检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Giudice, Enrico Kuipers, Jack Moffa, Giusi Dep. of Mathematics and Computer Science University of Basel Basel Switzerland Dep. of Biosystems Science and Engineering ETH Zurich Basel Switzerland Division of Psychiatry University College London London United Kingdom

Learning the graphical structure of Bayesian networks is key to describing data-generating mechanisms in many complex applications but poses considerable computational challenges. Observational data can only identify the equivalence class of the directed acyclic graph underlying a Bayesian network model, and a variety of methods exist to tackle the problem. Under certain assumptions, the popular PC algorithm can consistently recover the correct equivalence class by reverse-engineering the conditional indep.ndence (CI) relationships holding in the variable distribution. The dual PC algorithm is a novel scheme to carry out the CI tests within the PC algorithm by leveraging the inverse relationship between covariance and precision matrices. By exploiting block matrix inversions we can also perform tests on partial correlations of complementary (or dual) conditioning sets. The multiple CI tests of the dual PC algorithm proceed by first considering marginal and full-order CI relationships and progressively moving to central-order ones. Simulation studies show that the dual PC algorithm outperforms the classic PC algorithm both in terms of run time and in recovering the underlying network structure, even in the presence of deviations from Gaussianity. Additionally, we show that the dual PC algorithm applies for Gaussian copula models, and demonstrate its performance in that setting. Copyright © 2021, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Growth and applications of AIScN and AIYN grown by MOCVD 20

Growth and applications of AIScN and AIYN grown by MOCVD

引用

Gallium Nitride Materials and Devices XX 2025

作者： Leone, S. Duarte, T. Straňák, P. Kirste, L. Nomoto, K. Schoenweger, G. Wolff, N. Streicher, I. Fichtner, S. Jena, D. Quay, R. Fraunhofer IAF Tullastrasse 72 Freiburg79102 Germany School of Electrical and Computer Engineering Cornell University IthacaNY14853 United States CNR-IMM Strada VIII n. 5 - Zona Industriale Catania95121 Italy Dep. Material Science Kiel University Kaiserstr. 2 Kiel24143 Germany

ISBN: (纸本)9781510684805

AlScN/GaN and AlYN/GaN HEMTs offer higher drain currents and output powers Pout than conventional AlGaN/GaN devices and are an attractive solution for power amplifiers operating in the millimeter wave range. Thanks to a lattice matching of AlScN and AlYN with GaN, strain-free heterostructures can be obtained. Growth of such structures by metal-organic chemical vapor dep.sition suffered from the low vapor pressure of the commercially available Sc precursor Cp3Sc, which led to low growth rates and degradation of the interfaces by atom interdiffusion. In this work, we used novel precursors to increase the growth rate and present homogenous AlScN or AlYN barriers, excellent structural quality, and abrupt interfaces to the GaN channel. HEMTs were fabricated by using MBE-regrown ohmic contacts and showed very low contact resistance as well as very good DC performance. The latest progress in the growth of multichannel AlScN/GaN heterostructures are presented too. © 2025 SPIE.

关键词： Metallorganic chemical vapor dep.sition

来源：评论

学校读者我要写书评

暂无评论

PacECG-Net: A Multi-modal Approach Integrating LLMs and ECG for LVSD Classification in Pacemaker Patients 25

PacECG-Net: A Multi-modal Approach Integrating LLMs and ECG ...

引用

40th Annual ACM Symposium on Applied Computing, SAC 2025

作者： Shim, Wonkyeong Park, Namjun Ko, Donggeun Kim, San Gwag, Hye Bin Park, Young Jun Park, Seung-Jung Kim, Jaekwang Department of Computer Science and Engineering Sungkyunkwan University Suwon Korea Republic of Aim Future AI Seoul Korea Republic of Dep. of Computer Science and Eng. Sungkyunkwan University Suwon Korea Republic of Samsung Changwon Hospital Changwon Korea Republic of Wonju Severance Christian Hospital Wonju Korea Republic of Samsung Medical Center Seoul Korea Republic of School of Convergence/Convergence Program for Social Innovation Sungkyunkwan University Seoul Korea Republic of

ISBN: (纸本)9798400706295

This study presents an AI-based model using ECG signals to predict left ventricular systolic dysfunction (LVSD) in pacemaker patients. A 1D convolutional neural network (CNN) combined with large language models processed both sequential ECG data and nonsequential clinical metadata. The model achieved an AUROC of 0.97 on both general and pacemaker-specific datasets, demonstrating its high accuracy. This approach offers a fast, cost-effective alternative to traditional echocardiography, improving LVSD detection in patients with pacemakers. Copyright © 2025 held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Characterization of Glioblastoma Organoid Bio-Responses Upon 30.5 GHz Continuous Wave Exposure

Characterization of Glioblastoma Organoid Bio-Responses Upon...

引用

IEEE MTT-S International Microwave Bio Conference ((IMBIOC)

作者： Elena Rampazzo Nissar Karim Luca Persano Rosanna Pinto Arianna Casciati Mirella Tanori George Hodgkins Ilan W. Davies Alessandro Zambotti Cristopher Hancock Cristiano Palego Gimapietro Viola Mariateresa Mancuso Caterina Merla Dep. of Women's and Children's Health (SDB) University of Padova Padova Italy School of Computer Science and Electronic Engineering Bangor University Bangor UK Div. Health Protection Technologies ENEA Rome Italy Group R&D CREO Medical Bath UK Group R& School of Computer Science and Electronic Engineering D CREO Medical Bath UK

This paper reports on the effects of 30.5 GHz continuous wave exposure on cancer stem cells of glioblastoma organoids. The exposure setup was completely developed and the dosimetry carried on based on both numerical and experimental activities. Our results showed modification in cell death and proliferation, suggesting that presented exposure at a power level of 0.1 W (RMS) seems useful for targeting glioblastoma cells, and improving future treatment of this complex pathology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a Low-Cost Interrogation System Using a MEMS Fabry-Pérot Tunable Filter 5

Development of a Low-Cost Interrogation System Using a MEMS ...

引用

5th International Conference on Applications of Optics and Photonics, AOP 2022

作者： Araújo, João C. C. Dias, Bernardo Dos Santos, Paulo S. S. De Almeida, J.M.M.M. Coelho, Luís C. C. INESC TEC - Institute for Systems and Computer Engineering Technology and Science FCUP Univ. of Porto R. Do Campo Alegre Porto4169-007 Portugal FCUP University of Porto Rua do Campo Alegre Porto4169-007 Portugal Dep. of Physics Univ. of Trás-os-Montes e Alto Douro Vila Real5001-801 Portugal

The interrogation of optic fiber sensors usually relies in complex and costly equipment with low portability due to their size such as Optical Spectrum Analyzers (OSA) or high-resolution spectrometers. Because of this, micro spectrometer devices, such as Micro-Electromechanical Systems (MEMS) with Fabry-Pérot tunable filters, are emerging as simpler and compact alternatives capable of being used to acquire spectral information in a wide wavelength band. In this work it is described the development of an interrogation system capable of infrared spectroscopy using a MEMS Fabry-Pérot Interferometer (MEMS-FPI) with a spectral response in the 1350nm to 1650nm range. Its performance is tested with the interrogation of long period fiber gratings both as a refractive index sensor and as a temperature sensor. Deconvolution techniques such as Wiener filtering are used to reduce the impact of the tunable filter's impulse response in the measured signal. Results are comparable to those obtained using a typical OSA which shows the system's potential as a cheaper and more transportable alternative. © Published under licence by IOP Publishing Ltd.

关键词： Fiber optic sensors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Road Object Detection for Collision Avoidance in Autonomous Driving

Deep Learning-based Road Object Detection for Collision Avoi...

引用

Public Safety Technology (WFPST), IEEE World Forum on

作者： Teena Sharma Abdellah Chehri Issouf Fofana Benoit Debaque Nicolas Duclos Siddhartha Khare Department of Applied Sciences (DSA) University of Quebec in Chicoutimi Saguenay QC Canada Dep. of Mathem & Computer Science Royal Military College of Canada Kingston ON Canada Department of Applied Sciences University of Quebec in Chicoutimi Saguenay QC Canada Thales Communications and Security SAS Quebec Canada Department of Civil Engineering IIT Roorkee India

ISBN: (数字)9798350329148

ISBN: (纸本)9798350329155

With the population in metro cities rising, traffic congestion has become a significant issue, resulting in an alarming number of traffic collisions and road accidents. Given the advancements in automated vehicles, it is crucial to have a vehicle detection system that is equipped to handle the various challenges that arise on the road, particularly when it comes to traffic collisions. Although many datasets are available to support object detection for traffic monitoring and management, the suitability of these datasets for specific weather conditions across the globe needs to be analyzed. We present Canadian vehicle datasets (CVD) and analyze the YOLOv8-based deep learning model using CVD. Thales, Canada, captured street-level videos in Quebec City, Canada, with a vehicle equipped with a high-quality RGB camera. The videos are taken day and night in all four seasons: rain, snow, hazy, and bright sunlight. We created 27378 labels for 11 classes for 8000 images. The YOLOv8 model trained on the publicly available roboFlow dataset was compared to the model trained on the combined roboflow and our weather-specific CVD.

关键词： Road accidents Roads Snow Urban areas Sociology Transportation Object detection

来源：评论

学校读者我要写书评

暂无评论

Automating Public Announcement Logic with Relativized Common Knowledge as a Fragment of HOL in LogiKEy

arXiv

引用

arXiv 2021年

作者： Benzmüller, Christoph Reiche, Sebastian University of Bamberg AI Systems Engineering Bamberg Germany FU Berlin Dep. of Mathematics and Computer Science Berlin Germany

A shallow semantical embedding for public announcement logic with relativized common knowledge is presented. This embedding enables the first-time automation of this logic with off-the-shelf theorem provers for classical higher-order logic. It is demonstrated (i) how meta-theoretical studies can be automated this way, and (ii) how non-trivial reasoning in the target logic (public announcement logic), required e.g. to obtain a convincing encoding and automation of the wise men puzzle, can be realized. Key to the presented semantical embedding is that evaluation domains are modeled explicitly and treated as an additional parameter in the encodings of the constituents of the embedded target logic;in previous related works, e.g. on the embedding of normal modal logics, evaluation domains were implicitly shared between meta-logic and target logic. The work presented in this article constitutes an important addition to the pluralist LogiKEy knowledge engineering methodology, which enables experimentation with logics and their combinations, with general and domain knowledge, and with concrete use cases - all at the same *** Codes 03B42, 03B60, 03B62, 68T27, 68T30 Copyright © 2021, The Authors. All rights reserved.

关键词： Formal logic

来源：评论

学校读者我要写书评

暂无评论

LLM Acceleration on FPGAs: A Comparative Study of Layer and Spatial Accelerators

LLM Acceleration on FPGAs: A Comparative Study of Layer and ...

引用

IEEE Central America and Panama Convention (CONCAPAN)

作者： Luis D. Prieto-Sibaja Luis G. Leόn-Vega Indra Leόn-Vega Jorge Castro-Godínez Stefano Cozzini Computer Engineering School Costa Rica Institute of Technology Cartago Costa Rica Math. Inf. and Geoscience Dep. University of Trieste Trieste Italy Industrial Design Engineering School Instituto Tecnolόgico de Costa Rica Cartago Costa Rica Electronics Engineering School Costa Rica Institute of Technology Cartago Costa Rica Institute of Research and Technology AREA Science Park Trieste Italy

ISBN: (数字)9798350366723

ISBN: (纸本)9798350366730

Large Language Models (LLMs) have emerged as the leading technique in Natural Language Processing due to their remarkable capabilities. These models are exceptionally complex, often utilising billions of parameters and consuming tens of gigabytes of memory unless optimised. Typically, LLMs are trained and accelerated using general-purpose Graphics Processing Units (GPUs), with a single inference potentially occupying an entire GPU. Consequently, cloud services may require hundreds of GPUs to deliver high-quality AI assistant services. This demand for extensive hardware acceleration allows exploring alternative architectures that offer improved execution time and energy *** study evaluates Field-Programmable Gate Arrays (FP-GAs), renowned for their flexibility and efficiency, to accelerate LLMs. We specifically compare the resource consumption and latency of two distinct architectures: layer and spatial accelerators. Analysing the Llama 2-7B model, we identified potential optimisation opportunities within its composition and operational graphs. Our most successful implementations demonstrate a performance improvement ranging from 1.37× to 10.98× over two AMD EPYC processors with 64 cores each. Moreover, our results indicate that, with further refinement, FPGAs have the potential to surpass GPU performance for LLM inference, showcasing their feasibility as a viable alternative for this demanding application.

关键词： Large language models High performance computing Graphics processing units computer architecture Logic gates Distance measurement Natural language processing Field programmable gate arrays Hardware acceleration Optimization

来源：评论

学校读者我要写书评

暂无评论

Preventing unauthorized use of proprietary data: Poisoning for secure dataset release

arXiv

引用

arXiv 2021年

作者： Fowl, Liam Chiang, Ping-Yeh Goldblum, Micah Geping, Jonas Bansal, Arpit Czaja, Wojtek Goldstein, Tom Department of Mathematics University of Maryland United States Department of Computer Science University of Maryland United States Dep. of Electrical Engineering and Computer Science University of Siegen Germany

Large organizations such as social media companies continually release data, for example user images. At the same time, these organizations leverage their massive corpora of released data to train proprietary models that give them an edge over their competitors. These two behaviors can be in conflict as an organization wants to prevent competitors from using their own data to replicate the performance of their proprietary models. We solve this problem by developing a data poisoning method by which publicly released data can be minimally modified to prevent others from training models on it. Moreover, our method can be used in an online fashion so that companies can protect their data in real time as they release it. We demonstrate the success of our approach on ImageNet classification and on facial recognition. © 2021, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Gait-Based User Identification for Smart Home: When Machine Learning Meets FBG Accelerometers

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Alhussein, Ghada Chi, Hao Ran Alberto, Nelia Antunes, Paulo Hadjileontiadis, Leontios Radwan, Ayman Domingues, M. Fatima Instituto de Telecomunicações-University of Aveiro Aveiro Portugal Instituto de Telecomunicações I3N and Dep. of Physics-University of Aveiro Aveiro Portugal Khalifa University of Science and Technology Department of Biomedical Engineering and Biotechnology Abu Dhabi United Arab Emirates Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki Greece Instituto de Telecomunicações Instituto Superior Tècnico -University of Lisbon Lisbon Portugal

Advancements in fiber optic sensor technology and telecommunications have paved the way for innovative health monitoring systems. However, previous works in this area have often been limited by the lack of comprehensive datasets, hindering the development of accurate and robust solutions. This paper addresses this gap by presenting a novel dataset and approach to gait-based user identification using a set of four optical Fiber Bragg Grating (FBG) sensor-based accelerometers, integrated into smart home environments. By computing features such as entropy, mean, standard deviation, kurtosis, and skewness from raw signals, and employing three unsupervised machine learning models-K-means, DB-scan, and Gaussian Mixture Model (GMM)-we achieve high accuracy in distinguishing individuals. Our dataset results for each sensor are as follows: for Sensor 1, K-means with a Silhouette Score of 0.3038 and Davies-Bouldin Index of 1.1238;for Sensor 2, K-means with a Silhouette Score of 0.3543 and Davies-Bouldin Index of 0.9659;for Sensor 3, DB-scan with a Silhouette Score of 0.2650 and Davies-Bouldin Index of 0.6855;and for Sensor 4, K-means with a Silhouette Score of 0.3949 and Davies-Bouldin Index of 1.0438. This approach not only enhances user identification but also facilitates personalized healthcare applications and unobtrusive monitoring. © 1975-2011 IEEE.

关键词： Smart homes

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：