Machine Learning Methods Support Vector Research Articles

Improving the accuracy of soil texture determination using pH and electro conductivity values with ultrasound penetration-based digital soil texture analyzer

Soil texture analysis is critical for advancing agricultural productivity, ensuring environmental sustainability, and maintaining ecosystem balance. Traditional sedimentation-based methods, such as the hydrometer technique, are fast and practical but prone to inaccuracies due to the effects of water-soluble substances. This study focuses on the practical framework of integrating pH (potential of hydrogen) and EC (electrical conductivity), as indicators of dissolved substances that influence soil texture estimation. Using the Ultrasound Penetration-based Digital Soil Texture Analyzer (USTA), this research combined ultrasound time series data with pH and EC measurements to predict sand, silt, and clay ratios through machine learning methods—support vector regression (SVR), Random Forest (RF), and multi-layer perceptron neural network (MLPNN). Simulations showed that RF yielded the best results, improving R2 values to 0.52, 0.33, and 0.31 for sand, silt, and clay, respectively. The enhanced model performance demonstrates the viability of integrating pH and EC with advanced machine learning techniques to improve soil texture analysis accuracy. These findings suggest that automated systems like USTA, with modular pH and EC sensors, can provide cost-effective, efficient alternatives to traditional methods, offering practical implications for soil management and agricultural optimization.

The use of Support Vector Machine learning method to predict moisture of building materials using the Time Domain Reflectometry

Abstract This article shows the possibility to adopt Support Vector Machine (SVM) learning method to predict moisture of building materials measured by the Time Domain Reflectometry (TDR) method. TDR is an indirect technique of moisture detection. It enables to evaluate apparent permittivity of moist material and then predict moisture using physical or empirical models. In this research it is presented the method that avoids evaluation of apparent permittivity value and estimate moisture basing on the raw TDR waveforms. SVM is one of the most popular machine learning methods that could be used both for classification and regression modelling. It is mostly applied for analysing of multidimensional signals, but could be also applied to evaluate moisture from raw TDR signals. SVM regression model allows quick estimation of material moisture and achieve similar or better measurement accuracy comparing to the standard calibration methods. Research was conducted on two types of building materials – the red and the silicate bricks and data analysis confirmed the suitability of SVM models in determining moisture content using the TDR method.

An investigation of machine learning methods applied to genomic prediction in yellow-feathered broilers

Machine learning (ML) methods have rapidly developed in various theoretical and practical research areas, including predicting genomic breeding values for large livestock animals. However, few studies have investigated the application of ML in broiler breeding. In this study, seven different ML methods—support vector regression (SVR), random forest (RF), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), kernel ridge regression (KRR) and multilayer perceptron (MLP) were employed to predict the genomic breeding values of laying traits, growth and carcass traits in a yellow-feathered broiler breeding population. The results indicated that classic methods, such as GBLUP and Bayesian, achieved superior prediction accuracy compared to ML methods in five of the eight traits. For half-eviscerated weight (HEW), ML methods showed an average improvement of 54.4% over GBLUP and Bayesian methods. Among the ML methods, SVR, RF, GBDT, and XGBoost exhibited improvements exceeding 60%, with respective values of 61.3%, 61.0%, 60.4%, and 60.7%; while MLP improved by 54.4% and LightGBM by 53.7%, KRR had the lowest improvement at 29.4%. For eviscerated weight (EW), ML methods still outperformed GBLUP and Bayesian methods. MLP gained the largest improvement at 19.0%, while SVR, RF, GBDT, XGBoost, LightGBM, and KRR improved by 15.0%, 16.5%, 9.5%, 7.0%, 1.6%, and 15.9%, respectively. Compared to default hyperparameters, the average improvement of ML methods with tuned hyperparameters was 34.0%, 32.9%, 27.0%, 19.3%, 26.8%, 13.2%, 18.9%, and 46.3%, respectively. The prediction accuracy of above algorithms could be optimized using genome-wide association study (GWAS) to select subsets of significant SNPs. This work provides valuable insights into genomic prediction, aiding genetic breeding in broilers.

Design and Research on Identification of Typical Tea Plant Diseases Using Small Sample Learning

Tea plants are susceptible to diseases during their growth. These diseases seriously affect the yield and quality of tea. The effective prevention and control of diseases requires accurate identification of diseases. With the development of artificial intelligence and computer vision, automatic recognition of plant diseases using image features has become feasible. As the support vector machine (SVM) is suitable for high dimension, high noise, and small sample learning, this paper uses the support vector machine learning method to realize the segmentation of disease spots of diseased tea plants. An improved Conditional Deep Convolutional Generation Adversarial Network with Gradient Penalty (C-DCGAN-GP) was used to expand the segmentation of tea plant spots. Finally, the Visual Geometry Group 16 (VGG16) deep learning classification network was trained by the expanded tea lesion images to realize tea disease recognition.

An empirical isochrone archive for nearby open clusters

Context. The ages of star clusters and co-moving stellar groups contain essential information about the Milky Way. Their special properties and placement throughout the galactic disk make them excellent tracers of galactic structure and key components to unlocking its star formation history. Yet, even though the importance of stellar population ages has been widely recognized, their determination remains a challenging task often associated with highly model-dependent and uncertain results. Aims. We propose a new approach to this long-standing problem, which relies on empirical isochrones of known clusters extracted from high-quality observational data. These purely observation-based data products open up the possibility of relative age determination, free of stellar evolution model assumptions. Methods. For the derivation of the empirical isochrones, we used a combination of the statistical analysis tool principal component analysis for preprocessing and the supervised machine learning method support vector regression for curve extraction. To improve the statistical reliability of our result, we defined the empirical isochrone of a color-magnitude diagram (CMD) of a cluster as the median calculated from a set of nboot = 1000 curves derived from bootstrapped data. The algorithm requires no physical priors, is computationally fast, and can easily be generalized over a large range of CMD combinations and evolutionary stages of clusters. Results. We provide empirical isochrones in all Gaia DR2 and DR3 color combinations for 83 nearby clusters (d < 500 pc), which cover an estimated age range of 7 Myr to 3 Gyr. In doing so, we pave the way for a relative comparison between individual stellar populations based on an age-scaling ladder of empirical isochrones of known clusters. Furthermore, due to the exceptional precision of the available observational data, we report accurate lower main sequence empirical isochrones for many clusters in our sample, which are of special interest as this region is known to be especially complex to model. We validate our method and results by comparing the extracted empirical isochrones to cluster ages in the literature. We also investigate the added information that empirical isochrones covering the lower main sequence can provide on case studies of the IC 4665 cluster and the Meingast 1 stream. Conclusions. The archive of empirical isochrones offers a novel approach to validating age estimates and can be used as an age-scaling ladder or age brackets for new populations and serve as calibration data for further constraining stellar evolution models.

Prediction of bone invasion of oral squamous cell carcinoma using a magnetic resonance imaging-based machine learning model

ObjectivesRadiomics, a recently developed image-processing technology, holds potential in medical diagnostics. This study aimed to propose a machine-learning (ML) model and evaluate its effectiveness in detecting oral squamous cell carcinoma (OSCC) and predicting bone metastasis using magnetic resonance imaging (MRI).Materials-methodsMRI radiomic features were extracted and analyzed to identify malignant lesions. A total of 86 patients (44 with benign lesions without bone invasion and 42 with malignant lesions with bone invasion) were included. Data and clinical information were managed using the RadCloud Platform (Huiying Medical Technology Co., Ltd., Beijing, China). The study employed a hand-crafted radiomics model, with the dataset randomly split into training and validation sets in an 8:2 ratio using 815 random seeds.ResultsThe results revealed that the ML method support vector machine (SVM) performed best for detecting bone invasion (AUC = 0.999) in the test set. Radiomics tumor features derived from MRI are useful to predicting bone invasion from oral squamous cell carcinoma with high accuracy.ConclusionsThis study introduces an ML model utilizing SVM and radiomics to predict bone invasion in OSCC. Despite the promising results, the small sample size necessitates larger multicenter studies to validate and expand these findings.

Precision in wheat flour classification: Harnessing the power of deep learning and two-dimensional correlation spectrum (2DCOS)

Wheat flour is a ubiquitous food ingredient, yet discerning its various types can prove challenging. A practical approach for identifying wheat flour types involves analyzing one-dimensional near-infrared spectroscopy (NIRS) data. This paper introduces an innovative method for wheat flour recognition, combining deep learning (DL) with Two-dimensional correlation spectrum (2DCOS). In this investigation, 316 samples from four distinct types of wheat flour were collected using a near-infrared (NIR) spectrometer, and the raw spectra of each sample underwent preprocessing employing diverse methods. The discrete generalized 2DCOS algorithm was applied to generate 3792 2DCOS images from the preprocessed spectral data. We trained a deep learning model tailored for flour 2DCOS images – EfficientNet. Ultimately, this DL model achieved 100% accuracy in identifying wheat flour within the test set. The findings demonstrate the viability of directly transforming spectra into two-dimensional images for species recognition using 2DCOS and DL. Compared to the traditional stoichiometric method Partial Least Squares Discriminant Analysis (PLS_DA), machine learning methods Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), and deep learning methods one-dimensional convolutional neural network (1DCNN) and residual neural network (ResNet), the model proposed in this paper is better suited for wheat flour identification, boasting the highest accuracy. This study offers a fresh perspective on wheat flour type identification and successfully integrates the latest advancements in deep learning with 2DCOS for spectral type identification. Furthermore, this approach can be extended to the spectral identification of other products, presenting a novel avenue for future research in the field.

Remotely sensed desertification modeling using ensemble of machine learning algorithms

Due to having a sensitive and fragile ecosystem, dry areas are constantly exposed to land degradation and desertification. Therefore, it is necessary to formulate appropriate strategies for quantitative assessment of desertification that are highly accurate. In this research, desertification of the region was first evaluated using MEDALUS model, then according to the results of MEDALUS model and reviewing the results of other researchers, 8 indicators remote sensing that had the highest correlation with field data were selected for modeling. Four machine learning methods Support Vector Machine (SVM), Gradient Boosting Machine (GBM), Generalized Linear Models (GLM) and Random Forests (RF) were used to model the risk of desertification in northeastern Iran. Finally, the weighted average of the ensemble model in the SDM statistical package was used to predict the desertification of the region. Based on the results obtained from MEDALUS model, the indicators of drought resistance (score 162), conservation operations (score 158) and soil salinity (score 155), in the working units of abandoned lands, wetland lands, and Salty lands located in the north East of the region, have increased the process of desertification. The results of modeling using machine learning methods showed that in 2002, the SVM model (AUC = 0.91, TSS = 0.93, and Kappa = 0.86) and in 2021, the RF model (AUC = 0.94, TSS = 0.94, and Kappa = 0.90) have performed best. The forecast of the combined model for desertification in 2021 in the studied area showed that the northeastern and sporadically in the central parts of the studied area are affected by the progress of the desertification process. Therefore, by considering the results of the combined model (as a model with the least uncertainty), it is possible to reduce the progress of the desertification process by planning, optimal management and applying corrective methods in the areas affected by desertification.

The coherence between PSMC6 and α-ring in the 26S proteasome is associated with Alzheimer's disease.

Alzheimer's disease (AD) is a heterogeneous age-dependent neurodegenerative disorder. Its hallmarks involve abnormal proteostasis, which triggers proteotoxicity and induces neuronal dysfunction. The 26S proteasome is an ATP-dependent proteolytic nanomachine of the ubiquitin-proteasome system (UPS) and contributes to eliminating these abnormal proteins. This study focused on the relationship between proteasome and AD, the hub genes of proteasome, PSMC6, and 7 genes of α-ring, are selected as targets to study. The following three characteristics were observed: 1. The total number of proteasomes decreased with AD progression because the proteotoxicity damaged the expression of proteasome proteins, as evidenced by the downregulation of hub genes. 2. The existing proteasomes exhibit increased activity and efficiency to counterbalance the decline in total proteasome numbers, as evidenced by enhanced global coordination and reduced systemic disorder of proteasomal subunits as AD advances. 3. The synergy of PSMC6 and α-ring subunits is associated with AD. Synergistic downregulation of PSMC6 and α-ring subunits reflects a high probability of AD risk. Regarding the above discovery, the following hypothesis is proposed: The aggregation of pathogenic proteins intensifies with AD progression, then proteasome becomes more active and facilitates the UPS selectively targets the degradation of abnormal proteins to maintain CNS proteostasis. In this paper, bioinformatics and support vector machine learning methods are applied and combined with multivariate statistical analysis of microarray data. Additionally, the concept of entropy was used to detect the disorder of proteasome system, it was discovered that entropy is down-regulated continually with AD progression against system chaos caused by AD. Another conception of the matrix determinant was used to detect the global coordination of proteasome, it was discovered that the coordination is enhanced to maintain the efficiency of degradation. The features of entropy and determinant suggest that active proteasomes resist the attack caused by AD like defenders, on the one hand, to protect themselves (entropy reduces), and on the other hand, to fight the enemy (determinant reduces). It is noted that these are results from biocomputing and need to be supported by further biological experiments.

Machine Learning Techniques to Predict Timeliness of Care among Lung Cancer Patients.

Delays in the assessment, management, and treatment of lung cancer patients may adversely impact prognosis and survival. This study is the first to use machine learning techniques to predict the quality and timeliness of care among lung cancer patients, utilising data from the Victorian Lung Cancer Registry (VLCR) between 2011 and 2022, in Victoria, Australia. Predictor variables included demographic, clinical, hospital, and geographical socio-economic indices. Machine learning methods such as random forests, k-nearest neighbour, neural networks, and support vector machines were implemented and evaluated using 20% out-of-sample cross validations via the area under the curve (AUC). Optimal model parameters were selected based on 10-fold cross validation. There were 11,602 patients included in the analysis. Evaluated quality indicators included, primarily, overall proportion achieving "time from referral date to diagnosis date ≤ 28 days" and proportion achieving "time from diagnosis date to first treatment date (any intent) ≤ 14 days". Results showed that the support vector machine learning methods performed well, followed by nearest neighbour, based on out-of-sample AUCs of 0.89 (in-sample = 0.99) and 0.85 (in-sample = 0.99) for the first indicator, respectively. These models can be implemented in the registry databases to help healthcare workers identify patients who may not meet these indicators prospectively and enable timely interventions.

A dataset of paddy rice planting areas along the Yangtze River (Jiangsu section) in 2020

As a staple food crop in China, paddy rice is one of the most widely grown crops in the country. Thanks to its abundant water resources, the Yangtze River has superiority in paddy rice planting. The prompt and accurate monitoring of paddy rice planting information plays an important role in providing essential technical support to safeguard China's food security. However, there is a scarcity of studies on the extraction of paddy rice planting areas along the Yangtze River using the remote sensing technology. In this paper, guided by paddy rice growth phenology information, we selected the Sentinel-2 satellite imagery that covered the paddy rice growing period (from May to September) along the Yangtze River in 2020. On the basis of high-spatial resolution images combined with field investigation, we obtained the real distribution map of the paddy rice planting area in Menghe Town and selected samples and validation samples from the map. Based on the maximum likelihood, neural network, SVM (Support Vector Machine) and other machine learning methods, we carried out the paddy rice extraction research, compared and analyzed the accuracy of extraction results of NDVI (Normalized Difference Vegetation Index) and REP (Red Edge Position Index) spectral index sets. The results show that the REP index sets of the three time phases in May, August and September are most effectively extracted using the neural network method. The overall accuracy of the results is 92.73%, with a corresponding Kappa coefficient of 0.72. We achieved global applicability by optimizing key parameters such as timing, spectral bands, and classifier methods for paddy rice extraction. Additionally, we conducted post-processing to refine the results. Finally, we obtained a vector dataset of paddy rice growing areas along the Yangtze River (Jiangsu section) in 2020, with an overall classification accuracy of 87.15%. This dataset is expected to provide a reference for further monitoring the paddy rice planting areas and enhancing the accuracy of grain production estimates throughout the Yangtze River region.

Support Vector Machine with Robust Low-Rank Learning for Multi-Label Classification Problems in the Steelmaking Process

In this paper, we present a novel support vector machine learning method for multi-label classification in the steelmaking process. The steelmaking process involves complicated physicochemical reactions. The end-point temperature is the key to the steelmaking process. According to the initial furnace condition information, the end-point temperature can be predicted using a data-driven method. Based on the setting value of the temperature before tapping, multi-scale predicted errors of the end-point temperature can be calculated and divided into different ranges. The quality evaluation problem can be attributed to the multi-label classification problem of molten steel quality. To solve the classification problem, considering that it is difficult to capture nonlinear relationships between the input and output in linear models, we propose a novel support vector machine with robust low-rank learning, which has the characteristics of class imbalance without label correlations; a low-rank constraint is used to deal with high-order label correlations in low-dimensional space. Furthermore, we derive an accelerated proximal gradient algorithm and then extend it to handle the nonlinear multi-label classifiers. To validate the proposed model, experiments are conducted with real data from a practical steelmaking problem. The results show that the proposed model can effectively solve the multi-label classification problem in industrial production. To evaluate the proposed approach as a general classification approach, we test it on multi-label classification benchmark datasets. The results illustrate that the proposed approach performs better than other state-of-the-art approaches across different scenarios.

Optimal Strategy on Radiation Estimation for Calculating Universal Thermal Climate Index in Tourism Cities of China.

The Universal Thermal Climate Index (UTCI) is believed to be a very powerful tool for providing information on human thermal perception in the domain of public health, but the solar radiation as an input variable is difficult to access. Thus, this study aimed to explore the optimal strategy on estimation of solar radiation to increase the accuracy in UTCI calculation, and to identify the spatial and temporal variation in UTCI over China. With daily meteorological data collected in 35 tourism cities in China from 1961 to 2020, two sunshine-based Angstrom and Ogelman models, and two temperature-based Bristow and Hargreaves models, together with neural network and support vector machine-learning methods, were tested against radiation measurements. The results indicated that temperature-based models performed the worst with the lowest NSE and highest RMSE. The machine-learning methods performed better in calibration, but the predictive ability decreased significantly in validation due to big data requirements. In contrast, the sunshine-based Angstrom model performed best with high NSE (Nash–Sutcliffe Efficiency) of 0.84 and low RMSE (Root Mean Square Error) of 35.4 J/m2 s in validation, which resulted in a small RMSE of about 1.2 °C in UTCI calculation. Thus, Angstrom model was selected as the optimal strategy on radiation estimation for UTCI calculation over China. The spatial distribution of UTCI showed that days under no thermal stress were high in tourism cities in central China within a range from 135 to 225 days, while the largest values occurred in Kunming and Lijiang in southwest China. In addition, days under no thermal stress during a year have decreased in most tourism cities of China, which could be attributed to the asymmetric changes in significant decrease in frost days and slightly increase in hot days. However, days under no thermal stress in summer time have indeed decreased, accompanying with increasing days under strong stress, especially in the developed regions such as Yangze River Delta and Zhujiang River Delta. Based on the study, we conclude that UTCI can successfully depict the overall spatial distribution and temporal change of the thermal environments in the tourism cities over China, and can be recommend as an efficient index in the operational services for assessing and predicting thermal perception for public health. However, extreme cold and heat stress in the tourism cities of China were not revealed by UTCI due to mismatch of the daily UTCI with category at hourly scale, which makes it an urgent task to redefine category at daily scale in the next research work.

Pterygium and Ocular Surface Squamous Neoplasia: Optical Biopsy Using a Novel Autofluorescence Multispectral Imaging Technique.

Simple SummaryCancer is able to damage the surface of the eye, especially in countries like Australia with high exposure to ultraviolet radiation from the sun. Such cancer (ocular surface squamous neoplasia or OSSN) is similar in appearance to a common and benign eye disease called pterygium. Currently, eye biopsy is the gold standard diagnostic method for OSSN, which is traumatic for the patient, carries risks, and has been potentially unnecessary in patients diagnosed with pterygium only. This research introduces an imaging-based method for OSSN screening, which will reduce pressure on health resources—and hopefully eliminate the need for eye biopsy in cases of suspected OSSN.In this study, differentiation of pterygium vs. ocular surface squamous neoplasia based on multispectral autofluorescence imaging technique was investigated. Fifty (N = 50) patients with histopathological diagnosis of pterygium (PTG) and/or ocular surface squamous neoplasia (OSSN) were recruited. Fixed unstained biopsy specimens were imaged by multispectral microscopy. Tissue autofluorescence images were obtained with a custom-built fluorescent microscope with 59 spectral channels, each with specific excitation and emission wavelength ranges, suitable for the most abundant tissue fluorophores such as elastin, flavins, porphyrin, and lipofuscin. Images were analyzed using a new classification framework called fused-classification, designed to minimize interpatient variability, as an established support vector machine learning method. Normal, PTG, and OSSN regions were automatically detected and delineated, with accuracy evaluated against expert assessment by a specialist in OSSN pathology. Signals from spectral channels yielding signals from elastin, flavins, porphyrin, and lipofuscin were significantly different between regions classified as normal, PTG, and OSSN (p < 0.01). Differential diagnosis of PTG/OSSN and normal tissue had accuracy, sensitivity, and specificity of 88 ± 6%, 84 ± 10% and 91 ± 6%, respectively. Our automated diagnostic method generated maps of the reasonably well circumscribed normal/PTG and OSSN interface. PTG and OSSN margins identified by our automated analysis were in close agreement with the margins found in the H&E sections. Such a map can be rapidly generated on a real time basis and potentially used for intraoperative assessment.

Red tide detection based on high spatial resolution broad band optical satellite data

Red tide, one of the major ecological disasters in the world, exerts great impact on the marine environment. The ocean color satellite data with low spatial resolution and high spectral resolution is often used for red tide detection, but is insufficient for the fine-scale red tide detection due to its coarse spatial resolution. To address this problem, a new red tide detection method based on pseudo hue angle (PHA-RI) for high spatial resolution broad band satellite data is proposed in this paper. Different from the standard International Commission on Illumination (CIE) system, the false-color bands of near infrared (NIR), red and green are used to calculate the CIE tristimulus X, Y, Z, instead of the true-color bands of red, green and blue. With this method, the red tide can be easily differentiated from non-red tide water, and the distinction between red tide and non-red tide water is doubled compared to that of true-color bands composite. Experiment results show that the PHA-RI method can effectively detect red tide, with an averaged overall accuracy, F1-score and precision of 92%, 0.92 and 0.92 respectively. Compared with the traditional machine learning method support vector machine (SVM) and spectral index algorithm Gaofen-1 (GF-1) red tide detection index (GF-RI), the proposed algorithm has obvious advantages in red tide detection, especially for the strip distributed red tide. Besides, the proposed algorithm has good applicability, and it is proved to be suitable for the detection of red tides with different dominant species including Noctiluca scintillans, Skeletonema costatum and Heterosigma akashiide. Also, it is applicable to different broad band sensors, such as Chinese satellites GF-1 Wide Field of View (WFV), Haiyang 1D (HY-1D) Coastal Zone Imager (CZI), Sentinel-2 MultiSpectral Instrument (MSI) and Landsat 8 Operational Land Imager (OLI). The application experiment indicates that the proposed algorithm is effective in red tide detection, and it can successfully detect fine-scale red tide events, which have not been detected by Moderate Resolution Imaging Spectroradiometer (MODIS) Aqua due to its coarse spatial resolution. The results also shows the advantages of high spatial resolution satellites in fine-scale red tide detection. This work provides a method for red tide detection using high spatial resolution broad band satellite data.

Single-Crystal Quality Detection and Evaluation Algorithms Applied to Roller Mill Orientation Instrument

The roller mill orientation instrument (RMOI) integrates the processing and the orientation of single-crystal bars. This type of equipment realizes the integration of two processes: grinding of the single-crystal ingot and orientation of the single-crystal bar. This integration enhances production efficiency and the precision of the orientation. However, this type of approach has two significant constraints: 1) there is no quality detection algorithm for the plane of the crystal bar; it is, therefore, currently necessary to randomly find a crystal plane for orientation, which means that there is no guarantee of the quality of the plane after cutting and 2) there is a lack of evaluation methods to determine the overall quality of the crystal bar. This affects the production process and the requirements for the quality of the crystal bar and further affects the popularization and application of the equipment. Here, to overcome these constraints, we first propose a deep learning 1-D convolutional neural network (1-D-CNN) algorithm to perform feature extraction and supervised classification based on the rocking curve of the single crystal. In sharp contrast to the shallow learning method support vector machine (SVM), SVM feature extraction is insufficient, and the accuracy is low. The average accuracy of 1-D-CNN is 92.00%. This realizes the quality requirements for the successful detection of the crystal plane. Next, using the obtained quality detection results of each crystal plane, a hybrid algorithm combining improved Canopy (ICanopy) and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means algorithms is presented, which improved the average accuracy by 10% compared with the traditional Canopy- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means algorithm, and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> -nearest neighbor ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> NN) algorithm is further utilized. Finally, an ICanopy- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> NN algorithm is formed, which realizes the overall quality evaluation of the crystal bar under various situations, and the average accuracy increases by 3.33%–90%. The effectiveness of the proposed algorithms is demonstrated by the analysis of results obtained from practical data.

A multi-discipline predictive intelligent control method for maintaining the thermal comfort on indoor environment

The emergence and application of soft computing have significantly changed the methods to solve engineering problems. For the indoor environmental control, various machine learning methods have been used, attempting to replace the traditional engineering methods. However, the recent single data-driven machine learning approach can hardly meet the requirement, since engineering problems still require prior knowledge to extract features and set up restrictions, while this knowledge should be obtained from engineering analysis. In this case, this paper has proposed an integrated multi-discipline method combining machine learning with engineering analysis, to implement predictive intelligent indoor environmental control in terms of thermal comfort and energy consumption. This method includes three parts, i.e., environmental modelling and simulation, producing an environmental prediction model, and creating an intelligent control agent and system. Firstly, a physical model is created to simulate the indoor environment and analysed through computational fluid dynamics, whose results can guide the setup of sensors in the indoor environment for collecting real-time data. Then, a machine learning method support vector regression is used to create an environmental prediction model for key parameters within the indoor environment, based on the collected data. Finally, a reinforcement learning method is used to train an intelligent agent for the intelligent control on the indoor environment, together with a system for implementation. Experiments and evaluations are carried out in a case study within an office, demonstrating the proposed method’s feasibility, which provides a more efficient and effective intelligently predictive control on the indoor environment considering the balance of thermal comfort and energy efficiency.

A novel hybrid of support vector regression and metaheuristic algorithms for groundwater spring potential mapping

Limited groundwater resources and their overexploitation have become major challenges for sustainable development worldwide. In this study, an innovative hybrid approach was proposed to generate a groundwater spring potential map (GSPM) from the Sarab plain located in Lorestan Province, Iran, which includes the new best-worst method (BWM), stepwise weight assessment ratio analysis (SWARA), support vector machine learning method (SVR), Harris hawk optimization (HHO), and bat algorithms (BA). The first step involved the inventory of a map prepared to contain 610 spring locations. Randomly, 70% of the spring points were selected as training data, and the remaining 30% were selected for validation. Based on the review of the literature and available data, thirteen factors were generated as independent variables. The BWM and SWARA methods were used to identify correlations between the occurrence of springs and factors. Finally, using SVR-BA and SVR-HHO hybrid models, potential maps of groundwater springs were generated and then evaluated with receiver operating characteristic (ROC) and several statistical evaluators such as sensitivity, specificity, accuracy, and kappa index. Validation of the training data set showed that the success rates for the SWARA-SVR-BA, SWARA-SVR-HHO, BWM-SVR-BA, and BWM-SVR-HHO models were 92.6%, 93.7%, 95.9%, and 96.4%, respectively. The results revealed that with a small difference, BWM-SVR-HHO performed better in training compared to other models. Evaluation of the prediction rate showed that the values of the area under the ROC curve for SWARA-SVR-BA, SWARA-SVR-HHO, BWM-SVR-HHO, and BWM-SVR-BA were 91.7%, 92.4%, 93.3%, and 94.7%, respectively. According to the results, although all models had excellent performance with more than 90% accuracy, BWM-SVR-BA was more accurate in predicting. The hybrid models presented in this study can be used as an accurate and effective methodology to improve the results of spatial modeling of the probability of groundwater occurrence.

Rapid detection and identification of charcoal by laser-induced breakdown spectroscopy

Identification based on laser-induced breakdown spectroscopy (LIBS) and machine learning is of great significance to reduce the risk of using low-quality charcoal or inappropriate charcoal, which does harm to fitness and environment. In this paper, fruit charcoal, mechanism charcoal, and bamboo charcoal were used as samples for detection. The characteristic lines of C, Mg, Al, Ca, Na, Fe, and K were observed in the spectra. Principal component analysis (PCA) was used to construct a model to show the sample in the principal component space. Based on the reduced-dimensional PCA model, combined with optimized k-nearest neighbor and optimized support vector machine learning methods, the classification accuracy of charcoal samples reached 96.0% and 97.3%, respectively. The results show that LIBS combined with machine learning provides a new method for charcoal detection and classification.

The Role of Surface Electromyography in Data Fusion with Inertial Sensors to Enhance Locomotion Recognition and Prediction.

Locomotion recognition and prediction is essential for real-time human–machine interactive control. The integration of electromyography (EMG) with mechanical sensors could improve the performance of locomotion recognition. However, the potential of EMG in motion prediction is rarely discussed. This paper firstly investigated the effect of surface EMG on the prediction of locomotion while integrated with inertial data. We collected EMG signals of lower limb muscle groups and linear acceleration data of lower limb segments from ten healthy participants in seven locomotion activities. Classification models were built based on four machine learning methods—support vector machine (SVM), k-nearest neighbor (KNN), artificial neural network (ANN), and linear discriminant analysis (LDA)—where a major vote strategy and a content constraint rule were utilized for improving the online performance of the classification decision. We compared four classifiers and further investigated the effect of data fusion on the online locomotion classification. The results showed that the SVM model with a sliding window size of 80 ms achieved the best recognition performance. The fusion of EMG signals does not only improve the recognition accuracy of steady-state locomotion activity from 90% (using acceleration data only) to 98% (using data fusion) but also enables the prediction of the next steady locomotion (∼370 ms). The study demonstrates that the employment of EMG in locomotion recognition could enhance online prediction performance.