检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Cai, Danwei Wang, Weiqing Li, Ming Xia, Rui Huang, Chuanzeng Duke University Department of Electrical and Computer Engineering Durham United States Duke Kunshan University Data Science Research Center Kunshan China Group Bytedance China

ISBN: (纸本)9781728163277

This paper proposes to pretrain Conformer with automatic speech recognition (ASR) task for speaker verification. Conformer combines convolution neural network (CNN) and Transformer model for modeling local and global features, respectively. Recently, multi-scale feature aggregation Conformer (MFA-Conformer) has been proposed for automatic speaker verification. MFA-Conformer concatenates frame-level outputs from all Conformer blocks for further pooling. However, our experiments show that Conformer can be easily overfitted with limited speaker recognition training data. To avoid overfitting, we propose to transfer the knowledge learned from ASR to speaker verification. Specifically, an ASR pretrained Conformer is used to initialize the training of MFA-Conformer for speaker verification. Our experiments show that pretraining Conformer with ASR leads to significant performance gains across model sizes. The best model achieves 0.48%, 0.71% and 1.54% EER on Voxceleb1-O, Voxceleb1-E, and Voxceleb1-H, respectively. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Analyzing Factors Associated with Taxi Driver Accidents in the UAE: A Comprehensive Study 8

Analyzing Factors Associated with Taxi Driver Accidents in t...

引用

8th International Conference on System Reliability and Safety, ICSRS 2024

作者： Alsyouf, Imad Obaideen, Khaled Shikhli, Amir Moued Ibrahim, Fakhariya Almaazmi, Meera Cheaitou, Ali Al Hawari, Alaa Alzghoul, Ahmad Haridy, Salah University of Sharjah Sustainable Engineering Asset Management Research Group Sharjah United Arab Emirates University of Sharjah Department of Industrial Engineering and Engineering Management Sharjah United Arab Emirates Princess Sumaya University for Technology Department of Data Science Amman Jordan

ISBN: (纸本)9798350354508

Improving road safety requires an understanding of the underlying factors that lead to collisions involving taxis. Compared to other road users, taxis are disproportionately involved in accidents in the United Arab Emirates (UAE), making it critical to research the risk factors associated with these accidents. This study investigates the factors contributing to taxi driver road accidents and the correlations between these factors and accident severity and occurrence. By reviewing and analyzing taxi organizational records from 2015 to 2021 and conducting a survey of 790 taxi drivers, we identified years of driving experience, annual paid leave, age, consecutive driving hours, fatigue, and hours of sleep as significant factors. These findings provide transportation authorities with valuable information for reducing road accidents and fatalities among taxi drivers, enhancing road safety in the UAE. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

A Review of Machine Learning and Algorithmic Methods for Protein Phosphorylation Site Prediction

引用

Genomics, Proteomics & Bioinformatics 2023年第6期21卷 1266-1285页

作者： Farzaneh Esmaili Mahdi Pourmirzaei Shahin Ramazi Seyedehsamaneh Shojaeilangari Elham Yavari Department of Information Technology Tarbiat Modares UniversityTehran 14115-111Iran Department of Biophysics Faculty of Biological SciencesTarbiat Modares UniversityTehran 14115-111Iran Biomedical Engineering Group Department of Electrical Engineering and Information TechnologyIranian Research Organization for Science and Technology(IROST)Tehran 33535-111Iran

Post-translational modifications(PTMs)have key roles in extending the functional diversity of proteins and,as a result,regulating diverse cellular processes in prokaryotic and eukaryotic *** modification is a vital PTM that occurs in most proteins and plays a significant role in many biological *** in the phosphorylation process lead to multiple diseases,including neurological disorders and *** purpose of this review is to organize this body of knowledge associated with phosphorylation site(p-site)prediction to facilitate future research in this *** first,we comprehensively review all related databases and introduce all steps regarding dataset creation,data preprocessing,and method evaluation in p-site ***,we investigate p-site prediction methods,which are divided into two computational groups:algorithmic and machine learning(ML).Additionally,it is shown that there are basically two main approaches for p-site prediction by ML:conventional and end-to-end deep learning methods,both of which are given an ***,this review introduces the most important feature extraction techniques,which have mostly been used in p-site ***,we create three test sets from new proteins related to the released version of the database of protein post-translational modifications(dbPTM)in 2022 based on general and human *** online p-site prediction tools on newly added proteins introduced in the dbPTM 2022 release,distinct from those in the dbPTM 2019 release,reveals their *** other words,the actual performance of these online p-site prediction tools on unseen proteins is notably lower than the results reported in their respective research pape.

关键词： Phosphorylation Machinelearning Deep learning Post-translational modification database

来源：评论

学校读者我要写书评

暂无评论

Haptic Interfaces Integration in Upper Limb Rehabilitation 3

Haptic Interfaces Integration in Upper Limb Rehabilitation

引用

3rd International Congress of biomedical engineering and Bioengineering, CIIBBI 2024

作者： Del Pilar Rubiano Giraldo, Andrea Dario Vargas Cardona, Hernan Felipe Amador, Andres Cobo, Estefania Montoya Pontificia Universidad Javeriana Cali Biomedical Engineering Student Cali Colombia Pontificia Universidad Javeriana Cali Applied Mathemathics Program Director Cali Colombia Pontificia Universidad Javeriana Cali MSc. Biomedical Science - Research Group Bchs Cali Colombia

ISBN: (纸本)9798331532352

The activities of daily living (ADLs) encompass self-care tasks that often rely on upper limb function. Stroke, or cerebrovascular accident (CVA), and musculoskeletal injuries (MSIs) can compromise these ADLs, necessitating rehabilitation therapy. However, many individuals exhibit poor adherence to prescribed therapies, which exacerbates their conditions and further impairs upper limb functionality. To tackle this challenge, we devised a software tool that integrates a mathematical model with haptic interfaces within a Unity-developed game for the Meta Quest 2 platform. Validation by physiotherapists indicated successful results, affirming its utility as an effective tool for upper limb rehabilitation therapy. © 2024 IEEE.

关键词： Haptic interfaces

来源：评论

学校读者我要写书评

暂无评论

Enhancing Scene Simplification and Optimization for Retinal Prosthesis Platform 5

Enhancing Scene Simplification and Optimization for Retinal ...

引用

5th International IEEE Novel Intelligent and Leading Emerging sciences Conference, NILES 2023

作者： Holiel, Heidi Ahmed Fawzi, Sahar Ali Al-Atabany, Walid Nile University Medical Imaging and Image Processing Research Group Center for Informatics Science Sheikh Zayed City Egypt Cairo University Systems and Biomedical Engineering Department Giza Egypt Helwan University Biomedical Engineering Department Helwan Egypt

ISBN: (纸本)9798350381030

Retinal prostheses are designed to aid individuals with retinal degenerative conditions such as Retinitis Pigmentosa (RP) and Age-related Macular Degeneration (AMD). These prostheses seek to restore vision and improve the perceived scene by stimulating degenerated retinal cells using retinal stimulating electrodes. While these electrodes allow more efficient interaction with the surroundings, they offer limited *** paper presents an innovative approach to revolutionize the visual perception of retinal prosthesis users. The key idea behind the proposed approach is to fuse information extracted from advanced Meanshift and saliency detection algorithms. This proposed approach aims to improve the perceived scene for users, leading to enhanced visual perception and increased efficiency of retinal prostheses. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Immunomodulatory effect of ethanol-soluble polypeptides from Atlantic cod (Gadus morhua)

引用

Food science and Human Wellness 2023年第4期12卷 1192-1203页

作者： Zhen Yuan Meilian Yang Dongyang Zhu Di Wu Shuzhen Cheng Chao Wu Hesham R.El-Seedi Ming Du School of Food Science and Technology National Engineering Research Center of SeafoodDalian Polytechnic UniversityDalian 116034China Beijing Advanced Innovation Center for Food Nutrition and Human Health College of Food Science and Nutritional EngineeringChina Agricultural UniversityBeijing 100083China Pharmacognosy Group Department of Medicinal ChemistryUppsala UniversityBiomedical CentreUppsala 75123Sweden

There are many active substances in Atlantic cod(Gadus morhua)explaining the variety of biological *** order to study the immunomodulatory activity and the mechanism of Atlantic cod peptides at the cellular *** this study,cod peptides were isolated by 80%ethanol extraction method,the isolated ethanol-soluble cod peptides(CP-ES)were investigated and their immunomodulatory activity was ***,CP-ES showed lower molecular weight and more hydrophobic amino ***-ES could promote the proliferation of spleen lymphocytes and T lymphocytes in mice,suggesting that CP-ES may regulate adaptive *** promoted the release of NO and the expression of iNOS,TNF-α,IL-6 and IL-1βgenes in macrophages,suggesting that CP-ES may regulate innate ***-ES could promote the expression of TLR2 gene,and the peptides identified in CP-ES were docked with TLR2 to predict the peptides playing a major role in *** results suggested that CP-ES may regulate the immune activity of both innate and adaptive lines.

关键词： Gadus morhua Immunomodulation Peptides TLR2 Molecular docking

来源：评论

学校读者我要写书评

暂无评论

Accelerating Parallel Sampling of Diffusion Models 41

Accelerating Parallel Sampling of Diffusion Models

引用

41st International Conference on Machine Learning, ICML 2024

作者： Tang, Zhiwei Tang, Jiasheng Luo, Hao Wang, Fan Chang, Tsung-Hui School of Science and Engineering The Chinese University of Hong Kong Shenzhen China DAMO Academy Alibaba Group China Hupan Lab Zhejiang Province China Shenzhen Research Institute of Big Data Shenzhen China

Diffusion models have emerged as state-of-the-art generative models for image generation. However, sampling from diffusion models is usually time-consuming due to the inherent autoregressive nature of their sampling process. In this work, we propose a novel approach that accelerates the sampling of diffusion models by parallelizing the autoregressive process. Specifically, we reformulate the sampling process as solving a system of triangular nonlinear equations through fixed-point iteration. With this innovative formulation, we explore several systematic techniques to further reduce the iteration steps required by the solving process. Applying these techniques, we introduce ParaTAA, a universal and training-free parallel sampling algorithm that can leverage extra computational and memory resources to increase the sampling speed. Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms such as DDIM and DDPM by a factor of 4∼14 times. Notably, when applying ParaTAA with 100 steps DDIM for Stable Diffusion, a widely-used text-to-image diffusion model, it can produce the same images as the sequential sampling in only 7 inference steps. The code is available at https://***/TZW1998/ParaTAA-Diffusion. Copyright 2024 by the author(s)

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Ubiquitously Expressed Genes in Humans from A data-driven Perspective

引用

Genomics, Proteomics & Bioinformatics 2023年第1期21卷 164-176页

作者： Jianlei Gu Jiawei Dai Hui Lu Hongyu Zhao SJTU-Yale Joint Center for Biostatistics and Data Science Department of Bioinformatics and BiostatisticsSchool of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghai 200240China Center for Biomedical Informatics Shanghai Engineering Research Center for Big Data in Pediatric Precision MedicineShanghai Children’s HospitalShanghai 200040China Department of Biostatistics Yale UniversityNew HavenCT 06511USA

Comprehensive characterization of spatial and temporal gene expression patterns in humans is critical for uncovering the regulatory codes of the human genome and understanding the molecular mechanisms of human *** expressed genes(UEGs)refer to the genes expressed across a majority of,if not all,phenotypic and physiological conditions of an *** is known that many human genes are broadly expressed across ***,most previous UEG studies have only focused on providing a list of UEGs without capturing their global expression patterns,thus limiting the potential use of UEG *** this study,we proposed a novel data-driven framework to leverage the extensive collection of40,000 human transcriptomes to derive a list of UEGs and their corresponding global expression patterns,which offers a valuable resource to further characterize human *** results suggest that about half(12,234;49.01%)of the human genes are expressed in at least 80%of human transcriptomes,and the median size of the human transcriptome is 16,342 genes(65.44%).Through gene clustering,we identified a set of UEGs,named LoVarUEGs,which have stable expression across human transcriptomes and can be used as internal reference genes for expression *** further demonstrate the usefulness of this resource,we evaluated the global expression patterns for 16 previously predicted disallowed genes in islet beta cells and found that seven of these genes showed relatively more varied expression patterns,suggesting that the repression of these genes may not be unique to islet beta cells.

关键词： Ubiquitous expression Housekeeping gene Disallowed gene Expression specificity Expression variability

来源：评论

学校读者我要写书评

暂无评论

Fabrication of PVA Hydrogel Coated 3D Printed PETG Optical Fiber for Biocompatible biomedical Applications 5

Fabrication of PVA Hydrogel Coated 3D Printed PETG Optical F...

引用

5th International Conference on Smart Sensors and Application, ICSSA 2024

作者： Safri, Nur Syakirah Mohamad Al-Ashwal, Rania Hussien Ibrahim, Raja Kamarulzaman Raja Advanced Diagnostic and Progressive Human Care research group Department of Biomedical Engineering and Health Sciences Faculty of Electrical Engineering Universiti Teknologi Malaysia Johor Bahru Malaysia Department of Physics Faculty of Science Universiti Teknologi Malaysia Johor Bahru Malaysia

ISBN: (纸本)9798350354294

Dip coating is widely used in hydrogel based optical fiber. However, obtaining a uniform coating for microstructure such as optical fiber remains a challenge where its influence on the optical output is still scarce in literature. Dip coating parameters such as speed and viscosity of the solution will affect both the uniformity and thickness of the coating. Therefore, this study aims to investigate the optical output of optical fiber core coated with Polyvinyl Alcohol (PVA) hydrogel with varied dip coating speed (15, 30, 45, 60, 75 and 90 mm/min) and PVA concentrations (10, 15 and 20%). Firstly, the core of the optical fiber was self-fabricated using 3D printing technology, directly extruded from the commercially available Polyethylene Terephthalate Glycol-modified (PETG) filament. The uniformity and thickness of the coating were observed under optical microscope follows by analyses in ImageJ software to measure the thickness at four different points (top, bottom, left and right). The optical output is measured using 650 nm light source and measured using optical power meter. The results revealed that the higher the concentrations with high speed will results in a thicker coating compared with employing low concentrations at high speed. However, regardless of the speed and concentrations, all the coatings show nonconcentricity which influence the optical output intensity. Optical power output shows that the higher optical output can be observed at high concentrations of 20% as it led to thicker coating regardless of the different speeds compared 10% PVA concentrations. Despite the non-uniform coating, the optical output of all the coated fiber shows improvement compared to non-coated fiber. © 2024 IEEE.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

A Comparison of the Instructor-Trainee Dance dataset Using Cosine similarity, Euclidean distance, and Angular difference 26

A Comparison of the Instructor-Trainee Dance Dataset Using C...

引用

26th International Computer science and engineering Conference, ICSEC 2022

作者： Srikaewsiew, Thanawat Khianchainat, Khatadet Tharatipyakul, Atima Pongnumkul, Suporn Kanjanawattana, Sarunya Institute of Engineering Suranaree University of Technology Department of Computer Engineering Nakhon Ratchasima Thailand Data Science and Analytics Research Group Pathumthani Thailand

ISBN: (纸本)9781665491983

The COVID-19 outbreak has restricted most outdoor activities, leads to increasing interest in exercise at home with online trainers. One issue of online exercise technology is the safety since improper motion might result in injury. As a basis to prevent improper motion, methods for evaluating the motion similarity between an instructor and a trainee are essential. Cosine similarity, Angular difference, and Euclidean distance are three general ways for the motion evaluation. This study aimed to determine the most effective way for analyzing the similarity of human motion on the dataset of instructor-led dances. We first experimented with the data to find the appropriate cut-off value for classifying posture into two classes based on the similarity score. Confusion matrix, precision, recall, F1-score, accuracy of the results were then used to compare the efficiency. We discovered that Cosine similarity had the highest accuracy, 82.77 percent at cut-off 93. © 2022 IEEE.

关键词： COVID-19

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：