Quantitative Detection of Chromium Pollution in Biochar Based on Matrix Effect Classification Regression Model

Returning biochar to farmland has become one of the nationally promoted technologies for soil remediation and improvement in China. Rapid detection of heavy metals in biochar derived from varied materials can provide a guarantee for contaminated soil, avoiding secondary pollution. This work aims first to apply laser-induced breakdown spectroscopy (LIBS) for the quantitative detection of Cr in biochar. Learning from the principles of traditional matrix effect correction methods, calibration samples were divided into 1–3 classifications by an unsupervised hierarchical clustering method based on the main elemental LIBS data in biochar. The prediction samples were then divided into diverse classifications of calibration samples by a supervised K-nearest neighbor (KNN) algorithm. By comparing the effects of multiple partial least squares regression (PLSR) models, the results show that larger numbered classifications have a lower averaged relative standard deviations of cross-validation (ARSDCV) value, signifying a better calibration performance. Therefore, the 3 classification regression model was employed in this study, which had a better prediction performance with a lower averaged relative standard deviations of prediction (ARSDP) value of 8.13%, in comparison with our previous research and related literature results. The LIBS technology combined with matrix effect classification regression model can weaken the influence of the complex matrix effect of biochar and achieve accurate quantification of contaminated metal Cr in biochar.

Download Full-text

Quantitative Determination of Cd in Soil Using Laser-Induced Breakdown Spectroscopy in Air and Ar Conditions

Molecules ◽

10.3390/molecules23102492 ◽

2018 ◽

Vol 23 (10) ◽

pp. 2492 ◽

Cited By ~ 8

Author(s):

Xiaodan Liu ◽

Fei Liu ◽

Weihao Huang ◽

Jiyu Peng ◽

Tingting Shen ◽

...

Keyword(s):

Heavy Metal ◽

Least Squares ◽

Three Dimensional ◽

Accurate Method ◽

Laser Induced Breakdown Spectroscopy ◽

Quantitative Detection ◽

Support Vector ◽

Least Squares Regression ◽

Breakdown Spectroscopy ◽

Laser Induced Breakdown

Rapid detection of Cd content in soil is beneficial to the prevention of soil heavy metal pollution. In this study, we aimed at exploring the rapid quantitative detection ability of laser- induced breakdown spectroscopy (LIBS) under the conditions of air and Ar for Cd in soil, and finding a fast and accurate method for quantitative detection of heavy metal elements in soil. Spectral intensity of Cd and system performance under air and Ar conditions were analyzed and compared. The univariate model and multivariate models of partial least-squares regression (PLSR) and least-squares support vector machine (LS-SVM) of Cd under the air and Ar conditions were built, and the LS-SVM model under the Ar condition obtained the best performance. In addition, the principle of influence of Ar on LIBS detection was investigated by analyzing the three-dimensional profile of the ablation crater. The overall results indicated that LIBS combined with LS-SVM under the Ar condition could be a useful tool for the accurate quantitative detection of Cd in soil and could provide reference for environmental monitoring.

Download Full-text

Correction: Accuracy improvement of boron by molecular emission with a genetic algorithm and partial least squares regression model in laser-induced breakdown spectroscopy

Journal of Analytical Atomic Spectrometry ◽

10.1039/d0ja90043e ◽

2020 ◽

Vol 35 (7) ◽

pp. 1498-1498

Author(s):

Zhihao Zhu ◽

Jiaming Li ◽

Yangmin Guo ◽

Xiao Cheng ◽

Yun Tang ◽

...

Keyword(s):

Genetic Algorithm ◽

Regression Model ◽

Least Squares ◽

Partial Least Squares ◽

Partial Least Squares Regression ◽

Laser Induced Breakdown Spectroscopy ◽

Least Squares Regression ◽

Accuracy Improvement ◽

Breakdown Spectroscopy ◽

Laser Induced Breakdown

Correction for ‘Accuracy improvement of boron by molecular emission with a genetic algorithm and partial least squares regression model in laser-induced breakdown spectroscopy’ by Zhihao Zhu et al., J. Anal. At. Spectrom., 2018, 33, 205–209, DOI: 10.1039/C7JA00356K.

Download Full-text

Moisture Analysis in Forage by Near-Infrared Reflectance Spectroscopy: Collaborative Study of Calibration Methodology

Journal of AOAC INTERNATIONAL ◽

10.1093/jaoac/74.2.324 ◽

1991 ◽

Vol 74 (2) ◽

pp. 324-331

Author(s):

William R Windham ◽

Franklin E Barton

Keyword(s):

Near Infrared ◽

Collaborative Study ◽

Calibration Method ◽

Reflectance Spectroscopy ◽

Near Infrared Reflectance ◽

Moisture Concentration ◽

Moisture Analysis ◽

Relative Standard ◽

Calibration Samples ◽

Standard Deviations

Abstract Fifteen collaborating laboratories analyzed 16 forage samples including 3 blind duplicate pairs for moisture by air-oven (AO) method 7.007 (14th Ed.; 930.15, 15th Ed.) and nearinfrared reflectance spectroscopy (NIRS). Laboratories performed method 7.007 on 50 calibration samples and applied the NIRS calibration method Independently. NIRS moisture equations were used to predict the 16 test samples, and the values were compared to those for method 7.007. Moisture concentration of the test samples ranged from approximately 6 to 16%. Within-laboratory repeatability (sr) ranged from 0.10 to 0.18% and 0.16 to 0.39% for NIRS and method 7.007, respectively. Between-laboratory reproducibility (sR) ranged from 0.22 to 0.57 and 0.29 to 0.57 for NIRS and method 7.007, respectively. Repeatability relative standard deviations (RSDr) for the NIRS and AO methods ranged from 1.18 to 1.50% and 1.84 to 3.68%, respectively. The range in the average reproducibility relative standard deviations (RSDR) for the NIRS and AO methods were 1.29-7.49% and 3.64-6.66%, respectively. The NIRS method demonstrated consistently lower wlthln-laboratory RSDr agreement and between-laboratory variabilities equal to method 7.007. Thereby, we demonstrated that NIRS can be used as a standard method for the determination of 6-16% moisture In forages. The method has been adopted official first action by A0AC.

Download Full-text

Use of Local Linear Regression Model for Short-Term Traffic Forecasting

Transportation Research Record Journal of the Transportation Research Board ◽

10.3141/1836-18 ◽

2003 ◽

Vol 1836 (1) ◽

pp. 143-150 ◽

Cited By ~ 105

Author(s):

Hongyu Sun ◽

Henry X. Liu ◽

Heng Xiao ◽

Rachel R. He ◽

Bin Ran

Keyword(s):

Linear Regression ◽

Regression Model ◽

Linear Regression Model ◽

Nearest Neighbor ◽

Time Of Day ◽

Local Linear Regression ◽

K Nearest Neighbor ◽

Short Term ◽

Traffic Forecasting ◽

Local Linear

The traffic-forecasting model, when considered as a system with inputs of historical and current data and outputs of future data, behaves in a nonlinear fashion and varies with time of day. Traffic data are found to change abruptly during the transition times of entering and leaving peak periods. Accurate and real-time models are needed to approximate the nonlinear time-variant functions between system inputs and outputs from a continuous stream of training data. A proposed local linear regression model was applied to short-term traffic prediction. The performance of the model was compared with previous results of nonparametric approaches that are based on local constant regression, such as the k-nearest neighbor and kernel methods, by using 32-day traffic-speed data collected on US-290, in Houston, Texas, at 5-min intervals. It was found that the local linear methods consistently showed better performance than the k-nearest neighbor and kernel smoothing methods.

Download Full-text

SCMTHP: A New Approach for Identifying and Characterizing of Tumor-Homing Peptides Using Estimated Propensity Scores of Amino Acids

Pharmaceutics ◽

10.3390/pharmaceutics14010122 ◽

2022 ◽

Vol 14 (1) ◽

pp. 122

Author(s):

Phasit Charoenkwan ◽

Wararat Chiangjong ◽

Chanin Nantasenamat ◽

Mohammad Ali Moni ◽

Pietro Lio’ ◽

...

Keyword(s):

Amino Acids ◽

Propensity Scores ◽

Nearest Neighbor ◽

Biochemical Properties ◽

Least Squares Regression ◽

K Nearest Neighbor ◽

Accurate Identification ◽

Major Drawback ◽

Benchmark Datasets ◽

Tumor Homing

Tumor-homing peptides (THPs) are small peptides that can recognize and bind cancer cells specifically. To gain a better understanding of THPs’ functional mechanisms, the accurate identification and characterization of THPs is required. Although some computational methods for in silico THP identification have been proposed, a major drawback is their lack of model interpretability. In this study, we propose a new, simple and easily interpretable computational approach (called SCMTHP) for identifying and analyzing tumor-homing activities of peptides via the use of a scoring card method (SCM). To improve the predictability and interpretability of our predictor, we generated propensity scores of 20 amino acids as THPs. Finally, informative physicochemical properties were used for providing insights on characteristics giving rise to the bioactivity of THPs via the use of SCMTHP-derived propensity scores. Benchmarking experiments from independent test indicated that SCMTHP could achieve comparable performance to state-of-the-art method with accuracies of 0.827 and 0.798, respectively, when evaluated on two benchmark datasets consisting of Main and Small datasets. Furthermore, SCMTHP was found to outperform several well-known machine learning-based classifiers (e.g., decision tree, k-nearest neighbor, multi-layer perceptron, naive Bayes and partial least squares regression) as indicated by both 10-fold cross-validation and independent tests. Finally, the SCMTHP web server was established and made freely available online. SCMTHP is expected to be a useful tool for rapid and accurate identification of THPs and for providing better understanding on THP biophysical and biochemical properties.

Download Full-text

Detection of Sclerotinia Stem Rot on Oilseed Rape (Brassica napus L.) Based on Laser- Induced Breakdown Spectroscopy

Transactions of the ASABE ◽

10.13031/trans.12206 ◽

2019 ◽

Vol 62 (1) ◽

pp. 123-130

Author(s):

Fei Liu ◽

Tingting Shen ◽

Jian Wang ◽

Yong He ◽

...

Keyword(s):

Oilseed Rape ◽

Nearest Neighbor ◽

Emission Lines ◽

Stem Rot ◽

Laser Induced Breakdown Spectroscopy ◽

Sclerotinia Stem Rot ◽

K Nearest Neighbor ◽

Brassica Napus L ◽

Breakdown Spectroscopy ◽

Laser Induced Breakdown

Abstract. In this study, a novel approachser-induced breakdown spectroscopy (LIBS) is proposed to rapidly diagnose stem rot (SSR) in oilseed rape ( L.). A rapid diagnostic method is important to prevent this worldwide disease and promote growth of oilseed rape. A total of 120 fresh leaves, including 60 healthy and 60 SSR-infected leaves, were collected to acquire LIBS spectra. Robust baseline estimation (RBE) and wavelet transform (WT) were applied to preprocess the raw LIBS spectra for baseline correction and denoising. K-nearest neighbor (KNN), radial basis function neural network (RBFNN), random forest (RF), and extreme learning machine (ELM) methods combining full LIBS spectra were chosen to establish classification models to identify healthy and SSR-infected leaves, and the ELM model obtained classified accuracy of more than 80.00% in the prediction set. Twenty-four emission lines were selected by second-derivative spectra as the most relevant to distinguish healthy and SSR-infected leaves. The ELM model using the optimal emission lines improved the classified accuracy to more than 85% and the specificity to 95.00%. Compared with full-spectra models, the number of variables in the models based on optimal wavelengths was reduced from 22,036 to 24, a reduction of 99.89%. This study indicates that LIBS combined with appropriate chemometric m. Keywords: Chemometrics, Laser-induced breakdown spectroscopy, Oilseed rape, Sclerotinia stem rot.

Download Full-text

A generalized fuzzy k-nearest neighbor regression model based on Minkowski distance

Granular Computing ◽

10.1007/s41066-021-00288-w ◽

2021 ◽

Author(s):

Mahinda Mailagaha Kumbure ◽

Pasi Luukka

Keyword(s):

Regression Model ◽

Euclidean Distance ◽

Nearest Neighbor ◽

Weighted Average ◽

Nearest Neighbors ◽

Manhattan Distance ◽

K Nearest Neighbor ◽

Minkowski Distance ◽

Regression Methods ◽

Target Sample

AbstractThe fuzzy k-nearest neighbor (FKNN) algorithm, one of the most well-known and effective supervised learning techniques, has often been used in data classification problems but rarely in regression settings. This paper introduces a new, more general fuzzy k-nearest neighbor regression model. Generalization is based on the usage of the Minkowski distance instead of the usual Euclidean distance. The Euclidean distance is often not the optimal choice for practical problems, and better results can be obtained by generalizing this. Using the Minkowski distance allows the proposed method to obtain more reasonable nearest neighbors to the target sample. Another key advantage of this method is that the nearest neighbors are weighted by fuzzy weights based on their similarity to the target sample, leading to the most accurate prediction through a weighted average. The performance of the proposed method is tested with eight real-world datasets from different fields and benchmarked to the k-nearest neighbor and three other state-of-the-art regression methods. The Manhattan distance- and Euclidean distance-based FKNNreg methods are also implemented, and the results are compared. The empirical results show that the proposed Minkowski distance-based fuzzy regression (Md-FKNNreg) method outperforms the benchmarks and can be a good algorithm for regression problems. In particular, the Md-FKNNreg model gave the significantly lowest overall average root mean square error (0.0769) of all other regression methods used. As a special case of the Minkowski distance, the Manhattan distance yielded the optimal conditions for Md-FKNNreg and achieved the best performance for most of the datasets.

Download Full-text

Determination of Heating Value of Estonian Oil Shale by Laser-Induced Breakdown Spectroscopy

Journal of Spectroscopy ◽

10.1155/2018/4605925 ◽

2018 ◽

Vol 2018 ◽

pp. 1-10 ◽

Cited By ~ 2

Author(s):

M. Aints ◽

P. Paris ◽

M. Laan ◽

K. Piip ◽

H. Riisalu ◽

...

Keyword(s):

Regression Model ◽

Oil Shale ◽

Optimal Number ◽

Spectral Lines ◽

Laser Induced Breakdown Spectroscopy ◽

Least Squares Regression ◽

Heating Value ◽

Breakdown Spectroscopy ◽

Laser Induced Breakdown

The laser-induced breakdown spectroscopy (LIBS) combined with multivariate regression analysis of measured data were utilised for determination of the heating value and the chemical composition of pellets made from Estonian oil shale samples with different heating values. The study is the first where the oil shale heating value is determined on the basis of LIBS spectra. The method for selecting the optimal number of spectral lines for ordinary multivariate least squares regression model is presented. The correlation coefficient between the heating value predicted by the regression model, and that measured by calorimetric bomb, was R2=0.98. The standard deviation of prediction was 0.24 MJ/kg. Concentrations of oil shale components predicted by the regression model were compared with those measured by ordinary methods.

Download Full-text

Property Mass Valuation on Small Markets

Land ◽

10.3390/land10040388 ◽

2021 ◽

Vol 10 (4) ◽

pp. 388

Author(s):

Sebastian Gnat

Keyword(s):

Machine Learning ◽

Regression Model ◽

Multiple Regression ◽

Nearest Neighbor ◽

Multiple Regression Model ◽

K Nearest Neighbor ◽

Real Property ◽

Explanatory Variables ◽

Land Taxation ◽

Land Valuation

The main bases for land taxation are its area or value. In many countries, especially in Eastern Europe, reforms of property taxation, including land taxation, are being carried out or planned, introducing property value as a tax base. Practice and research in this area indicate that such a change in the tax system leads to large changes in land use and reallocation. The taxation of land value requires construction of mass valuation system. Different methodological solutions can serve this purpose. However, mass land valuation requires a large amount of information on property transactions. Such data are not available in every case. The main objective of the paper is to evaluate the possibility of applying selected algorithms of machine learning and a multiple regression model in property mass valuation on small, underdeveloped markets, where a scarce number of transactions takes place or those transactions demonstrate little volatility in terms of real property attributes. A hypothesis is verified according to which machine learning methods result in more accurate appraisals than multiple regression models do, considering the size of training datasets. Three types of models were employed in the study: a multiple regression model, k nearest neighbor regression algorithm and XGBoost regression algorithm. Training sets were drawn from a larger dataset 1000 times in order to draw conclusions for averaged results. Thanks to the application of KNN and XGBoost algorithms, it was possible to obtain models much more resistant to a low number of observations, a substantial number of explanatory variables in relation to the number of observations, a low property attributes variability in the training datasets as well as collinearity of explanatory variables. This study showed that algorithms designed for large datasets can provide accurate results in the presence of a limited amount of data. This is a significant observation given that small or underdeveloped real estate markets are not uncommon.

Download Full-text