检索结果-南通市图书馆

Multi-channel electromyography pattern classification using deep belief networks for enhanced user experience

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Central South University 2015年第5期22卷 1801-1808页

作者： SHIM Hyeon-min LEE sangmin Institute for Information and Electronic Research Inha University 100 Inharo Incheon 402-751 Korea Department of Electronic Engineering Inha University 100 Inharo Incheon 402-751 Korea

An enhanced algorithm is proposed to recognize multi-channel electromyography(EMG) patterns using deep belief networks(DBNs). It is difficult to classify the EMG features because an EMG signal has nonlinear and time-varying ***, in several previous studies, various machine-learning methods have been applied. A DBN is a fast, greedy learning algorithm that can find a fairly good set of weights rapidly, even in deep networks with a large number of parameters and many hidden layers. To evaluate this model, we acquired EMG signals, extracted their features, and then compared the model with the DBN and other conventional classifiers. The accuracy of the DBN is higher than that of the other algorithms. The classification performance of the DBN model designed is approximately 88.60%. It is 7.55%(p=9.82×10-12) higher than linear discriminant analysis(LDA) and 2.89%(p=1.94×10-5) higher than support vector machine(SVM). Further, the DBN is better than shallow learning algorithms or back propagation(BP), and this model is effective for an EMG-based user-interfaced system.

关键词： electromyography(EMG) pattern classification feature extraction deep learning deep belief network(DBN)

Fabrication and Characterization of Au Nanoparticle-aggregated Nanowires by Using Nanomeniscus-induced Colloidal Stacking Method

在线全文

学校读者我要写书评

暂无评论

Nano-Micro Letters 2015年第1期7卷 27-34页

作者： sangmin An Wonho Jhe Department of Physics and Astronomy Institute of Applied Physics Seoul National University Center for Nanoscale Science and Technology National Institute of Standards and Technology

We fabricate and characterize Au nanoparticle-aggregated nanowires by using the nano meniscus-induced colloidal stacking method. The Au nanoparticle solution ejects with guidance of nanopipette/quartz tuning fork-based atomic force microscope in ambient conditions, and the stacking particles form Au nanoparticle-aggregated nanowire while the nozzle retracts from the surface. Their mechanical properties with relatively low elastic modulus are in situ investigated by using the same apparatus.

关键词： Au nanoparticle-aggregated nanowire Nanomeniscus-induced colloidal stacking method Atomic force microscope Liquid–solid coexistence phase

Capillary grip-induced stick-slip motion

在线全文

学校读者我要写书评

暂无评论

Nano Research 2022年第8期15卷 7384-7391页

作者： sangmin An Manhee Lee Bongsu Kim Wonho Jhe Department of Physics&Astronomy Seoul National UniversitySeoul 08826Republic of Korea Department of Physics Institute of Photonics and Information TechnologyJeonbuk National UniversityJeonju 54896Republic of Korea Department of Physics Chungbuk National UniversityCheongjuChungbuk 28644Republic of Korea Samsung Advanced Institute of Technology(SAIT) Samsung ElectronicsSuwon 16678Republic of Korea

We present capillary grip-induced stick-slip motion,a nanoscale tribological effect,where the role of a nanoscale confined water meniscus formed between a buckled sharp tip and a glass or mica surface is addressed by shear dynamic force *** obtained the effective elasticity,viscosity,conservative(elastic)and non-conservative(viscous)forces,energy dissipation,and lateral force using small oscillation,amplitude-modulation,and shear-mode quartz tuning fork-atomic force microscopy(QTFAFM).We distinguished the conservative and non-conservative forces by investigating the dependence of normal load and relative humidity,slip length,and stick-slip *** found that the confined nanoscale water enhances the lateral forces via capillary grip-induced stick-slip on a rough surface,resulting in an increase of static lateral force(3-fold for both substrates)and kinetic lateral force(6-fold for glass,3-fold for mica).This work provides quantitative and systematic understanding of nanoscale tribology properties in humid ambient conditions and is thus useful for control of friction as well as characterization of tribology in nanomaterials and nanodevices.

关键词： dynamic force measurement nanoscale water meniscus relative humidity lateral force stick-slip motion

Voice activity detection based on deep belief networks using likelihood ratio

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Central South University 2016年第1期23卷 145-149页

作者： KIM Sang-Kyun PARK Young-Jin LEE sangmin Department of Electronic Engineering Inha University Incheon 402-751 Korea Korea Electrotechnology Research Institute (KERI) 111 Hanggaul ro Sangrok Gu An-San shi Kyunggi Do 426-170 Korea Institute for Information and Electronics Research Inha University Incheon 402-751 Korea

A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spectral components that are assumed to follow the Gaussian probability density function(PDF). The proposed algorithm employs DBN learning in order to classify voice activity by using the input signal to calculate the likelihood ratio. Experiments show that the proposed algorithm yields improved results in various noise environments, compared to the conventional VAD algorithms. Furthermore, the DBN based algorithm decreases the detection probability of error with [0.7, 2.6] compared to the support vector machine based algorithm.

关键词： voice activity detection likelihood ratio deep belief networks

Sorting Gold and Sand(Silica) Using Atomic Force Microscope-Based Dielectrophoresis

在线全文

学校读者我要写书评

暂无评论

Nano-Micro Letters 2022年第2期14卷 1-11页

作者： Chungman Kim Sunghoon Hong Dongha Shin sangmin An Xingcai Zhang Wonho Jhe Department of Physics and Astronomy Seoul National UniversitySeoul 08826Republic of Korea John A.Paulson School of Engineering and Applied Sciences Harvard UniversityCambridgeMA 02138United States Department of Chemistry and Chemical Engineering Inha UniversityIncheon 22212Republic of Korea Department of Physics Institute of Photonics and Information TechnologyJeonbuk National UniversityJeonju 54896Korea School of Engineering Massachusetts Institute of TechnologyCambridgeMA 02139United States

Additive manufacturing-also known as 3D printing-has attracted much attention in recent years as a powerful method for the simple and versatile fabrication of complicated three-dimensional ***,the current technology still exhibits a limitation in realizing the selective deposition and sorting of various materials contained in the same reservoir,which can contribute significantly to additive printing or manufacturing by enabling simultaneous sorting and deposition of different substances through a single ***,we propose a dielectrophoresis(DEP)-based material-selective deposition and sorting technique using a pipette-based quartz tuning fork(QTF)-atomic force microscope(AFM) platform DEPQA and demonstrate multi-material sorting through a single nozzle in ambient *** used Au and silica nanoparticles for sorting and obtained 95% accuracy for spatial separation,which confirmed the surfaceenhanced Raman spectroscopy(SERS).To validate the scheme,we also performed a simulation for the system and found qualitative agreement with the experimental *** method that combines DEP,pipette-based AFM,and SERS may widely expand the unique capabilities of 3D printing and nano-micro patterning for multi-material patterning,materials sorting,and diverse advanced applications.

关键词： Dielectrophoresis-empowered Pipette/AFM platform On-demand materials sorting Additive 3D printing Multimaterial nano-patterning Nanopipette-based atomic force microscope

Effects of Korean Red Ginseng on Semen Parameters in Male Infertility Patients:A Randomized,Placebo-Controlled,Double-Blind Clinical Study

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Integrative Medicine 2016年第7期22卷 490-495页

作者： Hyun Jun Park sangmin Choe Nam Cheol Park Department of Urology Pusan National University School of MedicineBusan(602-739)Republic of Korea Medical Research Institute of Pusan National University Hospital Busan(602-739)Republic of Korea Division of Clinical Pharmacology Clinical Trial CenterPusan National University HospitalBusan(602-739)Republic of Korea

Objective： To investigate the effects of Korean red ginseng （KRG） on semen parameters in male infertility patients in a randomized, double-blind, placebo-controlled study. Methods： A total of 80 male infertility patients with varicocele were recruited from April 2011 to February 2012. The subjects were then divided into the following four groups： non-varicocelectomy （V）＋placebo （P） group, V＋P group, non-V＋KRG group （1.5-g KRG daily）, and V＋KGR group （1.5-g KRG daily）. Semen analysis was performed and hormonal levels were measured in each treatment arm after 12 weeks. Results： All groups but not the non-V＋P group, showed significant improvements in sperm concentrations, motility, morphology, and viability at the end of the study. However, there were no significant differences in serum follicle-stimulating hormone, luteinizing hormone, and testosterone among groups. The incidence of adverse events was low, and all events were assumed to be unrelated to the treatments administered. Conclusions： Although the exact mechanism by which KRG improves spermatogenesis remains unclear, KRG may be a useful agent for the treatment of male infertility. Nevertheless, additional studies to evaluate the optimal dose and duration of treatment are needed.

关键词： Panax ginseng male infertility spermatogenesis

Room temperature hydrogen sensing performances of multiple networked Ga N nanowire sensors codecorated with Au and Pt nanoparticles

在线全文

学校读者我要写书评

暂无评论

Journal of Central South University 2015年第5期22卷 1614-1618页

作者： PARK Sunghoon KIM Soohyun PARK Suyoung LEE sangmin LEE Chongmu Department of Materials Science and Engineering Inha University 253 Yonghyun-dong Nam-gu Incheon 402-751 Korea Department of Electronic Engineering Inha University 253 Yonghyun-dong Nam-gu Incheon 402-751 Korea

The sensing performances of multiple networked Ga N nanowire(NW) sensor codecorated with Au and Pt nanoparticles were examined. The pristine Ga N nanowires show responses of approximately 108%-173% to 0.05%-0.25% H2 at room temperature. On the other hand, the Ga N nanowires decorated with Au and those decorated with Pt lead to 1.1-1.3 and 1.2-1.6 times,respectively, stronger responses to 0.05%-0.25% H2. In contrast, the Au Pt-codecorated Ga N nanowires show 1.3-2.0 times stronger responses to 0.05%-0.25% H2. In other words, the Ga N nanorods codecorated with Au and Pt nanoparticles show much stronger response to H2 gas than the Au or Pt monometal-decorated counterpart. The underlying mechanism for the enhanced response of the Au Pt-codecorated Ga N nanowire was discussed.

关键词： Ga N nanowires metal catalyst bimetallic system gas sensor codecoration

Advancing Autoencoder Architectures for Enhanced Anomaly Detection in Multivariate Industrial Time Series

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第10期81卷 1275-1300页

作者： Byeongcheon Lee sangmin Kim Muazzam Maqsood Jihoon Moon Seungmin Rho Department of Security Convergence Chung-Ang UniversitySeoul06974Republic of Korea Department of Computer Science COMSATS University IslamabadAttock CampusAttock43600Pakistan Department of AI and Big Data Soonchunhyang UniversityAsan31538Republic of Korea Department of Industrial Security Chung-Ang UniversitySeoul06974Republic of Korea

In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)datasets?This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things(IoT)devices,which can significantly improve the reliability and safety of these *** this paper,we propose a hybrid autoencoder model,called ConvBiLSTMAE,which combines convolutional neural network(CNN)and bidirectional long short-term memory(BiLSTM)to more effectively train complex temporal data patterns in anomaly *** the hardware-in-the-loopbased extended industrial control system dataset,the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance,achieving F1 scores of 0.78 and 0.41 for the first and second datasets,*** results suggest that hybrid autoencoder models are not only viable,but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems,offering a promising approach to improving their reliability and safety.

关键词： Advanced anomaly detection autoencoder innovations unsupervised learning industrial security multivariate time series analysis

Variable step-size affine projection algorithm based on global speech absence probability for adaptive feedback cancellation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Central South University 2014年第2期21卷 646-650页

作者： KIM Young-Sear SONG Ji-hyun KIM Sang-Kyun LEE sangmin Department of Biomedical Engineering Eulji University Department of Electronic Engineering Inha University Institute for Information and Electronics Research Inha University

A novel approach is proposed for improving adaptive feedback cancellation using a variable step-size affine projection algorithm(VSS-APA) based on global speech absence probability(GSAP).The variable step-size of the proposed VSS-APA is adjusted according to the GSAP of the current *** weight vector of the adaptive filter is updated by the probability of the speech *** performance measure of acoustic feedback cancellation is evaluated using normalized *** results demonstrate that the proposed approach has better performance than the normalized least mean square(NLMS) and the constant step-size affine projection algorithms.

关键词： adaptive feedback cancellation affine projection global speech absence probability(GSAP)