2021年

作者： Gao, Xiaojie Jin, Yueming Dou, Qi Fu, Chi-Wing Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The CUHK T Stone Robotics Institute Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

Video prediction methods generally consume substantial computing resources in training and deployment, among which keypoint-based approaches show promising improvement in efficiency by simplifying dense image prediction to light keypoint prediction. However, keypoint locations are often modeled only as continuous coordinates, so noise from semantically insignificant deviations in videos easily disrupt learning stability, leading to inaccurate keypoint modeling. In this paper, we design a new grid keypoint learning framework, aiming at a robust and explainable intermediate keypoint representation for long-term efficient video prediction. We have two major technical contributions. First, we detect keypoints by jumping among candidate locations in our raised grid space and formulate a condensation loss to encourage meaningful keypoints with strong representative capability. Second, we introduce a 2D binary map to represent the detected grid keypoints and then suggest propagating keypoint locations with stochasticity by selecting entries in the discrete grid space, thus preserving the spatial structure of keypoints in the long-term horizon for better future frame generation. Extensive experiments verify that our method outperforms the state-of-the-art stochastic video prediction methods while saves more than 98% of computing resources. We also demonstrate our method on a robotic-assisted surgery dataset with promising results. Our code is available at https://***/ xjgaocs/Grid-Keypoint-Learning. Copyright © 2021, The Authors. All rights reserved.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Brain Age Estimation: A Systematic Review

arXiv

引用

arXiv 2022年

作者： Tanveer, M. Ganaie, M.A. Beheshti, Iman Goel, Tripti Ahmad, Nehal Lai, Kuan-Ting Huang, Kaizhu Zhang, Yu-Dong Ser, Javier Del Lin, Chin-Teng Department of Mathematics Indian Institute of Technology Indore Simrol Indore453552 India Department of Robotics University of Michigan Ann ArborMI48109 United States Department of Human Anatomy and Cell Science Rady Faculty of Health Sciences Max Rady College of Medicine University of Manitoba WinnipegMB Canada Biomedical Imaging Lab National Institute of Technology Assam Silchar788010 India Department of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan Data Science Research Center Duke Kunshan University China School of Computing and Mathematical Sciences University of Leicester United Kingdom Derio48160 Spain Bilbao48013 Spain School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated to the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required for eliciting accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Novel Smart N95 Filtering Facepiece Respirator with Real-time Adaptive Fit Functionality and Wireless Humidity Monitoring for Enhanced Wearable Comfort

arXiv

引用

arXiv 2023年

作者： Kwon, Kangkyu Lee, Yoon Jae Jung, Yeongju Soltis, Ira Choi, Chanyeong Na, Yewon Romero, Lissette Kim, Myung Chul Rodeheaver, Nathan Kim, Hodam Lloyd, Michael S. Zhuang, Ziqing King, William Xu, Susan Ko, Seung-Hwan Lee, Jinwoo Yeo, Woon-Hong School of Electrical and Computer Engineering College of Engineering Georgia Institute of Technology AtlantaGA30332 United States Center for Human-Centric Interfaces and Nanoengineering Institute for Electronics and Nanotechnology Georgia Institute of Technology AtlantaGA30332 United States Applied Nano and Thermal Science Lab Department of Mechanical Engineering Seoul National University 1 Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30332 United States School of Industrial Design Georgia Institute of Technology AtlantaGA30332 United States Division of Cardiology Emory University School of Medicine AtlantaGA30322 United States National Institute for Occupational Safety and Health National Personal Protective Technology Laboratory PittsburghPA15236 United States Seoul National University Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of Department of Mechanical Robotics and Energy Engineering Dongguk University 30 Pildongro 1-gil Jung-gu Seoul04620 Korea Republic of Wallace H. Coulter Department of Biomedical Engineering Parker H. Petit Institute for Bioengineering and Biosciences Neural Engineering Center Institute for Materials Institute for Robotics and Intelligent Machines Georgia Institute of Technology AtlantaGA30332 United States

The widespread emergence of the COVID-19 pandemic has transformed our lifestyle, and facial respirators have become an essential part of daily life. Nevertheless, the current respirators possess several limitations such as poor respirator fit because they are incapable of covering diverse human facial sizes and shapes, potentially diminishing the effect of wearing respirators. In addition, the current facial respirators do not inform the user of the air quality within the smart facepiece respirator in case of continuous long-term use. Here, we demonstrate the novel smart N-95 filtering facepiece respirator that incorporates the humidity sensor and pressure sensory feedback-enabled self-fit adjusting functionality for the effective performance of the facial respirator to prevent the transmission of airborne pathogens. The laser-induced graphene (LIG) constitutes the humidity sensor, and the pressure sensor array based on the dielectric elastomeric sponge monitors the respirator contact on the user’s face, providing the sensory information for a closed-loop feedback mechanism. As a result of the self-fit adjusting mode along with elastomeric lining, the fit factor is increased by 3.20 and 5 times at average and maximum respectively. We expect that the experimental proof-of-concept of this work will offer viable solutions to the current commercial respirators to address the *** Codes 92C55 Copyright © 2023, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

A human-cyber-physical system approach to lean automation using an industrie 4.0 reference architecture

引用

Procedia Manufacturing 2020年 51卷 1082-1090页

作者： Matteo Pantano Daniel Regulin Benjamin Lutz Dongheui Lee Functional Materials & Manufacturing Processes Corporate Technology Department Siemens Aktiengesellschaft Munich 81739 Germany Human-Centered Assistive Robotics (HCR) Department of Electrical and Computer Engineering Technical University of Munich Munich 80333 Germany Institute of Robotics and Mechatronics German Aerospace Center (DLR) Oberpfaffenhofen-Weßling 82234 Germany

The factory of the future requires flexibility and adaptability to satisfy market demands. However, these properties are difficult to ensure when collaborative manipulators are considered. Thus, approaches for integrating these devices, fostering the adoption of new engineering methodologies for augmenting manipulators are studied. In this work we address how integration of human operators with robotic manipulators might accommodate flexibility requirements using a concept of lean automation. To answer this question, we compare the current research in the field, and we propose a design structure which addresses safety, interfaces and design methods. Our results show safety hardware posing considerable constraints on flexibility. The human interface influences the workload perceived by an operator and, Industrie 4.0 reference architectures do not foresee the human and reconfigurable production cells yet. From a design prospective, this study emphasizes the need to take into consideration human and engineering aspects while planning for the factory of the future.

关键词： human-cyber-physical system lean automation human-centred design Industrie 4.0 RAMI 4.0

来源：评论

学校读者我要写书评

暂无评论

One to many: Adaptive instrument segmentation via meta learning and dynamic online adaptation in robotic surgical video

arXiv

引用

arXiv 2021年

作者： Zhao, Zixu Jin, Yueming Lu, Bo Ng, Chi-Fai Dou, Qi Liu, Yun-Hui Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The T Stone Robotics Institute The Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China The Department of Surgery The Chinese University of Hong Kong Hong Kong

Surgical instrument segmentation in robot-assisted surgery (RAS) - especially that using learning-based models - relies on the assumption that training and testing videos are sampled from the same domain. However, it is impractical and expensive to collect and annotate sufficient data from every new domain. To greatly increase the label efficiency, we explore a new problem, i.e., adaptive instrument segmentation, which is to effectively adapt one source model to new robotic surgical videos from multiple target domains, only given the annotated instruments in the first frame. We propose MDAL, a meta-learning based dynamic online adaptive learning scheme with a two-stage framework to fast adapt the model parameters on the first frame and partial subsequent frames while predicting the results. MDAL learns the general knowledge of instruments and the fast adaptation ability through the video-specific meta-learning paradigm. The added gradient gate excludes the noisy supervision from pseudo masks for dynamic online adaptation on target videos. We demonstrate empirically that MDAL outperforms other state-of-the-art methods on two datasets (including a real-world RAS dataset). The promising performance on ex-vivo scenes also benefits the downstream tasks such as robot-assisted suturing and camera control. Copyright © 2021, The Authors. All rights reserved.

关键词： Surgical equipment

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for human Locomotion Analysis in Lower-Limb Exoskeletons: A Comparative Study

arXiv

引用

arXiv 2025年

作者： Coser, Omar Tamantini, Christian Tortora, Matteo Furia, Leonardo Sicilia, Rosa Zollo, Loredana Soda, Paolo Unit of Computer Systems & Bioinformatics Università Campus Bio-Medico di Roma Via Álvaro del Portillo 21 Rome00128 Italy Unit of Advanced Robotics and Human-Centered Technologies Università Campus Bio-Medico di Roma Via Álvaro del Portillo 21 Rome00128 Italy Dipartimento di Ingegneria Navale Elettrica Elettronica e delle Telecomunicazioni Università degli Studi di Genova Via all’Opera Pia 11a Genova16145 Italy Department of Diagnostics and Intervention Radiation Physics Biomedical Engineering Umeå University Universitetstorget 4 Umeå40196 Sweden Institute of Cognitive Sciences and Technologies National Research Council of Italy Rome00196 Italy

Wearable robotics for lower-limb assistance have become a pivotal area of research, aiming to enhance mobility for individuals with physical impairments or augment the performance of able-bodied users. Accurate and adaptive control systems are essential to ensure seamless interaction between the wearer and the robotic device, particularly when navigating diverse and dynamic terrains. Despite the recent advances in neural networks for time series analysis, no attempts have been directed towards the classification of ground conditions, categorized into five classes and subsequently determining the ramp’s slope and stair’s height. In this respect, this paper presents an experimental comparison between eight deep neural network backbones to predict high-level locomotion parameters across diverse terrains. All the models are trained on the publicly available CAMARGO 2021 dataset. IMU-only data equally or outperformed IMU+EMG inputs, promoting a cost-effective and efficient design. Indeeds, using three IMU sensors, the LSTM achieved high terrain classification accuracy (0.94 ± 0.04) and precise ramp slope (1.95 ± 0.58°) and the CNN-LSTM a stair height (15.65 ± 7.40 mm) estimations. As a further contribution, SHAP analysis justified sensor reduction without performance loss, ensuring a lightweight setup. The system operates with 2 ms inference time, supporting real-time applications. The code is code available at https://***/cosbidev/human-Locomotion-Identification. © 2025, CC BY.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Walking-in-Place Characteristics-Based Geriatric Assessment Using Deep Convolutional Neural Networks

Walking-in-Place Characteristics-Based Geriatric Assessment ...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Dawoon Jung Mau Dung Nguyen Mina Park Miji Kim Chang Won Won Jinwook Kim Kyung-Ryoul Mun Center for Imaging Media Research KIST Seoul South Korea Department of Human Computer Interface & Robotics Engineering University of Science and Technology Daejeon South Korea Department of Biomedical Science and Technology College of Medicine East-West Medical Research Institute Kyung Hee University Seoul South Korea Department of Family Medicine College of Medicine Kyung Hee University Seoul South Korea

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

The world population is aging, and this phenomenon is expected to continue for the next decades. This study aimed to propose a simple and reliable method that can be used for daily in-home monitoring of frailty and cognitive dysfunction in the elderly based on their walking-in-place characteristics. Fifty-four community-dwelling elderly people aged 65 years or older participated in this study. The participants were categorized into the robust and the non-robust groups according to the FRAIL scale. The mini-mental state examination was used to classify the cognitive impairment and the non-cognitive impairment groups. The 3-axis acceleration and the 3-axis angular velocity signals were measured using the inertial measurement units attached to the foot, shank, thigh, and posterior pelvis while each participant was walking in place for 20 seconds. The walking-in-place spectrograms were acquired by applying time-frequency analysis to the lower body movement signals measured in one stride. Four-fold cross-validation was applied to 80% of the total samples and the remaining 20% were used as test data. The deep convolutional neural network-based classifiers trained with the walking-in-place spectrograms enabled to categorize the robust and the non-robust groups with 94.63% accuracy and classify the cognitive impairment and the non-cognitive impairment groups with 97.59% accuracy. This study suggests that the walking-in-place spectrograms, which can be obtained without spacious experimental space, cumbersome equipment, and laborious processes, are effective indicators of frailty and cognitive dysfunction in the elderly.

关键词： Spectrogram Foot Acceleration Angular velocity Atmospheric measurements Particle measurements Senior citizens

来源：评论

学校读者我要写书评

暂无评论

GardnerNet: An Interpretable Deep Learning Model for Quantitative human Blastocyst Evaluation - A Retrospective Model Development and Validation Study

SSRN

引用

SSRN 2024年

作者： Liu, Hang Chen, Longbin Shan, Guanqiao Sun, Chen Liao, Hongqing Lu, Changfu Zhang, Shuoping Dong, Shaonan Xu, Xinxin Yan, Qiuyun Gong, Fei Zhang, Zhuoran Dai, Changsheng Chen, Wenyuan Song, Haocong Chen, Lei Sun, Haixiang Wang, Shanshan Lin, Ge Sun, Yu Gu, Yifan Department of Mechanical and Industrial Engineering University of Toronto 5 King’s College Road TorontoONM5S 3G8 Canada Institute of Reproductive and Stem Cell Engineering School of Basic Medical Science Central South University 172 Tongzipo Road Hunan Province Changsha China Hengyang Nanhua-Xinghui Reproductive Health Hospital 30 Jiefang Road Hunan Province Hengyang China The second Affiliated Hospital Hengyang Medical School University of South China 30 Jiefang Road Hunan Province Hengyang City China Reproductive & Genetic Hospital of CITIC-Xiangya 567 Tongzipo Road Hunan Province Changsha China NHC Key Laboratory of Human Stem Cell and Reproductive Engineering School of Basic Medical Science Central South University 172 Tongzipo Road Hunan Province Changsha China Clinical Research Center for Reproduction and Genetics in Hunan Province Reproductive & Genetic Hospital of CITIC-Xiangya 567 Tongzipo Road Hunan Province Changsha China School of Science and Engineering The Chinese University of Hong Kong-Shenzhen 2001 Longxiang Boulevard Longgang District Shenzhen China Institute of Robotics and Intelligent Systems Dalian University of Technolgy 2 Linggong Road Liaoning Province Dalian China Department of Computer Science University of Toronto 40 St George Street TorontoONM5S 2E4 Canada Center for Reproductive Medicine and Obstetrics and Gynecology Nanjing Drum Tower Hospital Nanjing University Medical School 321 Zhongshan Road Jiangsu Province Nanjing China National Engineering and Research Center of Human Stem Cell 8 Luyun Road Jiangsu Province Changsha China Department of Electrical and Computer Engineering 10 King’s College Road TorontoONM5S 3G8 Canada Institute of Biomedical Engineering University of Toronto 164 College Street TorontoONM5S 3G9 Canada

Background: Selecting the blastocyst with the highest potential for live birth from a cohort is crucial for the success of in vitro fertilization (IVF). While the Gardner and Schoolcraft morphological grading system, commonly known as the Gardner grading system, is widely used by embryologists worldwide, blastocysts having similar or the same inner cell mass (ICM) and trophectoderm (TE) grades cause challenges for embryologists in decision-making. Furthermore, human assessment is subjective and inconsistent in predicting which blastocysts have higher potential to result in live birth. This study aims to develop an interpretable, quantitative method aligned with the Gardner grading system, providing continuous scores that correlate with live birth outcomes, thereby assisting embryologists in improving blastocyst selection. Methods: In this retrospective study, we developed GardnerNet, an interpretable deep learning model that outputs expansion degree grade and continuous scores quantifying a blastocyst's ICM morphology and TE morphology, based on the Gardner grading system. The continuous ICM and TE scores were calculated by weighting each base grade's predicted probability and summing the predicted probabilities. To represent each blastocyst's overall potential for live birth, we combined the ICM and TE scores using their odds ratios (ORs) for live birth. We further assessed the correlation between the ICM score, TE score, and the OR-combined score (adjusted for expansion degree) with live birth rates by applying GardnerNet to blastocysts with known live birth outcomes. To test its generalizability, we also applied GardnerNet to an external IVF institution, accounting for variations in imaging conditions, live birth rates, and embryologists' experience levels. Findings: GardnerNet was developed using data from 2760 blastocysts with majority-voted grades for expansion degree, ICM, and TE. The model achieved mean area under the receiver operating characteristic curve

关键词： Risk assessment

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：