检索结果-内蒙古大学图书馆

IEEE International Conference on Healthcare informatics (ICHI)

作者： Liyue Fan Luca Bonomi Dept. of Computer Science University of North Carolina at Charlotte Charlotte NC USA Dept. of Biomedical Informatics Vanderbilt University Medical Center Nashville TN USA

Deep neural networks have been increasingly integrated in healthcare applications to enable accurate predicative analyses. Sharing trained deep models not only facilitates knowledge integration in collaborative research efforts but also enables equitable access to computational intelligence. However, recent studies have shown that an adversary may leverage a shared model to learn the participation of a target individual in the training set. In this work, we investigate privacy-protecting model sharing for survival studies. Specifically, we pose three research questions. (1) Do deep survival models leak membership information? (2) How effective is differential privacy in defending against membership inference in deep survival analyses? (3) Are there other effects of differential privacy on deep survival analyses? Our study assesses the membership leakage in emerging deep survival models and develops differentially private training procedures to provide rigorous privacy protection. The experimental results show that deep survival models leak membership information and our approach effectively reduces membership inference risks. The results also show that differential privacy introduces a limited performance loss, and may improve the model robustness in the presence of noisy data, compared to non-private models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Biological age estimation from ECG using Artificial Intelligence approaches 2

Biological age estimation from ECG using Artificial Intellig...

引用

2nd Jordanian International biomedical Engineering Conference, JIBEC 2024

作者： Sleiman, Jana Daher, Mohamad Khalil, Mohamad Diab, Ahmad Kassem, Abdallah Lebanese University Computer and Communications Engineering Tripoli Lebanon Faculty of Science Faculty of Applied Sciences & Technology Dep. of Computer Science Dep. of Computer Science & Information Technology Tripoli Lebanon Lebanese University Electrical Engineering Tripoli Lebanon Lebanese International University Biomedical Engineering Beirut Lebanon Notre Dame University Faculty Of Engineering ECCE Dept. Zouk Mosbeh Lebanon

ISBN: (纸本)9798331539542

This paper explores the application of Artificial Intelligence (AI) techniques in healthcare, specifically focusing on electrocardiogram (ECG) data analysis and biological age estimation. The study begins with an overview of ECG as a diagnostic tool and discusses the integration of Deep Learning (DL) models, particularly Convolutional Neural Networks (CNNs), in healthcare for various applications. Previous studies reviewed in this context consistently identify CNNs as the superior model for ECG analysis and prediction tasks. The primary research investigates the use of Machine Learning (ML) algorithms to estimate biological age from ECG data, employing metrics such as Mean Absolute Error (MAE) and variance to evaluate model performance. Subsequently, DL models are implemented and compared, demonstrating superior accuracy in estimating the biological age of new patients. While both ML and DL approaches were initially explored, this paper primarily focuses on deep learning methodologies due to their demonstrated superiority in healthcare applications. The findings highlight the efficacy of deep learning over traditional ML methods, underscoring its potential for enhancing diagnostic accuracy and personalized patient care. For instance, the most accurate deep learning model, the Convolutional Neural Network (CNN), achieved a Mean Absolute Error (MAE) of 1.49 and an R2 score of 0.53, whereas the best-performing traditional ML model, Random Forest, achieved an MAE of 1.54 and an R2 score of 0.55. These results clearly indicate the advantage of deep learning models in capturing complex patterns in ECG data, leading to more precise and reliable estimations of biological age. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Perceptual Crack Detection for Rendered 3D Textured Meshes

Perceptual Crack Detection for Rendered 3D Textured Meshes

引用

International Workshop on Quality of Multimedia Experience, QoMEx

作者： Armin Shafiee Sarvestani Wei Zhou Zhou Wang Dept. of Electrical & Computer Engineering University of Waterloo Canada School of Computer Science and Informatics Cardiff University United Kingdom

ISBN: (数字)9798350361582

ISBN: (纸本)9798350361599

Recent years have witnessed many advancements in the applications of 3D textured meshes. As the demand continues to rise, evaluating the perceptual quality of this new type of media content becomes crucial for quality assurance and optimization purposes. Different from traditional image quality assessment, crack is an annoying artifact specific to rendered 3D meshes that severely affects their perceptual quality. In this work, we make one of the first attempts to propose a novel Perceptual Crack Detection (PCD) method for detecting and localizing crack artifacts in rendered meshes. Specifically, motivated by the characteristics of the human visual system (HVS), we adopt contrast and Laplacian measurement modules to characterize crack artifacts and differentiate them from other undesired artifacts. Extensive experiments on large-scale public datasets of 3D textured meshes demonstrate effectiveness and efficiency of the proposed PCD method in correct localization and detection of crack artifacts. Moreover, to quantify the performance of the proposed detection method and validate its effectiveness, we propose a simple yet effective weighting mechanism to incorporate the resulting crack map into classical quality assessment (QA) models, which creates significant performance improvement in predicting the perceptual image quality when tested on public datasets of static 3D textured meshes. A software release of the proposed method is publicly available at: https://***/arshafiee/crack-detection-VVM

关键词： Image quality Solid modeling Visualization Three-dimensional displays Quality assurance Visual systems Predictive models

来源：评论

学校读者我要写书评

暂无评论

Real-Time Automatic Checkout via Prompt-Based Product Extraction and Cross-Domain Learning 23

Real-Time Automatic Checkout via Prompt-Based Product Extrac...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Pettersson, Tobias Riveiro, Maria Löfström, Tuwe University of Skövde Jönköping University Itab Shop Products Ab Jönköping Sweden Jönköping University Dept. of Computer Science and Informatics Jönköping Sweden Jönköping University Dept. of Computing Jönköping Sweden

ISBN: (纸本)9798350374889

Automatic checkout systems are designed to predict a complete shopping receipt using an image from the checkout area. These systems require high classification accuracy across numerous classes and must operate in real-time, despite domain differences between training data and real-world conditions. Building on recent advancements, we propose a method that outperforms current solutions and can be applied in real-time in automatic checkout systems. Our method leverages the Segment Anything Model to extract high-quality masks from lab product images, which are then transformed into synthetic checkout images and adapted to the real domain using contrastive unpaired translation. We train a product recognition model with data augmentation, named SCA+Y8, and further improve it through fine-tuning with pseudo-labels from unlabeled checkout images, resulting in an improved model called SCAFT+Y8. SCAFT+Y8 achieves a great increase in state-of-the-art performance, with an average receipt classification accuracy of 97.58%, and shows strong performance in smaller models, indicating the potential for deployment on low-cost edge devices. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Perceptual Crack Detection for Rendered 3D Textured Meshes

arXiv

引用

arXiv 2024年

作者： Sarvestani, Armin Shafiee Zhou, Wei Wang, Zhou Dept. of Electrical & Computer Engineering University of Waterloo Canada School of Computer Science and Informatics Cardiff University United Kingdom

关键词： Quality assurance

来源：评论

学校读者我要写书评

暂无评论

NEAR-INFRARED AND LOW-RANK ADAPTATION OF VISION TRANSFORMERS IN REMOTE SENSING

arXiv

引用

arXiv 2024年

作者： Ulku, Irem Ozgur Tanriover, O. Akagündüz, Erdem Dept. of Computer Science Ankara University Ankara Turkey Dept. of Modeling and Simulation Graduate School of Informatics METU Ankara Turkey

Plant health can be monitored dynamically using multispectral sensors that measure Near-Infrared reflectance (NIR). Despite this potential, obtaining and annotating high-resolution NIR images poses a significant challenge for training deep neural networks. Typically, large networks pre-trained on the RGB domain are utilized to fine-tune infrared images. This practice introduces a domain shift issue because of the differing visual traits between RGB and NIR images. As an alternative to fine-tuning, a method called low-rank adaptation (LoRA) enables more efficient training by optimizing rank-decomposition matrices while keeping the original network weights frozen. However, existing parameter-efficient adaptation strategies for remote sensing images focus on RGB images and overlook domain shift issues in the NIR domain. Therefore, this study investigates the potential benefits of using vision transformer (ViT) backbones pre-trained in the RGB domain, with low-rank adaptation for downstream tasks in the NIR domain. Extensive experiments demonstrate that employing LoRA with pre-trained ViT backbones yields the best performance for downstream tasks applied to NIR images. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and construction of a medium chamber for a tissue bioreactor system

Design and construction of a medium chamber for a tissue bio...

引用

International Symposium on Applied Machine Intelligence and informatics (SAMI)

作者： Petra Kolembusová Norbert Ferenčík William Steingartner Radovan Hudák Veronika Sedláková Branko Štefanovič Dept. of Biomedical Engineering Technical University of Košice Košice Slovakia Dept. of Computer and Informatics Technical University of Košice Košice Slovakia

In the field of tissue engineering and regenerative medicine, understanding the intricate properties and behaviors of cells and tissues within their natural environment is fundamental for translating theory into practical applications. This scientific article introduces the development of a functional medium chamber. The design of this chamber was driven by the need to align it with the volume requirements and specified conditions of bioreactor systems. The objective was to acquire new practical and theoretical insights in the realms of tissue engineering, 3D printing, and bioreactor technology. The emphasis throughout the project was on simplicity in design, with the aim of enabling easy construction and disassembly of the model. This initiative not only involved the creation of a chamber design but also encompassed the 3D printing process and extended functional testing over the long term. The design parameters, including the closing mechanism and chamber shape, were thoughtfully selected to enhance versatility, making the chamber adaptable for various bioreactor systems in the future. Subsequently, the printed chamber underwent rigorous testing using water as the culture medium, laying the groundwork for potential advancements in bioreactor technology and tissue cultivation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HistoSmith: Single-Stage Histology Image-Label Generation via Conditional Latent Diffusion for Enhanced Cell Segmentation and Classification

arXiv

引用

arXiv 2025年

作者： Vadori, Valentina Graïc, Jean-Marie Peruffo, Antonella Finos, Livio Chaudhari, Ujwala Kiran Grisan, Enrico Dept. of Computer Science & Informatics London South Bank University United Kingdom Dept. of Comparative Biomedicine & Food Science University of Padova Italy Dept. of Statistical Sciences University of Padova Italy

Precise segmentation and classification of cell instances are vital for analyzing the tissue microenvironment in histology images, supporting medical diagnosis, prognosis, treatment planning, and studies of brain cytoarchitecture. However, the creation of high-quality annotated datasets for training remains a major challenge. This study introduces a novel single-stage approach (HistoSmith) for generating image-label pairs to augment histology datasets. Unlike state-of-the-art methods that utilize diffusion models with separate components for label and image generation, our approach employs a latent diffusion model to learn the joint distribution of cellular layouts, classification masks, and histology images. This model enables tailored data generation by conditioning on user-defined parameters such as cell types, quantities, and tissue types. Trained on the Conic H&E histopathology dataset and the Nissl-stained CytoDArk0 dataset, the model generates realistic and diverse labeled samples. Experimental results demonstrate improvements in cell instance segmentation and classification, particularly for underrepresented cell types like neutrophils in the Conic dataset. These findings underscore the potential of our approach to address data scarcity challenges. © 2025, CC BY-NC-SA.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Explainable Tracking of Political Violence Using the Tsetlin Machine

Explainable Tracking of Political Violence Using the Tsetlin...

引用

Tsetlin Machine (ISTM), International Symposium on the

作者： Hsu-Chiang Hsu Bree Bang-Jensen Michael P. Colaresi Panos K. Chrysanthis Vladimir I. Zadorozhny Dept. of Informatics & Network Systems University of Pittsburgh Dept. of Political Science University of Pittsburgh Dept. of Computer Science University of Pittsburgh

In this paper we introduce a framework that utilizes an architecture based on the Tsetlin Machine to output explainable rules for the prediction of political violence. The framework includes a data processing pipeline, modeling architecture, and visualization tools for early warning about notable events. We conducted an experimental study to explain and predict a one of the most notable events, - a civil war. We observed that the rules that we produced are consistent with theories that emphasize the continuing risks that accumulate from a history of conflict as well as the stickiness of civil war.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Analytics Task Management at the Edge: A Fuzzy Reasoning Approach 9

Data-Driven Analytics Task Management at the Edge: A Fuzzy R...

引用

9th International Conference on Future Internet of Things and Cloud, FiCloud 2022

作者： Aladwani, Tahani Alghamdi, Ibrahim Kolomvatsos, Kostas Anagnostopoulos, Christos University of Glasgow School of Computing Science United Kingdom Al-Baha University Faculty of Science and Arts in Baljurashi Dept. of Computer Science Sa Saudi Arabia University of Thessaly Dept. of Informatics and Telecommunications Gr Greece

ISBN: (数字)9781665493505

ISBN: (纸本)9781665493505

Dynamic data-driven applications such as tracking and surveillance have emerged in the Internet of Things (IoT) environments. Such applications rely heavily on data generated by connected devices (e.g., sensors). Consequently, leveraging these data in building data-driven predictive analytics tasks improves the Quality of Service (QoS) and, as a result, Quality of Experience (QoE). Such data support various data-driven tasks such as regression and classification. Analytics tasks require data and resources to be executed at the edge since transferring them to the cloud negatively affects response times and QoS. However, the network edge is characterized by limited resources compared to the cloud, being the subject of constraints that are violated upon offloading data-driven tasks to improper edge nodes. We contribute with an analytics task management mechanism based on the context of the requested data, the task delay sensitivity, and the VM utilization. We introduce a novel Fuzzy inference mechanism for determining whether data-driven tasks should be executed locally, offloaded to peer edge servers, or sent to the cloud. We showcase how our fuzzy reasoning mechanism efficiently derives such decisions by calculating the offloading probability per task. The derived optimal actions are compared against benchmark models in Edge Computing (EC). © 2022 IEEE.

关键词： Quality of service

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：