检索结果-内蒙古大学图书馆

Learning Co-Speech Gesture for Multimodal Aphasia Type Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lee, Daeun Son, Sejung Jeon, Hyolim Kim, Seungbae Han, Jinyoung Department of Applied Artificial Intelligence Sungkyunkwan University Seoul Korea Republic of Department of Human-AI Interaction Sungkyunkwan University Seoul Korea Republic of Department of Computer Science & Engineering University of South Florida TampaFL United States

Aphasia, a language disorder resulting from brain damage, requires accurate identification of specific aphasia types, such as Broca’s and Wernicke’s aphasia, for effective treatment. However, little attention has been paid to developing methods to detect different types of aphasia. Recognizing the importance of analyzing co-speech gestures for distinguish aphasia types, we propose a multimodal graph neural network for aphasia type detection using speech and corresponding gesture patterns. By learning the correlation between the speech and gesture modalities for each aphasia type, our model can generate textual representations sensitive to gesture information, leading to accurate aphasia type detection. Extensive experiments demonstrate the superiority of our approach over existing methods, achieving state-of-the-art results (F1 84.2%). We also show that gesture features outperform acoustic features, highlighting the significance of gesture expression in detecting aphasia types. We provide the codes for reproducibility purposes1 Copyright © 2023, The Authors. All rights reserved.

关键词： Damage detection

User-Driven Value Alignment: Understanding Users’ Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fan, Xianzhe Xiao, Qing Zhou, Xuhui Pei, Jiaxin Sap, Maarten Lu, Zhicong Shen, Hong Tsinghua University Beijing China Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Language Technologies Institute Carnegie Mellon University PittsburghPA United States Stanford University StanfordCA United States Department of Computer Science George Mason University FairfaxVA United States

Large language model-based AI companions are increasingly viewed by users as friends or romantic partners, leading to deep emotional bonds. However, they can generate biased, discriminatory, and harmful outputs. Recently, users are taking the initiative to address these harms and re-align AI companions. We introduce the concept of user-driven value alignment, where users actively identify, challenge, and attempt to correct AI outputs they perceive as harmful, aiming to guide the AI to better align with their values. We analyzed 77 social media posts about discriminatory AI statements and conducted semi-structured interviews with 20 experienced users. Our analysis revealed six common types of discriminatory statements perceived by users, how users make sense of those AI behaviors, and seven user-driven alignment strategies, such as gentle persuasion and anger expression. We discuss implications for supporting user-driven value alignment in future AI systems, where users and their communities have greater agency. Copyright © 2024, The Authors. All rights reserved.

关键词：

Left inferior parietal lobe and auditory cortex jointly contribute to sound knowledge retrieval

学校读者我要写书评

暂无评论

Brain Stimulation 2025年第4期18卷 1037-1047页

作者： Kuhnke, Philipp Numssen, Ole Voeller, Johannah Cheung, Vincent K.M. Weise, Konstantin Kiefer, Markus Hartwigsen, Gesa Wilhelm Wundt Institute for Psychology Leipzig University Germany Research Group Cognition and Plasticity Max Planck Institute for Human Cognitive and Brain Sciences (MPI CBS) Leipzig Germany Methods and Development Group Brain Networks MPI CBS Leipzig Germany TMS Group Department of Neuroscience and Biomedical Engineering Aalto University Finland TMS Lab Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital Boston United States Department of Experimental Psychology University of Granada Spain Mind Brain and Behavior Research Center (CIMCYC) University of Granada Spain Sony Computer Science Laboratories Tokyo Japan Leipzig University of Applied Sciences HTWK Leipzig Germany Department of Psychiatry Ulm University Germany

Background: Conceptual knowledge is central to human cognition. Neuroimaging studies suggest that conceptual processing relies on the joint contribution of modality-specific perceptual-motor and multimodal brain regions. In particular, the multimodal left inferior parietal lobe (IPL) couples with auditory association cortex during sound knowledge retrieval and with somatomotor cortex during action feature retrieval. However, it remains unknown whether the interaction between modality-specific and multimodal cortices is causally relevant for conceptually-guided behavior. Methods: To tackle this issue, we applied offline transcranial magnetic stimulation (TMS) over modality-specific cortex (somatomotor, auditory, or sham), before 24 healthy participants received online TMS over multimodal cortex (IPL, or sham) during action and sound knowledge tasks on written words. For the first time in a TMS study on higher cognition, TMS targeting and dosing were optimized using individual a priori computational electric field simulations. Results: We found that combined stimulation of auditory association cortex and multimodal IPL selectively impaired sound judgments, but not action judgments, on low sound–low action words (BF₁₀ = 5.316). Unifocal TMS over auditory cortex or IPL alone did not disrupt behavior, suggesting adaptive compensatory plasticity. Conclusions: These results indicate that the joint contribution of multimodal IPL and auditory cortex is causally relevant for sound knowledge retrieval: The functional relevance of left IPL depends on the integrity of the auditory cortex, and vice versa, as single perturbation of either region did not disrupt performance. Our findings support “hybrid theories” of conceptual processing, which propose that task-dependent functional interactions between modality-specific and multimodal regions are crucial. © 2025 The Authors

关键词： Compensation Computational modeling Concepts Plasticity Semantics TMS

A Passive Variable Impedance Control Strategy with Viscoelastic Parameters Estimation of Soft Tissues for Safe Ultrasonography

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Beber, Luca Lamon, Edoardo Nardi, Davide Fontanelli, Daniele Saveriano, Matteo Palopoli, Luigi Department of Industrial Engineering Università di Trento Trento Italy Department of Information Engineering and Computer Science Università di Trento Trento Italy Human-Robot Interfaces and Interaction Istituto Italiano di Tecnologia Genoa Italy

In the context of telehealth, robotic approaches have proven a valuable solution to in-person visits in remote areas, with decreased costs for patients and infection risks. In particular, in ultrasonography, robots have the potential to reproduce the skills required to acquire high-quality images while reducing the sonographer’s physical efforts. In this paper, we address the control of the interaction of the probe with the patient’s body, a critical aspect of ensuring safe and effective ultrasonography. We introduce a novel approach based on variable impedance control, allowing the real-time optimisation of compliant controller parameters during ultrasound procedures. This optimisation is formulated as a quadratic programming problem and incorporates physical constraints derived from viscoelastic parameter estimations. Safety and passivity constraints, including an energy tank, are also integrated to minimise potential risks during human-robot interaction. The proposed method’s efficacy is demonstrated through experiments on a patient’s dummy torso, highlighting its potential for achieving safe behaviour and accurate force control during ultrasound procedures, even in cases of contact loss. Copyright © 2023, The Authors. All rights reserved.

关键词： Parameter estimation

Congenital hydrocephalus:a review of recent advances in genetic etiology and molecular mechanisms

学校读者我要写书评

暂无评论

Military Medical Research 2024年第6期11卷 942-958页

作者： Xiu-Yun Liu Xin Song Marek Czosnyka Chiara Robba Zofia Czosnyka Jennifer Lee Summers Hui-Jie Yu Guo-Yi Gao Peter Smielewski Fang Guo Mei-Jun Pang Dong Ming Medical School Tianjin UniversityTianjin 300072China State Key Laboratory of Advanced Medical Materials and Devices Tianjin UniversityTianjin 300072China Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration Tianjin 300380China School of Pharmaceutical Science and Technology Tianjin University300072 TianjinChina Department of Clinical Neurosciences Addenbrooke’s HospitalUniversity of CambridgeCambridge CB20QQUK San Martino Policlinico Hospital IRCCS for Oncology and Neuroscience16132 GenoaItaly Department of Anesthesiology and Critical Care Medicine Johns Hopkins UniversityBaltimoreMD 21287USA Department of Neurosurgery Tianjin Medical University General HospitalTianjin 300052China Department of Neurosurgery Beijing Tiantan HospitalCapital Medical UniversityBeijing 100070China Department of Neurosurgery Tianjin Huanhu HospitalTianjin 300350China

The global prevalence rate for congenital hydrocephalus(CH)is approximately one out of every five hundred births with multifaceted predisposing factors at *** influences stand as a major contributor to CH pathogenesis,and epidemiological evidence suggests their involvement in up to 40%of all cases observed *** about an individual’s genetic susceptibility can significantly improve prognostic precision while aiding clinical decision-making ***,the precise genetic etiology has only been pinpointed in fewer than 5%of human *** occurrences of CH cases are required for comprehensive gene sequencing aimed at uncovering additional potential genetic loci.A deeper comprehension of its underlying genetics may offer invaluable insights into the molecular and cellular basis of this brain *** review provides a summary of pertinent genes identified through gene sequencing technologies in humans,in addition to the 4 genes currently associated with CH(2 X-linked genes L1CAM and AP1S2,2 autosomal recessive MPDZ and CCDC88C).Others predominantly participate in aqueduct abnormalities,ciliary movement,and nervous system *** prospective CH-related genes revealed through animal model gene-editing techniques are further outlined,focusing mainly on 4 pathways,namely cilia synthesis and movement,ion channels and transportation,Reissner’s fiber(RF)synthesis,cell apoptosis,and ***,the proper functioning of motile cilia provides significant impulsion for cerebrospinal fluid(CSF)circulation within the brain ventricles while mutations in cilia-related genes constitute a primary cause underlying this *** far,only a limited number of CH-associated genes have been identified in *** integration of genotype and phenotype for disease diagnosis represents a new trend in the medical *** models provide insights into the pathogenesis of CH and contribute to our understanding of its association w

关键词： Congenital hydrocephalus Genetic disease Central system Cilia Ventricle

Variable Selection for the Prediction of TSS, pH and TA of Intact Berries of Thompson Seedless Grapes from their NIS Reflection 30

学校读者我要写书评

暂无评论

Variable Selection for the Prediction of TSS, pH and TA of I...

30th International Conference on Software, Telecommunications and computer Networks, SoftCOM 2022

作者： Chariskou, Chrysanthi Bazinas, Christos Daniels, Andries J. Opara, Umezuruike L. Nieuwoudt, Helene H. Kaburlasos, Vassilis G. Human-Machines Interaction Lab International Hellenic University Department of Computer Science Kavala Greece University of Stellenbosch Department of Viticulture and Oenology Stellenbosch South Africa University of Stellenbosch Faculty of AgriSciences Department of Horticultural Sciences Postharvest Technology Research Stellenbosch South Africa Institute for Wine Biotechnology University of Stellenbosch Department of Viticulture and Oenology Stellenbosch South Africa

ISBN: (数字)9789532901177

ISBN: (纸本)9789532901177

Wavenumbers of high absolute value of correlation coefficient to Total Soluble Solids (TSS), pH, or Titratable Acidity (TA) were selected from reflection Fourier transform near infrared (FT -NIR) spectra of intact grape berries of the white variety Thompson Seedless. Multiple linear regression (MLR) and partial least squares (PLS) regression were applied to the spectra to construct trained regression models able to predict TSS, pH, and TA. Square Pearson's correlation coefficient (R2) and the Mean Square Error (MSE) were used to evaluate the precision of prediction. TSS content was predicted with R2 score of 0.972 and MSE 0.094 using MLR and with R2 0.926 and MSE 0.223 using PLS regression. The pH prediction scores were R2 0.812 and MSE 0.002 with MLR. With PLS regression the values were R2 0.485 and MSE 0.004. TA can be predicted only from the second derivatives of the spectra. MLR produced R2 for prediction 0.745 and MSE 0.076, while the scores using PLS regression were R2 0.648 and MSE 0.114. It was concluded that variable selection could greatly improve the prediction accuracy. The appropriateness of the two regression methods depends on the structure of the spectra dataset and on the characteristics whose prediction is sought. © 2022 University of Split, FESB.

关键词： Multiple linear regression

SpeechMirror: A Multimodal Visual Analytics System for Personalized Reflection of Online Public Speaking Effectiveness

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Zeyuan He, Qiang Maher, Kevin Deng, Xiaoming Lai, Yu-Kun Ma, Cuixia Qin, Sheng-Feng Liu, Yong-Jin Wang, Hongan The Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences and also with the School of Computer Science and Technology University of Chinese Academy of Sciences China Diatom Design Limited Liability Company United States The School of Computer Science and Informatics Cardiff University United Kingdom The School of Design Northumbria University United Kingdom The Department of Computer Science and Technology MOE-Key Laboratory of Pervasive Computing Tsinghua University China

As communications are increasingly taking place virtually, the ability to present well online is becoming an indispensable skill. Online speakers are facing unique challenges in engaging with remote audiences. However, there has been a lack of evidence-based analytical systems for people to comprehensively evaluate online speeches and further discover possibilities for improvement. This paper introduces SpeechMirror, a visual analytics system facilitating reflection on a speech based on insights from a collection of online speeches. The system estimates the impact of different speech techniques on effectiveness and applies them to a speech to give users awareness of the performance of speech techniques. A similarity recommendation approach based on speech factors or script content supports guided exploration to expand knowledge of presentation evidence and accelerate the discovery of speech delivery possibilities. SpeechMirror provides intuitive visualizations and interactions for users to understand speech factors. Among them, SpeechTwin, a novel multimodal visual summary of speech, supports rapid understanding of critical speech factors and comparison of different speech samples, and SpeechPlayer augments the speech video by integrating visualization of the speaker's body language with interaction, for focused analysis. The system utilizes visualizations suited to the distinct nature of different speech factors for user comprehension. The proposed system and visualization techniques were evaluated with domain experts and amateurs, demonstrating usability for users with low visualization literacy and its efficacy in assisting users to develop insights for potential improvement. Copyright © 2023, The Authors. All rights reserved.

关键词： Modal analysis

CL-MIL: Multi-Instance Learning on Whole-Slide Images with Self-Supervised Contrastive Learning

学校读者我要写书评

暂无评论

CL-MIL: Multi-Instance Learning on Whole-Slide Images with S...

International Conference on computer and Communications (ICCC)

作者： Pengfei Xiu Dongying Liu Sheng Wang Hongliang Wang Wei Wang Shun Li Shenyang Institute of Computing Technology Chinese Academy of Science Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Department of Gastroenterology Shengjing Hospital of China Medical University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Histopathological examination of tissue slides is considered the gold standard for clinical cancer diagnosis. However, it heavily relies on pathologists' subjective judgment and involves substantial workload. Existing convolutional neural network (CNN)-based whole slide image (WSI) diagnostic methods suffer from high annotation costs and complex data acquisition processes. Therefore, this study proposes a weakly supervised multiple instance learning method based on self-supervised contrastive learning (CL-MIL) for WSI classification. By integrating self-supervised contrastive learning strategies, leveraging data augmentation through H&E stain separation, and introducing causal intervention via backdoor adjustment to mitigate dataset bias, our approach significantly enhances feature representation and classification performance in pathological images. Experimental results on the Camelyon16 and TCGA lung cancer datasets demonstrate that our method outperforms other comparable WSI classification models across various evaluation metrics, achieving higher diagnostic efficiency and accuracy. Additionally, our method exhibits good interpretability, enabling precise localization of pathological regions and providing robust technical support for clinical applications.

关键词： Measurement Location awareness Pathology Accuracy Weak supervision Lung cancer Contrastive learning Feature extraction Standards Image classification

CL-MIL: Multi-Instance Learning on Whole-Slide Images with Self-Supervised Contrastive Learning 10

学校读者我要写书评

暂无评论

CL-MIL: Multi-Instance Learning on Whole-Slide Images with S...

10th International Conference on computer and Communications, ICCC 2024

作者： Xiu, Pengfei Liu, Dongying Wang, Sheng Wang, Hongliang Wang, Wei Li, Shun Shenyang Institute of Computing Technology Chinese Academy of Science Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shengjing Hospital of China Medical University Department of Gastroenterology Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

关键词： Self-supervised learning