检索结果-内蒙古大学图书馆

Noise Reduction in Industry Based on Virtual Instrumentation

computers, Materials & Continua 2021年第10期69卷 1073-1096页

作者： Radek Martinek Rene Jaros Jan Baros Lukas Danys Aleksandra Kawala-Sterniuk Jan Nedoma Zdenek Machacek Jiri Koziorek Faculty of Electrical Engineering and Computer Science Department of Cybernetics and Biomedical EngineeringVSB–Technical University of Ostrava70800Ostrava-PorubaCzechia Faculty of Electrical Engineering Automatic Control and InformaticsOpole University of TechnologyOpolePoland Faculty of Electrical Engineering and Computer Science Department of TelecommunicationsVSB–Technical University of Ostrava70800Ostrava-PorubaCzechia

This paper discusses the reduction of background noise in an industrial environment to extend *** the Industry 4.0 era,the mass development of voice control(speech recognition)in various industrial applications is possible,especially as related to augmented reality(such as hands-free control via voice commands).As Industry 4.0 relies heavily on radiofrequency technologies,some brief insight into this problem is provided,including the Internet of things(IoT)and 5G *** study was carried out in cooperation with the industrial partner Brose CZ spol.s.r.o.,where sound recordings were made to produce a *** experimental environment comprised three workplaces with background noise above 100 dB,consisting of a laser/magnetic welder and a press.A virtual device was developed from a given dataset in order to test selected commands from a commercial speech recognizer from *** tested a hybrid algorithm for noise reduction and its impact on voice command recognition *** virtual devices,the study was carried out on large speakers with 20 participants(10 men and 10 women).The experiments included a large number of repetitions(100 times for each command under different noise conditions).Statistical results confirmed the efficiency of the tested *** welding environment efficiency was 27%before applied filtering,76%using the least mean square(LMS)algorithm,and 79%using LMS+independent component analysis(ICA).Magnetic welding environment efficiency was 24%before applied filtering,70%with LMS,and 75%with LMS+*** workplace environment efficiency showed no success before applied filtering,was 52%with LMS,and was 54%with LMS+ICA.

关键词： 5G hybrid algorithms signal processing speech recognition

来源：评论

学校读者我要写书评

暂无评论

Fully Unsupervised Deep-Learning with Dimension Expansion for Nanophotonic Design

Fully Unsupervised Deep-Learning with Dimension Expansion fo...

引用

2024 Frontiers in Optics, FiO 2024

作者： Huang, Shuo Torfeh, Mahsa Shi, Yonggang Hsu, Chia Wei Stevens Neuroimaging and Informatics Institute University of Southern California Los AngelesCA90033 United States Department of Biomedical Engineering University of Southern California Los AngelesCA90089 United States Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States

We propose a fully unsupervised deep-learning approach using dimension expansion for nanophotonic design. The neural network generates binary broadband integrated Y-splitters with average efficiency 98% and splitting error 2%, without any pre-generated dataset. © Optica Publishing Group 2024, © 2024 The Author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Benchmarking changepoint detection algorithms on cardiac time series

arXiv

引用

arXiv 2024年

作者： Cakmak, Ayse Selen Reinertsen, Erik Nemati, Shamim Clifford, Gari D. Department of Biomedical Informatics Emory University United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Department of Biomedical Informatics University of California at San Diego United States

The pattern of state changes in a biomedical time series can be related to health or disease. This work presents a principled approach for selecting a changepoint detec- tion algorithm for a specific task, such as disease classification. Eight key algorithms were compared, and the performance of each algorithm was evaluated as a function of temporal tolerance, noise, and abnormal conduction (ectopy) on realistic artificial cardiovascular time series data. All algorithms were applied to real data (cardiac time series of 22 patients with REM-behavior disorder (RBD) and 15 healthy controls) using the parameters selected on artificial data. Finally, features were derived from the de- tected changepoints to classify RBD patients from healthy controls using a K-Nearest Neighbors approach. On artificial data, Modified Bayesian Changepoint Detection al- gorithm provided superior positive predictive value for state change identification while Recursive Mean Difference Maximization (RMDM) achieved the highest true positive rate. For the classification task, features derived from the RMDM algorithm provided the highest leave one out cross validated accuracy of 0.89 and true positive rate of 0.87. Automatically detected changepoints provide useful information about subject's phys- iological state which cannot be directly observed. However, the choice of change point detection algorithm depends on the nature of the underlying data and the downstream application, such as a classification task. This work represents the first time change point detection algorithms have been compared in a meaningful way and utilized in a classification task, which demonstrates the effect of changepoint algorithm choice on application *** Codes 92C30, 92C32, 03H10, 62H30, 68Q07, 8T07, 78-10, 92-10, 62R07, 68T09, 68T10 © 2024, CC BY-NC-SA.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Automated Diagnosis of Heart-Lung Diseases in Chest X-ray Images 5

Automated Diagnosis of Heart-Lung Diseases in Chest X-ray Im...

引用

5th International Conference on engineering Technology and its Applications, IICETA 2022

作者： Alslatie, Mohammad Alquran, Hiam Mustafa, Wan Azani Abu-Qasmieh, Isam Alqudah, Ali Mohammad Alkhayyat, Ahmed The Institute of Biomedical Technology King Hussein Medical Center Royal Jordanian Medical Service Amman Jordan Yarmouk University Biomedical Systems and Medical Informatics Engineering Irbid Jordan Arau Faculty of Electrical Engineering Technology Perlis Malaysia University of Manitoba Biomedical Engineering Program Department of Electrical and Computer Engineering Canada The Islamic University Faculty of Engineering Najaf Iraq

ISBN: (纸本)9781665472159

The state of the art of artificial intelligence (AI) for various medical imaging applications leads to enhanced accuracy, analysis, visualization, and interpretation of chest Xray (CXR) images for diagnosis. Many diseases are diagnosed based on CXR images. In this paper, two types of abnormalities are diagnosed based on AI techniques. The two classes are atelectasis and cardiomegaly. The acquired images are segmented to localize the chest region and then enhanced using gray-level transformation methods. The enhanced images are passed to two pretrained convolutional neural networks (CNNs): shuffle and mobile net. The transfer learning approach is utilized in this stage. The automated features are extracted from the last fully connected layer. Each CNN deserves to have the two most representative features for the two classes. These four features are passed to support the vector machine classifier. The training accuracy reached 100% and the test accuracy was 96.7%. The proposed method can be extended to be a milestone in the classification of all heart-lung diseases that can be diagnosed using chest X-ray images. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transforming Synthesized Netlists into a Feasible & Compliant Functional Bookshelf Format 24

Transforming Synthesized Netlists into a Feasible & Complian...

引用

Proceedings of the 28th Pan-Hellenic Conference on Progress in Computing and informatics

作者： George Kranas Kosmas Kariotis Antonios Dadaliaris George Stamoulis Athanasios Kakarountas Dept. of Computer Science & Biomedical Informatics University of Thessaly Lamia Greece Dept. of Informatics & Telecommunications University of Thessaly Lamia Greece Dept. of Electrical and Computer Engineering University of Thessaly Volos Greece

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Refractive Index Estimation Based on Non-interferometric Optical Diffraction Tomography with Angular and Axial Illumination Scanning

Three-Dimensional Refractive Index Estimation Based on Non-i...

引用

Digital Holography and Three-Dimensional Imaging, DH 2024

作者： Bazow, Brad Raub, Christopher B. Nehmetallah, George Departments of Electrical Engineering and Computer Science The Catholic University of America 620 Michigan Avenue N.E. WashingtonDC20064 United States The Johns Hopkins University Applied Physics Laboratory 11100 Johns Hopkins Road LaurelMD20723 United States Departments of Biomedical Engineering The Catholic University of America 620 Michigan Avenue N.E. WashingtonDC20064 United States

We present computational inverse scattering to achieve three-dimensional refractive index reconstructions of biological specimens with sub-micron resolution in an optical diffraction tomography system with angular and...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal feature learning framework for disease biomarker discovery

Multimodal feature learning framework for disease biomarker ...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Ghandikota, Sudhir Yella, Jaswanth K. Jegga, Anil G. University of Cincinnati Department of Electrical Engineering and Computer Science OH United States Cincinnati Children's Hospital Medical Center Division of Biomedical Informatics OH United States

ISBN: (纸本)9781665468190

Most in silico biomarker discovery methods are based on a single disease data modality. However, they often fail to identify and understand the relationships between different biomarkers emerging from various data types. Heterogeneous multimodal analysis methods facilitate the integration of multiple disease-related data resources, allowing us to gain a more accurate understanding of the mechanisms involved in a disease. Multimodal biomarkers resulting from such integrated analyses are complementary and robust and enable a holistic understanding of the disease. In this study, we proposed a novel neural network model that integrates and analyzes data from tissue transcriptomics, protein-protein interactions, and gene functional annotation resources. We employed a network-based approach by constructing a heterogeneous knowledge graph consisting of different biomedical entities and their inherent relationships. In addition, we utilized contextualized gene features mined from the biomedical literature. Our multimodal framework accurately predicts the differential activity of genes in idiopathic pulmonary fibrosis (IPF). Evaluation experiments were performed to determine the benefits of implementing the multimodal approaches. We also employed transcription factor enrichment analysis (TFEA) to validate the learned features. Finally, the gene clusters identified using multimodal gene features in IPF were found to be biologically relevant and meaningful. © 2022 IEEE.

关键词： Biomarkers

来源：评论

学校读者我要写书评

暂无评论

Obstructive Sleep Apnea Home-Monitoring Using a Commercial Wearable Device 18

Obstructive Sleep Apnea Home-Monitoring Using a Commercial W...

引用

18th World Congress on Medical and Health informatics: One World, One Health - Global Partnership for Digital Innovation, MEDINFO 2021

作者： Mokhtaran, Mehrshad Sacchi, Lucia Tibollo, Valentina Risi, Irene Ramella, Vittoria Quaglini, Silvana Fanfulla, Francesco Biomedical Informatics Laboratory Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy Lisrc Laboratory Irccs Ics Maugeri Pavia Italy Sleep Medicine Unit Irccs Ics Maugeri Pavia Italy

ISBN: (纸本)9781643682648

Obstructive sleep apnea (OSA) is a common sleep disorder and polysomnography (PSG) is the gold standard for its diagnosis and treatment monitoring. There are nowadays several activity trackers measuring sleep quality through the detection of sleep stages. To allow an easier monitoring of the treatment efficacy at home, this work explores the possibility of using one of those commercial smart-bands. To this aim, we studied the signals provided by PSG and a Fitbit smart-band on 26 consecutive patients, admitted to the hospital after the diagnosis of OSA, and submitted to ventilation or positional treatment. They underwent monitoring for three nights (basal, titration, and control). We developed both a visualization software allowing doctors to visually compare the two hypnograms, and a set of statistics for assessing the concordance of the two methods. Results indicate that Fitbit can detect normal sleep patterns, while it is less able to detect the abnormal ones. © 2022 International Medical informatics Association (IMIA) and IOS Press.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Building blocks for complex tasks: Robust generative event extraction for radiology reports under domain shifts

arXiv

引用

arXiv 2023年

作者： Zhou, Sitong Yetisgen, Meliha Ostendorf, Mari University of Washington Electrical & Computer Engineering United States University of Washington Biomedical and Health Informatics United States

This paper explores methods for extracting information from radiology reports that generalize across exam modalities to reduce requirements for annotated data. We demonstrate that multi-pass T5-based text-to-text generative models exhibit better generalization across exam modalities compared to approaches that employ BERT-based task-specific classification layers. We then develop methods that reduce the inference cost of the model, making large-scale corpus processing more feasible for clinical applications. Specifically, we introduce a generative technique that decomposes complex tasks into smaller subtask blocks, which improves a single-pass model when combined with multitask training. In addition, we leverage target-domain contexts during inference to enhance domain adaptation, enabling use of smaller models. Analyses offer insights into the benefits of different cost reduction strategies. © 2023, CC BY.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Navigating Complexity: Data Structure Impact on Path Planning Algorithms in Autonomous Systems

Navigating Complexity: Data Structure Impact on Path Plannin...

引用

Novel Intelligent and Leading Emerging Sciences Conference (NILES)

作者： Hend Emad Mai S. Mabrouk Ahmed F. Elnokrashy Computer Science Nile University Giza Egypt Biomedical Informatics Nile University Giza Egypt Electrical Engineering Benha University Benha Egypt

ISBN: (数字)9798350378511

ISBN: (纸本)9798350378528

Navigating a busy cityscape with a fleet of autonomous vehicles requires each to seamlessly maneuver through traffic with split-second decisions. Path planning is the backbone of such advanced machinery applications, from mobile robots to unmanned ground vehicles, where the choice of data structure plays a pivotal role in determining memory usage, planning time, and algorithm reliability. This research rigorously evaluates Grassfire, Dijkstra, A *, and RRT * algorithms based on key metrics using real GPS readings, across diverse environment representations and obstacle conditions. Our findings provide guidance for selecting the optimal algorithms and data structures tailored to specific environmental complexities. By evaluating the performance of these algorithms under various environmental conditions, the study offers insights that can help researchers and practitioners choose the most suitable algorithms and data structures for their autonomous vehicle applications. The ability to match the algorithm and data structure to the specific environmental challenges faced by autonomous vehicles is crucial for ensuring efficient and reliable path planning, which is the backbone of advanced machinery applications.

关键词： Measurement Navigation Data structures Probabilistic logic Path planning Complexity theory Reliability Machinery Autonomous vehicles Global Positioning System

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：