检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Durall, Ricard Keuper, Margret Keuper, Janis Competence Center High Performance Computing Fraunhofer ITWM Kaiserslautern Germany Data- and Webscience Group University Mannheim Germany IWR University of Heidelberg Germany Institute for Machine Learning and Analytics Offenburg University Germany

Generative convolutional deep neural networks, e.g. popular GAN architectures, are relying on convolution based up-sampling methods to produce non-scalar outputs like images or video sequences. In this paper, we show that common up-sampling methods, i.e. known as up-convolution or transposed convolution, are causing the inability of such models to reproduce spectral distributions of natural training data correctly. This effect is independent of the underlying architecture and we show that it can be used to easily detect generated data like deepfakes with up to 100% accuracy on public benchmarks. To overcome this drawback of current generative models, we propose to add a novel spectral regularization term to the training optimization objective. We show that this approach not only allows to train spectral consistent GANs that are avoiding high frequency errors. Also, we show that a correct approximation of the frequency spectrum has positive effects on the training stability and output quality of generative networks. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions

Watch Your Up-Convolution: CNN Based Generative Deep Neural ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ricard Durall Margret Keuper Janis Keuper Competence Center High Performance Computing Fraunhofer ITWM Kaiserslautern Germany IWR University of Heidelberg Germany Data and Web Science Group University of Mannheim Germany Institute for Machine Learning and Analytics Offenburg University Germany

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

关键词： Gallium nitride Convolution Distortion Neural networks Training Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Imaging Diagnostics in Neurosurgery

Artificial Intelligence for Imaging Diagnostics in Neurosurg...

引用

2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019

作者： Letyagin, Andrey Yu. Degtyareva, Liana O. Golushko, Sergey K. Rzaev, Jamil A. Amelin, Mihail E. Pavlovsky, Evgeniy N. Tuchinov, Bair N. Amelina, Evgeniya V. Moisak, Galina I. Bulgakova, Ekaterina G. Novosibirsk State University Novosibirsk Russia Federal State Budget Institution Federal Center of Neurosurgery Novosibirsk Russia FSBI 'Federal Neurosurgical Center' Novosibirsk Russia Stread Data Analytics Machine Learning Lab. Novosibirsk State University Novosibirsk Russia

ISBN: (纸本)9781728144016

Improving the accuracy and timeliness of medical imaging in everyday clinical neurosurgery practice is an urgent problem for the health care of all countries. This problem will be solved with the help of artificial intelligence (AI). By performing the search and contouring of 'suspicious' pathological objects, making automatic measurements on 3D medical images (MRI, CT), formalizing quantitative indicators and compiling medical statistical reports, AI can solve diagnostic problems in radiology and medical imaging. The effect of introducing AI will be at least a more accurate and quick interpretation of images, implemented through a set of decision-making tools for medical specialists. © 2019 IEEE.

关键词： Neurosurgery

来源：评论

学校读者我要写书评

暂无评论

Accurately predicting anticancer peptide using an ensemble of heterogeneously trained classifiers

引用

Informatics in Medicine Unlocked 2023年 42卷

作者： Azim, Sayed Mehedi Sabab, Noor Hossain Nuri Noshadi, Iman Alinejad-Rokny, Hamid Sharma, Alok Shatabda, Swakkhar Dehzangi, Iman Center for Computational and Integrative Biology Rutgers University Camden 08102 NJ United States Department of Computer Science and Engineering United International University Plot 2 United City Madani Avenue BaddaDhaka 1212 Bangladesh Department of Bioengineering University of California Riverside 92507 CA United States BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering The University of New South Wales (UNSW Sydney) Sydney NSW 2052 Australia UNSW Data Science Hub UNSW Sydney Sydney NSW 2052 Australia Health Data Analytics Program AI-enabled Processes Research Centre Macquarie University Sydney 2109 Australia Institute for Integrated and Intelligent Systems Griffith University Brisbane Australia Laboratory for Medical Science Mathematics RIKEN Center for Integrative Medical Sciences Yokohama 230-0045 Japan Department of Computer Science Rutgers University Camden 08102 NJ United States

The use of therapeutic peptides for the treatment of cancer has received tremendous attention in recent years. Anticancer peptides (ACPs) are considered new anticancer drugs which have several advantages over chemistry-based drugs including high specificity, strong tumor penetration capacity, and low toxicity level for normal cells. Due to the rise of experimentally verified bioactive peptides, several in silico approaches became imperative for the investigation of the characteristics of ACPs. In this paper, we proposed a new machine learning tool named iACP-RF that uses a combination of several sequence-based features and an ensemble of three heterogeneously trained Random Forest classifiers to accurately predict anticancer peptides. Experimental results show that our proposed model achieves an accuracy of 75.9% which outperforms other state-of-the-art methods by a significant margin. We also achieve 0.52, 75.6%, and 76.2% in terms of Matthews Correlation Coefficient (MCC), Sensitivity, and Specificity, respectively. iACP-RF as a standalone tool and its source code are publicly available at: https://***/MLBC-lab/iACP-RF. © 2023 The Authors

关键词： Anticancer peptides Ensemble learning Feature extraction Heterogeneous classifiers machine learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

Unmasking DeepFakes with simple features

arXiv

引用

arXiv 2019年

作者： Durall, Ricard Keuper, Margret Pfreundt, Franz-Josef Keuper, Janis Fraunhofer ITWM Germany IWR University of Heidelberg Germany Fraunhofer Center Machine Learning Germany Data and Web Science Group University Mannheim Germany Institute for Machine Learning and Analytics Offenburg University Germany

Deep generative models have recently achieved impressive results for many real-world applications, successfully generating high-resolution and diverse samples from complex data sets. Due to this improvement, fake digital contents have proliferated growing concern and spreading distrust in image content, leading to an urgent need for automated ways to detect these AI-generated fake images. Despite the fact that many face editing algorithms seem to produce realistic human faces, upon closer examination, they do exhibit artifacts in certain domains which are often hidden to the naked eye. In this work, we present a simple way to detect such fake face images - so-called DeepFakes. Our method is based on a classical frequency domain analysis followed by a basic classifier. Compared to previous systems, which need to be fed with large amounts of labeled data, our approach showed very good results using only a few annotated training samples and even achieved good accuracies in fully unsupervised scenarios. For the evaluation on high resolution face images, we combined several public data sets of real and fake faces into a new benchmark: Faces-HQ. Given such high-resolution images, our approach reaches a perfect classification accuracy of 100% when it is trained on as little as 20 annotated samples. In a second experiment, in the evaluation of the medium-resolution images of the CelebA data set, our method achieves 100% accuracy supervised and 96% in an unsupervised setting. Finally, evaluating a low-resolution video sequences of the FaceForensics++ data set, our method achieves 91% accuracy detecting manipulated videos. Copyright © 2019, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Harnessing multimodal approaches for depression detection using large language models and facial expressions

Npj mental health research

引用

Npj mental health research 2024年第1期3卷 66页

作者： Misha Sadeghi Robert Richer Bernhard Egger Lena Schindler-Gmelch Lydia Helene Rupp Farnaz Rahimi Matthias Berking Bjoern M Eskofier Machine Learning and Data Analytics Lab (MaD Lab) Department Artificial Intelligence in Biomedical Engineering (AIBE) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen 91052 Germany. misha.sadeghi@fau.de. Machine Learning and Data Analytics Lab (MaD Lab) Department Artificial Intelligence in Biomedical Engineering (AIBE) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen 91052 Germany. Chair of Visual Computing (LGDV) Department of Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen 91058 Germany. Chair of Clinical Psychology and Psychotherapy (KliPs) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen 91052 Germany. Translational Digital Health Group Institute of AI for Health Helmholtz Zentrum München - German Research Center for Environmental Health Neuherberg 85764 Germany.

Detecting depression is a critical component of mental health diagnosis, and accurate assessment is essential for effective treatment. This study introduces a novel, fully automated approach to predicting depression severity using the E-DAIC dataset. We employ Large Language Models (LLMs) to extract depression-related indicators from interview transcripts, utilizing the Patient Health Questionnaire-8 (PHQ-8) score to train the prediction model. Additionally, facial data extracted from video frames is integrated with textual data to create a multimodal model for depression severity prediction. We evaluate three approaches: text-based features, facial features, and a combination of both. Our findings show the best results are achieved by enhancing text data with speech quality assessment, with a mean absolute error of 2.85 and root mean square error of 4.02. This study underscores the potential of automated depression detection, showing text-only models as robust and effective while paving the way for multimodal analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Complementary App-Based Yoga Home Exercise Therapy for Patients With Axial Spondyloarthritis: Usability Study

引用

JMIR Formative Research 2024年 8卷 e57185页

作者： Grube, Lara Petit, Pascal Vuillerme, Nicolas Nitschke, Marlies Nwosu, Obioma Bertrand Knitza, Johannes Krusche, Martin Seifer, Ann-Kristin Eskofier, Bjoern Schett, Georg Morf, Harriet Department of Internal Medicine 3- Rheumatology & Immunology Universitätsklinikum Erlangen Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Deutsches Zentrum Immuntherapie Universitätsklinikum Erlangen Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany AGEIS Université Grenoble Alpes Grenoble France Institut Universitaire de France Paris France LabCom Telecom4Health Orange Labs & Université Grenoble Alpes CNRS Inria Grenoble France Machine Learning and Data Analytics Lab Department Artificial Intelligence in Biomedical Engineering (AIBE) Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Institute for Digital Medicine University Hospital of Giessen and Marburg Philipps-University Marburg Marburg Germany III. Department of Medicine University Medical Center Hamburg-Eppendorf Hamburg Germany Translational Digital Health Group Institute of AI for Health German Research Center for Environmental Health Helmholtz Zentrum München Neuherberg Germany

Background: Axial spondyloarthritis (AS) is a chronic inflammatory rheumatic disease characterized by potentially disabling inflammation of the spine and adjacent joints. Regular exercise is a cornerstone of treatment. However, patients with AS currently have little support. YogiTherapy (MaD Lab) is an app developed to support patients with AS by providing instructions for yoga-based home exercise therapy. Objective: This study aimed to evaluate the usability and acceptance of the newly designed YogiTherapy app for patients with AS. Methods: Patients completed the User Version of the Mobile Application Rating Scale (uMARS) and net promoter score (NPS) questionnaires after the app introduction. Wilcoxon Mann-Whitney rank sum test, chi-square test for count data, and correlation analysis were conducted to examine the usability of the app, acceptance, and patient characteristics. Results: A total of 65 patients with AS (33, 51% female;age: mean 43.3, SD 13.6 years) were included in the study from May 2022 to June 2023. Subsequently, the data were analyzed. Usability was rated moderate, with a mean uMARS of 3.35 (SD 0.47) points on a scale from 0 to 5. The highest-rated uMARS dimension was information (mean 3.88, SD 0.63), followed by functionality (mean 3.84, SD 0.87). Females reported a significantly higher uMARS total score than males (mean 3.47, SD 0.48 vs mean 3.23, SD 0.45;P=.03, Vargha and Delaney A [VDA] 0.66, 95% CI 0.53-0.77). The mean average of the NPS was 6.23 (SD 2.64) points (on a scale from 0 to 10), based on 43% (26/65 nonpromoters, 42% (25/65) indifferent, and 15% (9/65) promoters. A total of 7% (5/65) of those surveyed did not answer the question. When applying the NPS formula, the result is –26%. The NPS showed a positive correlation with the usage of mobile apps (r=0.39;P=.02). uMARS functionality was significantly higher rated by patients younger than 41 years (mean 4.17, SD 0.55 vs mean 3.54, SD 1;P<.001;VDA 0.69, 95% CI 0.56-0.80). Patients consi

关键词： adjacent joints ankylosing spondylitis app apps axial spondylarthritis chronic correlation analysis DHA digital health application digital therapeutics DTx eHealth exercise home exercise joint joints patient patient acceptance patients physical exercise rheumatic disease self-assessment spine spondyloarthritis therapy usability usability study Yoga YogiTherapy

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Imaging Diagnostics in Neurosurgery

Artificial Intelligence for Imaging Diagnostics in Neurosurg...

引用

IEEE Region 8 International Conference on Computational Technologies in Electrical and Electronics Engineering, SIBIRCON

作者： Andrey Yu. Letyagin Sergey K. Golushko Jamil A. Rzaev Mihail E. Amelin Evgeniy N. Pavlovsky Bair N. Tuchinov Evgeniya V. Amelina Galina I. Moisak Ekaterina G. Bulgakova Liana O. Degtyareva Novosibirsk State University Novosibirsk Russia Federal State Budget Institution Federal Center of Neurosurgery Novosibirsk Russia FSBI “Federal Neurosurgical Center” Novosibirsk Russia Stread Data Analytics & Machine Learning lab. Novosibirsk State University Novosibirsk Russia

Improving the accuracy and timeliness of medical imaging in everyday clinical neurosurgery practice is an urgent problem for the health care of all countries. This problem will be solved with the help of artificial intelligence (AI). By performing the search and contouring of “suspicious” pathological objects, making automatic measurements on 3D medical images (MRI, CT), formalizing quantitative indicators and compiling medical statistical reports, AI can solve diagnostic problems in radiology and medical imaging. The effect of introducing AI will be at least a more accurate and quick interpretation of images, implemented through a set of decision-making tools for medical specialists.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lessons Learned from Assessing Trustworthy AI in Practice

引用

Digital Society 2023年第3期2卷 1-25页

作者： Vetter, Dennis Amann, Julia Bruneault, Frédérick Coffee, Megan Düdder, Boris Gallucci, Alessio Gilbert, Thomas Krendl Hagendorff, Thilo van Halem, Irmhild Hickman, Eleanore Hildt, Elisabeth Holm, Sune Kararigas, Georgios Kringen, Pedro Madai, Vince I. Wiinblad Mathez, Emilie Tithi, Jesmin Jahan Westerlund, Magnus Wurth, Renee Zicari, Roberto V. Computational Vision and Artificial Intelligence Lab Goethe University Frankfurt Frankfurt Am Main Germany Z-Inspection® Initiative Venice Italy Health Ethics and Policy Lab ETH Zurich Zurich Switzerland Strategy and Innovation Careum Foundation Zurich Switzerland Philosophie Departement Collège André-Laurendeau Montréal Canada École Des Médias Université du Québec À Montréal Montréal Canada Department of Medicine Division of Infectious Diseases and Immunology New York University Grossman School of Medicine New York City USA Department of Computer Science University of Copenhagen Copenhagen Denmark Digital Life Initiative Cornell Tech New York City USA Cluster of Excellence “Machine Learning: New Perspectives for Science” University of Tuebingen Tuebingen Germany School of Law University of Bristol Bristol UK Center for the Study of Ethics in the Professions Illinois Institute of Technology Chicago USA Department of Business Management and Analytics Arcada University of Applied Sciences Helsinki Finland Department of Food & Resource Economics University of Copenhagen Copenhagen Denmark Department of Physiology Faculty of Medicine University of Iceland Reykjavik Iceland QUEST Centre for Responsible Research Berlin Institute of Health Charité Universitätsmedizin Berlin Berlin Germany Faculty of Computing Engineering and the Built Environment School of Computing and Digital Technology Birmingham City University Birmingham UK Parallel Computing Labs Intel Santa Clara USA School of Economics Innovation and Technology Kristiania University College Oslo Norway Data Science Graduate School Seoul National University Seoul South Korea

Building artificial intelligence (AI) systems that adhere to ethical standards is a complex problem. Even though a multitude of guidelines for the design and development of such trustworthy AI systems exist, these guidelines focus on high-level and abstract requirements for AI systems, and it is often very difficult to assess if a specific system fulfills these requirements. The Z-Inspection® process provides a holistic and dynamic framework to evaluate the trustworthiness of specific AI systems at different stages of the AI lifecycle, including intended use, design, and development. It focuses, in particular, on the discussion and identification of ethical issues and tensions through the analysis of socio-technical scenarios and a requirement-based framework for ethical and trustworthy AI. This article is a methodological reflection on the Z-Inspection® process. We illustrate how high-level guidelines for ethical and trustworthy AI can be applied in practice and provide insights for both AI researchers and AI practitioners. We share the lessons learned from conducting a series of independent assessments to evaluate the trustworthiness of real-world AI systems, as well as key recommendations and practical suggestions on how to ensure a rigorous trustworthiness assessment throughout the lifecycle of an AI system. The results presented in this article are based on our assessments of AI systems in the healthcare sector and environmental monitoring, where we used the framework for trustworthy AI proposed in the Ethics Guidelines for Trustworthy AI by the European Commission’s High-Level Expert Group on AI. However, the assessment process and the lessons learned can be adapted to other domains and include additional frameworks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Structure of Attention in a Transformer Language Model

arXiv

引用

arXiv 2019年

作者： Vig, Jesse Belinkov, Yonatan Palo Alto Research Center Machine Learning and Data Science Group Interaction and Analytics Lab Palo AltoCA United States Harvard John A. Paulson School of Engineering and Applied Sciences MIT Computer Science and Artificial Intelligence Laboratory CambridgeMA United States

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the GPT-2 small pretrained model. We visualize attention for individual instances and analyze the interaction between attention and syntax over a large corpus. We find that attention targets different parts of speech at different layer depths within the model, and that attention aligns with dependency relations most strongly in the middle layers. We also find that the deepest layers of the model capture the most distant relationships. Finally, we extract exemplar sentences that reveal highly specific patterns targeted by particular attention heads. Copyright © 2019, The Authors. All rights reserved.

关键词： Recurrent neural networks

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：