检索结果-内蒙古大学图书馆

Companion Proceedings of the 29th International Conference on Intelligent User Interfaces

作者： Bruce Ferwerda Panagiotis Germanakos Marko Tkalcic Department of Computer Science and Informatics Jönköping University Sweden User Experience ? Industry Product Engineering Intelligent Enterprise Group SAP SE Germany Faculty of Mathematics Natural Sciences and Information Technologies University of Primorska Slovenia

ISBN: (纸本)9798400705090

The seventh HUMANIZE workshop1 on Transparency and Explainability in Adaptive Systems through User Modeling Grounded in Psychological Theory took place in conjunction with the 29th annual meeting of the Intelligent User Interfaces (IUI)2 community that took place on between March 18-21, 2024 in Greenville, South Carolina, USA. The 2024 edition of the workshop was held together with SOCIALIZE (social and cultural integration with personalized interfaces) 3. The workshop provided a venue for researchers from different fields to interact by accepting contributions on the intersection of practical data mining methods and theoretical knowledge for personalization. A total of two papers were accepted for this edition of the workshop.

关键词： Human-centered AI Personalization Tailoring User Interfaces User Modeling

来源：评论

学校读者我要写书评

暂无评论

HIGH NOISE SCHEDULING IS A MUST

arXiv

引用

arXiv 2024年

作者： Gokmen, Mahmut S. Bumgardner, Cody Zhang, Jie Wang, Ge Chen, Jin Department of Computer Science University of Kentucky United States Department of Internal Medicine Institute for Biomedical Informatics University of Kentucky United States Department of Radiology University of Kentucky United States Department of Biomedical Engineering Rensselaer Polytechnic Institute United States Department of Medicine Department of Biomedical Informatics and Data Science University of Alabama Birmingham United States

Consistency models possess high capabilities for image generation, advancing sampling steps to a single step through their advanced techniques. Current advancements move one step forward consistency training techniques and eliminates the limitation of distillation training. Even though the proposed curriculum and noise scheduling in improved training techniques yield better results than basic consistency models, it lacks well balanced noise distribution and its consistency between curriculum. In this study, it is investigated the balance between high and low noise levels in noise distribution and offered polynomial noise distribution to maintain the stability. This proposed polynomial noise distribution is also supported with a predefined Karras noises to prevent unique noise levels arises with Karras noise generation algorithm. Furthermore, by elimination of learned noisy steps with a curriculum based on sinusoidal function increase the performance of the model in denoising. To make a fair comparison with the latest released consistency model training techniques, experiments are conducted with same hyper-parameters except curriculum and noise distribution. The models utilized during experiments are determined with low depth to prove the robustness of our proposed technique. The results show that the polynomial noise distribution outperforms the model trained with log-normal noise distribution, yielding a 33.54 FID score after 100,000 training steps with constant discretization steps. Additionally, the implementation of a sinusoidal-based curriculum enhances denoising performance, resulting in a FID score of 30.48. Copyright © 2024, The Authors. All rights reserved.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization

arXiv

引用

arXiv 2023年

作者： Balaskas, Konstantinos Karatzas, Andreas Sad, Christos Siozios, Kostas Anagnostopoulos, Iraklis Zervakis, Georgios Henkel, Jörg The Department of Physics Aristotle University of Thessaloniki Thessaloniki54124 Greece Karlsruhe Institute of Technology Karlsruhe76131 Germany The School of Electrical Computer and Biomedical Engineering Southern Illinois University Carbondale CarbondaleIL62901 United States The Dept. of Computer Engineering & Informatics University of Patras Patras26504 Greece

Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is a vast demand for running sophisticated DNN-based services on resource constrained embedded devices. In this paper, we target energy-efficient inference on embedded DNN accelerators. To that end, we propose an automated framework to compress DNNs in a hardware-aware manner by jointly employing pruning and quantization. We explore, for the first time, per-layer fine- and coarse-grained pruning, in the same DNN architecture, in addition to low bit-width mixed-precision quantization for weights and activations. Reinforcement Learning (RL) is used to explore the associated design space and identify the pruning-quantization configuration so that the energy consumption is minimized whilst the prediction accuracy loss is retained at acceptable levels. Using our novel composite RL agent we are able to extract energy-efficient solutions without requiring retraining and/or fine tuning. Our extensive experimental evaluation over widely used DNNs and the CIFAR-10/100 and ImageNet datasets demonstrates that our framework achieves 39% average energy reduction for 1.7% average accuracy loss and outperforms significantly the state-of-the-art approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Normative Modeling for Multi-Modal Neuroimaging Data Using Mixture-of-Product-of-Experts Variational Autoencoders

Improving Normative Modeling for Multi-Modal Neuroimaging Da...

引用

IEEE International Symposium on Biomedical Imaging

作者： Sayantan Kumar Philip Payne Aristeidis Sotiras Department of Computer Science and Engineering Washington University in St. Louis USA Institute for Informatics Data Science and Biostatistics Washington University in St.Louis USA Department of Radiology Washington University in St.Louis USA

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Normative models in neuroimaging learn the brain patterns of healthy population distribution and estimate how disease subjects like Alzheimer’s Disease (AD) deviate from the norm. Existing variational autoencoder (VAE)-based normative models using multimodal neuroimaging data aggregate information from multiple modalities by estimating product or averaging of unimodal latent posteriors. This can often lead to uninformative joint latent distributions which affects the estimation of subject-level deviations. In this work, we addressed the prior limitations by adopting the Mixture-of-Product-of-Experts (MoPoE) technique which allows better modelling of the joint latent posterior. Our model labelled subjects as outliers by calculating deviations from the multimodal latent space. Further, we identified which latent dimensions and brain regions were associated with abnormal deviations due to AD pathology.

关键词： Neuroimaging Pathology Sociology Estimation Data aggregation Brain modeling Data models

来源：评论

学校读者我要写书评

暂无评论

Causal Structure Learning from Imperfect Longitudinal Data in Healthcare

Causal Structure Learning from Imperfect Longitudinal Data i...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Haoyu Yang Roshan Tourani Jia Li Pedro Caraballo Michael Steinbach Vipin Kumar Gyorgy Simon Dept. of Computer Science and Engineering University of Minnesota Minneapolis USA Institute for Health Informatics University of Minnesota Minneapolis USA Dept. of Internal Medicine Mayo Clinic Rochester USA

Causal Structure Discovery (CSD) is the task of learning the set of underlying causal relationships from observational data. Due to their computational scalability and flexibility, a recently developed class of CSD methods, NOTEARS, based on a formulation allowing for continuous optimization, is gaining popularity. However, this formulation can lead to incorrect edge orientations when little/no likelihood advantage is conferred upon any edge orientation, e.g., a → b → c versus c → b → a. In longitudinal data, like electronic health records (EHRs), temporal relationships are observable among many pairs of variables. Such temporal relationship is imperfect but still suggest an orientation since causal effects cannot travel backwards in time. Following this idea, we propose methods to incorporate precedence constraints into continuous optimization-based CSD methods. Experiments on both a synthetic and two real-world datasets validate the effectiveness of the proposed precedence constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Technical light-field setup for 3D imaging of the human nerve head validated with an eye model

引用

Current Directions in Biomedical engineering 2021年第2期7卷 433-436页

作者： Schramm, Stefan Dietzel, Alexander Blum, Maren-Christina Link, Dietmar Klee, Sascha Institute of Biomedical Engineering and Informatics Faculty of Computer Sciences and Automation Technische Universität Ilmenau Ilmenau Germany Department of General Health Studies Division Biostatistics and Data Science Karl Landsteiner University of Health Sciences Krems an der Donau Austria

With the new technology of 3D light field (LF) imaging, fundus photography can be expanded to provide depth information. This increases the diagnostic possibilities and additionally improves image quality by digitally refocusing. To provide depth information in the human optic nerve head such as in glaucoma diagnostics, a mydriatic fundus camera was upgraded with an LF imager. The aim of the study presented here was the validation of the technical setup and resulting depth estimations with an appropriate eye model. The technical setup consisted of a mydriatic fundus camera (FF450, Carl Zeiss Meditec AG, Jena, Germany) and an LF imager (R12, Raytrix GmbH, Kiel, Germany). The field of view was set to 30°. The eye model (24.65 mm total length) consisted of a two-lens optical system and interchangeable fundus models with papilla excavations from 0.2 to 1 mm in steps of 0.2 mm. They were coated with red acrylic lacquer and vessels were drawn with a thin brush. 15 images were taken for each papilla depth illuminated with green light (wavelength 520 nm ± 20 nm). Papilla depth was measured from the papilla ground to the surrounding flat region. All 15 measurements for each papilla depth were averaged and compared to the printed depth. It was possible to perform 3D fundus imaging in an eye model by means of a novel LF-based optical setup. All LF images could be digitally refocused subsequently. Depth estimation in the eye model was successfully performed over a 30° field of view. The measured virtual depth and the printed model papilla depth is linear correlated. The presented LF setup allowed high-quality 3D one-shot imaging and depth estimation of the optic nerve head in an eye model. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Optical systems

来源：评论

学校读者我要写书评

暂无评论

Stroke Prediction Using Machine Learning

Stroke Prediction Using Machine Learning

引用

International Conference on Advances in Electronics, computers and Communications (ICAECC)

作者： Abinandhini D M Aman Kumar Gudi Vishnu Teja Mandava Sukesh Divya S Naman Chauhan I R Oviya Kalpana Raja Department of Computer Science and Engineering (Artificial Intelligence) Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven Connecticut USA

ISBN: (数字)9798350305449

ISBN: (纸本)9798350305456

A stroke is a serious medical emergency that happens when bleeding or blood clots cut off the blood flow to a part of the brain. With a mortality rate of 5.5 million per year, it ranks as the second leading cause of death globally. Over 15 million individuals experience a stroke each year, and one person dies from one every four minutes. According to the World Health Organization, stroke is the main cause of death and disability worldwide (WHO). Identifying the many stroke warning signs helps lessen the severity of the stroke. A stroke can be avoided in up to 80% of instances because it is typically the result of a poor lifestyle. As a result, stroke prediction becomes important and should be employed to stop it from causing long-term harm. The current study uses a variety of machine learning models, including Gaussian Naive Bayes, Logistic Regression, Support Vector Machine (SVM), KNN and Random Forest to predict stroke. The paper presents the comparison among all machine learning algorithms. Analysis of results revealed that KNN had the least accuracy of 76.32% and Random Forest had the highest accuracy of 94.81%.

关键词： Support vector machines Accuracy Organizations Stroke (medical condition) Predictive models Vectors Physiology

来源：评论

学校读者我要写书评

暂无评论

Multi-Parameter Analysis of Biosignals in Long-Term Control Medical Devices Management

Multi-Parameter Analysis of Biosignals in Long-Term Control ...

引用

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Serhii Holdobin Natalia Brynza Olha Tiutiunyk Olena Serhiienko Ihor Sosnov Pavlo Samus Industrial and Biomedical Electronics Department Kharkiv polytechnic institute National Technical University Kharkiv Ukraine Department of Informatics and Computer Technology Simon Kuznets Kharkiv National University of Economics Kharkiv Ukraine Department of Applied Mathematics Kharkiv National University of Radio Electronics Kharkiv Ukraine Department of Informatics and Computer Engineering Simon Kuznets Kharkiv National University of Economics Kharkiv Ukraine Business Trade and Logistics Department Kharkiv Polytechnic Institute National Technical University Kharkiv Ukraine

ISBN: (数字)9798331510886

ISBN: (纸本)9798331510893

The development of data processing technologies, microelectronics and sensor systems allows for high-precision multiparametric analysis of biosignals in real time. The paper considers the problem of automating medical processes to reduce the influence of the human factor and increase the accuracy of diagnostics. An improved method of multiparametric analysis of biosignals is proposed for long-term monitoring of the state of the cardiovascular system using modern sensor devices, data processing algorithms and artificial intelligence technologies. The research is aimed at improving the methods of collecting, transmitting and analyzing biosignals, which contributes to the creation of personalized medical devices and effective prediction of cardiovascular pathologies. The issues of classification of devices and biosignals, as well as their mathematical modeling to increase the accuracy of diagnostics, are considered.

关键词： Cardiovascular system Wireless sensor networks Accuracy Medical devices Heuristic algorithms Robot sensing systems Prediction algorithms Real-time systems Classification algorithms Monitoring

来源：评论

学校读者我要写书评

暂无评论

Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography

arXiv

引用

arXiv 2024年

作者： Ghosh, Shantanu Poynton, Clare B. Visweswaran, Shyam Batmanghelich, Kayhan Department of Electrical and Computer Engineering Boston University BostonMA United States Boston University Chobanian & Avedisian School of Medicine BostonMA United States Department of Biomedical Informatics University of Pittsburgh PittsburghPA United States

The lack of large and diverse training data on computer- Aided Diagnosis (CAD) in breast cancer detection has been one of the concerns that impedes the adoption of the system. Recently, pre-training with large-scale image text datasets via Vision-Language models (VLM) (e.g., CLIP) partially addresses the issue of robustness and data efficiency in computer vision (CV). This paper proposes Mammo-CLIP, the first VLM pre-trained on a substantial amount of screening mammogramreport pairs, addressing the challenges of dataset diversity and size. Our experiments on two public datasets demonstrate strong performance in classifying and localizing various mammographic attributes crucial for breast cancer detection, showcasing data efficiency and robustness similar to CLIP in CV. We also propose Mammo-FActOR, a novel feature attribution method, to provide spatial interpretation of representation with sentence-level granularity within mammography reports. Code is available publicly: https://***/batmanlab/Mammo-CLIP. © 2024, CC BY.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis

Memory-Friendly Scalable Super-Resolution via Rewinding Lott...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jin Lin Xiaotong Luo Ming Hong Yanyun Qu Yuan Xie Zongze Wu School of Informatics Xiamen University Fujian China School of Computer Science and Technology East China Normal University Shanghai China School of Mechatronics and Control Engineering Shenzhen University Shenzhen China

Scalable deep Super-Resolution (SR) models are increasingly in demand, whose memory can be customized and tuned to the computational recourse of the platform. The existing dynamic scalable SR methods are not memory-friendly enough because multi-scale models have to be saved with a fixed size for each model. Inspired by the success of Lottery Tickets Hypothesis (LTH) on image classification, we explore the existence of unstructured scalable SR deep models, that is, we find gradual shrinkage subnetworks of extreme sparsity named winning tickets. In this paper, we propose a Memory-friendly Scalable SR framework (MSSR). The advantage is that only a single scalable model covers multiple SR models with different sizes, instead of reloading SR models of different sizes. Concretely, MSSR consists of the forward and backward stages, the former for model compression and the latter for model expansion. In the forward stage, we take advantage of LTH with rewinding weights to progressively shrink the SR model and the pruning-out masks that form nested sets. Moreover, stochastic self-distillation (SSD) is conducted to boost the performance of sub-networks. By stochastically selecting multiple depths, the current model inputs the selected features into the corresponding parts in the larger model and improves the performance of the current model based on the feedback results of the larger model. In the backward stage, the smaller SR model could be expanded by recovering and fine-tuning the pruned parameters according to the pruning-out masks obtained in the forward. Extensive experiments show the effectiveness of MMSR. The smallest-scale sub-network could achieve the sparsity of 94% and outperforms the compared lightweight SR methods.

关键词：

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：