Random Forest Regression Method Research Articles

Identification of important symptoms and diagnostic hypothyroidism patients using machine learning algorithms

Background: Hypothyroidism is one of the most common endocrine diseases. It is, however, usually challenging for physicians to diagnose due to nonspecific symptoms. The usual procedure for diagnosis of Hypothyroidism is a blood test. In recent years, machine learning algorithms have proved to be powerful tools in medicine due to their diagnostic accuracy. In this study, the authors aim to predict and identify the most important symptoms of Hypothyroidism using machine learning algorithms. Method: In this cross-sectional, single-center study, 1296 individuals who visited an endocrinologist for the first time with symptoms of Hypothyroidism were studied, 676 of whom were identified as patients through thyroid-stimulating hormone testing. The outcome was binary (with Hypothyroidism /without Hypothyroidism). In a comparative analysis, random forest, decision tree, and logistic regression methods were used to diagnose primary Hypothyroidism. Results: Symptoms such as tiredness, unusual cold feeling, yellow skin (jaundice), cold hands and feet, numbness of hands, loss of appetite, and weight Hypothyroidism gain were recognized as the most important symptoms in identifying Hypothyroidism. Among the studied algorithms, random forest had the best performance in identifying these symptoms (accuracy=0.83, kappa=0.46, sensitivity=0.88, specificity=0.88). Conclusions: The findings suggest that machine learning methods can identify Hypothyroidism patients who show relatively simple symptoms with acceptable accuracy without the need for a blood test. Greater familiarity and utilization of such methods by physicians may, therefore, reduce the expense and stress burden of clinical testing.

Reconstruction of Hourly FY-4A AGRI Land Surface Temperature under Cloud-Covered Conditions Using a Hybrid Method Combining Spatial and Temporal Information

Land Surface Temperature (LST) products obtained by thermal infrared (TIR) remote sensing contain considerable blank areas due to the frequent occurrence of cloud coverage. The studies on the all-time reconstruction of the cloud-covered LST of geostationary meteorological satellite LST products are relatively few. To accurately fill the blank area, a hybrid method for reconstructing hourly FY-4A AGRI LST under cloud-covered conditions was proposed using a random forest (RF) regression algorithm and Savitzky-Golay (S-G) filtering. The ERA5-Land surface cumulative net radiation flux (SNR) reanalysis data was first introduced to represent the change in surface energy arising from cloud coverage. The RF regression method was used to estimate the LST correlation model based on clear-sky LST and the corresponding predictor variables, including the normalized difference vegetation index (NDVI), the normalized difference water index (NDWI), surface elevation and slope. The fitted model was then applied to reconstruct the cloud-covered LST. The S–G filtering method was used to smooth the outliers of reconstructed LST in the temporal dimension. The accuracy evaluation was performed using the measured LST of the representative meteorological stations after scale correction. The coefficients of determination derived with the reference LST were all above 0.73 on the three examined days, with a bias of −1.13–0.39 K, mean absolute errors (MAE) of 1.46–2.4 K, and root mean square errors (RMSE) of 1.77–3.2 K. These results indicate that the proposed method has strong potential for accurately restoring the spatial and temporal continuity of LST and can provide a solution for the production and research of gap-free LST products with high temporal resolution.

Mapping Seagrass Percent Cover And Biomass In Nusa Lembongan, Bali, Indonesia

Seagrass meadow is one of the blue-carbon ecosystems capable of absorbing and storing carbon more effectively in the bodies and sediments than terrestrial ecosystems. However, nationwide data on its carbon stock remains elusive due to limitations and challenges in data collection and mapping. Seagrass percent cover and biomass, which were closely related with above-ground carbon stock, can be effectively mapped and monitored using remote sensing techniques. Therefore, this study aimed to compare the accuracy of 4 scenarios as well as assess the performance of random forest and stepwise regression methods, for mapping seagrass percent cover and biomass in Nusa Lembongan, Bali, Indonesia. The scenarios were experimented using only atmospherically corrected images, sunglint, water, as well as sunglint and water column corrected images. Furthermore, WorldView-3 images and in-situ seagrass data were used, with the image corrected by applying the scenarios. Random forest and stepwise regression methods were adopted for mapping and modelling. The optimum mapping scenario and method were chosen based on R2, RMSE, and seagrass spatial distribution. The results show that the atmospherically corrected image produced the best seagrass percent cover and biomass map. Range of R2 using random forest and stepwise regression model was 0.49–0.64 and 0.50–0.58, with RMSE ranging from 18.50% to 21.41% and 19.36% to 20.72%, respectively. Based on R2, RMSE, and seagrass spatial distribution, it was concluded that the random forest model produced better mapping results, specifically for areas with high seagrass percent cover.

Assessment of environmental water strategies for improving fringing vegetation health by modelling vegetation condition in a connected floodplain lakes system

AbstractAcross the globe, environmental water has been allocated with the purpose of preserving the health and vitality of floodplain vegetation. However, the influences of environmental water volume and environmental water delivery strategies have not been studied widely because of shortage of on‐ground monitoring data. Remotely sensed data can bridge this gap by providing long‐term and continuous information; Landsat imagery from 1988 to 2020 was used in this research. We used the normalized difference vegetation index (NDVI) as an indicator of physiological condition of lake‐fringing trees on the Hattah Lakes floodplain, south‐east Australia. We employed the random forest (RF) regression method to model the relationship between NDVI and various climate and hydrological factors, such as the volume of water delivered to the connected lakes system as environmental water allocations or natural floods. The RF models performed well overall, with a mean R2 value of 0.73. The analysis identified the monthly total of environmental water delivered 3 months prior to the Landsat image date as a more crucial factor than natural floods over the same period for driving vegetation condition. Environmental water from 3 months previously exerts a positive influence on NDVI until the volume reaches a specific threshold. We have observed significant improvements in floodplain vegetation through the current environmental water strategy, particularly since the construction of pumping infrastructure in 2013. We suggest that managers aim to inundate the lake fringing area every 3 years, specifically from August to September, by delivering environmental water up to the modelled threshold volume. Finally, the use of infrastructure has proven to be an effective and efficient method for irrigating floodplain lakes, leading to improvements in vegetation condition while conserving water resources.

OPTIMASI KINERJA LINEAR REGRESSION, RANDOM FOREST REGRESSION DAN MULTILAYER PERCEPTRON PADA PREDIKSI HASIL PANEN

Rice yield prediction is a significant challenge in the context of climate uncertainty and farmland variation. Erratic weather factors, along with land differences, make this prediction more complex. This research aims to address these issues using a machine learning approach. The method used involves three machine learning models namely Linear regression, Random Forest Regression, and ANN with MultiLayer Perceptron algorithm as well as the evaluation matrix RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) and MAPE (Mean Absolute Percentage Error). This research focuses on testing the accuracy of the three models in the face of uncertain seasonal conditions and variations in agricultural land. The results showed that the MultiLayer Perceptron prediction model gave the best results with an error value of 0.094. The random forest regression method ranks second with an error value of 0.510, followed by Linear regression with an error value of 0.281. The importance of outlier testing in the model development process can be seen from the significant improvement in the performance of the MultiLayer Perceptron model. This research contributes to the development of a more reliable and dependable rice yield prediction system, especially in the midst of uncertain climatic conditions. Machine learning models, particularly MultiLayer Perceptron, can be an effective solution to increase agricultural productivity and reduce risks associated with weather changes and land variations.

Prediction And Investigation for U.S. Used Car Prices and Factors Related to Price

In contemporary society, as transportation infrastructure continues to advance, a growing number of families opt for car ownership as a means of commuting. However, constrained by budget considerations, many households opt for pre-owned vehicles. This underscores the significance of comprehending the dynamics of the used car market and delving into the factors that influence the pricing of these previously owned automobiles. The author found a data set of used cars in United States on Kaggle and used it for analysis. This dataset contains data about 762,091 used cars scraped from cars.com. The data was collected in Apr, 2023. The research question is how to predict the used car prices and what factors are related to the used car prices. The author uses Linear Regression and Random Forest Regression to predict used car prices. The author found the factors related to the price of used cars as well. The study found that the Random Forest Regression method is more accurate in predicting used car prices. A total of 17 used car factors correlated with used car price. Such as mileage, car age, mpg and so on.

The Construction and Application of a Deep Learning-Based Primary Support Deformation Prediction Model for Large Cross-Section Tunnels

The deformation of tunnel support structures during tunnel construction is influenced by geological factors, geometrical factors, support factors, and construction factors. Accurate prediction of tunnel support structure deformation is crucial for engineering safety and optimizing support parameters. Traditional methods for tunnel deformation prediction have often relied on numerical simulations and model experiments, which may not always meet the time-sensitive requirements. In this study, we propose a fusion deep neural network (FDNN) model that combines multiple algorithms with a complementary tunnel information encoding method. The FDNN model utilizes Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to extract features related to tunnel structural deformation. FDNN model is used to predict deformations in the Capital Ring Expressway, and the predictions align well with monitoring results. To demonstrate the superiority of the proposed model, we use four different performance evaluation metrics to analyze the predictive performance of FDNN, DNN, XGBoost, Decision Tree Regression (DTR), and Random Forest Regression (RFR) methods. The results indicate that FDNN exhibits high precision and robustness. To assess the impact of different data types on the predictive results, we use tunnel geometry data as the base and combine geological, support, and construction data. The analysis reveals that models trained on datasets comprising all four data types perform the best. Geological parameters have the most significant impact on the predictive performance of all models. The findings of this research guide predicting tunnel construction parameters, particularly in the dynamic design of support parameters.

Analysis of the Comparison Between Linear Regression, Random Forest, and Logistic Regression Methods in Predicting Crude Palm Oil (CPO) Price

This study compared the predictive capabilities of linear regression, random forest, and logistic regression models for forecasting crude palm oil prices. Utilizing historical data from 02/11/2020 to 13/11/2023, the dataset underwent training and testing with three scenarios: 90:10, 80:20, and 70:30. Evaluation metrics, including RMSE, MSE, and MAPE, assessed model performance. Each method had unique strengths and weaknesses, and the choice depended on application needs. The goal was to improve decision accuracy in predicting crude palm oil price trends. In the 90:10 scenario, random forest outperformed linear and logistic regression, yielding smaller MSE (43948.56), MAE (80.37), and RMSE (209.64). Similarly, in the 80:20 scenario, random forest had smaller MSE (137787.61), MAE (106.38), and RMSE (371.20). In the 70:30 scenario, random forest showed smaller MSE (107582.32), MAE (104.13), and RMSE (328). Overall, random forest consistently demonstrated better performance than linear and logistic regression.

Simultaneous estimation of five temporally regular land variables at seven spatial resolutions from seven satellite data using a multi-scale and multi-depth convolutional neural network

Various satellite sensors have provided a huge amount of observations of Earth's environment at variable spatial and temporal resolutions. Many global coarse-resolution land products have been generated from single-satellite data, but global temporally regular land products at fine spatial resolutions (say 10-30 m) are scarce because of infrequent observations. An ideal inversion framework can estimate multiple global continuous land variables at different spatial resolutions by combining all sources of satellite data. This paper proposes a new framework that can estimate five land variables simultaneously from the top-of-atmosphere (TOA) reflectance acquired by seven satellite sensors based on a multi-scale and multi-depth convolutional neural network (MSDCNN). This framework enables us to estimate temporally regular land variables at as fine as 10 m spatial resolution by transforming information from satellite data at coarser spatial resolutions. The estimated land variables include Leaf Area Index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FAPAR), shortwave albedo, visible albedo, and spectral reflectance. Seven sensors that acquire data at different spatial resolutions, include Visible Infrared Imaging Radiometer Suite (VIIRS) (750 m), Moderate Resolution Imaging Spectroradiometer (MODIS) (500 m), Fengyun-3 (FY-3) Medium Resolution Spectral Imager (MERSI) (250 m), China-Brazil Earth Resources Satellite 04 (CBERS-04) Wide Field Imager (WFI) (73 m), Landsat 8 Operational Land Imager (OLI) (30 m), Gaofen-1 (GF-1) Wide-Field-of-View (16 m) and Sentinel 2 A/B Multispectral Imager (MSI) (10 m). This framework is mainly composed of four steps. First, a Shuffled Complex Evolution (SCE) optimization method is adopted to estimate these variables from VIIRS TOA reference. Second, a joint-output random forest regression (RF) method is used to link the satellite observations and the estimated values from step 1. Third, the six-type multi-resolution satellite observations are used to downscale the VIIRS TOA reflectance to six different spatial resolutions by using the MSDCNN. Finally, the downscaled six-resolution VIIRS TOA reflectance is fed into the multiple-variable RF model to estimate land variables. The framework was validated, and the results based on high-resolution reference maps from ImagineS network and time series shortwave albedo field values from Surface Radiation (SURFRAD) and Integrated Carbon Observation System (ICOS) network show that the retrieved variables had high validation accuracy, with root mean square error (RMSE) ranges of 0.361–0.489 (LAI), 0.023–0.120 (FAPAR), 0.013–0.026 (snow-free shortwave albedo), respectively. Comparison results of the retrieved multi-scale variables with the Sentinel 2 A/B (10 m), Landsat 8 (30 m), Global LAnd Surface Satellite (GLASS, 250 m, 500 m), MODIS (500 m), and VIIRS (750 m) products show that their values were close, with RMSE ranges of 0.107–0.273 (LAI), 0.015–0.027 (FAPAR), 0.003–0.007 (shortwave albedo), 0.001–0.007 (visible albedo), and 0.003–0.025 (spectral reflectance), respectively. The results of the direct validation as well as the product intercomparison show that this novel framework has the potential to be used in estimating global land variables at various spatial scales using a variety of satellite data sources.

Analysis of pressure perception of internal roads in existing settlements based on random forest/deep learning

The quality of road space has an influential role in human psychological health. Quantifying residents' perceptions of road spatial quality and exploring the relationship between perceptions and constituent elements have become topics of interest to many parties. In this study, based on the high-resolution remote sensing images acquired by Baidu Maps, the road images of built-up settlements in Beijing in three different periods (1949-1977, 1978-1997, and 1998-2022) were semantically segmented. The large-scale rating data and subjective evaluations of residents' spatial perceptions of roads were analyzed using random forest and multiple linear regression methods. The results show that stress, a negative perception, is positively correlated with buildings and cars, and negatively correlated with vegetation, sky, and sidewalks. The composition of elements affecting residents' stress perceptions in communities of different build-up years was consistent, but the degree of influence of each element was ranked differently. This study attempts to summarize the road characteristics and residential advantages of different built-up neighborhoods, and proposes optimization strategies for upgrading road space in old neighborhoods and countermeasure suggestions for future improvement of the human living environment.

The noise prediction of cassette air conditioners using AI models and analysis based on SHAP

This paper introduces a new noise prediction method for air conditioners. In this study, XAI (eXplainable Artificial Intelligence) technology was used to identify the refrigerant flow noise of cassette air conditioners. Using the RandomForest regression method of machine learning models and DNN and CNN of deep learning models, the noise prediction models were designed, and their performance were compared. In addition, a method of analyzing factors contributing to each model was presented using SHAP (SHapley Additive exPlanation), one of XAI that can explain the predicted model. Based on these results, the idea of the analysis was suggested to find the control factors for reducing the air conditioner noise.

Potentiality of ultraspectral sensor in biophysical and biochemical vegetation parameter inversion

ABSTRACT Biophysical and biochemical vegetation parameters are important indicators for quantitatively monitoring vegetation growth status and ecosystem. Compared to hyperspectral data, the emergence of ultraspectral remote sensing technology supports the acquisition of thousands of more narrow bands in near-infrared spectrum. It is helpful to capture more detailed vegetation spectral features, thereby providing more accurate quantitative inversion. However, there are still many unknowns in utilizing ultraspectral sensors for vegetation biochemical and biophysical parameters inversion, particularly in extracting meaningful inversion information from thousands of spectral bands. Here, we discuss the potentiality, efficiency and accuracy of the ultraspectral sensor AisaIBIS in this field. Firstly, we conducted sensitivity analysis based on simulated sensor dataset and the PROSAIL model to determine the vegetation parameters suitable for inversion. Secondly, in order to enhance the inversion efficiency and reduce the effects of multicollinearity in ultraspectral data, we proposed the stepped asymptotic optimization strategy that combined random forest (RF) and Gaussian process regression (GPR-BAT) methods for dimensionality reduction. Lastly, using experimental data, we compared the inversion accuracy between traditional band selection methods and our proposed method, thereby validating the application potential of ultraspectral sensors. The experimental results indicate that leaf area index (LAI), chlorophyll content, and brown pigment are the most sensitive parameters to the spectral information and are suitable for inversion. Based on the stepped asymptotic optimization strategy, we effectively avoid incomplete information extraction caused by high correlation and spectral redundancy, achieving optimal bands covering the entire spectrum of the sensor. The LAI inversion shows a correlation of 0.691 and an RMSE of 1.955 with the original data, outperforming the accuracy of the traditional band selection methods RF and principal component analysis (PCA). Moreover, the inversion time has decreased by approximately 66% after the dimensionality reduction. This study illustrates the application value of monitoring vegetation parameters by ultraspectral sensor.

Improving the Accuracy of Satellite-Derived Bathymetry Using Multi-Layer Perceptron and Random Forest Regression Methods: A Case Study of Tavşan Island

The spatial and spectral information brought by the Very High Resolution (VHR) and multispectral satellite images present an advantage for Satellite-Derived Bathymetry (SDB), especially in shallow-water environments with dense wave patterns. This work focuses on Tavşan Island, located in the Sea of Marmara (SoM), and aims to evaluate the accuracy and reliability of two machine learning (ML) regression methods, Multi-Layer Perceptron (MLP) and Random Forest (RF), for bathymetry mapping using Worldview-2 (WV-2) imagery. In situ bathymetry measurements were collected to enhance model training and validation. Pre-processing techniques, including water pixel extraction, sun-glint correction, and median filtering, were applied for image enhancement. The MLP and RF regression models were then trained using a comprehensive dataset that included spectral bands from the satellite image and corresponding ground truth depth values. The accuracy of the models was assessed using metrics such as Root-Mean-Square Error (RMSE), Mean Absolute Error (MAE), and R2 value. The RF regression model outperformed the MLP model, with a maximum R2 value of 0.85, lowest MAE values from 0.65 to 1.86 m, and RMSE values from 0.93 to 2.41 m at depth intervals between 6 and 9 m. These findings highlight the effectiveness of ML regression methods, specifically the RF model, for SDB based on remotely sensed images in wave-dense shallow-water environments.

A Comparative Investigation of Random Forest Regression and Artificial Neural Networks for Predicting Crack Growth Life of a Fighter Aircraft Wing Joint Under Spectrum Loading

Estimating fatigue life is challenging due to the input parameters’ statistical natures, such as the manufacturing process, scatter of service loads, microstructure, etc. Regarding fatigue life calculation in the aerospace industry, the importance of an accurate estimation becomes more critical due to strict safety, certification, service costs, and competitiveness regulations. The ability of soft computing methods to reveal complex relationships between multiple parameters and their computational speed could help predict fatigue life, especially in the service. This study compares random forest regression and artificial neural network methods to estimate the crack growth life of a fighter jet aircraft wing joint in terms of their computational time and accuracy. In addition, permutation feature importance and hyper parameter optimisation studies are conducted to extract essential features, investigate their effects on estimation performance, and fine-tune model parameters. The analysed joint is made of 7050-T7451 aluminium, widely used as a structural element in the aerospace industry. Since a hole is one of the major sources of stress concentration, and there may be many holes involved in any engineering structure, it is reasonable to assume that fatigue cracks may initiate at some of these holes during the service life of engineering structures. The crack type considered is a thru-crack around a hole, which is more severe than a corner crack. Load spectra are derived using the Fighter Aircraft Loading Standard for Fatigue (FALSTAFF) to calculate crack growth life. Considering particular service load conditions, ninety different spectra are developed, and the crack growth life of the joint is calculated based on linear elastic fracture mechanics correspondingly. Also, to simulate the worst-case scenario, friction between members and the retardation effect of load spectra are not considered when calculating crack growth life. Python’s Tensor Flow and Scikit-learn libraries are utilised to build machine learning models......

Improving estimation of maize leaf area index by combining of UAV-based multispectral and thermal infrared data: The potential of new texture index

Crop leaf area index (LAI) is one of the important indicators to evaluate crop growth and guide field management, and can be used to predict crop yield. Spectral and thermal information extracted by multispectral (MS) and thermal infrared (TIR) sensors mounted on an unmanned aerial vehicle (UAV) can be used for LAI estimation. Image texture is sensitive to the changes in crop surface grayscale or color characteristics, and can be combined with spectral and thermal information to estimate the LAI. But single texture metric has limitations in LAI estimation. Therefore, the purpose of this study is to construct new texture indices based on texture metrics extracted from MS and TIR images, and combined spectral and thermal information to enhance the estimation accuracy of maize LAI. Three replicates of maize experiments under different irrigation treatments were conducted in 2020. The MS and TIR sensors were mounted on a UAV to acquire maize canopy images during critical growth stages and acquire field LAI value of samples synchronously. The LAI estimation models were established using MS data, TIR data, as well as their combination. These models were constructed by Back Propagation Neural Network (BPNN), Partial least squares regression (PLSR), and Random Forest Regression (RFR). Finally, the performance of LAI estimation models was evaluated by the coefficient of determination (R2), root mean square error (RMSE) and relative root mean square error (rRMSE). Results shown that: (i) Among the eight kinds of texture metrics extracted from MS and TIR images, the texture metric mean (MEA) has the best performance. Compared with single texture metrics, texture indices constructed by different metrics has stronger correlation with LAI. (ii) Adding texture indices to estimation models significantly improved model accuracy, especially multispectral three-texture index(MS-TTI) has higher LAI estimation potential than thermal infrared three-texture index(TIR-TTI). (iii) Compared with the use of MS or TIR data alone, the estimation model constructed by combining MS data and TIR data have better performance. The best estimation model obtained by the RFR method (R2 = 0.862, RMSE = 0.246 and rRMSE = 10.20 %) further improved the LAI estimation of maize, with R2 increasing by 6.55 % and 14.48 %, respectively. In conclusion, the combination of MS and TIR data can effectively improve the estimation accuracy of maize LAI, and also provide a feasible method for monitoring crop growth.

Optimizing the growth of vertically aligned carbon nanotubes by literature mining and high-throughput experiments

Vertically aligned carbon nanotube (VACNT) arrays with good mechanical properties and high thermal conductivity can be used as effective thermal interface materials in thermal management. In order to take advantage of the high thermal conductivity along the axis of nanotubes, the quality and height of the arrays need to be optimized. However, the immense synthesis parameter space for VACNT arrays and the interdependence of structural features make it challenging to improve both their height and quality. We have developed a literature mining approach combined with machine learning and high-throughput design to efficiently optimize the height and quality of the arrays. To reveal the underlying relationship between VACNT structures and their key growth parameters, we used random forest regression (RFR) and SHapley Additive exPlanation (SHAP) methods to model a set of published sample data (864 samples). High-throughput experiments were designed to change 4 key parameters: growth temperature, growth time, catalyst composition, and concentration of the carbon source. It was found that a screened Fe/Gd/Al2O3 catalyst was able to grow VACNT arrays with millimeter-scale height and improved quality. Our results demonstrate that this approach can effectively deal with multi-parameter processes such as nanotube growth and improve control over their structures.

Application of a Hyperspectral Remote Sensing Model for the Inversion of Nickel Content in Urban Soil

Hyperspectral remote sensing technology can provide a rapid and nondestructive method for soil nickel (Ni) content detection. In order to select a high-effective method for estimating the soil Ni content using a hyperspectral remote sensing technique, 88 soil samples were collected in Urumqi, northwest China, to obtain Ni contents and related hyperspectral data. At first, 12 spectral transformations were used for the original spectral data. Then, Pearson’s correlation coefficient analysis (PCC) and the CARS method were used for selecting important wavelengths. Finally, partial least squares regression (PLSR), random forest regression (RFR) and support vector machine regression (SVMR) models were used to establish the hyperspectral inversion models of the Ni content in the soil using the important wavelengths. The coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and residual prediction deviation (RPD) were selected to evaluate the inversion effects of the models. The results indicated that using the PCC and CARS method for the original and transformed wavebands can effectively improve the correlations between the spectral data and Ni content of the soil in the study area. The random forest regression model, based on the first-order differentiation of the reciprocal (RTFD–RFR), was more stable and had the best inversion effects, with the highest predictive ability (R2 = 0.866, RMSE = 1.321, MAE = 0.986, RPD = 2.210) for determining the Ni content in the soil. The RTFD–RFR methods can be used as a means of the inversion of the Ni content in urban soil. The results of the study can provide a technical support for the hyperspectral estimation of the Ni content of urban soil.

Benchmarking Travel Time and Demand Prediction Methods Using Large-scale Metro Smart Card Data

Urban mass transit systems generate large volumes of data via automated systems established for ticketing, signalling, and other operational processes. This study is motivated by the observation that despite the availability of sophisticated quantitative methods, most public transport operators are constrained in exploiting the information their datasets contain. This paper intends to address this gap in the context of real-time demand and travel time prediction with smart card data. We comparatively benchmark the predictive performance of four quantitative prediction methods: multivariate linear regression (MVLR) and semiparametric regression (SPR) widely used in the econometric literature, and random forest regression (RFR) and support vector machine regression (SVMR) from machine learning. We find that the SVMR and RFR methods are the most accurate in travel flow and travel time prediction, respectively. However, we also find that the SPR technique offers lower computation time at the expense of minor inefficiency in predictive power in comparison with the two machine learning methods.

Sprinkler Irrigation Automation System to Reduce the Frost Impact Using Machine Learning

Frosts reduce the ambient temperature to the freezing point of water, affecting the agricultural sector and the integrity of plant tissues, severely damaged by freezing, destroying plant cells. In addition, losses are generated in the economy due to the death of cattle due to cold, hunger, diseases, etc. Latin America is a region that depends, to a considerable extent, on its crops for its consumption and export, so frost represents an urgent problem to solve, considering that in Perú the area of agriculture is not technical. Among the methods most used by farmers is anticipated irrigation, through automatic learning techniques, which allows predicting the behavior of a variable based on previous historical data. In this paper, sprinkler irrigation is implemented in crops exposed to frost, using an automated system with machine learning techniques and prediction models. Therefore, three types of models are evaluated (linear regression, random forests, and decision trees) to predict the occurrence of frosts, reducing damage to plants. The results show that the protection activation indicator from 1.1°C to 1.7°C was updated to decrease the number of false positives. On the three models evaluated, it is determined that the most accurate method is the Random Forest Regression method, which has 80.91% reliability, absolute mean error, and mean square error close to zero.

Optical coherence tomography angiography metrics in diabetes: Focusing on diabetic retinopathy and carotid atherosclerosis

BackgroundTo explore the value of Optical Coherence Tomography Angiography (OCTA) metrics in the early diagnosis of vascular complications in diabetes. MethodsAll participants underwent OCTA with a swept-source OCT device. Automated measurements of the foveal avascular zone (FAZ) area, vessel density (VD), and blood flow density (BFD) of both 3 × 3 and 6 × 6 windows were then obtained after a quality check. ResultsDiagnostic models based on multiple risk factors were developed separately for diabetic retinopathy and carotid atherosclerosis using random forest and multivariate logistic regression methods. The addition of specific OCTA metrics improved the diagnostic prediction of DR compared with the models of risk factors alone (Inner Retinal Blood Flow Density in 3 × 3 window, IRBFD; Brier score 0.124 vs. 0.149; AUC, 0.887 vs. 0.836) (Central Retinal Blood Flow Density in 3 × 3 window, CRBFD; Brier score 0.142 vs. 0.149; AUC, 0.851 vs. 0.836). Adding diabetic peripheral vascular disease (DPVD) indicator improved the prediction of carotid atherosclerosis (Brier score, 0.180 vs. 0.192; AUC, 0.802 vs. 0.781. The FAZ in the 3 × 3 window also achieved this effect when targeting only T2DM patients (AUC, 0.797 vs. 0.766; Brier score, 0.183 vs. 0.195). ConclusionsFocusing on IRBFD and CRBFD in the 3 × 3 window of OCTA allows for a more sensitive prediction of the occurrence of DR in diabetic patients. Meanwhile, the quantitative microvascular information provided by OCTA and the occurrence of DPVD may be crucial for diagnosing carotid atherosclerosis. For T2DM patients, we also propose the possibility of FAZ in the 3 × 3 window as a potential diagnostic indicator.