检索结果-内蒙古大学图书馆

International Conference on Advances in biomedical engineering (ICABME)

作者： Amira J. Zaylaa Alaa Daher Mohammad Ayache Niveen Omeirat Razane Mahmoud Bader Abou Hawili Biomedical Engineering Laboratory Biomedical Engineering Program Electrical and Computer Engineering Faculty of Engineering Beirut Arab University Lebanon

Osteoporosis is a common disease characterized by low bone density and structural deterioration of bone tissue. For a successful course of treatment and fracture avoidance, early diagnosis of this disease is essential. The aim was to provide a novel method for osteoporosis prediction using Artificial Intelligence (AI)-based framework. The purpose was to predict the likelihood of osteoporosis based on the Bone Mineral Density (BMD), along with other characteristics such as age, weight, height, gender, and Body Mass Index (BMI) extracted from medical reports and images collected from a comprehensive medical center in Lebanon. Three machine-learning algorithms were implemented and tested, Logistic Regression (LR), Support Vector Machines (SVM), and Decision Trees (DT). Variety of quantitative statistical metrics were used to evaluate the performance of our framework, upon training and testing our algorithms. The metrics that were employed to evaluate our results included accuracy, precision, sensitivity, and F-score, in addition to the Receiver Operating Characteristic (ROC) Curve and the Area Under the Curve (AUC). Experimental Results demonstrated that both the SVM and LR algorithms achieved the highest accuracy of detection of osteoporosis as compared to existing algorithms applied in this field, with an accuracy of 89%. The sensitivity of diagnosis obtained was 98% by LR and 97% by SVM and surpassed the sensitivity obtained by DT. As such LR showed the best performance. The output of the algorithms could help medical doctors assess patients automatically. These findings demonstrated the potential of AI in osteoporosis prediction and thus prevention, highlighting the significance of early diagnosis. Thereby as a future prospect, choosing carefully the framework is crucial and additional algorithms have to be considered and tested.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DENSE-Guided Deep Motion Networks Accounted by Large Rotations to Improve Myocardial Strain Analysis from Routine Cine MRI 22

DENSE-Guided Deep Motion Networks Accounted by Large Rotatio...

引用

22nd IEEE International Symposium on biomedical Imaging, ISBI 2025

作者： Lei, Pengcheng Xing, Jiarui Fang, Faming Epstein, Frederick H. Zhang, Miaomiao University of Virginia Department of Electrical and Computer Engineering United States School of Computer Science and Technology East China Normal University Shanghai China University of Virginia Health System Department of Biomedical Engineering United States

ISBN: (纸本)9798331520526

Myocardial strain imaging provides a valuable tool for detecting subclinical left ventricular (LV) dysfunction and adding prognostic value in assessing various types of heart disease. Recent studies have utilized highly accurate strain-dedicated techniques, such as displacement encoding with stimulated echoes (DENSE), to train a deep learning (DL) framework to predict the myocardial displacements/deformations from routine cine balanced steady state free precession (bSSFP) images. However, these methods have shown limited performance in capturing the large rotational motion of the myocardium associated with twist and torsion over time, which are important aspects of myocardial mechanics. To address this gap, this paper introduces a novel DENSE-guided DL network that explicitly accounts for large rotational motion to further improve strain analysis of standard cine bSSFP images. Specifically, our proposed network includes two key components: (i) a time-series rotation estimation network employing a 3D convolutional encoder-decoder architecture to model the large rotational dynamics of the LV myocardium over time, and (ii) a radial motion prediction network based on deformable image registration. The output of these two sub-networks was integrated and refined through a fusion network to predict the final myocardial displacements, supervised by DENSE ground truth. Experimental results show that our method improves the accuracy of myocardial strain with effectively captured large rotations. © 2025 IEEE.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

Capturing statistical fluctuations in gene expression activity using discrete stochastic systems

引用

IFAC-PapersOnLine 2024年第1期58卷 276-281页

作者： Zahra Vahdat Sayeh Rezaee Abhyudai Singh Department of Electrical and Computer Engineering University of Delaware Newark DE USA 19716 Department of Electrical and Computer Engineering Department of Biomedical Engineering Mathematical Sciences Center for Bioinformatics and Computational Biology University of Delaware Newark DE USA 19716

We present a discrete-event system formalism to capture experimentally observed activity of genes in single cells, where a gene can stochastically switch between an active state (synthesis of gene products, such as mRNA and proteins) and an inactive state (synthesis is turned OFF). Extending prior work that focused on memory-less switching kinetics, this contribution extends the models considering the time spent in each state to be an arbitrary positively-valued random variable. Here, memory-based switching is captured via the introduction of molecular timers that measure the time spent in a state, and switching rates are timer-dependent. Hence, a gene is more likely to turn OFF if it has been active for a long period. We provide exact analytical derivations of the mean and extent of stochasticity in the gene product level for these models and systematically study how different model parameters can be calibrated to attenuate or amplify noise in gene expression. These results can be combined with experimental data on measured levels inside individual cells to gain valuable insights into the gene expression process across different cell types, from bacterial to human cells.

关键词： Stochastic modeling Gene switching

来源：评论

学校读者我要写书评

暂无评论

BI-RADS prediction of mammographic masses using uncertainty information extracted from a Bayesian Deep Learning model

arXiv

引用

arXiv 2025年

作者： Chegini, Mohaddeseh Mahloojifar, Ali Department of Biomedical Engineering Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

The BI‐RADS score is a probabilistic reporting tool used by radiologists to express the level of uncertainty in predicting breast cancer based on some morphological features in mammography images. There is a significant variability in describing masses which sometimes leads to BI-RADS misclassification. Using a BI-RADS prediction system is required to support the final radiologist decisions. In this study, the uncertainty information extracted by a Bayesian deep learning model is utilized to predict the BI-RADS score. The investigation results based on the pathology information demonstrate that the f1-scores of the predictions of the radiologist are 42.86%, 48.33% and 48.28%, meanwhile, the f1-scores of the model performance are 73.33%, 59.60% and 59.26% in the BI-RADS 2, 3 and 5 dataset samples, respectively. Also, the model can distinguish malignant from benign samples in the BI-RADS 0 category of the used dataset with an accuracy of 75.86% and correctly identify all malignant samples as BI-RADS 5. The Grad-CAM visualization shows the model pays attention to the morphological features of the lesions. Therefore, this study shows the uncertainty-aware Bayesian Deep Learning model can report his uncertainty about the malignancy of a lesion based on morphological features, like a radiologist. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Capturing non-Gaussian statistics in noise-injection driven dynamical systems

引用

IFAC-PapersOnLine 2024年 57卷 250-255页

作者： Zahra Vahdat Cesar Nieto Abhyudai Singh Department of Electrical and Computer Engineering University of Delaware Newark DE USA 19716 Department of Electrical and Computer Engineering Department of Biomedical Engineering Mathematical Sciences Center for Bioinformatics and Computational Biology University of Delaware Newark DE USA 19716

The canonical approach to modeling stochasticity considers a dynamical system driven by Gaussian white noise. Here, we propose an alternative hybrid formulation, in which continuous dynamics is interspersed with noise injection events that occur at discrete times. The time interval between two successive events is drawn from an arbitrary, positively-valued continuous distribution. Although the hybrid approach converges to the classical stochastic differential equation when events occur sufficiently fast, the hybrid formulation captures a wider range of stochastic phenomena that deviate from Gaussian statistics when events occur at slower timescales. These deviations are mathematically captured by exact analytical expressions for higher-order moments, such as skewness and kurtosis of the state space. We illustrate this approach using the example of a nanosensor impacted by collisions from surrounding molecules. Our results provide an important generalization to capture the stochastic dynamics of physical, biological, and engineering systems and reveal a novel approach for exploiting higher-order moments to infer parameters that are not observable in lower-order moments.

关键词： Event Triggered Control Linear Systems Theory Stochastic Modeling Stochastic Differential Equations Time Triggered Stochastic Hybrid Systems

来源：评论

学校读者我要写书评

暂无评论

Critical Analysis of Inter-Turn Fault Related Harmonics in the Line Current

Critical Analysis of Inter-Turn Fault Related Harmonics in t...

引用

2024 International Conference on electrical Machines, ICEM 2024

作者： Bonet-Jara, Jorge Minervini, Marcello Frosini, Lucia Pons-Llinares, Joan Instituto de Tecnología Eléctrica Universitat Politècnica de València Valencia Spain University of Bergamo Department of Engineering and Applied Sciences Dalmine Italy University of Pavia Department of Electrical Computer and Biomedical Engineering Pavia Italy

ISBN: (纸本)9798350370607

Inter-Turn faults (ITFs) rapidly evolve into catastrophic failures of induction motors, thereby needing continuous monitoring. In this regard, methods based on localizing ITF-related harmonics in the line current are an attractive option, since they only need a current sensor in the motor cabinet. This paper presents for the first time a critical analysis of these harmonics, comparing their aptitudes as ITF indicators under different conditions, to determine which are the best. Comparison is performed considering not only the principal harmonic of each type, but the whole set of main harmonics. To this end, 52 laboratory tests are generated with different fault severities, loads, voltage unbalances and supply conditions. In each test, the amplitude of up to 19 harmonics is extracted, first to determine the most sensitive indicators in each group and then to compare them with each other. Finally, a critical discussion is provided, clarifying the best approach to take. © 2024 IEEE.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

DEEP LEARNING-BASED CHANNEL ESTIMATION FOR RIS-ASSISTED UAV-ENABLED WIRELESS COMMUNICATIONS SYSTEM

DEEP LEARNING-BASED CHANNEL ESTIMATION FOR RIS-ASSISTED UAV-...

引用

2023 International Conference on Innovation, Communication and engineering, ICICE 2023

作者： Tesfaw, Belayneh A. Lin, Hsin-Piao Tarekegn, Getaneh B. Juang, Rong-Terng Jeng, Shiann-Shiun Department of International Graduate Program in Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Institute of Aerospace and System Engineering National Taipei University of Technology Taipei10608 Taiwan Department of Electrical and Computer Engineering National Yang-Ming Chiao Tung University Hsinchu30010 Taiwan Department of Electrical Engineering National Dong Hwa University Hualien Taiwan

ISBN: (纸本)9781839539954

Wireless communication via unmanned aerial vehicles (UAVs) has drawn a great deal of attention due to its flexibility in establishing line-of-sight (LoS) communications. However, in complex urban and dynamic environments, the movement of UAVs can be blocked by trees and high-rise buildings that obstruct directional paths. This problem can be effectively addressed by employing reconfigurable intelligent surfaces (RIS). To achieve this goal, accurate channel estimation in RIS-assisted UAV-enabled wireless communications is crucial. This paper proposes an accurate channel estimation model using long short-term memory (LSTM) for a multi-user RIS-assisted UAV-enabled wireless communications system. Simulation results showed that LSTM can effectively improve the channel estimation performance of RIS-assisted UAV-enabled wireless communications. © The Institution of engineering & Technology 2023.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive, Cerebral Blood Volume Measurements During Sleep: Toward Naturalistic Measurements of Glymphatic Flux

Non-Invasive, Cerebral Blood Volume Measurements During Slee...

引用

Optical Tomography and Spectroscopy, OT and S 2024 - Part of Optica Biophotonics Congress: biomedical Optics

作者： Otic, Nikola Renna, Marco Lewis, Laura Franceschini, Maria Angela Robinson, Mitchell B. Department of Biomedical Engineering Boston University BostonMA United States Harvard Medical School MGH/HST Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Department of Electrical Engineering and Computer Science Institute for Medical Engineering and Science Massachusetts Institute of Technology CambridgeMA United States

The hemodynamic sources of glymphatic flow are typically measured using MRI. In this work, we demonstrate the feasibility of measuring cerebral hemodynamics through NIRS toward the goal of estimating glymphatic flux i... 详细信息

ISBN: (纸本)9781957171340

关键词： Hemodynamics

来源：评论

学校读者我要写书评

暂无评论

Design of High-Performance Optical TE Modulator Based on Si/VO2/Si Structure 2

Design of High-Performance Optical TE Modulator Based on Si/...

引用

2nd International engineering Conference on electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Heidari, Mohsen Mansour, Ibrahim Vatani, Sareh Heydari, Ebrahim Tarbiat Modares University Department of Electrical and Computer Engineering Tehran Iran Zarqa University Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia University of Nevada Department of Electrical and Biomedical Engineering RenoNV89557 United States

ISBN: (纸本)9798350373363

Phase transition in vanadium dioxide (VO2) from insulation to metallic phase, makes it an attractive candidate for the realization of electro-absorption modulators. In this paper, we investigate and design a high-performance modulator at the telecommunication wavelength of λ = 1.55 μm, based on a silicon rib waveguide incorporated with a nanostrip V02 layer. The modulator utilizes an asymmetric structure for enhancing the modulation depth and reaching the minimum insertion loss. We show that for transverse electric optical modes, the asymmetric structure shows better characteristics. The results show a high-modulation depth of about 6.54 dB/μm and the corresponding insertion loss of about 1.34 dB/μm. © 2023 IEEE.

关键词： Optical signal processing

来源：评论

学校读者我要写书评

暂无评论

Effect of electrolyte anions on the cycle life of a polymer electrode in aqueous batteries

引用

eScience 2022年第1期2卷 110-115页

作者： Ye Zhang Lihong Zhao Yanliang Liang Xiaojun Wang Yan Yao Department of Electrical and Computer Engineering Materials Science and Engineering ProgramUniversity of HoustonHoustonTX77204USA Texas Center for Superconductivity at the University of Houston HoustonTX77204USA

Redox polymers are a class of high-capacity, low-cost electrode materials for electrochemical energy storage, butthe mechanisms governing their cycling stability are not well understood. Here we investigate the effect of anionson the longevity of a p-dopable polymer through comparing two aqueous zinc-based electrolytes. Galvanostaticcycling studies reveal the polymer has better capacity retention in the presence of triflate anions than that withsulfate anions. Based on electrode microstructural analysis and evolution profiles of the cell stacking pressure, theorigin of capacity decay is ascribed to mechanical fractures induced by volume change of the polymer activematerials during repeated cycling. The volume change of the polymer with the triflate anion is 61% less than thatwith the sulfate anion, resulting in fewer cracks in the electrodes. The difference is related to the different anionsolvation structures—the triflate anion has fewer solvated water molecules compared with the sulfate anion,leading to smaller volume expansion. This work highlights that anions with low solvation degree are preferablefor long-term cycling.

关键词： Aqueous batteries Polymer electrode Anions Volume chang

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：