检索结果-内蒙古大学图书馆

Developing Ethics and Equity Principles, Terms, and Engagement Tools to Advance Health Equity and Researcher Diversity in ai and machine learning: Modified Delphi Approach

引用

JMIR ai 2023年 2卷 e52888页

作者： Hendricks-Sturrup, Rachele Simmons, Malaika Anders, Shilo Aneni, Kammarauche Clayton, Ellen Wright Coco, Joseph Collins, Benjamin Heitman, Elizabeth Hussain, Sajid Joshi, Karuna Lemieux, Josh Novak, Laurie Lovett Rubin, Daniel J. Shanker, Anil Washington, Talitha Waters, Gabriella Harris, Joyce Webb Yin, Rui Wagner, Teresa Yin, Zhijun Malin, Bradley Natl Alliance Dispar Patient Hlth 2700 Neabsco Common PlSuite 101 Woodbridge VA 22191 USA Vanderbilt Univ Med Ctr Nashville TN USA Yale Univ New Haven CT USA Univ Texas Southwestern Med Ctr Dallas TX USA Fisk Univ Nashville TN USA Univ Maryland Baltimore MD USA OCHIN Portland OR USA Temple Univ Philadelphia PA USA Meharry Med Coll Nashville TN USA Clark Atlanta Univ AUC Data Sci Initiat Atlanta GA USA Ctr Equitable & Machine Learning Syst Ctr Equitable AI & Machine Learning Syst Baltimore MD USA Univ Florida Gainesville FL USA Univ North Texas Hlth Sci Ctr SaferCare Texas Ft Worth TX USA

Background: Artificial intelligence (ai) and machine learning (ML) technology design and development continues to be rapid, despite major limitations in its current form as a practice and discipline to address all sociohumanitarian issues and complexities. From these limitations emerges an imperative to strengthen ai and ML literacy in underserved communities and build a more diverse ai and ML design and development workforce engaged in health research. Objective: ai and ML has the potentialto account for and assess a variety of factors that contribute to health and disease and to improve prevention, diagnosis, and therapy. Here, we describe recent activities within the Artificial Intelligence/machine learning Consortium to Advance Health Equity and Researcher Diversity (aiM-AHEAD) Ethics and Equity Workgroup (EEWG) that led to the development of deliverables that will help put ethics and fairness at the forefront of ai and ML applications to build equity in biomedical research, education, and health care. Methods: The aiM-AHEAD EEWG was created in 2021 with 3 cochairs and 51 members in year 1 and 2 cochairs and similar to 40 members in year 2. Members in both years included aiM-AHEAD principal investigators, coinvestigators, leadership fellows, and research fellows. The EEWG used a modified Delphi approach using polling, ranking, and other exercises to facilitate discussions around tangible steps, key terms, and definitions needed to ensure that ethics and fairness are at the forefront of ai and ML applications to build equity in biomedical research, education, and health care. Results: The EEWG developed a set of ethics and equity principles, a glossary, and an interview guide. The ethics and equity principles comprise 5 core principles, each with subparts, which articulate best practices for working with stakeholders from historically and presently underrepresented communities. The glossary contains 12 terms and definitions, with particular emphasis on optimal de

关键词： artificial intelligence ai Delphi disparities disparity engagement equitable equities equity ethic ethical ethics fair fairness health disparities healthequity humanitarian machine learning ML

来源：评论

学校读者我要写书评

暂无评论

MHNfs: Prompting In-Context Bioactivity Predictions for Low-Data Drug Discovery

引用

JOURNAL OF CHEMICAL INFORMATION AND MODELING 2025年第9期65卷 4243-4250页

作者： Schimunek, Johannes Luukkonen, Sohvi Klambauer, Guenter Johannes Kepler Univ Linz ELLIS Unit Linz Inst Machine Learning A-4040 Linz Austria Johannes Kepler Univ Linz Inst Machine Learning LIT AI Lab A-4040 Linz Austria

Today's drug discovery increasingly relies on computational and machine learning approaches to identify novel candidates, yet data scarcity remains a significant challenge. To address this limitation, we present MHNfs , an application specifically designed to predict molecular activity in low-data scenarios. At its core, MHNfs leverages a state-of-the-art few-shot activity prediction model, named MHNfs, which has demonstrated strong performance across a large set of prediction tasks in the benchmark data set FS-Mol. The application features an intuitive interface that enables users to prompt the model for precise activity predictions based on a small number of known active and inactive molecules, akin to interactive interfaces for large language models. To evaluate its efficacy, we simulate real-world scenarios by recasting PubChem bioassays as few-shot prediction tasks. MHNfs offers a streamlined and accessible solution for deploying advanced few-shot learning models, providing a valuable tool for accelerating drug discovery.

关键词： Bioactivity

来源：评论

学校读者我要写书评

暂无评论

Exact Implementation of Closed-Form Liquid Neural Networks With Arbitrary Precision

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 921-925页

作者： Cantini, Clotilde Rolland-Piegue, Emilie Schmitter, Daniel Swiss Life Machine Learning & AI Grp CH-8022 Zurich Switzerland Ecole Ponts ParisTech F-77420 Champs sur Marne France

Continuous-time liquid neural networks constitute a novel class of machine learning models that emulate the dynamics of biological neurons and synapses using ordinary differential equations. Despite their promising applications in predicting spatiotemporal dynamics, the adoption of these models has been constrained by their reliance on computationally expensive numerical differential equation solvers or approximate solutions. In this work, we propose a redefinition of the network's core neuron that accommodates for multiple presynaptic connections. We then derive a closed-form solution and present an implementation through a computationally efficient recursive algorithm. Our solution is validated both at the level of individual neurons and within a deep neural network architecture. Experimental results on sequential modeling tasks with image, sensor or medical data, demonstrate improved performance compared to state-of-the-art numerical and approximate methods.

关键词： Neurons Synapses Biological neural networks Mathematical models Electrocardiography Training Liquids Data models Computational modeling Biological system modeling Closed-form continuous domain deep learning liquid time constant neural networks ordinary differential equation sampling

来源：评论

学校读者我要写书评

暂无评论

NeuralCFD: Deep learning on High-Fidelity Automotive Aerodynamics Simulations

arXiv

引用

arXiv 2025年

作者： Bleeker, Maurits Dorfer, Matthias Kronlachner, Tobias Sonnleitner, Reinhard Alkin, Benedikt Brandstetter, Johannes Emmi AI GmbH Linz Austria ELLIS Unit LIT AI Lab Institute for Machine Learning JKU Linz Austria

Recent advancements in neural operator learning are paving the way for transformative innovations in fields such as automotive aerodynamics. However, key challenges must be overcome before neural network-based simulation surrogates can be implemented at an industry scale. First, surrogates must become scalable to large surface and volume meshes, especially when using raw geometry inputs only, i.e., without relying on the simulation mesh. Second, surrogates must be trainable with a limited number of high-fidelity numerical simulation samples while still reaching the required performance levels. To this end, we introduce Geometry-preserving Universal Physics Transformer (GP-UPT), which separates geometry encoding and physics predictions, ensuring flexibility with respect to geometry representations and surface sampling strategies. GP-UPT enables independent scaling of the respective parts of the model according to practical requirements, offering scalable solutions to open challenges. GP-UPT circumvents the creation of high-quality simulation meshes, enables accurate 3D velocity field predictions at 20 million mesh cells, and excels in transfer learning from low-fidelity to high-fidelity simulation datasets, requiring less than half of the high-fidelity data to match the performance of models trained from scratch. © 2025, CC BY-SA.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Evaluating normative representation learning in generative ai for robust anomaly detection in brain imaging

引用

NATURE COMMUNICATIONS 2025年第1期16卷 1-10页

作者： Bercea, Cosmin I. Wiestler, Benedikt Rueckert, Daniel Schnabel, Julia A. Tech Univ Munich TUM Computat Imaging & AI Med Munich Germany Helmholtz AI & Helmholtz Ctr Munich Munich Germany TUM Sch Med & Hlth AI Image Guided Diag & Therapy Sch Med & Hlth Munich Germany Munich Ctr Machine Learning MCML Munich Germany Tech Univ Munich TUM Healthcare & Med Munich Germany TUM Univ Hosp Munich Germany Imperial Coll London Dept Comp London England Kings Coll London Sch Biomed Engn & Imaging Sci London England

Normative representation learning focuses on understanding the typical anatomical distributions from large datasets of medical scans from healthy individuals. Generative Artificial Intelligence (ai) leverages this attribute to synthesize images that accurately reflect these normative patterns. This capability enables the ai allowing them to effectively detect and correct anomalies in new, unseen pathological data without the need for expert labeling. Traditional anomaly detection methods often evaluate the anomaly detection performance, overlooking the crucial role of normative learning. In our analysis, we introduce novel metrics, specifically designed to evaluate this facet in ai models. We apply these metrics across various generative ai frameworks, including advanced diffusion models, and rigorously test them against complex and diverse brain pathologies. In addition, we conduct a large multi-reader study to compare these metrics to experts' evaluations. Our analysis demonstrates that models proficient in normative learning exhibit exceptional versatility, adeptly detecting a wide range of unseen medical conditions. Our code is available at https://***/compai-lab/***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CCStereo: Audio-Visual Contextual and Contrastive learning for Binaural Audio Generation

arXiv

引用

arXiv 2025年

作者： Chen, Yuanhong Shimada, Kazuki Simon, Christian Ikemiya, Yukara Shibuya, Takashi Mitsufuji, Yuki Australian Institute for Machine Learning University of Adelaide Australia Sony AI Japan Sony Group Corporation Japan

Binaural audio generation (BAG) aims to convert monaural audio to stereo audio using visual prompts, requiring a deep understanding of spatial and semantic information. However, current models risk overfitting to room environments and lose fine-grained spatial details. In this paper, we propose a new audio-visual binaural generation model incorporating an audiovisual conditional normalisation layer that dynamically aligns the mean and variance of the target difference audio features using visual context, along with a new contrastive learning method to enhance spatial sensitivity by mining negative samples from shuffled visual features. We also introduce a cost-efficient way to utilise test-time augmentation in video data to enhance performance. Our approach achieves state-of-the-art generation accuracy on the FaiR-Play and MUSIC-Stereo benchmarks. © 2025, CC BY-NC-SA.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Millimeter Wave Radar-Based Human Pose Estimation Enabled by a Deep learning Neural Network Trained With Optical Motion Capture Ground Truth Data

IEEE JOURNAL OF MICROWAVES

引用

IEEE JOURNAL OF MICROWAVES 2025年第2期5卷 373-387页

作者： Engel, Lukas Mueller, Jonas Rendon, Eduardo Javier Feria Dorschky, Eva Krauss, Daniel Ullmann, Ingrid Eskofier, Bjoern M. Vossiek, Martin Friedrich Alexander Univ Erlangen Nurnberg Inst Microwaves & Photon D-91058 Erlangen Germany Friedrich Alexander Univ Erlangen Nurnberg Machine Learning & Data Analyt Lab D-91052 Erlangen Germany Helmholtz Zentrum Munchen Inst AI Hlth German Res Ctr Environm Hlth Translat Digital Hlth Grp Neuherberg 85764 Germany

This paper presents a deep learning-enabled method for human pose estimation using radar target lists, obtained through a low-cost radar system with three transmitters and four receivers in a multiple-input multiple-output setup. We address challenges in previous research that often relied on extracting ground truth poses from RGB data, which are constrained by the need for 3D mapping and vulnerability to occlusions. To overcome these limitations, we utilized optical motion capture, which is widely recognized as the gold standard for precise human motion analysis. We conducted an extensive optical motion capture study involving various recorded movement activities, which resulted in mmRadPose, a new dataset that enhances existing benchmarks for radar-based pose estimation. This dataset has been made publicly accessible. Building on this approach, we designed an application-tailored radar signal processing chain to generate suitable input for the machine learning algorithm. We further developed an attentional recurrent-based deep learning model, PntPoseAT, which predicts 24 keypoints of human poses using radar target lists. We employed cross validation to thoroughly evaluate the model. This model surpasses previous approaches and achieves an average mean per-joint position error of $6.49 \,\mathrm{c}\mathrm{m}$ with a standard deviation of $3.74 \,\mathrm{c}\mathrm{m}$ on totally unseen test data. This excellent accuracy of the reconstructed keypoint positions is particularly remarkable when you consider that a very simple radar was used for the measurements. Additionally, we conducted a comprehensive analysis of the model's performance by exploring aspects such as network architecture, the use of long short-term memory versus gated recurrent units, input data selection, and the integration of multi-head self-attention mechanisms.

关键词： Human pose estimation radar optical motion capture optical motion capture millimeter wave millimeter wave target list target list point cloud point cloud machine learning machine learning deep learning deep learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Dataset Bias and Scaling Techniques in Multi-Source Gait Biomechanics: An Explainable machine learning Approach

引用

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 2025年第1期16卷 1-19页

作者： Fleischmann, Sophie Dietz, Simon Shanbhag, Julian Wuensch, Annika Nitschke, Marlies Miehling, Joerg Wartzack, Sandro Leyendecker, Sigrid Eskofier, Bjoern m. Koelewijn, Anne d. Friedrich Alexander Univ Erlangen Nurnberg FAU Machine Learning & Data Analyt Lab Erlangen Germany Friedrich Alexander Univ Erlangen Nurnberg FAU Engn Design Erlangen Germany Friedrich Alexander Univ Erlangen Nurnberg FAU Inst Appl Dynam Erlangen Germany Helmholtz Zentrum Munchen Inst AI Hlth German Res Ctr Environm Hlth Translat Digital Hlth Grp Neuherberg Germany

machine learning has become increasingly important in biomechanics. It allows to unveil hidden patterns from large and complex data, which leads to a more comprehensive understanding of biomechanical processes and deeper insights into human movement. However, machine learning models are often trained on a single dataset with a limited number of participants, which negatively affects their robustness and generalizability. Combining data from multiple existing sources provides an opportunity to overcome these limitations without spending more time on recruiting participants and recording new data. It is furthermore an opportunity for researchers who lack the financial requirements or laboratory equipment to conduct expensive motion capture studies themselves. At the same time, subtle interlaboratory differences can be problematic in an analysis due to the bias that they introduce. In our study, we investigated differences in motion capture datasets in the context of machine learning, for which we combined overground walking trials from four existing studies. Specifically, our goal was to examine whether a machine learning model was able to predict the original data source based on marker and GRF trajectories of single strides and how different scaling methods and pooling procedures affected the outcome. Layer-wise relevance propagation was applied to understand which factors were influential to distinguish the original data sources. We found that the model could predict the original data source with a very high accuracy (up to >99%), which decreased by about 15 percentage points when we scaled every dataset individually prior to pooling. However, none of the proposed scaling methods could fully remove the dataset bias. Layer-wise relevance propagation revealed that there was not only one single factor that differed between all datasets. Instead, every dataset had its unique characteristics that were picked up by the model. These variables differed between the scaling

关键词： datasets dataset combination neural networks explainable ai scaling biomechanics motion capture machine learning LRP

来源：评论

学校读者我要写书评

暂无评论

Feature importance analysis using ensemble decision tree models for aspirational luxury purchase intention of young cohorts in emerging markets

引用

JOURNAL OF DECISION SYSTEMS 2025年第1期34卷

作者： Nair, Manas Nair, Jessy Congruence Syst AI & Machine Learning Bengaluru India St Josephs Inst Management PGDM Program Bengaluru India Carnegie Mellon Univ Informat Networking Inst Pittsburgh PA 15251 USA

Millennial and Gen Z consumers in emerging countries form the biggest growth market for luxury businesses. While extant luxury research treats them as a homogenous unit, the Generational Cohort Theory proposes segmenting young consumers based on demographics. Using a conceptual framework developed through an extensive literature review, Random Forest regressors and Gradient Boosted Regression Trees are used to study the feature importances of the factors that drive Consumer Luxury Value and Luxury Purchase Intention. Ensemble tree methods are capable of capturing nonlinearities within the model and leverage the explainability of their decision tree learners to provide insight into the feature importances. Consumer Luxury Value, Other-directed and Experiential values are the most significant predictors of Luxury Purchase Intention across all gender and demographic cohorts with specific differences between cohorts. Gen Z consumers display stronger Other-Directed and Cost Perception values. Cohort-specific findings show Gen Z luxury consumers are more collectivistic than Millennials.

关键词： Feature importance luxury purchase intention Gen Z Millennials random forests gradient boosted trees

来源：评论

学校读者我要写书评

暂无评论

Diffusion models for 3D generation: A survey

引用

Computational Visual Media 2025年第1期11卷 1-28页

作者： Chen Wang Hao-Yang Peng Ying-Tian Liu Jiatao Gu Shi-Min Hu Department of Computer and Information Science University of PennsylvaniaPhiladelphiaPennsylvania 19104USA Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Machine Learning Research Apple AI/MLNew YorkUSA.E-mail:jiatao@***

Denoising diffusion models have demonstrated tremendous success in modeling data distributions and synthesizing high-quality *** the 2D image domain,they have become the state-of-the-art and are capable of generating photo-realistic images with high *** recently,researchers have begun to explore how to utilize diffusion models to generate 3D data,as doing so has more potential in real-world *** requires careful design choices in two key ways:identifying a suitable 3D representation and determining how to apply the diffusion *** this survey,we provide the first comprehensive review of diffusion models for manipulating 3D content,including 3D generation,reconstruction,and 3D-aware image *** classify existing methods into three major categories:2D space diffusion with pretrained models,2D space diffusion without pretrained models,and 3D space *** also summarize popular datasets used for 3D generation with diffusion *** with this survey,we maintain a repository https://***/cwchenwang/awesome-3d-diffusion to track the latest relevant papers and ***,we pose current challenges for diffusion models for 3D generation,and suggest future research directions.

关键词： diffusion models 3D generation generative models aiG

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：