检索结果-内蒙古大学图书馆

Difficulty-aware meta-learning for rare disease diagnosis 23rd

学校读者我要写书评

暂无评论

Difficulty-aware meta-learning for rare disease diagnosis

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

作者： Li, Xiaomeng Yu, Lequan Jin, Yueming Fu, Chi-Wing Xing, Lei Heng, Pheng-Ann Department of Computer Science and Engineering The Chinese University of Hong Kong Shatin Hong Kong Department of Radiation Oncology Stanford University Stanford United States Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9783030597092

Rare diseases have extremely low-data regimes, unlike common diseases with large amount of available labeled data. Hence, to train a neural network to classify rare diseases with a few per-class data samples is very challenging, and so far, catches very little attention. In this paper, we present a difficulty-aware meta-learning method to address rare disease classifications and demonstrate its capability to classify dermoscopy images. Our key approach is to first train and construct a meta-learning model from data of common diseases, then adapt the model to perform rare disease classification. To achieve this, we develop the difficulty-aware meta-learning method that dynamically monitors the importance of learning tasks during the meta-optimization stage. To evaluate our method, we use the recent ISIC 2018 skin lesion classification dataset, and show that with only five samples per class, our model can quickly adapt to classify unseen classes by a high AUC of 83.3%. Also, we evaluated several rare disease classification results in the public Dermofit Image Library to demonstrate the potential of our method for real clinical practice. © Springer Nature Switzerland AG 2020.

关键词： Learning systems

A Precise Hip Protection System with Multi-scale Fall Warning Algorithm Based on Offset Displacement

学校读者我要写书评

暂无评论

A Precise Hip Protection System with Multi-scale Fall Warnin...

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

作者： Qiangqiang Chen Yanan Diao Yaping Wang Yumin Chen Yunkun Ning Guanglin Li Guoru Zhao CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Research Center for Neural Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China College of Computer Science and Technology Xiamen University of Technology China Department of Neurology Shenzhen Second People's Hospital Shenzhen China

Falls occur frequently in daily life and the damage to the body is irreversible. Therefore, it is crucial to implement timely and effective warning and protection systems for falls to minimize the damage caused by falls. Currently, the fall warning algorithm has shortcomings such as low recognition rates for falls and fall-risk movements and insufficient lead-time, the time before the subject impacts the floor, making it difficult for falling protection devices to function effectively. In this study, a multi-scale falls warning algorithm based on offset displacement is built, and a hip protection system is designed. The performance of the algorithm and the system is validated using 150 falling and 500 fall-risk actions from 10 volunteers. The results showed that the recognition accuracy for falling actions is 98.7% and the recognition accuracy for fall-risk actions is 99.4%, with an average lead-time of 402ms. The protection rate for falling movements reached 98.7%. This proposed algorithm and hip protection system have the potential to be applied in elderly communities, hospitals, and homes to reduce the damage caused by *** Relevance— This study provides important reference for clinicians in analyzing fall behaviors to patients at risk of falls in clinical settings, offering valuable technical support for ensuring the safety of patients in danger of falling. It also contributes to further promoting the development of falling-prevention medical devices.

关键词：

Dose-response effect of pre-exercise carbohydrates under muscle glycogen unavailability:Insights from McArdle disease

学校读者我要写书评

暂无评论

Journal of Sport and Health science 2024年第3期13卷 398-408页

作者： Pedro L.Valenzuela Alfredo Santalla Lidia B.Alejo Andrea Merlo Asuncion Bustos Laura Castellote-Belles Roser Ferrer-Costa Nicola A.Maffiuletti David Barranco-Gil Tomas Pinos Alejandro Lucia Physical Activity and Health Research Group(“PaHerg”) Research Institute of Hospital“12 de Octubre”(“imas12”)Madrid 28041Spain Department of Systems Biology University of AlcalaMadrid 28871Spain Department of Sport and Computer Science Section of Physical Education and SportsFaculty of SportUniversidad Pablo de OlavideSevilla 41013Spain EVOPRED Research Group Universidad Europea de CanariasTenerife 38300Spain Faculty of Sport Sciences Universidad Europea de MadridMadrid 28670Spain Gait&Motion Analysis Laboratory Sol et Salus HospitalTorre Pedrera di Rimini(RN)47922Italy Department of Clinical Biochemistry Laboratoris ClınicsHospital Universitari Vall d’HebronBarcelona 08035Spain Human Performance Lab Schulthess ClinicZurich 8008Switzerland Biomedical Research Networking Center on Rare Disorders(CIBERER) Barcelona 08035Spain Mitochondrial and Neuromuscular Disorders Unit Vall d’Hebron Institut de RecercaUniversitat Autonoma de BarcelonaBarcelona 08035Spain

Background:This study aimed to determine the effect of different carbohydrate(CHO)doses on exercise capacity in patients with McArdle disease—the paradigm of“exercise intolerance”,characterized by complete muscle glycogen unavailability—and to determine whether higher exogenous glucose levels affect metabolic responses at the McArdle muscle cell(in vitro)***:Patients with McArdle disease(n=8)and healthy controls(n=9)underwent a 12-min submaximal cycling constant-load bout followed by a maximal ramp test 15 min after ingesting a non-caloric *** a randomized,double-blinded,cross-over design,patients repeated the tests after consuming either 75 g or 150 g of CHO(glucose:fructose=2:1).Cardiorespiratory,biochemical,perceptual,and electromyographic(EMG)variables were ***,glucose uptake and lactate appearance were studied in vitro in wild-type and McArdle mouse myotubes cultured with increasing glucose concentrations(0.35,1.00,4.50,and 10.00 g/L).Results:Compared with controls,patients showed the“classical”second-wind phenomenon(after prior disproportionate tachycardia,myalgia,and excess electromyographic activity during submaximal exercise,all p<0.05)and an impaired endurance exercise capacity(-51%ventilatory threshold and55%peak power output,both p<0.001).Regardless of the CHO dose(p<0.05 for both doses compared with the placebo),CHO intake increased blood glucose and lactate levels,decreased fat oxidation rates,and attenuated the second wind in the ***,only the higher dose increased ventilatory threshold(+27%,p=0.010)and peak power output(+18%,p=0.007).In vitro analyses revealed no differences in lactate levels across glucose concentrations in wild-type myotubes,whereas a doseresponse effect was observed in McArdle ***:CHO intake exerts beneficial effects on exercise capacity in McArdle disease,a condition associated with total muscle glycogen *** of these benefits are dose dependent.

关键词： Endurance Glycogen storage disease Glycogenosis Nutrition Supplement

PUSH-PULL: CHARACTERIZING THE ADVERSARIAL ROBUSTNESS FOR AUDIO-VISUAL ACTIVE SPEAKER DETECTION

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Xuanjun Wu, Haibin Meng, Helen Lee, Hung-Yi Jang, Jyh-Shing Roger Department. of Computer Science Information Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Centre for Perceptual and Interactive Intelligence The Chinese University of Hong Kong Hong Kong Human-Computer Communications Laboratory The Chinese University of Hong Kong Hong Kong

Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD models hasn't been investigated, not to mention the effective defense against such attacks. In this paper, we are the first to reveal the vulnerability of AVASD models under audio-only, visual-only, and audio-visual adversarial attacks through extensive experiments. What's more, we also propose a novel audiovisual interaction loss (AVIL) for making attackers difficult to find feasible adversarial examples under an allocated attack budget. The loss aims at pushing the inter-class embeddings to be dispersed, namely non-speech and speech clusters, sufficiently disentangled, and pulling the intra-class embeddings as close as possible to keep them compact. Experimental results show the AVIL outperforms the adversarial training by 33.14 mAP (%) under multi-modal attacks. © 2022, CC0.

关键词： Budget control

Bayesian deep multi-instance learning for student performance prediction based on campus big data

学校读者我要写书评

暂无评论

Neurocomputing 2025年 647卷

作者： Jiayang Huang Keyi Yang Quan Wang Pengfei Yang Ziling Ruan Jiaxi Wang Zhi-Qiang Zhang School of Computer Science and Technology Xidian University Xi’an 710126 China The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province Xi’an 710126 China School of Electronic and Electrical Engineering Institute of Robotics Autonomous Systems and Sensing University of Leeds Leeds UK

Problem: Predicting student performance using campus big data and deep learning methods has emerged as a promising alternative to traditional psychological assessments, which are often delayed and subjective. However, existing deep learning approaches face significant challenges, including the sparsity of campus big data and susceptibility to overfitting. Objective: To address these issues, this study aims to develop a robust and effective framework for predicting student performance by overcoming data sparsity and overfitting problems. Method: We propose a novel Bayesian Deep Multi-Instance Learning (Bay-DeepMIL) framework. The method integrates multi-instance learning (MIL) to handle data sparsity and incorporates a Bayesian framework to treat network parameters as probabilistic distributions, enhancing robustness and mitigating overfitting. Additionally, a Bayesian multi-head attention mechanism is introduced to dynamically assign importance to different instances, improving the extraction of key information from multi-instance data. Results: Extensive experiments demonstrate that Bay-DeepMIL outperforms state-of-the-art methods in prediction accuracy. The framework also provides uncertainty estimates for each prediction, offering valuable confidence measures and decision support for educational stakeholders. Conclusion: The proposed Bay-DeepMIL framework not only advances the technical capabilities of predictive models but also provides practical tools for enhancing educational decision-making. This study underscores the effectiveness of integrating Bayesian inference with multi-instance learning to address core challenges such as data sparsity and model overfitting in student performance prediction.

关键词： Academic performance Bayesian neural network Deep learning Educational data mining Multi-instance learning

Improving AlphaFLOW for Efficient Protein Ensembles Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Shaoning Li, Mingyu Wang, Yusong He, Xinheng Zheng, Nanning Zhang, Jian Heng, Pheng Ann Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Medicinal Chemistry and Bioinformatics Center Shanghai Jiao Tong University School of Medicine China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Shanghai Institute of Materia Medica Chinese Academy of Sciences China

Investigating conformational landscapes of proteins is a crucial way to understand their biological functions and properties. AlphaFLOW stands out as a sequence-conditioned generative model that introduces flexibility into structure prediction models by fine-tuning AlphaFold under the flow-matching framework. Despite the advantages of efficient sampling afforded by flow-matching, AlphaFLOW still requires multiple runs of AlphaFold to finally generate one single conformation. Due to the heavy consumption of AlphaFold, its applicability is limited in sampling larger set of protein ensembles or the longer chains within a constrained timeframe. In this work, we propose a feature-conditioned generative model called AlphaFLOW-Lit to realize efficient protein ensembles generation. In contrast to the full fine-tuning on the entire structure, we focus solely on the light-weight structure module to reconstruct the conformation. AlphaFLOW-Lit performs on-par with AlphaFLOW and surpasses its distilled version without pretraining, all while achieving a significant sampling acceleration of around 47 times. The advancement in efficiency showcases the potential of AlphaFLOW-Lit in enabling faster and more scalable generation of protein ensembles. © 2024, CC BY.

关键词： Proteins

Environment-Driven Online LiDAR-Camera Extrinsic Calibration

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Zhiwei Li, Jiaqi Zhong, Ping Fan, Rui The Department of Control Science & Engineering The College of Electronics & Information Engineering Tongji University Shanghai201804 China The School of Computer Science and Engineering Central South University Hunan Changsha410083 China The National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Hunan Changsha410073 China The Department of Control Science & Engineering The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China

LiDAR-camera extrinsic calibration (LCEC) is the core for data fusion in computer vision. Existing methods typically rely on customized calibration targets or fixed scene types, lacking the flexibility to handle variations in sensor data and environmental contexts. This paper introduces EdO-LCEC, the first environment-driven, online calibration approach that achieves human-like adaptability. Inspired by the human perceptual system, EdO-LCEC incorporates a generalizable scene discriminator to actively interpret environmental conditions, creating multiple virtual cameras that capture detailed spatial and textural information. To overcome cross-modal feature matching challenges between LiDAR and camera, we propose dual-path correspondence matching (DPCM), which leverages both structural and textural consistency to achieve reliable 3D-2D correspondences. Our approach formulates the calibration process as a spatial-temporal joint optimization problem, utilizing global constraints from multiple views and scenes to improve accuracy, particularly in sparse or partially overlapping sensor views. Extensive experiments on real-world datasets demonstrate that EdO-LCEC achieves state-of-the-art performance, providing reliable and precise calibration across diverse, challenging environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

To Understand Representation of Layer-aware Sequence Encoders as Multi-order-Graph

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Duan, Sufeng Zhao, Hai 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

In this paper, we propose an explanation of representation for self-attention network (SAN) based neural sequence encoders, which regards the information captured by the model and the encoding of the model as graph structure and the generation of these graph structures respectively. The proposed explanation applies to existing works on SAN-based models and can explain the relationship among the ability to capture the structural or linguistic information, depth of model, and length of sentence, and can also be extended to other models such as recurrent neural network based models. We also propose a revisited multigraph called Multi-order-Graph (MoG) based on our explanation to model the graph structures in the SAN-based model as subgraphs in MoG and convert the encoding of SAN-based model to the generation of MoG. Based on our explanation, we further introduce a Graph-Transformer by enhancing the ability to capture multiple subgraphs of different orders and focusing on subgraphs of high orders. Experimental results on multiple neural machine translation tasks show that the Graph-Transformer can yield effective performance improvement. Copyright © 2021, The Authors. All rights reserved.

关键词： Neural machine translation

TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery

学校读者我要写书评

暂无评论

TraSeTR: Track-to-Segment Transformer with Contrastive Query...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Zixu Zhao Yueming Jin Pheng– Ann Heng Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Comouter Science University College London UK Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences

Surgical instrument segmentation - in general a pixel classification task - is fundamentally crucial for promoting cognitive intelligence in robot-assisted surgery (RAS). However, previous methods are struggling with discriminating instrument types and instances. To address above issues, we explore a mask classification paradigm that produces per-segment predictions. We propose TraSeTR, a novel Track-to-Segment Transformer that wisely exploits tracking cues to assist surgical instrument segmentation. TraSeTR jointly reasons about the instrument type, location, and identity with instance-level predictions i.e., a set of class-bbox-mask pairs, by decoding query embeddings. Specifically, we introduce the prior query that encoded with previous temporal knowledge, to transfer tracking signals to current instances via identity matching. A contrastive query learning strategy is further applied to reshape the query feature space, which greatly alleviates the tracking difficulty caused by large temporal variations. The effectiveness of our method is demonstrated with state-of-the-art instrument type segmentation results on three public datasets, including two RAS benchmarks from EndoVis Challenges and one cataract surgery dataset CaDIs.

关键词：