Rapid differentiation of Ghana cocoa beans by FT-NIR spectroscopy coupled with multivariate classification

For the safe and economical construction of embankment dams, the mechanical behaviour of the rockfill materials used in the dam’s shell must be analyzed. The characterization of rockfill materials with specified shear strength is difficult and expensive due to the presence of particles greater than 500 mm in diameter. This work investigates the feasibility of using an extreme gradient boosting (XGBoost) computing paradigm to estimate the shear strength of rockfill materials. To train and validate the proposed XGBoost model, a total of 165 databases obtained from the literature are chosen. The XGBoost model was compared against support vector machine (SVM), adaptive boosting (AdaBoost), random forest (RF), and K‐nearest neighbor (KNN) models described in the literature. XGBoost beats SVM, RF, AdaBoost, and KNN models in terms of performance evaluation metrics such as coefficient of determination ( R 2 ), Nash–Sutcliffe coefficient (NSE), and error in the root mean square ratio (RMSE) to the standard deviation of the measured data (RSR). The results demonstrated that the XGBoost model has the highest prediction performance with ( R 2 = 0.9707, NSE = 0.9701, and RSR = 0.1729), followed by the SVM model with ( R 2 = 0.9655, NSE = 0.9639, and RSR = 0.1899), RF ( R 2 = 0.9545, NSE = 0.9542, and RSR = 0.2140), the AdaBoost model with ( R 2 = 0.9390, NSE = 0.9388, and RSR = 0.2474) and the KNN model with ( R 2 = 0.6233, NSE = 0.6180, and RSR = 0.6181). A sensitivity analysis has been conducted to ascertain the impact of each investigated input parameter. This study demonstrates that the established XGBoost model for estimating the shear strength of rockfill materials is reliable.

Existing studies have attempted to determine the tool chipping condition using the indirect method of data capture and intelligent analysis techniques considering machine parameters, and tool conditions using signal processing techniques. Due to the obstructive nature of the machining operation, however, it is daunting to use signal capturing to intelligently capture the condition of the tool as well as that of the workpiece. This study aimed to apply some advanced signal processing techniques to the vibration signals captured experimentally during machining operation for the decision making and analysis of tool and workpiece conditions. Vibration signals were captured during turning operations while using four (4) classes of tools, based on their flank wear. The signals were first pre-processed and decomposed using the Empirical Mode Decomposition (EMD) method. The Hilbert–Huang transform (HHT) was applied to the resulting IMFs obtained to compute the feature vectors used to classify the condition of the tool and workpiece. A total of 12 features, consisting of instantaneous properties such as instantaneous energy, instantaneous frequencies, and amplitudes, were obtained for data training and classification of tool conditions. To optimize the classification process, feature selection was performed using a genetic algorithm (GA) to reduce the number of features from 12 to 4 for data training and classification. The feature vectors were first trained for tool classification with a neural network scaled conjugate gradient (SCG) algorithm. The result showed that the model classification error was 0.102. Two other machine learning models, support vector machine (SVM) and K-Nearest Neighbors (KNN), were also implemented for classifying the tool conditions, from the feature vector, to determine the model that most accurately predicted the condition of the tool. To avoid bias and reduce misclassification errors, the k-fold cross-validation technique was applied with ‘k’ taken as 5 and 10. The computed feature vectors were used as inputs to train the machine learning model using both SVM and KNN models to classify the tool and workpiece condition during machining. The error loss of each model was evaluated and plotted to review the performance. The average overall error loss of 0.5031 was observed for the SVM model with 5-fold cross-validation, whereas the error loss of 0.0318 was observed for the KNN model with 5-fold cross-validation. The average overall error loss of 0.5009 was observed for the SVM model with 10-fold cross-validation when trained using the features selected by a genetic algorithm (GA), while the average overall error loss of 0.0343 was observed for the KNN model. The optimal performance of the SVM model was obtained when all features were used for the training, whereas the KNN model performed better when feature selection was implemented. The error losses of the models were evaluated to be less in KNN models, compared to SVM and SCG. The obtained results also showed that the developed KNN models performed 10 times better than the SVM model in predicting the tool condition from the captured vibration signal during the machining process.

The global market for organic cocoa beans continues to show sturdy growth. A low-cost handheld NIR spectrometer (900-1700 nm) combined with multivariate classification algorithms was used for rapid differentiation analysis of organic cocoa beans' integrity. In this research, organic and conventionally cultivated cocoa beans were collected from different locations in Ghana and scanned nondestructively with a handheld spectrometer. Different preprocessing treatments were employed. Principal component analysis (PCA) and classification analysis, RF (random forest), KNN (K-nearest neighbours), LDA (linear discriminant analysis), and PLS-DA (partial least squares-discriminant analysis) were performed comparatively to build classification models. The performance of the models was evaluated by accuracy, specificity, sensitivity, and efficiency. Second derivative preprocessing together with PLS-DA algorithm was superior to the rest of the algorithms with a classification accuracy of 100.00% in both the calibration set and prediction set. Second derivative algorithm was found to be the best preprocessing tool. The identification rates for the calibration set and prediction set were 96.15% and 98.08%, respectively, for RF, 91.35% and 92.31% for KNN, and 90.38% and 98.08% for LDA. Generally, the results showed that a handheld NIR spectrometer coupled with an appropriate multivariate algorithm could be used in situ for the differentiation of organic cocoa beans from conventional ones to ensure food integrity along the cocoa bean value chain.

We present a data‐driven model, Support Vector Machine (SVM), for long lead time streamflow forecasting using oceanic‐atmospheric oscillations. The SVM is based on statistical learning theory that uses a hypothesis space of linear functions based on Kernel approach and has been used to predict a quantity forward in time on the basis of training from past data. The strength of SVM lies in minimizing the empirical classification error and maximizing the geometric margin by solving inverse problem. The SVM model is applied to three gages, i.e., Cisco, Green River, and Lees Ferry in the Upper Colorado River Basin in the western United States. Annual oceanic‐atmospheric indices, comprising Pacific Decadal Oscillation (PDO), North Atlantic Oscillation (NAO), Atlantic Multidecadal Oscillation (AMO), and El Nino–Southern Oscillations (ENSO) for a period of 1906–2001 are used to generate annual streamflow volumes with 3 years lead time. The SVM model is trained with 86 years of data (1906–1991) and tested with 10 years of data (1992–2001). On the basis of correlation coefficient, root means square error, and Nash Sutcliffe Efficiency Coefficient the model shows satisfactory results, and the predictions are in good agreement with measured streamflow volumes. Sensitivity analysis, performed to evaluate the effect of individual and coupled oscillations, reveals a strong signal for ENSO and NAO indices as compared to PDO and AMO indices for the long lead time streamflow forecast. Streamflow predictions from the SVM model are found to be better when compared with the predictions obtained from feedforward back propagation artificial neural network model and linear regression.

The chemical industrial park is an important source of volatile organic compounds (VOCs) emissions which is difficult to monitor due to its diversity and low concentration. In this work, a hybrid sensor array consisting of six gas sensors (four semiconductor sensors, one electrochemical sensor, and one photo ionization detector) was constructed to measure VOCs. Three most frequently detected VOCs in a Chinese fine chemical industrial park, namely toluene, dichloromethane, ethyl acetate, and their mixtures, were tested all below 5 ppm (even below 1 ppm in many cases). Support vector machine (SVM) and back-propagation artificial neural network (BP-ANN) based on different input features, including steady-state responses (SS), the first four components preprocessed by principal component analysis (PCA) and linear discriminant analysis (LDA), were trained and evaluated. The 10-fold cross validation results indicate that SS-SVM and SS-ANN are two best models with accuracy and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{R}^{{2}}$ </tex-math></inline-formula> of about 94% and 0.95 for the validation set, respectively. Compared with LDA, PCA is more suitable for dimension reduction in this study, since the performance of models with the first 4 PCs are closer to that of models with SS. The results demonstrate that the proposed hybrid sensor array system with SVM and ANN models is able to identify and quantify low-concentration VOCs mixtures. This method is promising to be used for low-cost and online monitoring of VOCs emissions in chemical industrial parks.

Near infrared spectroscopy was used in discrimination of intact bovine teeth in terms of animal sex, diet, tooth type and place of origin. Discriminant Analysis (DA) models were developed and tested using a stratified random 70:30 data split to calibration and test sets. Of the discriminant techniques of Soft Independent Modelling of Class Analogy (SIMCA), Partial Least Squares – DA, Artificial Neural Networks (ANN) and Support Vector Machine (SVM), SVM and PLS-DA models performed best in most instances, with pretreatment choice impacting technique success. For test set prediction of animal sex, an accuracy of 95% was achieved using a PLS-DA model, and similar performance achieved using a SVM model. SVM, ANN and SIMCA models predicted three categories of tooth type (deciduous, permanent unerupted and erupted) with similar accuracies (89, 79 and 82%, respectively), however, permanent unerupted teeth were conflated with permanent erupted teeth. Prediction accuracy for ANN, SVM and PLS-DA models were also similar for discrimination of teeth from animals on a grain versus grass diet (PLS-DA 82%). There was considerable variation between models in prediction of geographic origin. Of the seven locations, two were discriminated with true positive rate around 70% using SVM and ANN models. Potential applications of this technology are discussed.

Due to the similar chemical composition and matrix effect, the accurate identification of mineral pigments on wall paintings has brought great challenges. This work implemented an identification study on three mineral pigments with similar chemical compositions by combining LIBS technology with the K-nearest neighbor algorithm (KNN), random forest (RF support vector machine (SVM), back propagation artificial neural network (Bp-ANN) and convolutional neural network (CNN) to find the most suitable identification method for mural research. Using the SelectKBest algorithm, 300 characteristic lines with the largest difference among the three pigments were determined. The identification models of KNN, RF, SVM, Bp-ANN and CNN were established and optimized. The results showed that, except for the KNN model, the identification accuracy of other models for mock-up mural samples was above 99%. However, only the identification accuracy of 2D-CNN models reached above 94% for actual mural samples. Therefore, the 2D-CNN model was determined as the most suitable model for the identification and analysis of mural pigments.

Many downscaling techniques have been developed in the past few years for projection of station‐scale hydrological variables from large‐scale atmospheric variables simulated by general circulation models (GCMs) to assess the hydrological impacts of climate change. This article compares the performances of three downscaling methods, viz. conditional random field (CRF), K‐nearest neighbour (KNN) and support vector machine (SVM) methods in downscaling precipitation in the Punjab region of India, belonging to the monsoon regime. The CRF model is a recently developed method for downscaling hydrological variables in a probabilistic framework, while the SVM model is a popular machine learning tool useful in terms of its ability to generalize and capture nonlinear relationships between predictors and predictand. The KNN model is an analogue‐type method that queries days similar to a given feature vector from the training data and classifies future days by random sampling from a weighted set of K closest training examples. The models are applied for downscaling monsoon (June to September) daily precipitation at six locations in Punjab. Model performances with respect to reproduction of various statistics such as dry and wet spell length distributions, daily rainfall distribution, and intersite correlations are examined. It is found that the CRF and KNN models perform slightly better than the SVM model in reproducing most daily rainfall statistics. These models are then used to project future precipitation at the six locations. Output from the Canadian global climate model (CGCM3) GCM for three scenarios, viz. A1B, A2, and B1 is used for projection of future precipitation. The projections show a change in probability density functions of daily rainfall amount and changes in the wet and dry spell distributions of daily precipitation. Copyright © 2011 John Wiley &amp; Sons, Ltd.

Mechanical fault detection has an important influence on production schedule and efficiency. With the development of intelligent technology, more and more intelligent detection technologies are applied to mechanical fault detection. In order to detect mechanical faults more efficiently and accurately, this experiment proposes a production knowledge base model based on genetic algorithm (GA algorithm). The model uses the unique biological genetics principle of genetic algorithm to evolve the interested population, and can conduct spatial search to find the global optimal solution. By comparing the performance of GA algorithm model with other similar detection models, it is found that the model proposed in the experiment has obvious advantages in mechanical fault detection performance. The experimental results show that the maximum accuracy of the GA algorithm is 0.935, 0.074 higher than the support vector machine (SVM) model, 0.118 higher than the linear discriminant analysis (LDA) model, 0.032 higher than the random forest (RF) model, and 0.166 higher than the K nearest neighbor (KNN) model. In addition, the error value of GA algorithm is the lowest among these models, which is 0.028. This proves that the genetic algorithm model has higher diagnostic accuracy and can play an important role in mechanical fault detection.

Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China

Aggregate stability is a useful soil physical dynamic index of soil resistivity to surface wind and water erosion in all ecosystems, especially, in arid and semi-arid regions. Two machine learning techniques including support vector machines (SVMs) and artificial neural networks (ANNs) were used to develop predictive models for the estimation of geometric mean diameter (GMD) of soil aggregates. An empirical multiple linear regression (MLR) model was also constructed as the benchmark to compare their performances. Furthermore, the influence of feature space dimension reduction using parallel genetic algorithm (PGA) on the prediction accuracy of all investigated techniques was evaluated. The ANN model achieved greater accuracy in GMD prediction as compared to the MLR and SVM models. The obtained ERROR% value in GMD prediction using the ANN model was 6.9%, while it was 15.7 and 10.6% for the MLR and SVM models, respectively. Feature selection using PGA improved the prediction accuracy of all investigated techniques. The coefficient of determination (R2) values between the measured and the predicted GMD values using PGA-based MLR, SVM, and ANN models increased by 20.0, 12.2, and 8.8% in comparison with the proposed MLR, SVM, and ANN models. In conclusion, it appears that the PGA-based ANN model could be considered as an alternative to conventional regression models for the GMD prediction.

Identification of rice storage time based on colorimetric sensor array combined hyperspectral imaging technology

Astrocytoma is the most common neuroepithelial neoplasm, and its grading greatly affects treatment and prognosis. According to relevant factors of astrocytoma, this study developed a support vector machine (SVM) model to predict the astrocytoma grades and compared the SVM prediction with the clinician's diagnostic performance. Patients were recruited from a cohort of astrocytoma patients in our hospital between January 2008 and April 2009. Among all astrocytoma patients, nine had grade I, 25 had grade II, 12 had grade III, and 60 had grade IV astrocytoma. An SVM model was constructed using radial basis kernel. The SVM model was trained with nine magnetic resonance (MR) features and one clinical parameter by fivefold cross-validation and differentiated astrocytomas of grades I-IV at two levels, respectively. The clinician also predicted the grade of astrocytoma. According to the two prediction methods above, the areas under receiving operating characteristics (ROC) curves to discriminate low- and high-grade groups, accuracies of high-grade grouping, overall accuracy, and overall kappa values were compared. For SVM, the overall accuracy was 0.821 and the overall kappa value was 0.679; for clinicians, the overall accuracy was 0.651 and the overall kappa value was 0.466. The diagnostic performance of SVM is significantly better than clinician performance, with the exception of the low-grade group. The SVM model can provide useful information to help clinicians improve diagnostic performance when predicting astrocytoma grade based on MR images.

The ability to rapidly and reliably screen for bacterial vaginosis (BV) during pregnancy is of great significance for maternal health and pregnancy outcomes. In this proof-of-concept study, we demonstrated the potential of carbon nanotube field-effect transistors (NTFET) in the rapid diagnostics of BV with the sensing of BV-related factors such as pH and biogenic amines. The fabricated sensors showed good linearity to pH changes with a linear correlation coefficient of 0.99. The pH sensing performance was stable after more than one month of sensor storage. In addition, the sensor was able to classify BV-related biogenic amine-negative/positive samples with machine learning, utilizing different test strategies and algorithms, including linear discriminant analysis (LDA), support vector machine (SVM), and principal component analysis (PCA). The biogenic amine sample status could be well classified using a soft-margin SVM model with a validation accuracy of 87.5%. The accuracy could be further improved using a gold gate electrode for measurement, with accuracy higher than 90% in both LDA and SVM models. We also explored the sensing mechanisms and found that the change in NTFET off current was crucial for classification. The fabricated sensors successfully detect BV-related factors, demonstrating the competitive advantage of NTFET for point-of-care diagnostics of BV.

기업의 부도를 예측하는 것은 회계나 재무 분야에서 중요한 연구주제이다. 지금까지 기업 부도예측을 위해 여러 가지 데이터마이닝 기법들이 적용되었으나 주로 단일 모형을 사용함으로서 복잡한 분류 문제에의 적용에 한계를 갖고 있었다. 본 논문에서는 최근에 각광받고 있는 SVM (support vector machine) 모형들을 결합한 앙상블 SVM 모형 (ensemble SVM model)을 부도예측에 사용하고자 한다. 제안된 앙상블 모형은 v-조각 교차 타당성 (v-fold cross-validation)에 의해 얻어진 여러 가지 모형 중에서 성능이 좋은 상위 k개의 단일 모형으로 구성하고 과반수 투표 방식 (majority voting)을 사용하여 미지의 클래스를 분류한다. 본 논문에서 제안된 앙상블 SVM 모형의 성능을 평가하기 위해 실제 기업의 재무비율 자료와 모의실험자료를 가지고 실험하였고, 실험결과 제안된 앙상블 모형이 여러 가지 평가척도 하에서 단일 SVM 모형들보다 좋은 성능을 보임을 알 수 있었다. Corporate bankruptcy prediction has been an important topic in the accounting and finance field for a long time. Several data mining techniques have been used for bankruptcy prediction. However, there are many limits for application to real classification problem with a single model. This study proposes ensemble SVM (support vector machine) model which assembles different SVM models with each different kernel functions. Our ensemble model is made and evaluated by v-fold cross-validation approach. The k top performing models are recruited into the ensemble. The classification is then carried out using the majority voting opinion of the ensemble. In this paper, we investigate the performance of ensemble SVM classifier in terms of accuracy, error rate, sensitivity, specificity, ROC curve, and AUC to compare with single SVM classifiers based on financial ratios dataset and simulation dataset. The results confirmed the advantages of our method: It is robust while providing good performance.