检索结果-内蒙古大学图书馆

A novel methodology based on static visual stimuli and kinesthetic motor imagery for upper limb neurorehabilitation

research on biomedical engineering 2024年第3-4期40卷 687-700页

作者： Bastos-Filho, T.F. Villa-Parra, A.C. Guerrero-Méndez, C.D. González-Cely, A.X. Blanco-Díaz, C.F. Delisle-Rodríguez, D. Igasaki, T. Vitoria Brazil Biomedical Engineering Research Group Salesian Polytechnic University Cuenca Ecuador Postgraduate Program in Neuroengineering Edmond and Lily Safra International Institute of Neurosciences Santos Dumont Institute Macaiba Brazil Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

Purpose: This work proposes a protocol to be used in a Brain-Computer Interface (BCI) for hand and finger movement rehabilitation aimed at post-stroke patients. This strategy is based on Electroencephalography (EEG) and uses concepts of both Static Visual Stimuli (SVS) of the own subject’s hand (OwnSVS) and Kinesthetic Motor Imagery (KMI) to improve the motor task recognition of the same limb. Methods: The protocol proposed here takes into account several aspects, such as physical rehabilitation strategies, Active Hand Orthosis (AHO) — represented by a robotic glove —, and the acquisition of the EEG signal over the brain motor area. Power Spectral Density (PSD) and Riemannian Geometry (RG) are used for feature extraction in this work, considering Mu (μ, 8–12 Hz), Low-Beta (Low-β, 13–17 Hz) and High-Beta (High-β, 18–24 Hz) frequency bands. Moreover, a feature selection stage using Pair-Wise Feature Proximity (PWFP) is also used before input to a Machine Learning (ML) classifier. Here, Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Decision Tree (DT) are compared. Results: As results, evaluated in 10 healthy subjects, features using PSD-PWFP and kNN achieved a maximum ACC of 89.81% (with AHO movements), improving by 3% the standard protocol (without AHO movements). Conclusions: The findings of this work indicate that AHO movement assistance can improve the recognition of hand opening and closing MI tasks, which can be implemented in the design of robotic BCI controllers for hand and finger movement neurorehabilitation in stroke patients. © The Author(s), under exclusive licence to The Brazilian Society of biomedical engineering 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Silk fibroin-based inks for in situ 3D printing using a double crosslinking process

引用

Bioactive Materials 2024年第5期35卷 122-134页

作者： Francesca Agostinacchio Vincent Fitzpatrick Sandra Dire David LKaplan Antonella Motta National Interuniversity Consortium of Material Science and Technology FlorenceItaly BIOtech Research Center and European Institute of Excellence on Tissue Engineering and Regenerative Medicine Department of Industrial EngineeringUniversity of TrentoTrentoItaly Materials Chemistry Group&“Klaus Müller”Magnetic Resonance Laboratory Department of Industrial EngineeringUniversity of TrentoTrentoItaly Department of Biomedical Engineering Tufts UniversityMedfordMA02155USA

The shortage of tissues and organs for transplantation is an urgent clinical *** situ 3D printing is an advanced 3D printing technique aimed at printing the new tissue or organ directly in the *** ink for this process is central to the outcomes,and must meet specific requirements such as rapid gelation,shape integrity,stability over time,and adhesion to surrounding healthy *** natural materials,silk fibroin exhibits fascinating properties that have made it widely studied in tissue engineering and regenerative ***,further improvements in silk fibroin inks are needed to match the requirements for in situ 3D *** the present study,silk fibroin-based inks were developed for in situ applications by exploiting covalent crosslinking process consisting of a pre-photo-crosslinking prior to printing and in situ enzymatic *** different silk fibroin molecular weights were characterized and the synergistic effect of the covalent bonds with shear forces enhanced the shift in silk secondary structure towardβ-sheets,thus,rapid *** hydrogels exhibited good mechanical properties,stability over time,and resistance to enzymatic degradation over 14 days,with no significant changes over time in their secondary structure and swelling ***,adhesion to tissues in vitro was demonstrated.

关键词： Silk fibroin inks In situ 3D printing Covalent crosslinking Regenerative medicine Rapid gelation

来源：评论

学校读者我要写书评

暂无评论

Towards Instruction-Tuned Verification for Improving biomedical Information Extraction with Large Language Models

Towards Instruction-Tuned Verification for Improving Biomedi...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Jin Yuan, Ruifan Tian, Yu Li, Jingsong Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing China Zhejiang University College of Biomedical Engineering & Instrumental Science Hangzhou China Research Center for Data Hub and Security Zhejiang Lab Hangzhou China

ISBN: (纸本)9798350386226

biomedical information extraction, including tasks like Named Entity Recognition (NER) and Relationship Extraction (RE), plays a critical role in analyzing unstructured biomedical data, facilitating more accurate downstream applications such as clinical decision support and personalized medicine. Although Large Language Models (LLMs) excel in various domains, they often struggle with issues like hallucinations and domain-specific inaccuracies, limiting their effectiveness in biomedical applications. To tackle these challenges, we propose a novel framework that incorporates an external dual-stage verifier to enhance biomedical information extraction. This verifier is prompted to first identify and complete missing entities and relations, and then filter out incorrect extractions, thereby enhancing both precision and recall in information extraction. Furthermore, we proposed an approach for constructing the instruction-tuning dataset using both positive and negative demonstrations, which improves the verifier's correction capabilities through Parameter-Efficient Fine-Tuning (PEFT). Our extensive experiments on three public benchmark datasets cover both biomedical NER and RE tasks, comparing four LLMs ranging from 7 to 175 billion parameters to validate the effectiveness and scalability of our approach. The results demonstrate that by integrating an external verifier specifically finetuned for biomedical tasks, we achieve substantial improvements in precision, recall, and F1 scores for NER and RE tasks. Our method consistently outperforms In-Context Learning (ICL) approaches in F1 scores, achieving increases of up to 20% in some cases. Furthermore, ablation studies demonstrate the effectiveness of both stages in the verification process. The proposed framework provides valuable insights for accurate biomedical information extraction using LLMs, highlighting its potential applications in real-world clinical settings. © 2024 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Biofabrication of nanocomposite-based scaffolds containing human bone extracellularmatrix for the differentiation of skeletal stem and progenitor cells

引用

Bio-Design and Manufacturing 2024年第2期7卷 121-136页

作者： Yang-Hee Kim Janos M.Kanczler Stuart Lanham Andrew Rawlings Marta Roldo Gianluca Tozzi Jonathan I.Dawson Gianluca Cidonio Richard O.C.Oreffo Faculty of Medicine Bone and Joint Research GroupCentre for Human DevelopmentStem Cells and RegenerationInstitute of Developmental SciencesUniversity of SouthamptonSouthampton SO166YDUK School of Pharmacy and Biomedical Science University of PortsmouthPortsmouth PO12DTUK School of Engineering Faculty of Engineering and ScienceUniversity of GreenwichGreenwich ME44TBUK Center for Life Nano-and Neuro-Science(CLN2S) Italian Institute of Technology00161 RomeItaly

Autograft or metal implants are routinely used in skeletal ***,they fail to provide long-term clinical resolution,necessitating a functional biomimetic tissue engineering *** use of native human bone tissue for synthesizing a biomimeticmaterial inkfor three-dimensional(3D)bioprintingof skeletal tissueis anattractivestrategyfor ***,human bone extracellular matrix(bone-ECM)offers an exciting potential for the development of an appropriate microenvironment for human bone marrow stromal cells(HBMSCs)to proliferate and differentiate along the osteogenic *** this study,we engineered a novel material ink(LAB)by blending human bone-ECM(B)with nanoclay(L,Laponite®)and alginate(A)polymers using extrusion-based *** inclusion of the nanoﬁller and polymeric material increased the rheology,printability,and drug retention properties and,critically,the preservation of HBMSCs viability upon *** composite of human bone-ECM-based 3D constructs containing vascular endothelial growth factor(VEGF)enhanced vascularization after implantation in an ex vivo chick chorioallantoic membrane(CAM)*** inclusion of bone morphogenetic protein-2(BMP-2)with the HBMSCs further enhanced vascularization and mineralization after only seven *** study demonstrates the synergistic combination of nanoclay with biomimetic materials(alginate and bone-ECM)to support the formation of osteogenic tissue both in vitro and ex vivo and offers a promising novel 3D bioprinting approach to personalized skeletal tissue repair.

关键词： Extracellular matrix Nanoclay Bone 3D bioprinting

来源：评论

学校读者我要写书评

暂无评论

Pedagogical Framework for Programming Courses in Higher Education

Pedagogical Framework for Programming Courses in Higher Educ...

引用

IEEE Education engineering (EDUCON)

作者： Reza Moosaei Gloria Molinero Data Science and Engineering Research Group Faculty of Science and Engineering Queen Mary University of London London UK

ISBN: (数字)9798331539498

ISBN: (纸本)9798331539504

Learning computer programming has proven to be the main challenge in computer education for undergraduates in higher education. Mastering computer programming involves developing a wide range of skills, including soft skills such as problem-solving and hard skills specific to programming. Students possess a variety of levels in both soft and hard skills in programming, and those with lower skill levels encounter learning difficulties. In the higher education (HE) context, the significant challenge for programming instructors lies in understanding and implementing effective teaching methods and techniques. The literature shows that traditional teaching methods and techniques are not ideal for computer programming pedagogy, as programming skills are effectively developed mainly through student-centred and collaborative learning involving hands-on and practical experiences. Therefore, it is essential to implement an effective teaching framework based on a studentcentred learning approach for HE that facilitates programming instruction and successfully achieves pedagogical goals. However, there is a lack of comprehensive research providing an effective framework for teaching programming to undergraduates in the HE context. This research aims to explore effective teaching frameworks for computer programming courses in HE, identifying key components that must be considered when designing such a framework.

关键词： Federated learning Computational modeling Education Problem-solving engineering education Programming profession

来源：评论

学校读者我要写书评

暂无评论

"Hi, My Name is Robin" – Remotely Co-designing an Embodied Conversational Agent for Empathy with Older Adults 9th

"Hi, My Name is Robin" – Remotely Co-designing an Embodied ...

引用

9th International Conference on Human Aspects of IT for the Aged Population, ITAP 2023, held as part of the 25th International Conference on Human-Computer Interaction, HCII 2023

作者： Tunc, Sefora Nijboer, Femke Tinga, Angelica M. Tabak, Monique Biomedical Signals and Systems Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands Roessingh Research and Development Enschede Netherlands

ISBN: (纸本)9783031348655

Embodied conversational agents (ECAs) have the potential to facilitate empathic relationships between older adults and eHealth coaches, but little research has been conducted on how to effectively include appearance and personality in the design of ECAs such that older adults can empathize with the agent. In this study, we aimed first to develop design requirements for ECAs that induce empathy in older adults. Second, we developed and reflected upon a remote (online), iterative co-design methodology which can be used as an alternative when traditional physical methods cannot take place (e.g. during COVID-19). Over the course of three months, five older adults (mean age 68 years) 1) received a paper booklet, 2) were invited to an Q&A session, 3) after which they were asked develop their own ECAs at home using the booklet, 4) and came back to discuss their designs online in a group setting to determine design requirements, 5) which were used to develop an interactive ECA, 6) that was individually evaluated in an online meeting. The final ECA, called Robin, was positively perceived in terms of appearance, but the participants expected the conversation with Robin to be more flexible and deeper. Overall, the current study demonstrated the feasibility of remote co-design activities for this population and presents recommendations for researchers and practitioners interested in or in need for a remote approach. Moreover, the current findings are translated in lessons learnt to inform design and development of future ECAs for older adults. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

Detecting Breast Cancer: A Comparative Study of Various Machine Learning Models 6

Detecting Breast Cancer: A Comparative Study of Various Mach...

引用

6th Parul International Conference on engineering and Technology, PICET 2024

作者： Patil, Pawan Sharma, Mansi Rewatkar, Rajendra Fulkar, Bhushan Department of Artificial Intelligence and Data Science Datta Meghe institute of Higher Education and Research Wardha India Department of Computer Science and Design Datta Meghe institute of Higher Education and Research Wardha India Department of Biomedical Engineering Datta Meghe Institute of Higher Education and Research Wardha India

ISBN: (纸本)9798350369748

One of the deadliest illnesses in the world, cancer primarily affects women. Therefore, the primary goal of our research must be to cure cancer through scientific means. The secondary goal should be to detect cancer early on, as this can aid in the eventual removal of the cancer. After looking over 41 publications, we discovered that there are a number of methods for detecting cancer. In the medical field, detecting breast cancer is crucial since a correct diagnosis may greatly enhance patient outcomes. In order to assess how well different machine learning models identify breast cancer, we compare them all in this research. In particular, we contrast the Naive Bayes, Random Forest, Support Vector Machines (SVM), Logistic Regression, and Decision Tree methods. Our goal is to evaluate how well these algorithms classify cases of breast cancer. Of all the models studied, Random Forest performs better in terms of accuracy. Healthcare practitioners may find Random Forest to be a potential tool as it generates excellent accuracy rates in identifying breast cancer patients by utilizing its ensemble learning technique. Our comparative review provides useful details on the advantages and disadvantages of several machine learning methods for breast cancer. This research compares and contrasts several machine learning methods, including deep learning techniques, and finds that our suggested approach performs better than all of them. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Federated Learning in Fragmented Digital Healthcare Systems: A Visionary Perspective 15

Unleashing the Power of Federated Learning in Fragmented Dig...

引用

15th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2023

作者： Tania, Marzia Hoque Clifton, David A. University of New South Wales Centre for Big Data Research in Health Sydney Australia Institute of Biomedical Engineering University of Oxford Department of Engineering Science Oxford United Kingdom Suzhou China

ISBN: (纸本)9798350316551

Digital healthcare landscape, including infrastructure, governance, interoperability, and user adoption, are continuously evolving, some taking more centralised approach, while others with higher degree of fragmentation. Attitude towards centralised healthcare systems in affluent countries are primarily influenced by historical development, infrastructure investments, and regulatory frameworks, which offers advantages with respect to standardised practises, centralised decision making, and economies of scale. In contrast, complexities due to diverse stakeholders, interoperability challenges, privacy and security concerns often pose challenges in achieving a completely centralised healthcare system even in high income countries such as the United Kingdom or in federal systems such as the United States. Moreover, decentralised healthcare systems are more prevalent in resource-poor countries. This paper presents our viewpoint and perspectives on the potential of federated learning in decentralised healthcare systems, especially in countries with infrastructure constraints and discusses its advantages, privacy and security concerns, and challenges. As data-hungry artificial intelligence-enabled systems are gradually changing the healthcare ecosystem, federated learning presents an opportunity for distributing the machine learning training process across multiple decentralised edge devices with reduced data transfer. Therefore, the decentralised digital healthcare system can leverage the collaborative model training while protecting highly sensitive and personal health information. However, challenges related to data heterogeneity, communication latency, and model aggregation need to be addressed for successful implementation of such systems. Adapting the federated learning framework to the specific needs and constraints of low and middle-income countries is crucial to unlock its potential in improving healthcare outcomes. © 2023 IEEE.

关键词： data transfer

来源：评论

学校读者我要写书评

暂无评论

A Review of Machine Learning Algorithms in Diabetes Management 4

A Review of Machine Learning Algorithms in Diabetes Manageme...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Gayaki, Unnati Daronde, Subodh Tale, Abhay Barhate, Aditya Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha India Faculty of Engineering and Technology Department of Biomedical Engineering Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India

ISBN: (纸本)9798331523923

Diabetes is a prevalent and chronic disease affecting millions worldwide, posing significant challenges in its management and treatment. This review article aims to explore the current and potential future roles of machine learning (ML) in diabetes management, focusing on progress, applications, and challenges. It discusses various ML techniques, including support vector machines (SVM), logistic regression, decision trees, ensemble methods, and advanced deep learning approaches such as long short-term memory (LSTM) networks and convolutional neural networks (CNN). These methods have demonstrated benefits in analytics, patient monitoring, decision support systems, personalised treatment, and patient engagement. However, significant challenges persist, such as computational complexity, data quality, limited interoperability of systems, and ethical concerns regarding AI use in healthcare. The article addresses these challenges by fostering collaboration between AI implementers and health care professionals. This collaboration is essential to develop long-term, legally compliant, and solution-oriented frameworks that enhance patient care and diabetes management and pave the way for more efficient and ethical AI applications in healthcare. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Convergence Study of Three-Dimensional Upper Skull Model: A Finite Element Method 22nd

Convergence Study of Three-Dimensional Upper Skull Model: A ...

引用

22nd Asia Simulation Conference, AsiaSim 2023

作者： Mohamad Azmi, Nor Aqilah Abdullah, Nik Nur Ain Azrin Mohd Salaha, Zatul Faqihah Ramlee, Muhammad Hanif Department of Biomedical Engineering and Health Science Faculty of Electrical Engineering Universiti Teknologi Malaysia Johor Johor Bahru81310 UTM Malaysia Research Group Universiti Teknologi Malaysia Johor Johor Bahru81310 UTM Malaysia

ISBN: (纸本)9789819972425

Le-fort I osteotomy has been widely used by maxillofacial surgeons as a procedure due to its versatility and simplicity to treat patient with dentofacial deformity. Technology such as virtual planning software has greatly aided surgeon to prepare for the surgery by allowing them to work with clinical engineer to plan for the surgery and create custom implants design on the patient’s scanned anatomy in form of three-dimensional (3D) model. Most of convergence study for skull was done by analyzing the total number of mesh elements. Hence, this study was conducted to determine the optimum mesh size by performing mesh convergence study using h-refinement method on the upper skull 3D model. The 2D Computed-Tomography (CT) images in DICOM format were used to create the 3D model by using Mimics software. The mesh refinement process of the segmented upper skull 3D model was performed in the 3-Matic software, and the mesh size used from 5 mm to 2.5 mm with 0.5 mm interval. Marc Mentat software was used to perform finite element analysis (FEA) where a fixed load was set on superior part of the skull meanwhile point load with 125N stress was applied on incisors. Results from the mesh convergence analysis showed that percentage difference of upper skull of 4.0 mm–3.5 mm mesh size is below 5% and from the convergence plot the line graph start to converge at 3.5 mm to 4 mm. Therefore, it can be concluded that 4 mm mesh size is the optimum mesh size for upper skull 3D model. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Finite element method

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：