检索结果-内蒙古大学图书馆

Learning Time-Series Images of Niacin Skin-Flushing Test for the Diagnosis of Schizophrenia and Affective Disorder

学校读者我要写书评

暂无评论

Learning Time-Series Images of Niacin Skin-Flushing Test for...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yuyang Huang Shiwen Dong Dandan Wang Chunling Wan Yang Yang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China Bio-X Institutes Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders Ministry of Education Shanghai Jiao Tong University Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Niacin skin-flushing test is a promising method for fast and objective diagnosis of schizophrenia and affective disorder. Compared to healthy controls, the patients have attenuated flushing extent and reduced flushing rate. The traditional analysis of niacin test relies on manually evaluated flushing extent, while flushing patterns sh own in the sk in test images have not yet been considered. To exploit the potential of raw images for diagnosis and avoid subjective and time-consuming estimation of the flushing levels, we propose a CNN-LSTM hybrid model to learn the time-series of images captured in the niacin skin-flushing test. Moreover, an attention layer is introduced to enhance the model performance and interpretability. We collect a data set of 796 participants, and the experimental results show that the new model outperforms the traditional 4-point scaled measurement and conventional deep learning methods by large margins. Besides, the attention scores yielded by the model reveals key time points during the flushing reaction.

关键词： Deep learning Atmospheric measurements Mental disorders Biological system modeling Estimation Biomedical measurement Particle measurements

Rethinking Textual Adversarial Defense for Pre-trained Language Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Jiayi Bao, Rongzhou Zhang, Zhuosheng Zhao, Hai The 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 MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Ant Group China

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels (sentence / word / character), adversarial attacks can fool PrLMs to generate incorrect predictions, which questions the robustness of PrLMs. However, we find that most existing textual adversarial examples are unnatural, which can be easily distinguished by both human and machine. Based on a general anomaly detector, we propose a novel metric (Degree of Anomaly) as a constraint to enable current adversarial attack approaches to generate more natural and imperceptible adversarial examples. Under this new constraint, the success rate of existing attacks drastically decreases, which reveals that the robustness of PrLMs is not as fragile as they claimed. In addition, we find that four types of randomization can invalidate a large portion of textual adversarial examples. Based on anomaly detector and randomization, we design a universal defense framework, which is among the first to perform textual adversarial defense without knowing the specific attack. Empirical results show that our universal defense framework achieves comparable or even higher after-attack accuracy with other specific defenses, while preserving higher original accuracy at the same time. Our work discloses the essence of textual adversarial attacks, and indicates that (i) further works of adversarial attacks should focus more on how to overcome the detection and resist the randomization, otherwise their adversarial examples would be easily detected and invalidated;and (ii) compared with the unnatural and perceptible adversarial examples, it is those undetectable adversarial examples that pose real risks for PrLMs and require more attention for future robustness-enhancing strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Network security

Pain level and pain-related behaviour classification using GRU-based sparsely-connected RNNs

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dehshibi, Mohammad Mahdi Olugbade, Temitayo Diaz-De-Maria, Fernando Bianchi-Berthouze, Nadia Tajadura-Jiménez, Ana Department of Computer Science and Engineering Universidad Carlos III de Madrid Leganés Spain UCL Interaction Centre University College London London United Kingdom Department of Signal Theory and Communications Universidad Carlos III de Madrid Leganés Spain Unconventional Computing Laboratory University of the West of England Bristol United Kingdom

There is a growing body of studies on applying deep learning to biometrics analysis. Certain circumstances, however, could impair the objective measures and accuracy of the proposed biometric data analysis methods. For instance, people with chronic pain (CP) unconsciously adapt specific body movements to protect themselves from injury or additional pain. Because there is no dedicated benchmark database to analyse this correlation, we considered one of the specific circumstances that potentially influence a person’s biometrics during daily activities in this study and classified pain level and pain-related behaviour in the EmoPain database. To achieve this, we proposed a sparsely-connected recurrent neural networks (s-RNNs) ensemble with the gated recurrent unit (GRU) that incorporates multiple autoencoders using a shared training framework. This architecture is fed by multidimensional data collected from inertial measurement unit (IMU) and surface electromyography (sEMG) sensors. Furthermore, to compensate for variations in the temporal dimension that may not be perfectly represented in the latent space of s-RNNs, we fused hand-crafted features derived from information-theoretic approaches with represented features in the shared hidden state. We conducted several experiments which indicate that the proposed method outperforms the state-of-the-art approaches in classifying both pain level and pain-related behaviour. © 2022, CC BY.

关键词： Recurrent neural networks

E-ffective: A visual analytic system for exploring the emotion and effectiveness of inspirational speeches

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Maher, Kevin Huang, Zeyuan Song, Jiancheng Deng, Xiaoming Lai, Yu-Kun Ma, Cuixia Wang, Hao Liu, Yong-Jin Wang, Hongan Institute of Software Chinese Academy of Sciences Tsinghua University China State Key Laboratory of Computer Science Beijing Key Lab of Human-Computer Interaction Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China Cardiff University United Kingdom Alibaba Group China Tsinghua University China

What makes speeches effective has long been a subject for debate, and until today there is broad controversy among public speaking experts about what factors make a speech effective as well as the roles of these factors in speeches. Moreover, there is a lack of quantitative analysis methods to help understand effective speaking strategies. In this paper, we propose E-ffective, a visual analytic system allowing speaking experts and novices to analyze both the role of speech factors and their contribution in effective speeches. From interviews with domain experts and investigating existing literature, we identified important factors to consider in inspirational speeches. We obtained the generated factors from multi-modal data that were then related to effectiveness data. Our system supports rapid understanding of critical factors in inspirational speeches, including the influence of emotions by means of novel visualization methods and interaction. Two novel visualizations include E-spiral (that shows the emotional shifts in speeches in a visually compact way) and E-script (that connects speech content with key speech delivery information). In our evaluation we studied the influence of our system on experts' domain knowledge about speech factors. We further studied the usability of the system by speaking novices and experts on assisting analysis of inspirational speech effectiveness. Copyright © 2021, The Authors. All rights reserved.

关键词： Visualization

Multi-span style extraction for generative reading comprehension

学校读者我要写书评

暂无评论

Multi-span style extraction for generative reading comprehen...

2021 Workshop on Scientific Document Understanding, SDU 2021

作者： Yang, Junjie Zhang, Zhuosheng Zhao, Hai SJTU-ParisTech Elite Institute of Technology Shanghai Jiao Tong University Shanghai China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Generative machine reading comprehension (MRC) requires a model to generate well-formed answers. For this type of MRC, answer generation method is crucial to the model performance. However, generative models, which are supposed to be the right model for the task, in generally perform poorly. At the same time, single-span extraction models have been proven effective for extractive MRC, where the answer is constrained to a single span in the passage. Nevertheless, they generally suffer from generating incomplete answers or introducing redundant words when applied to the generative MRC. Thus, we extend the single-span extraction method to multi-span, proposing a new framework which enables generative MRC to be smoothly solved as multi-span extraction. Thorough experiments demonstrate that this novel approach can alleviate the dilemma between generative models and single-span models and produce answers with better-formed syntax and semantics. Copyright © 2021for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Extraction

An alternate statistical lens to look at collaboration data: Extreme value theory 13

学校读者我要写书评

暂无评论

An alternate statistical lens to look at collaboration data:...

13th International Conference on computer Supported Collaborative Learning - A Wide Lens: Combining Embodied, Enactive, Extended, and Embedded Learning in Collaborative Settings, CSCL 2019

作者： Sharma, Kshitij Olsen, Jennifer Department of Computer Science Norwegian University of Science and Technology Norway Computer Human Interaction Lab in Learning and Instruction École Polytechnique Fédérale de Lausanne Switzerland

ISBN: (纸本)9781732467231

To provide beneficial feedback to students during their collaboration, it is important to identify behaviors that are indicative of good collaboration. However, in a collaborative learning session, students engage in a range of behaviors and it can be difficult to indicate which of those behaviors correlate with higher outcomes. In this paper, we propose using Extreme Value Theory (EVT), a method that considers the data points in the tail (upper or lower) of the distribution, to analyse the relationship between collaborative process variables and outcome measures through insights derived from high impact, low-frequency events. Specifically, in this paper, we analyse the relationship between dual gaze patterns and outcome measures across two different datasets. In both datasets we found that students with lower outcomes had lower focus during the collaborative session. This paper provides a contribution by both introducing EVT as a viable method for analysing CSCL data as well as demonstrating the effectiveness of eyetracking as a collaborative indicator to use to adapt to in real-time. © ISLS.

关键词： Students

Speech AI for All: Promoting Accessibility, Fairness, Inclusivity, and Equity

学校读者我要写书评

暂无评论

Speech AI for All: Promoting Accessibility, Fairness, Inclus...

2025 CHI Conference on human Factors in Computing Systems, CHI EA 2025

作者： Wu, Shaomei Wenzel, Kimi Li, Jingjin Li, Qisheng Pradhan, Alisha Kushalnagar, Raja Lea, Colin Koenecke, Allison Vogler, Christian Hasegawa-Johnson, Mark Su, Norman Makoto Ratner, Nan Bernstein *** Mountain ViewCA United States Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States *** SeattleWA United States Department of Informatics Ying Wu College of Computing New Jersey Institute of Technology NewarkNJ United States Gallaudet University WashingtonDC United States Apple CupertinoCA United States Cornell University IthacaNY United States Technology Access Program Gallaudet University WashingtonDC United States The Grainger College of Engineering University of Illinois Urbana-Champaign Urbana-ChampaignIL United States Department of Computational Media University of California Santa Cruz Santa CruzCA United States Department of Hearing and Speech Sciences University of Maryland College Park College ParkMD United States Neuroscience and Cognitive Science University of Maryland College Park College ParkMD United States

ISBN: (纸本)9798400713958

Trained and optimized for typical and fluent speech, speech AI works poorly for people with speech diversities, often interrupting them and misinterpreting their speech. The increasing deployment of speech AI in automated phone menus, AI-conducted job interviews, and everyday devices poses tangible risks to people with speech diversities. To mitigate these risks, this workshop aims to build a multidisciplinary coalition and set the research agenda for fair and accessible speech AI. Bringing together a broad group of academics and practitioners with diverse perspectives, including HCI, AI, and other relevant fields such as disability studies, speech language pathology, and law, this workshop will establish a shared understanding of the technical challenges for fair and accessible speech AI, as well as its ramifications in design, user experience, policy, and society. In addition, the workshop will invite and highlight first-person accounts from people with speech diversities, facilitating direct dialogues and collaboration between speech AI developers and the impacted communities. The key outcomes of this workshop include a summary paper that synthesizes our learnings and outlines the roadmap for improving speech AI for people with speech diversities, as well as a community of scholars, practitioners, activists, and policy makers interested in driving progress in this domain. © 2025 Copyright held by the owner/author(s).

关键词： Speech enhancement

Experience with the use of a digital sleep diary in symptom management by individuals with insomnia -a pilot mixed method study

学校读者我要写书评

暂无评论

Sleep Medicine: X 2023年 6卷 100093页

作者： Thorshov, Thea Christine Øverby, Caroline Tonje Hansen, Diana Dobran Bong, Way Kiat Skifjeld, Knut Hurlen, Petter Dammen, Toril Moen, Anne Hrubos-Strøm, Harald Division of Surgery Department of Otorhinolaryngology Akershus University Hospital Lørenskog Norway Faculty of Technology Art and Design Department of Computer Science Human-Computer Interaction and Universal Design of ICT Oslo Metropolitan University Oslo Norway Norsk e-helse Oslo Norway Division of Clinical Informatics Department of Diagnostics and Technology Akershus University Hospital Lørenskog Norway Faculty of Medicine Institute of Clinical Medicine Campus Ahus University of Oslo Norway Faculty of Medicine Institute of Health and Society Department of Nursing Science University of Oslo Norway Faculty of Medicine Institute of Clinical Medicine University of Oslo Norway Department of Research and Innovation Division of Mental Health and Addiction Oslo University Hospital Oslo Norway

Background: Insomnia is the most common sleep disorder. The recommended treatment is cognitive behavioural therapy for insomnia (CBTi). A sleep diary is a core tool in CBTi. We have developed a digital sleep diary with a standardised feedback function. Aim: To study feasibility of the digital sleep diary in participants of the Akershus Sleep Apnea (ASAP) cohorts with difficulties falling asleep or maintaining sleep. To describe sleep diary engagement and explore experiences with the digital sleep diary with potential influences in insomnia symptom management. Material and methods: Twenty participants were recruited from the ASAP. All filled out a digital sleep diary up to 12 weeks. Treatment options provided were a self-help book (N = 11) or electroencephalography neurofeedback (N = 9) in addition to the sleep diary standardised feedback function. We collected quantitative data from the sleep diary reports and we sub-divided insomnia by sleep onset insomnia and non-sleep onset insomnia. Finally, we performed qualitative interviews. Results: The median number of entries to the sleep diary was 81 (25th quartile: 26, 75th quartile 84). In the qualitative analysis, we identified two main themes;“structure and overview” and “usability and digital features”. Conclusion: The sleep diary was found to be feasible when distributed in combination with a self-help book or electroencephalography neurofeedback. The qualitative results emphasised the importance of a timely graphical overview and visualisations of self-recorded sleep. © 2023 The Authors

关键词： Digital sleep diary Engagement Feasibility Insomnia Motivation Patient-reported outcomes Self-management

Correlation-Distance Graph Learning for Treatment Response Prediction from rs-fMRI

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xiatan Zheng, Sisi Shum, Hubert P.H. Zhang, Haozheng Song, Nan Song, Mingkang Jia, Hongxiao Beijing Key Laboratory of Mental Disorders National Clinical Research Center for Mental Disorders National Center for Mental Disorders Beijing Anding Hospital Capital Medical University Beijing China Advanced Innovation Center for Human Brain Protection Beijing Anding Hospital Capital Medical University Beijing China Department of Computer Science Durham University Durham United Kingdom

Resting-state fMRI (rs-fMRI) functional connectivity (FC) analysis provides valuable insights into the relationships between different brain regions and their potential implications for neurological or psychiatric disorders. However, specific design efforts to predict treatment response from rs-fMRI remain limited due to difficulties in understanding the current brain state and the underlying mechanisms driving the observed patterns, which limited the clinical application of rs-fMRI. To overcome that, we propose a graph learning framework that captures comprehensive features by integrating both correlation and distance-based similarity measures under a contrastive loss. This approach results in a more expressive framework that captures brain dynamic features at different scales and enables more accurate prediction of treatment response. Our experiments on the chronic pain and depersonalization disorder datasets demonstrate that our proposed method outperforms current methods in different scenarios. To the best of our knowledge, we are the first to explore the integration of distance-based and correlation-based neural similarity into graph learning for treatment response prediction. © 2023, CC BY.

关键词： Forecasting