检索结果-南通市图书馆

Development,validation,and transportability of several machine-learned,non-exercise-based VO_(2max)prediction models for older adults

引用

Journal of Sport and Health Science 2024年第5期13卷 611-620页

作者： Benjamin T.Schumacher Michael J.LaMonte Andrea Z.LaCroix Eleanor M.Simonsick Steven P.Hooker Humberto Parada Jr. John Bellettiere arun kumar Herbert Wertheim School of Public Health and Human Longevity Science University of California San DiegoLa JollaCA 92093USA Department of Epidemiology and Environmental Health School of Public Health and Health ProfessionsUniversity at BuffaloState University of New YorkBuffaloNY 14214USA Translational Gerontology Branch Intramural Research ProgramNational Institute on AgingNational Institutes of HealthBaltimoreMD 21225USA College of Health and Human Services San Diego State UniversitySan DiegoCA 92182USA Division of Epidemiology and Biostatistics School of Public HealthSan Diego State UniversitySan DiegoCA 92182USA University of California San Diego Moores Cancer Center La JollaCA 92093USA Computer Science and Engineering and Halicioglu Data Science Institute University of California San DiegoLa JollaCA 92093USA

Background:There exist few maximal oxygen uptake(VO_(2max))non-exercise-based prediction equations,fewer using machine learning(ML),and none specifically for older adults.Since direct measurement of VO_(2max)is infeasible in large epidemiologic cohort studies,we sought to develop,validate,compare,and assess the transportability of several ML VO_(2max)prediction algorithms.Methods:The Baltimore Longitudinal Study of Aging(BLSA)participants with valid VO2_(max)tests were included(n=1080).Least absolute shrinkage and selection operator,linear-and tree-boosted extreme gradient boosting,random forest,and support vector machine(SVM)algorithms were trained to predict VO_(2max)values.We developed these algorithms for:(a)the overall BLSA,(b)by sex,(c)using all BLSA variables,and(d)variables common in aging cohorts.Finally,we quantified the associations between measured and predicted VO_(2max)and mortality.Results:The age was 69.0±10.4 years(mean±SD)and the measured VO_(2max)was 21.6±5.9 mL/kg/min.Least absolute shrinkage and selection operator,linear-and tree-boosted extreme gradient boosting,random forest,and support vector machine yielded root mean squared errors of 3.4 mL/kg/min,3.6 mL/kg/min,3.4 mL/kg/min,3.6 mL/kg/min,and 3.5 mL/kg/min,respectively.Incremental quartiles of measured VO_(2max)showed an inverse gradient in mortality risk.Predicted VO_(2max)variables yielded similar effect estimates but were not robust to adjustment.Conclusion:Measured VO_(2max)is a strong predictor of mortality.Using ML can improve the accuracy of prediction as compared to simpler approaches but estimates of association with mortality remain sensitive to adjustment.Future studies should seek to reproduce these results so that VO_(2max),an important vital sign,can be more broadly studied as a modifiable target for promoting functional resiliency and healthy aging.

关键词： Cardiorespiratory fitness Prediction algorithms Epidemiology Mortality

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Machine learning for predicting the outcome of terminal ballistics events

引用

Defence Technology（防务技术） 2024年第1期31卷 14-26页

作者： Shannon Ryan Neeraj Mohan Sushma arun kumar AV Julian Berk Tahrima Hashem Santu Rana Svetha Venkatesh Applied Artificial Intelligence Institute(A2I2) Deakin University75 Pigdons RdWaurn PondsVIC3216Australia

Machine learning(ML) is well suited for the prediction of high-complexity,high-dimensional problems such as those encountered in terminal ballistics.We evaluate the performance of four popular ML-based regression models,extreme gradient boosting(XGBoost),artificial neural network(ANN),support vector regression(SVR),and Gaussian process regression(GP),on two common terminal ballistics’ problems:(a)predicting the V50ballistic limit of monolithic metallic armour impacted by small and medium calibre projectiles and fragments,and(b) predicting the depth to which a projectile will penetrate a target of semi-infinite thickness.To achieve this we utilise two datasets,each consisting of approximately 1000samples,collated from public release sources.We demonstrate that all four model types provide similarly excellent agreement when interpolating within the training data and diverge when extrapolating outside this range.Although extrapolation is not advisable for ML-based regression models,for applications such as lethality/survivability analysis,such capability is required.To circumvent this,we implement expert knowledge and physics-based models via enforced monotonicity,as a Gaussian prior mean,and through a modified loss function.The physics-informed models demonstrate improved performance over both classical physics-based models and the basic ML regression models,providing an ability to accurately fit experimental data when it is available and then revert to the physics-based model when not.The resulting models demonstrate high levels of predictive accuracy over a very wide range of projectile types,target materials and thicknesses,and impact conditions significantly more diverse than that achievable from any existing analytical approach.Compared with numerical analysis tools such as finite element solvers the ML models run orders of magnitude faster.We provide some general guidelines throughout for the development,application,and reporting of ML models in terminal ballistics problems.

关键词： Machine learning Artificial intelligence Physics-informed machine learning Terminal ballistics Armour

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Scheme Based on Multi-Level Patch Attention and Lesion Localization for Diabetic Retinopathy Grading

引用

Computer Modeling in Engineering & Sciences 2024年第7期140卷 409-430页

作者： Zhuoqun Xia Hangyu Hu Wenjing Li Qisheng Jiang Lan Pu Yicong Shu arun kumar Sangaiah School of Computer and Communication Engineering Changsha University of Science and TechnologyChangshaChina Hunan Province People’s Hospital(The First Affiliated Hospital of Hunan Normal University) ChangshaChina The First Affiliated Hospital of Guangxi Medical University NanningChina International Graduate Institute of AI National Yunlin University of Science and TechnologyYunlinChina Department of Electrical and Computer Engineering Lebanese American UniversityBayrutLebanon

Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.

关键词： DDR dataset diabetic retinopathy lesion localization multi-level patch attention mechanism

来源：

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

PAPR Reduction of NOMA Using Vandermonde Matrix-Particle Transmission Sequence

引用

Computer Systems Science & Engineering 2022年第10期43卷 193-201页

作者： arun kumar Sandeep Gupta Himanshu Sharma Mehedi Masud Department of Electronics and Communication Engineering JECRC UniversityJaipur303905India Department of Electrical Engineering JECRC UniversityJaipur303905India Department of Computer Science and Engineering JECRC UniversityJaipur303905India Department of Computer Science College of Computers and Information TechnologyTaif University11099Saudi Arabia

Non-Orthogonal Multiple Access(NOMA)is an ideal choice for 5G waveforms due to their characteristics such as high data rate,massive device connectivity,high spectral access,and effective frequency selective fading.Thus,it permits gigantic connectivity.The spectrum overlaps with NOMA,which consents several operators to segment the spectrum at the same frequency.These features make NOMA more suitable for use beyond 5G.Peak to Average Power(PAPR)is a major problem in Multi-Carrier Techniques(MCT)like NOMA and it also degrades the performance of the amplifier.The Partial Transmission Sequence(PTS)is a superior algorithm for moderating the PAPR.However,it also increases the complexity of the structure.The PAPR is reduced in NOMA by multiplying the NOMA signal with optimised phase vectors(P).The phase vectors are generated by using the Vandermonde Matrix(VM).In this work,we proposed a VM-PTS algorithm for the NOMA system,and the number of computations to search the optimal phase vectors for NOMA high PAPR signal is less as compared with existing PTS.The outcomes demonstrate that the performance of the recommended PTS in terms of PAPR,Bit Error Rate(BER),and complexity is better than the conventional PTS(C-PTS).

关键词： VM-PTS NOMA PAPR 5G

来源：

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

PAPR Reduction Using Advanced Partial Transmission Scheme for 5G Waveforms

引用

Computer Systems Science & Engineering 2022年第8期42卷 483-492页

作者： arun kumar Sumit Chakravarty SSuganya Mehedi Masud Sultan Aljahdali Department of Electronics and Communication Engineering JECRC UniversityJaipur303905INDIA Department of Electrical and Computer Engineering Kennesaw State UniversityGAUSA Electronics and Communication Engineering CMR Institute of TechnologyBangaloreINDIA Department of Computer Science College of Computers and Information TechnologyTaif University11099Saudi Arabia

The implementation of Peak Average to Power Ratio(PAPR)reduction technologies will play an important role in the regularization of Fifth Generation(5G)radio communication.PAPR reduction in the advanced waveform will be the key part of designing a 5G network for different applications.This work introduces the simulation of an Advanced Partial Transmission Sequence(A-PTS)reduction techniques for Orthogonal Frequency Division Multiplexing(OFDM)and Filter Bank Multi-Carrier(FBMC)transmission schemes.In the projected A-PTS,the FBMC signals are mapped into the number of sub-blocks and Inverse Fast Fourier transform(IFFT)is performed to estimate the high peak power in the time domain.The FBMC sub-blocks are multiplied with the phase elements to achieve an optimal PAPR value.A MATLAB 2014v simulation is used to estimate the PAPR,Bit Error Rate(BER),Error Vector Magnitude(EVM),and Modulation Error Rate(MER)performance of the proposed reduction schemes.The simulated result reveals that the performance of the projected algorithm is better than the conventional algorithms.

关键词： PAPR PTS OFDM FBMC 5G

来源：

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

Analysis of Cognitive Radio for LTE and 5G Waveforms

引用

Computer Systems Science & Engineering 2022年第12期43卷 1207-1217页

作者： Ramesh Ramamoorthy Himanshu Sharma A.Akilandeswari Nidhi Gour arun kumar Mehedi Masud Centre for Artificial Intelligence Chennai Institute of TechnologyChennaiIndia Department of Computer Science and Engineering JECRC UniversityJaipur303905India Institute of ECE Saveetha School of EngineeringChennaiIndia Department of Electronics and Communication Engineering JECRC UniversityJaipur303905India Department of Computer Science College of Computers and Information TechnologyTaif University11099Saudi Arabia

Spectrum sensing is one of the major concerns in reaching an efficientQuality of service (QOS) in the advanced mobile communication system. Theadvanced engineering sciences such as 5G, device 2 device communications(D2D), Internet of things (IoT), MIMO require a large spectrum for better service.Orthogonal frequency division multiplexing (OFDM) is not a choice in advancedradio due to the Cyclic Prefix (CP), wastage of the spectrum, and so on. Hence, itis important to explore the spectral efficient advanced waveform techniques andcombine a cognitive radio (CR) with the 5G waveform to sense the idle spectrum,which overcomes the spectrum issue. The demand for spectrum is ever increasing;however, spectrum is limited and is an acutely scarce resource. To alleviate theissue, techniques like Cognitive Radios (CR) have been devised. However, suchtechniques are non-standardized, and many variations of CR algorithms have beentried and tested. This paper details the several spectrum sensing methods tailoredfor CR. We explain the benefits, uniqueness, and drawbacks of the various techniques to provide a comprehensive review of the scene, including all recent andnovel techniques of CR. Finally, we provided experimental results for the performance of the CR for key 5G and beyond modulation techniques to elaborate thedependency of the CR techniques for CR applications and provide a competitivereview of their performance. Experiments show that the CR integrated withNOMA shows better performance as compared with existing techniques.

关键词： CR Energy detection FBMC NOMA OFDM

来源：

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

Comparative cytotoxicity of nanoparticles and ions to Escherichia coli in binary mixtures

引用

Journal of Environmental Sciences 2017年第5期29卷 11-19页

作者： Swati Srivastaua arun kumar Department of Civil Engineering Indian Institute of Technology Delhi New Delhi 110016 India

The objective of this study was to understand toxicity of mixture of nanoparticles （NPs）（ZnO and TiO2） and their ions to Escherichia coll. Results indicated the decrease in percentage growth of E. coli with the increase in concentration of NPs both in single and mixture setups. Even a small concentration of I mg/L was observed to be significantly toxic to E. coli in binary mixture setup （exposure concentration： 1 mg/L ZnO and 1 mg/L TiO2; 21.15% decrease in plate count concentration with respect to control）. Exposure ofE. coli to mixture of NPs at 1000 mg/L （i.e., 1000 mg/L ZnO and 1000 mg/L TiO2） resulted in 99.63% decrease in plate count concentration with respect to control. Toxic effects of ions to E. coli were found to be lesser than their corresponding NPs. The percentage growth reduction was found to be 36% for binary mixture of zinc and titanium ions at the highest concentration （i.e., 803.0 mg/L Zn and 593.3 mg/L Ti where ion concentrations are equal to the Zn ions present in 1000 mg/L ZnO NP solution and Ti＋4 ions present in 1000 mg/L TiO2 NP solution）. Nature of mixture toxicity of the two NPs to E. coli was found to be antagonistic. The alkaline phosphatase （Alp） assay indicated that the maximum damage was observed when E. coli was exposed to 1000 mg/L of mixture of NPs. This study tries to fill the knowledge gap on information of toxicity of mixture of NPs to bacteria which has not been reported earlier.

关键词： E. coli Zinc oxide nanoparticles Titanium dioxide nanoparticles Mixture toxicity Alkaline phosphatase assay

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Spatial and Contextual Path Network for Image Inpainting

引用

Intelligent Automation & Soft Computing 2024年第2期39卷 115-133页

作者： Dengyong Zhang Yuting Zhao Feng Li arun kumar Sangaiah Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China International Graduate Institute of AI National Yunlin University of Science and TechnologyYunlinTaiwan Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon

Image inpainting is a kind of use known area of information technology to repair the loss or damage to the area.Image feature extraction is the core of image restoration.Getting enough space for information and a larger receptive field is very important to realize high-precision image inpainting.However,in the process of feature extraction,it is difficult to meet the two requirements of obtaining sufficient spatial information and large receptive fields at the same time.In order to obtain more spatial information and a larger receptive field at the same time,we put forward a kind of image restoration based on space path and context path network.For the space path,we stack three convolution layers for 1/8 of the figure,the figure retained the rich spatial details.For the context path,we use the global average pooling layer,where the accept field is the maximum of the backbone network,and the pooling module can provide global context information for the maximum accept field.In order to better integrate the features extracted from the spatial and contextual paths,we study the fusion module of the two paths.Features fusionmodule first path output of the space and context path,and then through themass normalization to balance the scale of the characteristics,finally the characteristics of the pool will be connected into a feature vector and calculate the weight vector.Features of images in order to extract context information,we add attention to the context path refinement module.Attention modules respectively from channel dimension and space dimension to weighted images,in order to obtain more effective information.Experiments show that our method is better than the existing technology in the quality and quantity of themethod,and further to expand our network to other inpainting networks,in order to achieve consistent performance improvements.

关键词： Image inpainting attention deep learning convolutional network

来源：

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

Evolution of the 2015/16 El Nio and historical perspective since 1979

引用

Science China Earth Sciences 2017年第9期60卷 1572-1588页

作者： Yan XUE arun kumar Climate Prediction Center National Centers for Environmental Prediction National Weather Service National Oceanic and Atmospheric Administration College Park MD 20740 USA

The 2015/16 El Nio developed from weak warm conditions in late 2014 and NINO3.4 reached 3℃ in November 2015. We describe the characteristics of the evolution of the 2015/16 El Nio using various data sets including SST, surface winds,outgoing longwave radiation and subsurface temperature from an ensemble operational ocean reanalyses, and place this event in the context of historical ENSO events since 1979. One salient feature about the 2015/16 El Nio was a large number of westerly wind bursts and downwelling oceanic Kelvin waves(DWKVs). Four DWKVs were observed in April-November 2015 that initiated and enhanced the eastern-central Pacific warming. Eastward zonal current anomalies associated with DWKVs advected the warm pool water eastward in spring/summer. An upwelling Kelvin wave(UWKV) emerged in early November 2015 leading to a rapid decline of the event. Another outstanding feature was that NINO4 reached a historical high(1.7℃), which was 1℃(0.8℃) higher than that of the 1982/83(1997/98) El Nio . Although NINO3 was comparable to that of the 1982/83 and 1997/98 El Nio , NINO1+2 was much weaker. Consistently, enhanced convection was displaced 20 degree westward, and the maximum D20 anomaly was about 1/3.1/2 of that in 1997 and 1982 near the west coast of South America.

关键词：历史演变 El Ni ENSO事件演化特征操作温度长波辐射西风爆发

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

PAPR Reduction in NOMA by Using Hybrid Algorithms

引用

Computers, Materials & Continua 2021年第10期69卷 1391-1406页

作者： Mohit kumar Sharma arun kumar Department of Electronics and Communication Engineering JECRC UniversityJaipur303905India

Non-orthogonal multiple access(NOMA)is gaining considerable attention due to its features,such as low out-of-band radiation,signal detection capability,high spectrum gain,fast data rate,and massive D2D connectivity.It may be considered for 5G networks.However,the high peak-to-average power ratio(PAPR)is viewed as a significant disadvantage of a NOMA waveform,and it weakens the quality of signals and the throughput of the scheme.In this article,we introduce a modified NOMA system by employing a block of wavelet transform,an alternative to FFT(Fast Fourier transform).The modified system combines the details of fractional frequency and time analysis of NOMA signals.In this correspondence,we utilize an advanced partial transmission scheme(PTS),and selective mapping(SLM),and present a genetic algorithm(GA)for SLM to investigate the peak power performance of a WT-based NOMA system.The performance of WT-SLM,WT-PTS,and WT-SLM-GA methods is compared with that of the traditional NOMAbased SLM and PTS methods.The simulation results demonstrate that the proposed system effectively reduces PAPR in comparison with the traditional schemes.

关键词： PAPR wavelet transform NOMA PTS SLM 5G

来源：

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

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：