检索结果-内蒙古大学图书馆

Annual IEEE Systems Conference

作者： Samar AboulEla Paria Zabihitari Nourhan Ibrahim Majid Afshar Rasha Kashef Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto ON Canada Faculty of Engineering Alexandria University Alexandria Egypt Department of Electronics and Computer Engineering Technology Indiana State University Terre Haute USA

ISBN: (数字)9798331508180

ISBN: (纸本)9798331508197

Large Language Models (LLMs) often face challenges in generating accurate and reliable information, particularly in knowledge-intensive tasks. This limitation, referred to as hallucination, occurs when models produce content that is incorrect, irrelevant, or unsupported by evidence. Retrieval Augmented Generation (RAG) solutions provide a promising approach by integrating relevant external knowledge, enabling models to generate factually grounded responses. This study evaluates the performance of a base LLM model, a fine-tuned DistilBERT model, and two RAG architectures, Naïve RAG and Graph RAG, to study their impact on reducing hallucinations and enhancing contextual understanding. Using subsets of HaluEval, Squad-V2, and TriviaQA benchmark datasets, the base model achieved accuracies of 10.18%, 12.67%, and 5.46% respectively; Naive RAG resulted in 44.56%, 19.04%, and 35.32% accuracies; while the fine-tuned LLM model's accuracies were 72.5%, 72.31%, and 88.7% respectively. Graph RAG resulted in 8.85% and 15.12% accuracies using Squad-V2 and TriviaQA, respectively. Our findings show that while fine-tuned LLMs outperform baseline models, incorporating RAG solutions did not result in significant performance improvements, suggesting that the incorporation of external knowledge may not always align with the needs of the task. Experiments demonstrate that Graph RAG handles complex queries by leveraging relationships within structured knowledge graphs. Data organized as a knowledge graph may enable Graph RAG solutions reach their full potential by utilizing their capacity to efficiently retrieve contextually relevant information. Although computing complexity remains a restriction, this study shows that RAG topologies might not consistently enhance LLM reliability in practical situations.

关键词： Accuracy Scalability Large language models Retrieval augmented generation Memory Knowledge graphs Topology Reliability Optimization Context modeling

来源：评论

学校读者我要写书评

暂无评论

GaAs-Based Photovoltaic Infrared Energy Harvesting for Microscale biomedical Implants 49

GaAs-Based Photovoltaic Infrared Energy Harvesting for Micro...

引用

49th IEEE Photovoltaics Specialists Conference, PVSC 2022

作者： Sun, Y. Letner, J. Lee, J. Ahmed, N. Chestek, C. Blaauw, D. Phillips, J. University of Michigan Electrical Engineering and Computer Science Department Ann ArborMI48109 United States University of Michigan Biomedical Enaineering Department Ann ArborMI48109 United States University of Delaware Electrical and Computer Engineering Department NewarkDE19716 United States

ISBN: (数字)9781728161174

ISBN: (纸本)9781728161174

Fully wireless biomedical implantable devices at the microscale are of great interest for a new generation of medical devices inlcluding precision health and brain computer interfaces. One of the greatest challenges for these devices is energy harvesting for self-powering at small dimensions. Here, we demonstrate a dual-junction (DJ) GaAs-based photovoltaic (PV) cell with an area of 200 times 200 mu mathrm{m} 2 and explore their energy harvesting potential for near surface bio-implantables. The devices achieve a power conversion efficiency of more than 23% and open circuit voltage of greater than 1.13 V under 1.03 mu mathrm{W}/ mathrm{mm} 2 near-infrared irradiation at a wavelength of 850 nm. Energy harvesting through biospecimens of mouse skins are demonstrated with sufficient power density for low power CMOS electronics at irradiance levels orders of magnitude below the maximum permissible exposure defined by the American National Standards Institute (ANSI) Z136.1 standard. © 2022 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Cloud-Integrated Clean Fuel Generation for Solar-Hydrogen Production with Wireless Sensor Networks 7

Cloud-Integrated Clean Fuel Generation for Solar-Hydrogen Pr...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Naveenkumar, N. Sridevi, V. Bharathi, R. Mishra, Nilamadhab Murugan, S. Velmurugan, S. Department of Computer Science And Engineering Namakkal Tamil Nadu Rasipuram India Academy of Maritime Education And Training Deemed To Be University Electrical And Electronics Engineering Tamil Nadu Chennai India Srm Institute of Science And Technology Faculty of Management Chennai Tamil Nadu Kattankulathur India Vit Bhopal University School of Computing Science And Engineering Madhya Pradesh India Saveetha Institute of Medical And Technical Sciences Saveetha University Saveetha School of Engineering Department of Biomedical Engineering Tamil Nadu Chennai India T.J.S. Engineering College Department of Electronics And Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350359299

This research study proposes a novel system that integrates Wireless Sensor Networks (WSNs) with cloud-based platforms to efficiently generate renewable energy and produce clean fuel. By enhancing the safety, efficiency, and reliability of solar power and hydrogen generation, the system integrates optimization strategies, data analysis, and real-time monitoring. Critical parameters such as temperature, sun irradiance, electrolysis efficiency, and hydrogen purity are monitored using WSNs, with data transmitted and processed via cloud techniques to identify patterns, outliers, and areas for improvement. Proactive decision-making and rapid adjustments are facilitated through remote monitoring and control capabilities, leading to maximized energy production and clean fuel output. Security measures including encryption, access controls, and regular audits safeguard data privacy and integrity, while multiple sensor deployments, robust communication protocols, and a resilient cloud infrastructure ensure system reliability. This integrated approach offers an effective solution for advancing renewable energy generation and clean fuel production, contributing to environmental sustainability and a greener future. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Multi-slice beam propagation method for imaging multiple-scattering samples on reflective substrates

arXiv

引用

arXiv 2025年

作者： Zhu, Jiabei Li, Tongyu Wang, Hao Shen, Yi Hu, Guorong Tian, Lei Department of Electrical and Computer Engineering Boston University BostonMA02215 United States Department of Biomedical Engineering Boston University BostonMA02215 United States

Diffraction tomography (DT) has been widely explored in transmission-mode configurations, enabling high-resolution, label-free 3D imaging. However, adapting DT for reflection-mode measurements presents significant challenges due to strong substrate reflections and complex multiple-scattering effects, particularly in metrology and industrial inspection applications. In this work, we introduce reflection-mode Fourier Ptychographic Tomography (rFPT) that achieves high-resolution, volumetric imaging of multi-layered, strongly scattering samples on reflective substrates. We develop a reflection-mode multi-slice beam propagation method (rMSBP) to model multiple scattering and substrate interactions, enabling precise 3D reconstruction. By incorporating darkfield measurements, rFPT enhances resolution beyond the traditional brightfield limit and provides sub-micrometer lateral resolution while achieving optical sectioning. We validate rFPT through numerical simulations on a four-layer resolution target and experimental demonstrations using a reflection-mode LED array microscope. Experiments on a two-layer resolution target and a multi-layer scattering sample confirm the method’s effectiveness. Our optimized implementation enables rapid imaging, covering a 1.2 mm × 1.2 mm area in 1.6 seconds, reconstructing over 109 voxels within a 0.4 mm3 volume. This work represents a significant step in extending DT to reflection-mode configurations, providing a robust and scalable solution for 3D metrology and industrial inspection. © 2025, CC BY-SA.

关键词： Multiple scattering

来源：评论

学校读者我要写书评

暂无评论

SABiT-MNet: Scale-Adaptive Autoencoder with BiT-M Model for Identifying AMD Grades

SABiT-MNet: Scale-Adaptive Autoencoder with BiT-M Model for ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Niveen Nasr El-Den Mohamed Elsharkawy Mohammed Ghazal Ali Mahmoud Harpal Sandhu Hani Mahdi Ayman El-Baz Department of Computer and System Engineering Ain Shams University Egypt Department of Bioengineering University of Louisville Louisville KY USA Electrical Computer and Biomedical Engineering Department Abu Dhabi University Abu Dhabi UAE

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurate early diagnosis is crucial in addressing Age-related Macular Degeneration (AMD), a chronic retinal disease that is a leading cause of blindness among the elderly. Medical imaging, particularly fundus imaging, is essential in facilitating timely detection and intervention. Due to the variability in image sizes within our dataset, this paper introduces the SABiT-MNet model, which effectively discriminates between healthy retinas, dry AMD, and wet AMD. The model integrates a novel scale-adaptive (SA) approach by combining an autoencoder with Big Transfer (BiT) as its backbone. Unlike traditional resizing methods, which often result in the loss of critical diagnostic information, the SA model dynamically adjusts to varying image sizes, preserving key retinal features essential for accurate diagnosis. The primary aim of this architecture is to retain crucial details in fundus images to ensure precise classification. In this study, 648 subjects were recruited through the Comparisons of AMD Treatments Trials study group, sponsored by the University of Pennsylvania. Experimental results demonstrate that the proposed SABiT-MNet model outperforms state-of-the-art approaches, including transformer-based models, achieving superior diagnostic accuracy. The model recorded performance metrics of 94% accuracy, 97% sensitivity, and 93.94% specificity. To further validate the robustness of the system, we tested it on the public ODiR dataset, where it achieved similarly promising results, confirming the effectiveness of our approach.

关键词： Macular degeneration Accuracy Sensitivity Autoencoders Signal processing Retina Transformers Robustness Speech processing Older adults

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-based Receding Horizon Control using Adaptive Control Barrier Functions for Safety-Critical Systems

arXiv

引用

arXiv 2024年

作者： Sabouni, Ehsan Sabbir Ahmad, H.M. Giammarino, Vittorio Cassandras, Christos G. Paschalidis, Ioannis Ch. Li, Wenchao Division of Systems Engineering Boston University BostonMA02215 United States The Department of Electrical and Computer Engineering The Division of Systems Engineering Boston University BostonMA02215 United States The Department of Electrical and Computer Engineering Division of Systems Engineering Department of Biomedical Engineering Boston University BostonMA02215 United States

Optimal control methods provide solutions to safety-critical problems but easily become intractable. Control Barrier Functions (CBFs) have emerged as a popular technique that facilitates their solution by provably guaranteeing safety, through their forward invariance property, at the expense of some performance *** approach involves defining a performance objective alongside CBF-based safety constraints that must always be enforced. Unfortunately, both performance and solution feasibility can be significantly impacted by two key factors such as the selection of the cost function and associated parameters, and the calibration of parameters within the CBF-based constraints, which capture the trade-off between performance and conservativeness. To address these challenges, we propose a Reinforcement Learning (RL)-based Receding Horizon Control (RHC) approach leveraging Model Predictive Control (MPC) with CBFs (MPC-CBF). In particular, we parameterize our controller and use bilevel optimization, where RL is used to learn the optimal parameters while MPC computes the optimal control input. We validate our method by applying it to the challenging automated merging control problem for Connected and Automated Vehicles (CAVs) at conflicting roadways. Results demonstrate improved performance and a significant reduction in the number of infeasible cases compared to traditional heuristic approaches used for tuning CBF-based controllers, showcasing the effectiveness of the proposed method. Copyright © 2024, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Simulating Brain Gradient-Echo Magnetic Resonance Images through Microstructural Modeling 13

Simulating Brain Gradient-Echo Magnetic Resonance Images thr...

引用

13th International Workshop on Innovative Simulation for Health Care, IWISH 2024, Held at the 21st International Multidisciplinary Modeling and Simulation Multiconference, I3M 2024

作者： Şişman, Mert Roberts, Alexandra Zhuang, Hangwei Hu, Renjiu Cho, Junghun Zhang, Shun Spincemaille, Pascal Nguyen, Thanh Wang, Yi Department of Electrical and Computer Engineering Cornell University IthacaNY14850 United States Department of Radiology Weill Cornell Medicine New YorkNY10021 United States Meinig School of Biomedical Engineering Cornell University IthacaNY14850 United States Sibley School of Mechanical and Aerospace Engineering Cornell University IthacaNY14850 United States Department of Biomedical Engineering State University of New York at Buffalo BuffaloNY14228 United States Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9791281988132

Quantitative magnetic resonance imaging (qMRI) methods usually suffer from the lack of appropriate or easy-to-implement methods of ***, we developed a detailed framework to synthetically generate realistic brain multi gradient-echo (mGRE) data incorporating biophysical modeling of the MRI signals and microstructure brain *** addition to validation, simulated data can also be utilized for the supervised training of deep learning models for the inverse mapping of the microstructural and physiological *** feasibility of one such parameter that is extremely valuable if can be measured noninvasively, oxygen extraction fraction (OEF), is *** simulated and in vivo tests demonstrated high accuracy in the *** developed method and the results reflect the significance of simulation-based computational approaches for answering the clinical needs. © 2024 The Authors.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

LaMoD: Latent Motion Diffusion Model For Myocardial Strain Generation

arXiv

引用

arXiv 2024年

作者： Xing, Jiarui Jayakumar, Nivetha Wu, Nian Wang, Yu Epstein, Frederick H. Zhang, Miaomiao Department of Electrical and Computer Engineering University of Virginia United States Department of Computer Science University of Virginia United States Department of Biomedical Engineering University of Virginia Health System United States

Motion and deformation analysis of cardiac magnetic resonance (CMR) imaging videos is crucial for assessing myocardial strain of patients with abnormal heart functions. Recent advances in deep learning-based image registration algorithms have shown promising results in predicting motion fields from routinely acquired CMR sequences. However, their accuracy often diminishes in regions with subtle appearance changes, with errors propagating over time. Advanced imaging techniques, such as displacement encoding with stimulated echoes (DENSE) CMR, offer highly accurate and reproducible motion data but require additional image acquisition, which poses challenges in busy clinical flows. In this paper, we introduce a novel Latent Motion Diffusion model (LaMoD) to predict highly accurate DENSE motions from standard CMR videos. More specifically, our method first employs an encoder from a pre-trained registration network that learns latent motion features (also considered as deformation-based shape features) from image sequences. Supervised by the ground-truth motion provided by DENSE, LaMoD then leverages a probabilistic latent diffusion model to reconstruct accurate motion from these extracted features. Experimental results demonstrate that our proposed method, LaMoD, significantly improves the accuracy of motion analysis in standard CMR images;hence improving myocardial strain analysis in clinical settings for cardiac patients. Our code is publicly available at https://***/jr-xing/LaMoD. © 2024, CC BY.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Guiding Ultrasound Breast Tumor Classification with Human-Specified Regions of Interest: A Differentiable Class Activation Map Approach

Guiding Ultrasound Breast Tumor Classification with Human-Sp...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Haotian Chen Zikui Wang Aiguo Han Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Urbana USA Department of Electrical Engineering Stanford University Stanford USA Department of Biomedical Engineering and Mechanics Virginia Polytechnic Institute and State University Blacksburg USA

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Ultrasound is a useful tool for evaluating the malignancy of breast tumors, but the interpretability of deep learning models used for benign-versus-malignant classification remains a challenge. Class Activation Maps (CAMs) offer a method to visualize and understand the neural network (NN) focus, but there lacks an established method to correct erroneous foci by the NN. To address this gap, we developed a deep learning framework that guides the NN's focus using human expert-specified Regions of Interest (ROIs). By formulating focus correction as a distance minimization task and introducing a differentiable peaked CAM (PCAM), our method ensures the NN's focus aligns with the human-specified ROI. By minimizing the difference between the PCAM and the binary ROI mask, the focus of NN is effectively driven into the ROI region. Evaluations on multi-center public datasets demonstrate the effectiveness of incorporating human-specified ROIs in improving both tumor classification accuracy and focus localization accuracy.

关键词： Deep learning Location awareness Visualization Ultrasonic imaging Breast tumors Accuracy Artificial neural networks Minimization Cams Reliability

来源：评论

学校读者我要写书评

暂无评论

Image reconstruction via autoencoding sequential deep image prior 24

Image reconstruction via autoencoding sequential deep image ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Ismail R. Alkhouri Shijun Liang Evan Bell Qing Qu Rongrong Wang Saiprasad Ravishankar Department of Computational Mathematics Science & Engineering Michigan State University and Department of Electrical Engineering & Computer Science University of Michigan - Ann Arbor Department of Biomedical Engineering Michigan State University Department of Computational Mathematics Science & Engineering Michigan State University Department of Electrical Engineering & Computer Science University of Michigan - Ann Arbor Department of Computational Mathematics Science & Engineering Michigan State University and Department of Mathematics Michigan State University Department of Computational Mathematics Science & Engineering Michigan State University and Department of Biomedical Engineering Michigan State University

ISBN: (纸本)9798331314385

Recently, Deep Image Prior (DIP) has emerged as an effective unsupervised one-shot learner, delivering competitive results across various image recovery problems. This method only requires the noisy measurements and a forward operator, relying solely on deep networks initialized with random noise to learn and restore the structure of the data. However, DIP is notorious for its vulnerability to overfitting due to the overparameterization of the network. Building upon insights into the impact of the DIP input and drawing inspiration from the gradual denoising process in cutting-edge diffusion models, we introduce Autoencoding Sequential DIP (aSeqDIP) for image reconstruction. This method progressively denoises and reconstructs the image through a sequential optimization of network weights. This is achieved using an input-adaptive DIP objective, combined with an autoencoding regularization term. Compared to diffusion models, our method does not require training data and outperforms other DIP-based methods in mitigating noise overfitting while maintaining a similar number of parameter updates as Vanilla DIP. Through extensive experiments, we validate the effectiveness of our method in various image reconstruction tasks, such as MRI and CT reconstruction, as well as in image restoration tasks like image denoising, inpainting, and non-linear deblurring. Our code is available at the GitHub repository https://***/sjames40/Aseq_DIP/tree/main.

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：