检索结果-内蒙古大学图书馆

Analysis of Gait data Based on deep Learning to Predict Multiple Balance Scale Scores

IEEE Sensors Journal 2024年第1期24卷 920-930页

作者： Lin, Chueh-Ho Peng, Chih-Wei Lee, I-Jung Wu, Chi-Ming Lin, Bor-Shing Taipei Medical University International Ph.D. Program in Gerontology and Long-Term Care Taipei City110 Taiwan Taipei Medical University Research Center in Nursing Clinical Practice Wan Fang Hospital Taipei City110 Taiwan Taipei Medical University School of Biomedical Engineering College of Biomedical Engineering Taipei City110 Taiwan Taipei Medical University School of Gerontology and Long-Term Care College of Nursing Taipei City110 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237 Taiwan National Taipei University College of Electrical Engineering and Computer Science New Taipei City237 Taiwan

Unbalanced walking is increasingly common among older adults;therefore, routinely assessing the balance of older adults is crucial. The traditional method of assessing balance uses scales, requires the supervision of a physical therapist (PT), and is time-consuming. The present study, therefore, proposes a deep learning (dL) model architecture that combines a convolutional neural network (CNN) and a long short-term memory (LSTM) network model to predict the scores of three scales, namely the Berg balance scale (BBS), timed up and go (TUG), and single-leg stance (SLS). The gait data of 15 m of walking were collected from seven inertial measurement units (IMUs) and input into the CNN-LSTM model for evaluation. The BBS and TUG only require the participants to wear two IMUs on the left and right thighs, respectively, for accurate predictions. The mean absolute errors (MAEs) of predicting the scores of the BBS and TUG are 1.2562 and 1.4016 s, respectively;however, the MAE of score predictions of SLS is higher than that of the BBS and TUG, indicating that gait data cannot be used for assessing SLS;moreover, participants only wear one IMU on the right calf for BBS and TUG evaluations, which yield MAEs of 1.4334 and 1.5229 s, respectively. The proposed system can quickly and accurately predict the scores of the BBS and TUG. The proposed model can assist PTs with making clinical decisions. © 2001-2012 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

High-Energy Lithium-Ion Capacitors Using the NiS2@MXene Electrode: Evidence of dual Faradaic Reactions driven by the Choice of Electrolytes

ACS Applied Engineering Materials

引用

ACS Applied engineering Materials 2025年第5期3卷 1277-1291页

作者： Keerthana dileep Pamangadan C. Sharafudeen Mani Govindasamy Pin-Yi Chen Perumal Elumalai Electrochemical Energy Storage Lab Department of Green Energy Technology Madanjeet School of Green Energy Technologies Pondicherry University Puducherry 605014 India International Ph.D. Program in Innovative Technology of Biomedical Engineering and Medical Devices Ming Chi University of Technology New Taipei City 24301 Taiwan；Research Centre for Intelligence Medical Devices Ming Chi University of Technology New Taipei City 243303 Taiwan International Ph.D. Program in Innovative Technology of Biomedical Engineering and Medical Devices Ming Chi University of Technology New Taipei City 24301 Taiwan；Department of Mechanical Engineering Ming Chi University of Technology New Taipei City 24301 Taiwan；Department of Mechanical Engineering Chang Gung University Taoyuan City 33302 Taiwan

Transition metal sulfides (TMSs) are emerging as promising supercapacitor electrodes due to their excellent pseudocapacitive properties and substantial theoretical charge density. The combination of TMS and layered MXene synergistically enhances the energy and power, making them ideal for advanced energy storage applications. Here, NiS2@MXene composites were successfully synthesized via a simple probe sonication, and their formation, morphology, and composition were scrutinized using materials characterization techniques. Electrochemical analyses of the NiS2@MXene electrode in the KOH electrolyte revealed the occurrence of a Faradaic reaction involving (Ni3+/Ni2+) redox. Consequently, lithium-ion capacitors (LICs) using the NiS2@MXene and reduced graphene oxide (rGO) as respective positive and negative electrodes in aqueous and different nonaqueous electrolytes were fabricated, and their performances were analyzed in the form of coin cells. It turned out that the aqueous LIC (NiS2@MXene|1 M LiClO4(aq.)|rGO) delivered a specific energy of 48.4 W h kg–1at a specific power of 800 W kg–1. Notably, the nonaqueous LIC (NiS2@MXene|1 M LiClO4(EC/dMC)|rGO) achieved an increased specific energy of 64 W h kg–1at a specific power of 1500 W kg–1and exhibited excellent capacity retention of 80% over 20,000 long cycles. Excitingly, the nonaqueous LIC (NiS2@MXene|1 M LiPF6(EC/dEC)|rGO) delivered a remarkable specific energy of 117.3 W h kg–1at a specific power of 2100 W kg–1and successfully powered a commercial LEd bulb and a stopwatch, showcasing the practicality of the electrode. The electrochemical measurements and the ex situ X-ray diffraction analyses confirmed the simultaneous occurrence of the conversion/reconversion and the intercalation/deintercalation reactions, facilitated on the electrode that led to such a high Li+charge storage performance. The conductive MXene matrix contributed to enhancing the charge transport by reducing the diffusion path and led to more active s

关键词：

来源：评论

学校读者我要写书评

暂无评论

Humming-to-Instrument Conversion based on CycleGAN

Humming-to-Instrument Conversion based on CycleGAN

引用

2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021

作者： Lai, Wen-Hsing Wang, Siou-Lin Xu, Zhi-Yao National Kaohsiung University of Science and Technology Dept. of Computer and Communication Engineering Kaohsiung Taiwan National Kaohsiung University of Science and Technology Ph.D. Program In Engineering Science and Technology College of Engineering Kaohsiung Taiwan

ISBN: (纸本)9781665419512

In this research, we propose a humming-to-instrument conversion system based on cycle-consistent adversarial networks (CycleGAN) to convert human humming to the sound of viola. This research adjusts the weight of cycle-consistency loss and identity loss to successfully convert the sound. From the experimental results of objective RMSE, the converted audio is more similar to viola compared to the similarity to humming. From the results of subjective MOS, the quality of the converted sound is fair to listeners. © 2021 IEEE.

关键词： Communication systems Signal processing

来源：评论

学校读者我要写书评

暂无评论

Colorectal Polyp detection and Classification using deep Learning Techniques

Colorectal Polyp Detection and Classification using Deep Lea...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Yao-Tien Chen Nisar Ahmad Chi-Che Hong M. david Honesty International Ph.D. Program in Innovative Technology of Biomedical Engineering and Medical Devices Ming Chi University of Technology New Taipei City Taiwan Department of Mechanical Engineering Ming Chi University of Technology New Taipei City Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

According to recent studies, colorectal cancer is one of the leading causes of death these days. Colorectal polyps are irregular formation of tissues that lead to colorectal cancer. Conventional methods are not sufficient to properly detect colorectal cancer in the early stages. Therefore, an efficient method is inevitable to detect and classify colorectal polyps in the early stage. In recent years, deep learning-based methods have been proposed, but there is still a need for improvement to make these methods more efficient. In this study, we have made a detailed comparison of the latest methods based on their computations and performance to propose an efficient model for real-time polyp detection. The comparison is made between deep learning based on three computation strategies: Edge Computing, General Purpose, and High Computing, using a custom colorectal dataset from a hospital. Similarly, data augmentation is also applied to analyse the performance of the mentioned techniques. We expect this study to provide insight into selecting an efficient method that would play a significant role in real-time polyp detection and classification to ensure invaluable medical aid.

关键词： deep learning Training Learning systems Hospitals Computational modeling Colorectal cancer data augmentation

来源：评论

学校读者我要写书评

暂无评论

Optimization Model in Manufacturing Scheduling for the Garment Industry

引用

Computers, Materials & Continua 2022年第6期71卷 5875-5889页

作者： Chia-Nan Wang Yu-Chen Wei Po-Yuk So Viet Tinh Nguyen phan Nguyen Ky phuc Department of Industrial Engineering and Management National Kaohsiung University of Science and TechnologyKaohsiung80778Taiwan Department of Money and Banking National Kaohsiung University of Science and TechnologyKaohsiung80778Taiwan Ph.D.Program in Finance and Banking National Kaohsiung University of Science and TechnologyKaohsiung80778Taiwan Faculty of Commerce Van Lang UniversityHo Chi Minh CityVietnam Faculty of Industrial Engineering and Management International UniversityHo Chi Minh City70000Vietnam

The garment industry in Vietnam is one of the country’s strongest industries in the ***,the production process still encounters problems regarding scheduling that does not equate to an optimal *** paper introduces a production scheduling solution that resolves the potential delays and lateness that hinders the production process using integer programming and order allocation with a make-to-order manufacturing viewpoint.A number of constraints were considered in the model and is applied to a real case study of a factory in order to viewhowthe tardiness and latenesswould be affected which resulted in optimizing the scheduling time ***,the constraints considered were order assignments,production time,and tardiness with an objective function which is to minimize the total cost of *** results of the study precisely the overall cost of delay of the orders given to the plant and successfully propose a suitable production schedule that utilizes the most of the plant *** study has shown promising results that would assist plant and production managers in determining an algorithm that they can apply for their production process.

关键词： Production scheduling problem order allocation integer programming make-to-order manufacturing apparel industry

来源：评论

学校读者我要写书评

暂无评论

Marine macro-litter sources and ecological impact: a review

引用

Environmental Chemistry Letters 2024年第3期22卷 1257-1273页

作者： Le, Van-Giang Nguyen, Hoang-Lam Nguyen, Minh-Ky Lin, Chitsan Hung, Nguyen T. Quang Khedulkar, Akhil P. Hue, Nguyen K. Trang, phung T. Thu Mungray, Arvind Kumar Nguyen, d. duc Central Institute for Natural Resources and Environmental Studies Vietnam National University Hanoi111000 Viet Nam Department of Civil Engineering McGill University MontrealQC Canada Faculty of Environment and Natural Resources Nong Lam University Hamlet 6 Linh Trung Ward Thu Duc City Ho Chi Minh City700000 Viet Nam Ph.D. Program in Maritime Science and Technology National Kaohsiung University of Science and Technology Kaohsiung81157 Taiwan Department of Marine Environmental Engineering National Kaohsiung University of Science and Technology Kaohsiung81157 Taiwan Department of Biomedical Engineering and Environmental Science National Tsing Hua University Hsinchu30013 Taiwan Environmental Research Center Institute of Hydrology and Meteorology Science and Climate Change Hanoi111000 Viet Nam Department of Chemical Engineering Sardar Vallabhbhai National Institute of Technology Gujarat Surat395007 India Department of Civil and Energy System Engineering Kyonggi University Suwon16227 Korea Republic of Institute of Applied and Sustainable Technology Nguyen Tat Thanh University Ho Chi Minh City700000 Viet Nam

Marine pollution by various debris is rising in the context of increasing urbanization, industrialization and worldwide trade. Here, we review marine macro-litter with focus on sources, abundance, distribution, and impact on aquatic wildlife, human health, and the economy. We observe that about 75–80% of marine litter originates from land-based sources, including poorly managed landfills and improper disposal. Macro-litter ingestion by marine life is of growing concern, in particular concerning the presence of plastics and associated pollutants, e.g., bisphenol A and phthalates, in fishes. These pollutants are accumulated and transferred to human via seafood. Marine plastic pollution induces a substantial rise of economic costs due to the decline of ecosystem services. Mitigation of marine plastic pollution should be done by following the ten Rs principles of refuse, rethink, reduce, re-use, repair, refurbish, remanufacture, repurpose, recycle, and recover. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of deepLabCut and Other Open-Source Pupillometry data Analysis Algorithms – Which to Choose?

引用

Machine Graphics and Vision 2024年第2期33卷 77-90页

作者： Badkul, Amitesh Mishra, Sonakshi Kommajosyula, Srinivasa P. Department of Electrical & Electronics Engineering Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Department of Pharmacy Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Ph.D. Program in Computer Science The Graduate Center The City University of New York New YorkNY United States

Pupillometry measures pupil size, and several open-source algorithms are available to analyse pupillometry data. However, only a few studies compared these algorithms’ accuracy and computational resources. This study aims to compare the accuracy of computer vision-based algorithms (Swirski, Starburst, PuRe, ElSe, ExCuSe algorithms) and the machine learning algorithm, deepLabCut, to the double-blinded human examiners (gold-standard). Training of deepLabCut with different architectures and a variable number of markers (2-9 markers) was done on an open-source dataset. The duration of training was statistically longer for the ResNet152 model compared to the MobileNet model. The pupil diameters in computer vision-based software such as PuRe, Starburst, and Swirski were statistically different from human measurements. MobileNet 2 and 3 marker models were the closest to the human measurements. In conclusion, this work highlights the efficiency of lower marker models based on MobileNet architecture in deepLabCut, which consumes fewer computational resources and is more accurate. © 2024 Institute of Information technology, Warsaw University of Life sciences - SGGW. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Flexoelectric Catalysts Based on Hierarchical Wrinkling Surface of Centrosymmetric High-Entropy Oxide

引用

ACS Nano 2023年第17期17卷 17417-17426页

作者： Wu, Ping Yun Le, Kim Tuyen Lin, Hsun-Yen Chen, Yu-Ching Wu, Po-Han Wu, Jyh Ming Department of Materials Science and Engineering National Tsing Hua University 101 Section 2 Kuang Fu Road Hsinchu300 Taiwan High Entropy Materials Center National Tsing Hua University 101 Section 2 Kuang Fu Road Hsinchu300 Taiwan Ph.D. Program in Prospective Functional Materials Industry National Tsing Hua University 101 Section 2 Kuang Fu Road Hsinchu300 Taiwan

A high-entropy oxide nanocomposite with Ag(CuZn)(AlCr)2O4 and CuO phases is fabricated to form an abundantly hierarchical wrinkled surface. Application of a mechanical force to the nanocomposite resulted in a nonhomogeneous strain gradient at the interface between the Ag(CuZn)(AlCr)2O4 and CuO phases, changing the local charge distribution and creating flexoelectric polarization that delayed electron/hole recombination. Transmission electron microscopy energy-dispersive X-ray spectroscopy mapping revealed that the Ag, Cu, Zn, Al, Cr, and O elements were highly distributed throughout the nanocomposite. The nanocomposite produced 2116 μmol·g-1 h-1 of H2 without external light irradiation, which is 980% higher than the H2 produced by the same nanocomposite under the photocatalytic process. A strong electrical field is observed at the interface between the Ag(CuZn)(AlCr)2O4 and CuO phases, demonstrating that a flexoelectric potential (flexopotential) is established at the structural boundaries because the strain gradient is localized at these interfaces. The nanocomposite is a promising approach for environmentally friendly energy production. © 2023 American Chemical Society.

关键词： Nanocomposites

来源：评论

学校读者我要写书评

暂无评论

A High-step-down Converter with Negative Output Voltage

A High-step-down Converter with Negative Output Voltage

引用

International Conference on Power Electronics (ICPE)

作者： Yeu-Torng. Yau Thanh-phu. Luu Ph.D. Program PTOEECS National Chin-Yi University of Technology Taichung Taiwan Department of Electrical Engineering National Chin-Yuuuuuuui University of Technology Taichung Taiwan

This paper proposes a new high step-down converter with negative voltage output, which has the following advantages: (1) Compared to conventional buck-boost or SEPIC converters, the proposed converter operates with zero voltage turn-on function. (2) The voltage gain of this circuit does not contain non-linear components, and the control is simple and can be driven by existing buck control ICs. (3) due to the dC blocking capacitor between the output and input terminals, the high voltage at the input will not pass through to the output when the converter fails to be controlled. The load is protected. Finally, a prototype is completed and the proposed method is verified to be feasible.

关键词：

来源：评论

学校读者我要写书评

暂无评论

photothermal Temperature-Modulated Cancer Metastasis Harnessed Using Proteinase-Triggered Assembly of Near-Infrared II photoacoustic/photothermal Nanotheranostics

引用

ACS Applied Materials and Interfaces 2024年第31期16卷 40611-40627页

作者： Chuang, Yao-Chen Hsia, Yu Chu, Chia-Hui Maharajan, Sivasubramanian Hsu, Fang-Chi Lee, Hsin-Lun Chiou, Jeng Fong Ch’ang, Hui-Ju Liao, Lun-de Lo, Leu-Wei Institute of Biomedical Engineering and Nanomedicine National Health Research Institutes Miaoli Zhunan35053 Taiwan Department of Radiation Oncology Taipei Medical University Hospital Taipei110301 Taiwan Institute of Biotechnology National Tsing Hua University Hsinchu30013 Taiwan The Ph.D. Program for Translational Medicine College of Medical Science and Technology Taipei Medical University and Academia Sinica Taipei110301 Taiwan Department of Radiology School of Medicine College of Medicine Taipei Medical University Taipei110301 Taiwan National Institute of Cancer Research National Health Research Institutes Miaoli Zhunan35053 Taiwan

Here we demonstrate that cancer metastasis could be modulated by the judicious tuning of physical parameters such as photothermal temperature in nanoparticle-mediated photothermal therapy (PTT). This is supported by theranostic nanosystem design and characterization, in vitro and in vivo analyses, and transcriptome-based gene profiling. In this work, the highly efficient near-infrared II (NIR-II) photoacoustic image (PA)-guided PTT are selectively activated using our developed matrix metalloproteinase (MMP)-triggered in situ assembly of gold nanodandelions (GNds@gelatin). Unlike other "always-on" NIR PTT agents lacking specific bioactivation and suffering from the intrinsic nonspecific pseudosignals and treatment-related side effects such as metastasis, our GNds@gelatin possesses important advantages while deployed in cancer PTT that include the following: (1) The theranostic effects could be "turned on" only after specific MMP-2/-9 activity and with acidity in the tumor microenvironment. (2) The quantitative PA diagnosis allows for precise PTT planning for better cancer treatment. (3) GNds@gelatin could noninvasively quantify MMP activity and efficiently harness NIR-I (808 nm) and NIR-II (1064 nm) energies for tumor ablation. (4) The multibranched nanostructures reabsorb scattered laser photons, thus enhancing the surface plasmons for the pronounced photothermal conversion of aggregated GNds@gelatin in situ. (5) It is noteworthy that in situ tumor eradication at higher PTT temperature (>55 °C) mediated by GNds@gelatin could induce subsequent metastasis, which could be otherwise abolished at lower PTT temperatures (50 °C > T > 43 °C). (6) Furthermore, the gene profiling using transcriptome-based microarray including GO and KEGG analyses revealed that 315 differentially expressed genes were identified in higher PTT temperature treated tumors compared with lower PTT temperature ones. These were enriched into some well-known cancer-related pathways, such as cell migrat

关键词： Plasmonics

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：