检索结果-内蒙古大学图书馆

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

Heart Sound Analysis for Smart Stethoscope in Mobile Environments 8

Heart Sound Analysis for Smart Stethoscope in Mobile Environ...

引用

8th IEEE International Conference on Smart Cloud, SmartCloud 2023

作者： Lee, Sungmin Shin, Younghoon Qun, Wei Lee, Miran Graduate School of IT Convergence Engineering Daegu University Gyeongsan Korea Republic of Dept. of Biomedical Engineering Keimyung University Daegu Korea Republic of 3Dept. of Computer & Information Engineering Daegu University Gyeongsan Korea Republic of

This study proposes a method of analysis method that can be monitored using bio-signals in mobile environments. The proposed model is designed in a parallel structure that utilizes PPG and PCG signals related to the h... 详细信息

ISBN: (纸本)9798350313505

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation with Student-Teacher Model for Whole Heart and Great Vessel Segmentation in Congenital Heart Disease Using CT-Scan Image

Knowledge Distillation with Student-Teacher Model for Whole ...

引用

2024 International Conference on Artificial Intelligence, Blockchain, Cloud Computing, and Data Analytics, ICoABCD 2024

作者： Putri Priambodo, Syifa Salsabila Ardiyanto, Igi Taufiq, Nahar Master of Biomedical Engineering Graduate School Universitas Gadjah Mada Yogyakarta Indonesia Universitas Gadjah Mada Faculty of Engineering Department of Electrical Engineering and Information Technology Yogyakarta Indonesia Universitas Gadjah Mada Faculty of Medicine Public Health and Nursing Department of Cardiology and Vascular Medicine Yogyakarta Indonesia

ISBN: (纸本)9798350368451

Congenital Heart Disease (CHD) results from imper-fect heart anatomy during early fetal development. According to the Perhimpunan Dokter Spesialis Kardiovaskular Indonesia (PERKI), around 8-10 babies out of every 1000 births in Indonesia suffer from CHD. However, with advances in medical technology, many children with heart defects can survive. Cardiac CT-Scan images are used as the basis for appropriate treatment, while image analysis allows evaluation of abnormalities and monitoring of disease progression posttherapy. Developing a system with lightweight computing and good performance that can segment the cardiac CT scan image to support the doctor's analysis is necessary. For more specific or complex tasks, the model will use a huge memory. Because the model should use more parameters. Bigger memory that model used, more difficult to implement in the device with limited storage. By reducing the number of parameters and removing redundant connections, it is possible to improve model performance while saving computational load significantly. This research applies Knowledge Distillation (KD), which is a model compression method where knowledge from the teacher model is transferred to the student model. KD aims to teach student models to generalize based on the teacher model's knowledge. This research uses the U-Net architecture as the teacher model and the CFPNet-M architecture as the student model. The KD model performs better IoU than the student model, 0.872 or 3% higher. Judging from the resulting model file size, the KD model file is 131.4MB or 33.33 % smaller than the teacher model file size. © 2024 IEEE.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Investigating Variances in Conductivity Contrast Across Different Frequencies by Electrical Impedance Tomography 6

Investigating Variances in Conductivity Contrast Across Diff...

引用

6th IEEE Eurasia Conference on biomedical engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Huynh, Hoang Nhut Nguyen Diep, Quoc Tuan Cao Dinh, Minh Quan Tran, Anh Tu Ching, Congo Tak-Shing Tran, Trung Nghia VNU-HCM Laboratory of Laser Technology Faculty of Applied Science Ho Chi Minh City Viet Nam Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung Taiwan

ISBN: (纸本)9798350396133

In Electrical Impedance Tomography (EIT), the intricate relationship between material impedance and frequency needs to be explored to implicate the precision and clarity of the reconstructed images. We delved into the complexities of frequency selection and its impact on image contrast, particularly on distinguishing between materials with varying conductivity levels, whether conductive or non-conductive. Furthermore, we explored specific frequency bands in which certain materials increase or diminish contrast within the reconstructed conductivity distribution image. Initial findings revealed that distinct frequency ranges influence the visibility of materials, suggesting potential applications for imaging specific tissue in EIT. The intermediary frequencies, notably at 25 and 50 kHz differentiate the characteristics of copper and resin. These frequencies facilitate a discernible contrast between conductive and non-conductive materials with intrinsic electromagnetic attributes. The observed disparities imply that the refinement of EIT imaging helps to discriminate materials with diverse conductivity effectively. Such results contribute to the development of EIT by addressing the intricacies of frequency-dependent imaging and allow for the understanding of material behavior in response to varying frequencies. Emphasizing the critical role of frequency considerations in the imaging process, future advancements are enabled to improve the precision and applicability of non-invasive imaging techniques, thereby allowing potential applications in diverse domains. © 2024 IEEE.

关键词： Conductive materials

来源：评论

学校读者我要写书评

暂无评论

The effect of HEMA and 10-MDP in the bonding agent of a two-step self-etch system on water sorption, elastic modulus, and microtensile bond strength to dentin

引用

Dental Materials Journal 2025年第1期44卷 17-23页

作者： Iuchi, Tomoki Yonekura, Kazuhide Ida, Yumika Motoyama, Yutaro Ikeda, Masaomi Hamada, Kenichi Nakajima, Masatoshi Hosaka, Keiichi Department of Regenerative Dental Medicine Tokushima University Graduate School of Biomedical Sciences 3-18-15 Kuramoto Tokushima770-8504 Japan Department of Cariology and Operative Dentistry Graduate School of Medical and Dental Sciences Tokyo Medical and Dental University 1-5-45 Yushima Bunkyo-ku Tokyo113-8510 Japan Department of Oral Prosthetic Engineering Graduate School Faculty of Dentistry Tokyo Medical and Dental University 1-5-45 Yushima Bunkyo-ku Tokyo113-8510 Japan Department of Biomaterials and Bioengineering Tokushima University Graduate School of Biomedical Sciences 3-18-15 Kuramoto Tokushima770-8504 Japan

This study evaluated the effects of HEMA and 10-MDP in the bonding agent in a 2-step self-etch adhesive system, Clearfil SE Bond 2, on water sorption (Wsp) and elastic modulus (E) of the polymerized bonding agent. The microtensile bond strength (µTBS) to dentin was also evaluated initially and after 10,000 thermal cycles (TC10,000). Four bonding agents were tested: the original, H-free (excluding HEMA), M-free (excluding 10-MDP), and HM-free (excluding HEMA and 10-MDP). HEMA increased Wsp and decreased E. Initial µTBS (TC0) was highest for the original and lowest for HM-free. After TC10,000, the original maintained the highest µTBS, indicating the importance of HEMA and 10-MDP. TC10,000 did not reduce µTBS for any groups. HEMA and 10-MDP compromised mechanical property and increased water sorption, suggesting these components could potentially compromise adhesive stability. © 2025, Japanese Society for Dental Materials and Devices. All rights reserved.

关键词： Dental materials

来源：评论

学校读者我要写书评

暂无评论

Utilizing Machine Learning Predictive Analytics to Enhance Early Sepsis Diagnosis in Critical Care Setting

Utilizing Machine Learning Predictive Analytics to Enhance E...

引用

Big Data, Cloud Computing, Data Science & engineering (BCD)

作者： Paron Daothong Sira Jampa-ngern Wongwit Senavongse Department of Biomedical Engineering The Graduate School Srinakharinwirot University Nakhon Nayok Thailand Department of Biomedical Engineering Faculty of Engineeringl Srinakharinwirot University Nakhon Nayok Thailand

ISBN: (数字)9798350394191

ISBN: (纸本)9798350394207

Sepsis remains a critical medical challenge worldwide, with millions of cases and fatalities annually, particularly affecting vulnerable populations like children. The evolving understanding of sepsis has led to refinements in diagnostic criteria, including the introduction of novel metrics like qSOFA. Despite advancements, early diagnosis remains pivotal for improved outcomes. This study leverages electronic medical records (EMR) and machine learning to propose a predictive model for early sepsis diagnosis in critical care patients. Using the eICU Collaborative Research Database, the dataset comprising vital signs was preprocessed and balanced. Various machine learning algorithms, including deep learning models, were evaluated using 10-fold cross-validation. Performance metrics are AUROC, accuracy, F1 score, and Brier score were computed to assess model effectiveness. XGBoost emerged as the top-performing algorithm, exhibiting superior performance across metrics compared to other models with AUROC = 0.78, Accuracy = 80, F1-Score = 72, Brier-Score = 0.20. While demonstrating promising results, XGBoost exhibited higher false-positive rates, indicating the need for further refinement. Overall, the study underscores the potential of machine learning in early sepsis diagnosis, providing insights for future optimization and clinical application.

关键词： Measurement Machine learning algorithms Accuracy Computational modeling Machine learning Predictive models Sepsis Predictive analytics Optimization Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Assembly of exfoliated α-zirconium phosphate nanosheets:Mechanisms and versatile applications

Aggregate

引用

Aggregate 2022年第4期3卷 41-60页

作者： Hao Ding Abbas Ahmed Kuangyu Shen Luyi Sun Polymer Program Institute of Materials ScienceUniversity of ConnecticutStorrsConnecticutUSA Department of Chemical and Biomolecular Engineering University of ConnecticutStorrsConnecticutUSA Department of Biomedical Engineering University of ConnecticutStorrsConnecticutUSA

α-Zirconium phosphate(Zr(HPO_(4))_(2)⋅H_(2)O,α-ZrP)is an inorganic layered *** the first report of crystallineα-ZrP in 1964,thanks to its simple synthesis and unique physiochemical properties,α-ZrP has found widespread application in many fields including mechanical reinforcing,barrier improvement,flame retardancy,anticorrosion,catalysis,environment,energy,and *** of the ease of exfoliation ofα-ZrP to obtain single-layer nanosheets,as well as its rich surface chemistry thanks to the high density of orderly arranged surface acidic hydroxyl groups,α-ZrP single-layer nanosheets are ideal building blocks for self-assembly or assembly with other *** assembly ofα-ZrP nanosheets could form a randomly dispersed structure(isotropic),roughly ordered structure(nematic),or highly ordered structure(smectic)within liquid colloids or solid hybrids(including hydrogels).Thanks to the combination of the unique structures and the novel functions of the components,the assembled materials have found a wide verity of applications due to their excellent *** this article,the methods to synthesizeα-ZrP,the approaches and mechanisms to exfoliateα-ZrP,and the strategies to assembleα-ZrP nanosheets to form various structures,as well as the applications of the assembled materials are *** emerging prospects ofα-ZrP nanosheets as a key material in next-generation functional applications are envisioned.

关键词： application assembly exfoliation nanosheets α-zirconium phosphate

来源：评论

学校读者我要写书评

暂无评论

mmYOLOH-p: A Clinically-Oriented mmWave-Based Human Pose Estimation Tool for Unobtrusive Patient Monitoring

mmYOLOH-p: A Clinically-Oriented mmWave-Based Human Pose Est...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Jonathan Williams Jimmy Wang Michael Stevens Nigel Lovell Ahmadreza Argha Graduate School of Biomedical Engineering UNSW Sydney Australia School of Electrical Engineering UNSW Sydney Australia

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Human pose estimation (HPE) identifies and locates keypoints on a person’s body. Despite the effectiveness of various existing methods, there remains a gap in addressing specific requirements for real-world clinical applications of HPE. In this study, we propose mmYOLOH-p, a novel clinical-oriented HPE approach. Requirements for patient monitoring influenced our choice of sensing modality, data representation, and deep learning architecture. We used millimeter-wave (mmWave) radar because it is unobtrusive, privacy friendly and robust against poor lighting and weather conditions. A pre-processing pipeline was developed to generate 2D heatmap representations of radar data and ultimately overcome scalability issues related to sparse point cloud representations. Cross-modal adaptation of the YOLOv8-pose architecture was performed since it enables one-shot efficiency and can be extended to perform concurrent tasks, such as human activity recognition, while avoiding cascading latency. mmYOLOH-p outperformed HuPRNet, the current state of the art in heatmap-based HPE, in terms of total average precision (AP), per-joint AP, and inference time. The highest AP50, AP75, and AP50-95 scores achieved in the experimental evaluation were 99.1, 92.6, and 83.0 respectively. The results position mmYOLOH-p as a potentially viable solution for activity recognition and gait analysis.

关键词： Heating systems Point cloud compression Patient monitoring Scalability Pose estimation Pipelines Gain measurement Sensors Human activity recognition Millimeter wave communication

来源：评论

学校读者我要写书评

暂无评论

A virtual positioning system for external beam radiotherapy

引用

Virtual Reality 2023年第3期27卷 2569-2582页

作者： Sung, Wen-Hsu Jiang, Ching-Fen Su, Tai-Sin Sun, Shuh-Ping Department of Physical Therapy and Assistive Technology National Yang Ming Chiao Tung University Taipei Taiwan Graduate Program of Smart Healthcare and Bioinformatics I-Shou University Kaohsiung Taiwan Department of Biomedical Engineering I-Shou University Kaohsiung Taiwan Department of Digital Media Design I-Shou University Kaohsiung Taiwan

In radiation therapy, positioning patients to ensure the accuracy of the setup of a procedure is a routine and labour-intensive process that substantially determines the efficacy of treatment. In this study, we propose a virtual positioning system that can simulate the positioning process with a visible beam path under the broad view of a life-like patient-positioning platform to obviate problems with excessively narrow view. This system integrates image processing, computer graphics, and virtual reality to encompass a 3D treatment target reconstructed from medical images of different modalities in a virtual scene. An innovative evaluation method is further proposed to verify the efficacy of the system using a full-scale 3D solid anthropometric model, and a treatment target showed an accuracy of 99% in calibration and a mean compatibility of 95% with an actual measurement. The proposed virtual positioning system provides a training and education platform for radiation therapy. The methodology through which the system was developed is also disclosed as a promising approach to improve the efficiency and safety of the position verification process for existing systems. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： Radiotherapy

来源：评论

学校读者我要写书评

暂无评论

Prediction of Parkinson’s disease based on artificial neural networks using speech datasets

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 13571-13584页

作者： Liu, Wei Liu, Jierong Peng, Tao Wang, Guojun Balas, Valentina Emilia Geman, Oana Chiu, Hung-Wen School of Information and Communication Engineering Hainan University Hainan Haikou570228 China School of Computer Science and Cyber Engineering Guangzhou University Guangdong Guangzhou510006 China College of Biomedical Information and Engineering Hainan Medical University Street Hainan Haikou571199 China Department of Automation and Applied Informatics Aurel Vlaicu University of Arad Arad310130 Romania Department of Health and Human Development Stefan cel Mare University of Suceava Suceava720229 Romania Graduate Institute of Biomedical Informatics Taipei Medical University Taipei Taiwan

Parkinson’s disease (PD) is a progressive disorder of the nervous system that affects movement. Early prediction of PD can increase the chances of earlier intervention and delay the onset of the disease. Vocal impairment is one of the most important signs in the early stages of PD. Therefore, PD detection based on speech analysis and vocal patterns has attracted significant attention recently. In this paper, we propose a vowel-based artificial neural network (ANN) model for PD prediction based on single vowel phonation. Firstly, we propose a novel multi-layer neural network based on speech features to predict PD. The speech samples from 48 PD patients and 20 healthy individuals are processed into four types: vowel, number, word, and short sentence. Secondly, we establish ANN models with single-type speech samples versus combinations of multi-type speech samples, respectively. Comparative experiments demonstrate that the single-type vowel model is superior to other single-type models as well as multi-type models. Finally, we build a vowel-based ANN model for PD prediction and evaluate its performance. Extensive experiments demonstrate that the proposed model has a prediction accuracy of 91%, sensitivity of 99%, specificity of 82%, and area under the receiver operating characteristic curve (AUC) of 91%, which is superior to the performance of previous methods. Overall, this study demonstrates that the proposed model can provide good classification accuracy for predicting PD and can improve the rate of early diagnosis. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Network layers

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：