scholarly journals An IoT enabled system for enhanced air quality monitoring and prediction on the edge

2021 ◽  
Author(s):  
Ahmed Samy Moursi ◽  
Nawal El-Fishawy ◽  
Soufiene Djahel ◽  
Marwa Ahmed Shouman
Keyword(s):  
Air Pollution ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Heart Diseases ◽  
Air Pollutant ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Remote Areas ◽  
The Past

AbstractAir pollution is a major issue resulting from the excessive use of conventional energy sources in developing countries and worldwide. Particulate Matter less than 2.5 µm in diameter (PM2.5) is the most dangerous air pollutant invading the human respiratory system and causing lung and heart diseases. Therefore, innovative air pollution forecasting methods and systems are required to reduce such risk. To that end, this paper proposes an Internet of Things (IoT) enabled system for monitoring and predicting PM2.5 concentration on both edge devices and the cloud. This system employs a hybrid prediction architecture using several Machine Learning (ML) algorithms hosted by Nonlinear AutoRegression with eXogenous input (NARX). It uses the past 24 h of PM2.5, cumulated wind speed and cumulated rain hours to predict the next hour of PM2.5. This system was tested on a PC to evaluate cloud prediction and a Raspberry Pi to evaluate edge devices’ prediction. Such a system is essential, responding quickly to air pollution in remote areas with low bandwidth or no internet connection. The performance of our system was assessed using Root Mean Square Error (RMSE), Normalized Root Mean Square Error (NRMSE), coefficient of determination (R2), Index of Agreement (IA), and duration in seconds. The obtained results highlighted that NARX/LSTM achieved the highest R2 and IA and the least RMSE and NRMSE, outperforming other previously proposed deep learning hybrid algorithms. In contrast, NARX/XGBRF achieved the best balance between accuracy and speed on the Raspberry Pi.

scholarly journals Authentication of Patin Fish Oil (Pangasius micronemus) using FTIR Spectroscopy Combined with Chemometrics

2020 ◽  
pp. 23
Author(s):  
Anggita Rosiana Putri ◽  
Abdul Rohman ◽  
Sugeng Riyanto ◽  
Widiastuti Setyaningsih
Keyword(s):  
Root Mean Square Error ◽  
Fish Oil ◽  
Ftir Spectroscopy ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Coefficient Of Determination ◽  
Mean Square

Authentication of Patin fish oil (MIP) is essential to prevent adulteration practice, to ensure quality, nutritional value, and product safety. The purpose of this study is to apply the FTIR spectroscopy combined with chemometrics for MIP authentication. The chemometrics method consists of principal component regression (PCR) and partial least square regression (PLSR). PCR and PLSR were used for multivariate calibration, while for grouping the samples using discriminant analysis (DA) method. In this study, corn oil (MJ) was used as an adulterate. Twenty-one mixed samples of MIP and MJ were prepared with the adulterate concentration range of 0-50%. The best authentication model was obtained using the PLSR technique using the first derivative of FTIR spectra at a wavelength of 650-3432 cm-1. The coefficient of determination (R2) for calibration and validation was obtained 0.9995 and 1.0000, respectively. The value of root mean square error of calibration (RMSEC) and root mean square error of prediction (RMSEP) were 0.397 and 0.189. This study found that the DA method can group the samples with an accuracy of 99.92%.

Estimating Center of Mass Kinematics During Perturbed Human Standing Using Accelerometers

2021 ◽  
pp. 1-10
Author(s):  
Sandra K. Hnat ◽  
Musa L. Audu ◽  
Ronald J. Triolo ◽  
Roger D. Quinn
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Mean Squared Error ◽  
Balance Control ◽  
Center Of Mass ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Cord Injury ◽  
Movement Type

Estimating center of mass (COM) through sensor measurements is done to maintain walking and standing stability with exoskeletons. The authors present a method for estimating COM kinematics through an artificial neural network, which was trained by minimizing the mean squared error between COM displacements measured by a gold-standard motion capture system and recorded acceleration signals from body-mounted accelerometers. A total of 5 able-bodied participants were destabilized during standing through: (1) unexpected perturbations caused by 4 linear actuators pulling on the waist and (2) volitionally moving weighted jars on a shelf. Each movement type was averaged across all participants. The algorithm’s performance was quantified by the root mean square error and coefficient of determination (R2) calculated from both the entire trial and during each perturbation type. Throughout the trials and movement types, the average coefficient of determination was 0.83, with 89% of the movements with R2 > .70, while the average root mean square error ranged between 7.3% and 22.0%, corresponding to 0.5- and 0.94-cm error in both the coronal and sagittal planes. COM can be estimated in real time for balance control of exoskeletons for individuals with a spinal cord injury, and the procedure can be generalized for other gait studies.

scholarly journals Estimating Maximum Daily Precipitation in the Upper Vistula Basin, Poland

Atmosphere ◽  
2019 ◽  
Vol 10 (2) ◽  
pp. 43 ◽  
Author(s):  
Dariusz Młyński ◽  
Andrzej Wałęga ◽  
Andrea Petroselli ◽  
Flavia Tauro ◽  
Marta Cebulska
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Goodness Of Fit ◽  
Daily Precipitation ◽  
Probability Distributions ◽  
Random Variables ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Probability Of Exceedance

The aim of this study was to determine the best probability distributions for calculating the maximum annual daily precipitation with the specific probability of exceedance (Pmaxp%). The novelty of this study lies in using the peak-weighted root mean square error (PWRMSE), the root mean square error (RMSE), and the coefficient of determination (R2) for assessing the fit of empirical and theoretical distributions. The input data included maximum daily precipitation records collected in the years 1971–2014 at 51 rainfall stations from the Upper Vistula Basin, Southern Poland. The value of Pmaxp% was determined based on the following probability distributions of random variables: Pearson’s type III (PIII), Weibull’s (W), log-normal, generalized extreme value (GEV), and Gumbel’s (G). Our outcomes showed a lack of significant trends in the observation series of the investigated random variables for a majority of the rainfall stations in the Upper Vistula Basin. We found that the peak-weighted root mean square error (PWRMSE) method, a commonly used metric for quality assessment of rainfall-runoff models, is useful for identifying the statistical distributions of the best fit. In fact, our findings demonstrated the consistency of this approach with the RMSE goodness-of-fit metrics. We also identified the GEV distribution as recommended for calculating the maximum daily precipitation with the specific probability of exceedance in the catchments of the Upper Vistula Basin.

scholarly journals Using Multi-Temporal MODIS NDVI Data to Monitor Tea Status and Forecast Yield: A Case Study at Tanuyen, Laichau, Vietnam

2020 ◽  
Vol 12 (11) ◽  
pp. 1814
Author(s):  
Phamchimai Phan ◽  
Nengcheng Chen ◽  
Lei Xu ◽  
Zeqiang Chen
Keyword(s):  
Remote Sensing ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Vegetation Index ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Mean Square ◽  
Multi Temporal

Tea is a cash crop that improves the quality of life for people in the Tanuyen District of Laichau Province, Vietnam. Tea yield, however, has stagnated in recent years, due to changes in temperature, precipitation, the age of the tea bushes, and diseases. Developing an approach for monitoring tea bushes by remote sensing and Geographic Information Systems (GIS) might be a way to alleviate this problem. Using multi-temporal remote sensing data, the paper details an investigation of the changes in tea health and yield forecasting through the normalized difference vegetation index (NDVI). In this study, we used NDVI as a support tool to demonstrate the temporal and spatial changes in NDVI through the extract tea NDVI value and calculate the mean NDVI value. The results of the study showed that the minimum NDVI value was 0.42 during January 2013 and February 2015 and 2016. The maximum NDVI value was in August 2015 and June 2017. We indicate that the linear relationship between NDVI value and mean temperature was strong with R 2 = 0.79 Our results confirm that the combination of meteorological data and NDVI data can achieve a high performance of yield prediction. Three models to predict tea yield were conducted: support vector machine (SVM), random forest (RF), and the traditional linear regression model (TLRM). For period 2009 to 2018, the prediction tea yield by the RF model was the best with a R 2 = 0.73 , by SVM it was 0.66, and 0.57 with the TLRM. Three evaluation indicators were used to consider accuracy: the coefficient of determination ( R 2 ), root-mean-square error (RMSE), and percentage error of tea yield (PETY). The highest accuracy for the three models was in 2015 with a R 2 ≥ 0.87, RMSE < 50 kg/ha, and PETY less 3% error. In the other years, the prediction accuracy was higher in the SVM and RF models. Meanwhile, the RF algorithm was better than PETY (≤10%) and the root mean square error for this algorithm was significantly less (≤80 kg/ha). RMSE and PETY showed relatively good values in the TLRM model with a RMSE from 80 to 100 kg/ha and a PETY from 8 to 15%.

scholarly journals Applicability of Near Infrared Reflectance Spectroscopy to Predict Amylose Contents of Single-Grain Maize

Agronomy ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 2463
Author(s):  
Qing Dong ◽  
Qianqian Xu ◽  
Jiandong Wu ◽  
Beijiu Cheng ◽  
Haiyang Jiang
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared ◽  
Reflectance Spectroscopy ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Near Infrared Reflectance ◽  
Single Grain ◽  
Single Seeds

Near infrared reflectance spectroscopy (NIRS) and reference data were used to determine the amylose contents of single maize seeds to enable rapid, effective selection of individual seeds with desired traits. To predict the amylose contents of a single seed, a total of 1069 (865 as calibration set, 204 as validation set) single seeds representing 120 maize varieties were analyzed using chemical methods and performed calibration and external validation of the 150 single seeds set in parallel. Compared to various spectral pretreatments, the regression of partial least squares (PLS) with mathematical treatment of Harmonization showed the final optimization. The single-seed amylose contents showed the root mean square error of calibration (RMSEC) of 2.899, coefficient of determination for calibration (R2) of 0.902, and root mean square error of validation (RMSEV) of 2.948. In external validations, the coefficient of determination in cross-validation (r2), root mean square error of the prediction (RMSEP) and ratio of the standard deviation to SEP (RPD) were 0.892, 2.975 and 3.086 in the range of 20–30%, respectively. Therefore, NIRS will be helpful to breeders for determining the amylose contents of single-grain maize.

DRYING KINETICS AND MOISTURE DIFFUSIVITY OF FOUR VARIETIES OF BAMBARA BEANS

2021 ◽  
Vol 6 (1) ◽  
pp. 30-33
Author(s):  
E.O. Awotona ◽  
A.O. Alade ◽  
S.A. Adebanjo ◽  
O. Duduyemi ◽  
T.J. Afolabi
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Goodness Of Fit ◽  
Moisture Diffusivity ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Fit Statistics ◽  
Drying Behavior ◽  
Maximum Coefficient

Drying of bambara beans was studied at 40oC at every 30 minutes in a Laboratory oven. Effective moisture diffusivity ranges between 5.886 x 10-10 m2/s – 4.354 x 10-10 m2/s respectively. The statistical criteria used in evaluation of the model were maximum coefficient of determination R2 and minimum root mean square error [RMSE]. Determination for goodness of fit statistics for drying of the beans was carried out. Midilli model was used to predict the drying curve. The Midili model was found to produce accurate predictions for all the four varieties of bambara beans and the model was shown to be an excellent model for predicting drying behavior of TVSU-47 and the R2 value was 0.9971 and the value of root mean square error was 0.0149 respectively.

Detailed Dynamic Model of an Institutional Building in Hot and Humid Climate Conditions

2017 ◽  
Author(s):  
Junaid Bin Masood ◽  
Sajid Hussain ◽  
Ali AlAlili ◽  
Sara Zaidan ◽  
Ebrahim Al Hajri
Keyword(s):  
Energy Consumption ◽  
Root Mean Square Error ◽  
Dynamic Model ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Building Envelope ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Audit Process ◽  
Simulation Engine

This paper is an ASHRAE Level 3 study of the energy audit process carried out in an institutional building, The Umm Shaif Building, of The Petroleum Institute, Abu Dhabi, UAE. It undertakes the study by collecting data and conditional surveys. The energy loss locations are highlighted through psychrometric and infrared camera analysis. The detailed dynamic model has been simulated using the EnergyPlus® simulation engine. The details of the building envelope, and fenestration, the occupancy schedules, the equipment energy consumption and HVAC details are presented. The detailed building model is used to allocate the energy usage and identify key energy consumers. The main results are reported using monthly total energy consumption. The validation and calibration are performed through different statistical metrics including Coefficient of Determination (R2), Root Mean Square Error (RMSE) and Coefficient of Variance Root Mean Square Error (CVRMSE). Finally, energy conservation measures are suggested with the energy and cost savings.

scholarly journals Potential of Multivariate Statistical Technique Based on the Effective Spectra Bands to Estimate the Plant Water Content of Wheat Under Different Irrigation Regimes

2021 ◽  
Vol 12 ◽  
Author(s):  
Hui Sun ◽  
Meichen Feng ◽  
Lujie Xiao ◽  
Wude Yang ◽  
Guangwei Ding ◽  
...  
Keyword(s):  
Root Mean Square Error ◽  
Winter Wheat ◽  
Water Content ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Coefficient Of Determination ◽  
Plant Water ◽  
Mean Square ◽  
Proximal Sensing ◽  
Sensing Data

Real-time, nondestructive, and accurate estimation of plant water status is important to the precision irrigation of winter wheat. The objective of this study was to develop a method to estimate plant water content (PWC) by using canopy spectral proximal sensing data. Two experiments under different water stresses were conducted in 2014–2015 and 2015–2016. The PWC and canopy reflectance of winter wheat were collected at different growth stages (the jointing, booting, heading, flowering, and filling stages in 2015 and the jointing, booting, flowering, and filling stages in 2016). The performance of different spectral transformation approaches was further compared. Based on the optimal pretreatment, partial least squares regression (PLSR) and four combination methods [i.e., PLSR-stepwise regression (SR), PLSR-successive projections algorithm (SPA), PLSR-random frog (RF), and PLSR-uninformative variables elimination (UVE)] were used to extract the sensitive bands of PWC. The results showed that all transformed spectra were closely correlated to PWC. The PLSR models based on the first derivative transformation method exhibited the best performance (coefficient of determination in calibration, R2C = 0.96; root mean square error in calibration, RMSEC = 20.49%; ratio of performance to interquartile distance in calibration, RPIQC = 9.19; and coefficient of determination in validation, R2V = 0.86; root mean square error in validation, RMSEV = 46.27%; ratio of performance to interquartile distance in validation, RPIQV = 4.34). Among the combination models, the PLSR model established with the sensitive bands from PLSR-RF demonstrated a good performance for calibration and validation (R2C = 0.99, RMSEC = 11.53%, and RPIQC = 16.34; and R2V = 0.84, RMSEV = 44.40%, and RPIQV = 4.52, respectively). This study provides a theoretical basis and a reference for estimating PWC of winter wheat by using canopy spectral proximal sensing data.

Fractional order calculus approach for drying modeling of eggplants

2019 ◽  
Vol 26 (5) ◽  
pp. 379-387
Author(s):  
Koksal Erenturk ◽  
Bircan Kose ◽  
Saliha Erenturk
Keyword(s):  
Regression Analysis ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Fractional Order ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Fractional Order Calculus ◽  
Squared Error ◽  
Drying Conditions

In order to determine the drying modeling of eggplants, fractional order calculus modeling was applied and compared to regression analysis in this study. The fractional order calculus based on the Caputo derivative approach was considered and applied for modeling of eggplant drying. The drying experiments were performed on three levels of drying air temperatures (60, 70, and 80 ℃), with two different air flow velocity levels (0.5 and 1 m/s), and three levels of thickness (3.5, 6.5, and 9.5 mm) to measure the effects of different drying conditions for eggplants in a convective dryer. Four different commonly used mathematical models from the literature were fitted to the experimental data with regression analysis. Based on obtained results, the coefficient of determination (R2) was found as 0.9956 for the values of 80 ℃, 0.5 m/s, and 3.5 mm, while sum squared error was 0.0061 and root mean square error was 0.0235 for the Page model. However, better and more accurate results were obtained using fractional order modeling with the values of R2 found as 0.9981, sum squared error as 0.0012, and root mean square error as 0.0099 for the considered case.

scholarly journals Alternative reference evapotranspiration methods for the main climate types of the state of Paraná, Brazil

2018 ◽  
Vol 53 (9) ◽  
pp. 1003-1010 ◽  
Author(s):  
Bruno César Gurski ◽  
Daniela Jerszurki ◽  
Jorge Luiz Moretti de Souza
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Reference Evapotranspiration ◽  
The State ◽  
Alternative Methods ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Standard Values

Abstract: The objective of this work was to define the best alternative methods for estimating the reference evapotranspiration (ETo) in the main climatic types (Cfa and Cfb) of the state of Paraná, Brazil. The methods tested were Budyko, Camargo, Hargreaves-Samani, Linacre, and Thornthwaite, which were compared to the ETo calculated with the Penman-Monteith ASCE (EToPM) method, between 1986 and 2015, in eight meteorological stations. The performance of the alternative methods was obtained from the coefficient of determination (R2), index “d” of agreement, index “c” of performance, and root mean square error (RMSE). The Hargreaves-Samani method has a better performance in estimating the ETo for the main climatic types in the state of Paraná. The Camargo method allows smaller errors between the standard values of ETo, obtained with the Penman-Monteith method, and the estimated values. The methods of Thornthwaite, Linacre, and Budyko are not adequate to estimate the ETo in any climatic type of the state of Paraná, Brazil.

Sign in / Sign up

Export Citation Format

Share Document