Federated learning (FL) is a collaborative learning paradigm where multiple clients are used to build the model without sharing data and preserving privacy. An FL-based linear regression model is designed to predict t...
详细信息
Federated learning (FL) is a collaborative learning paradigm where multiple clients are used to build the model without sharing data and preserving privacy. An FL-based linear regression model is designed to predict the length of stay for patients at hospitals using the low-power Arduino Nano 33 BLE Sense microcontroller unit (MCU). FL uses a distributed learning technique that allows model building from decentralized data sources. The Arduino Nano 33 BLE Sense is a compact and energy-efficient MCU providing an ideal platform for implementing FL in resource-constrained environments. FL algorithms aggregate model parameters from multiple Arduino clients and collectively train and build a predictive model to estimate the length of stay at the hospital by patients. Experiments were conducted to understand the performance of FL on clients with data of equal and varying sizes and heterogeneous data from multiple sources. The performance of the algorithm is evaluated based on Mean Absolute Error (MAE), Percentage Decrease in Training error (PDTE), and Percentage Difference with Optimal Testing (PDOT) value. Experimental results show that the number of local epochs and FL rounds affects the convergence of clients to the optimal value. The experimental results demonstrate the applicability of FL on low-power MCUs, preserving privacy which is a core requirement for healthcare solutions.
Background: The accuracy of any bioanalytical method depends on the selection of an appropriate calibration model. The most commonly used calibration model is the unweighted linearregression, where the response (y-ax...
详细信息
Background: The accuracy of any bioanalytical method depends on the selection of an appropriate calibration model. The most commonly used calibration model is the unweighted linearregression, where the response (y-axis) is plotted against the corresponding concentration (x-axis). The degree of association between these two variables is expressed in terms of correlation coefficient (r(2)). However, the satisfactory r(2) alone is not adequate to accept the calibration model. The wide calibration curve range used in the bioanalytical methods is susceptible to the heteroscedasticity of the calibration curve data. The use of weighted linearregression with an appropriate weighting factor reduces the heteroscedasticity and improves the accuracy over the selected concentration range. Methods: The present work describes a rapid and simple RP-HPLC method for the estimation of chlorthalidone in spiked human plasma. The calibration curve standards were studied in the concentration range of 100-3200ng/mL. The chromatography was performed on a C18 column (250x4.6mm, 5m) in an isocratic mode at a flow rate of 1mL/min using methanol:water (60:40%, v/v) as a mobile phase. The detection was carried out at 276nm. Both the unweighted regressionmodel and weighted regressionmodels with different weighting factors (1/x, 1/x, and 1/x(2)) were evaluated for heteroscedasticity. The statistical approach for the selection of a suitable regressionmodel with appropriate weighting factors was discussed and the developed bioanalytical method was further validated, as per US-FDA guidelines. Results: In calibration curve experiments, although the acceptable r(2) of 0.998 was obtained, the % residual plot showed that the data were susceptible to heteroscedasticity. When the weighted linearregression was applied to the same calibration curve data set, no significant difference between % relative residual (% RR) was observed. Furthermore, when % relative error (% RE) was calculated for different
In this paper, we investigate the limit of the eigenvector empirical spectral distribution (VESD) of large dimensional information plus noise matrices Cn = 1 n T1/2 n (Xn + Rn)(Xn + Rn)' T1/2 n , where Xn are p x ...
详细信息
In this paper, we investigate the limit of the eigenvector empirical spectral distribution (VESD) of large dimensional information plus noise matrices Cn = 1 n T1/2 n (Xn + Rn)(Xn + Rn)' T1/2 n , where Xn are p x n random matrices with independent and identically distributed entries, Tn and Rn are non-random matrices. It is shown that as p/n -> c E (0, oo), the VESD of Cn has a deterministic limit under some mild conditions. The theoretical result is applied to the model selection problems in high dimensional linear regression model. (c) 2023 Elsevier B.V. All rights reserved.
The district heating (DH) system consists of three basic elements - a heat source, heating network and heat consumers. All of these elements have a definite role in the overall development of the DH system. The transi...
详细信息
The district heating (DH) system consists of three basic elements - a heat source, heating network and heat consumers. All of these elements have a definite role in the overall development of the DH system. The transition to 4th generation DH (4GDH) involves changes in each of those elements that interact with each other. Therefore, various related processes form the potential energy savings and reduction of CO2 emissions when introducing 4GDH as whole system in all elements. To estimate the potential outcome from such projects it requires complex engineering calculations, which is not always possible without relevant expertise. The article describes a novel simplified methodology for evaluating the potential GHG emission reduction when implementing 4GDH. Thus, it is proposed to use a simplified calculation formula from linear regression model for the calculation of CO2 reduction.
Precise registration is very important in augmented *** magnetic tracking is a normal instrument to measure position and *** paper presents a novel registration method with linear regression model in augmented *** on ...
详细信息
Precise registration is very important in augmented *** magnetic tracking is a normal instrument to measure position and *** paper presents a novel registration method with linear regression model in augmented *** on the data,which are measured by the magnetic tracking,a linear regression model is set *** the linear regression model,the world coordinate and the magnetic tracking coordinate are *** theory analysis and simulation prove the feasibility of this brand new *** system is more precise and robust with linear regression model.
In response to water scarcity, Morocco faces the challenge of using treated wastewater for irrigation purposes. This study evaluates the efficiency of a full-scale trickling filter (TF) system in Imintanout, Morocco. ...
详细信息
In response to water scarcity, Morocco faces the challenge of using treated wastewater for irrigation purposes. This study evaluates the efficiency of a full-scale trickling filter (TF) system in Imintanout, Morocco. The system consists of three septic tanks, two TFs, and secondary decanters. Over a 5-year period, the system showed significant reductions in pollutants: 98 % of TSS, 94 % of BOD5, 98 % of COD, 41 % of TP, and 88 % of NH4+, with these reductions being statistically significant at the 95 % confidence level. A multiple linearregression (MLR) model successfully predicted the removal of fecal coliform (FC) by the TF, and a reduction of 2.88 log units was achieved. High cos2 values indicated the importance of hydraulic loading rate (HLR), BOD5, and FC, which were particularly affected by seasonal variations. Positive correlations between FC and TSS in certain periods highlight the seasonal variability in the composition of urban wastewater, which is effectively captured by the MLR model (R2 = 0.77). Although the treated water complied with Moroccan discharge standards, its high nitrate (140 mg L-1) and FC (4.32 log units) levels made it unsuitable for reuse in agricultural and landscape irrigation, as they exceeded safety limits. This work highlights the importance of optimizing treatment systems to produce high quality reclaimed water, which is essential to meet the challenges of water scarcity.
The stochastic restricted r-k class estimator and stochastic restricted r-d class estimator are proposed for the vector of parameters in a multiple linear regression model with stochastic linear restrictions. The mean...
详细信息
The stochastic restricted r-k class estimator and stochastic restricted r-d class estimator are proposed for the vector of parameters in a multiple linear regression model with stochastic linear restrictions. The mean squared error matrix of the proposed estimators is derived and compared, and some properties of the proposed estimators are also discussed. Finally, a numerical example is given to show some of the theoretical results.
After years of fast economic development in China,urbanization has lifted the housing demand in urban cities to a significant *** as the capital city in China is where the house prices jumped the *** investigate how v...
详细信息
After years of fast economic development in China,urbanization has lifted the housing demand in urban cities to a significant *** as the capital city in China is where the house prices jumped the *** investigate how various factors affect the house prices in Beijing,10 factors both from the demand side and the supply side are being *** this paper,a linear regression model is constructed for predicting the Beijing house prices by using the R programming *** the demand side,factors include the number of permanent populations,average disposable income of Beijing urban residents,Beijing consumer price index,the average GDP per capita,household saving deposit balance,balance of loans and the debt base *** the supply side,factors include urban residential floor area per capita,total investments in Beijing urban area,and the urban building completed area.10 factors are narrowed into 3 after comparing their multicollinearity,reached a foundation for next regression *** a series of optimization,this paper concludes a final model for predicting the Beijing house prices accompany with a comparison between a full model and model added with log transformation.
Test score is the main criteria to measure the learning effort of *** are many factors may improve or lower the test score or examination results,such as classroom attendance,home work,communication and interaction,te...
详细信息
Test score is the main criteria to measure the learning effort of *** are many factors may improve or lower the test score or examination results,such as classroom attendance,home work,communication and interaction,teaching methods,self-learning,review,discussion,*** is very important to teachers and students to figure out the inherent correlation between test score and these *** this paper,a research on correlation analysis between test score and classroom attendance based on linear regression model is *** analysis is introduced and the curves of correlation between test score and classroom attendance are ploted based on the test score and classroom attendance records during two *** scatter diagram and linear regression model of three courses indicate that the test score or examination results closely related to the classroom attendance.
It is very important to scientifically predict the consumption of aviation equipment maintenance material and to make scientific decisions on aviation equipment maintenance resources and make full use of existing reso...
详细信息
It is very important to scientifically predict the consumption of aviation equipment maintenance material and to make scientific decisions on aviation equipment maintenance resources and make full use of existing resources to improve maintenance capability. In this paper, aiming at the main influencing factors of material consumption of aviation equipment maintenance, a linearregression prediction model of equipment maintenance material consumption was constructed by using actual statistical sample data. Based on the analysis of examples, the simple linearregression method is used to predict and test the material consumption of aviation equipment maintenance materials. The research results provide a scientific and effective method for forecasting the consumption of aviation equipment maintenance materials.
暂无评论