Search

Rubber is a perennial plant grown for natural rubber production, which is used in various global products. Ensuring the sustainability of rubber cultivation is crucial for smallholder farmers and economic development. Accurately predicting rubber yields is necessary to maintain price stability. Remote sensing technology is a valuable tool for collecting spatial data on a large scale. However, for smaller plots of land owned by smallholder farmers, it is necessary to process productivity estimates from high-resolution satellite data that are accurate and reliable. This study examines the impact of spatial factors on rubber yield and evaluates the technical suitability of using grouping analysis with the forest classification and regression (FCR) method. We developed a high-density variable using spatial data from rubber plots in close proximity to each other. Our approach incorporates eight environmental variables (proximity to streamlines, proximity to main river, soil drainage, slope, aspect, NDWI, NDVI, and precipitation) using an FCR model and GIS. We obtained a dataset of 1951 rubber yield locations, which we split into a training set (60%) for model development and a validation set (40%) for assessment using area under the curve (AUC) analysis. The results of the alternative FCR models indicate that Model 1 performs the best. It achieved the lowest root mean square error (RMSE) value of 19.15 kg/ha, the highest R-squared (R2) value (FCR) of 0.787, and also the highest R2 (OLS) value of 0.642. The AUC scores for Model 1, Model 2, and Model 3 were 0.792, 0.764, and 0.732, respectively. Overall, Model 4 exhibited the highest performance according to the AUC scores, while Model 3 performed the poorest with the lowest AUC score. Based on these findings, it can be concluded that Model 1 is the most effective in predicting FCR compared to the other alternative models. [ABSTRACT FROM AUTHOR]

A Bayesian additive regression tree (BART) is a recent statistical method that blends ensemble learning with nonparametric regression. BART is constructed using a Bayesian approach, which provides the benefit of model-based prediction uncertainty, enhancing the reliability of predictions. This study proposes the development of a BART model with a binomial likelihood to predict the percentage of students retained in tutorial classes using attendance data sourced from a South African university database. The data consist of tutorial dates and encoded (anonymized) student numbers, which play a crucial role in deriving retention variables such as cohort age, active students, and retention rates. The proposed model is evaluated and benchmarked against the random forest regressor (RFR). The proposed BART model reported an average of 20% higher predictive performance compared to RFR across six error metrics, achieving an R-squared score of 0.9414. Furthermore, the study demonstrates the utility of the highest density interval (HDI) provided by the BART model, which can help in determining the best- and worst-case scenarios for student retention rate estimates. The significance of this study extends to multiple stakeholders within the educational sector. Educational institutions, administrators, and policymakers can benefit from this study by gaining insights into how future tutorship programme student retention rates can be predicted using predictive models. Furthermore, the foresight provided by the predicted student retention rates can aid in strategic resource allocation, facilitating more informed planning and budgeting for tutorship programmes. [ABSTRACT FROM AUTHOR]

Beam pumping is currently the broadly used method for oil extraction worldwide. A pumpjack shutdown can be incurred by failures from the load, corrosion, work intensity, and downhole working environment. In this study, the duration of uninterrupted pumpjack operation is defined as the pump inspection cycle. Accurate prediction of the pump inspection cycle can extend the lifespan, reduce unexpected pump accidents, and significantly enhance the production efficiency of the pumpjack. To enhance the prediction performance, this study proposes an improved two-layer stacking ensemble model, which combines the power of the random forests, light gradient boosting machine, support vector regression, and Adaptive Boosting approaches, for predicting the pump inspection cycle. A big pump-related oilfield data set is used to demonstrate the proposed two-layer stacking ensemble model can significantly enhance the prediction quality of the pump inspection cycle. [ABSTRACT FROM AUTHOR]

In organic farming, clover is an important basis for green manure in crop rotation systems due to its nitrogen-fixing effect. However, clover is often sown in mixtures with grass to achieve a yield-increasing effect. In order to determine the quantity and distribution of clover and its influence on the subsequent crops, clover plants must be identified at the individual plant level and spatially differentiated from grass plants. In practice, this is usually done by visual estimation or extensive field sampling. High-resolution unmanned aerial vehicles (UAVs) offer a more efficient alternative. In the present study, clover and grass plants were classified based on spectral information from high-resolution UAV multispectral images and texture features using a random forest classifier. Three different timestamps were observed in order to depict the phenological development of clover and grass distributions. To reduce data redundancy and processing time, relevant texture features were selected based on a wrapper analysis and combined with the original bands. Including these texture features, a significant improvement in classification accuracy of up to 8% was achieved compared to a classification based on the original bands only. Depending on the phenological stage observed, this resulted in overall accuracies between 86% and 91%. Subsequently, high-resolution UAV imagery data allow for precise management recommendations for precision agriculture with site-specific fertilization measures. [ABSTRACT FROM AUTHOR]

Salinization is a major soil degradation process threatening ecosystems and posing a great challenge to sustainable agriculture and food security worldwide. This study aimed to evaluate the potential of state-of-the-art machine learning algorithms in soil salinity (EC1:5) mapping. Further, we predicted the distribution patterns of soil salinity under different future scenarios in the Yellow River Delta. A geodatabase comprising 201 soil samples and 19 conditioning factors (containing data based on remote sensing images such as Landsat, SPOT/VEGETATION PROBA-V, SRTMDEMUTM, Sentinel-1, and Sentinel-2) was used to compare the predictive performance of empirical bayesian kriging regression, random forest, and CatBoost models. The CatBoost model exhibited the highest performance with both training and testing datasets, with an average MAE of 1.86, an average RMSE of 3.11, and an average R2 of 0.59 in the testing datasets. Among explanatory factors, soil Na was the most important for predicting EC1:5, followed by the normalized difference vegetation index and soil organic carbon. Soil EC1:5 predictions suggested that the Yellow River Delta region faces severe salinization, particularly in coastal zones. Among three scenarios with increases in soil organic carbon content (1, 2, and 3 g/kg), the 2 g/kg scenario resulted in the best improvement effect on saline–alkali soils with EC1:5 > 2 ds/m. Our results provide valuable insights for policymakers to improve saline–alkali land quality and plan regional agricultural development. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) applications have been helping society in several ways. However, challenges still must be faced to enable efficient and secure IoT operations. In this context, IoT profiling refers to the service of identifying and classifying IoT devices' behavior based on different features using different approaches (e.g., Deep Learning). Data poisoning and adversarial attacks are challenging to detect and mitigate and can degrade the performance of a trained model. Thereupon, the main goal of this research is to propose the Overlapping Label Recovery (OLR) framework to mitigate the effects of label-flipping attacks in Deep-Learning-based IoT profiling. OLR uses Random Forests (RF) as underlying cleaners to recover labels. After that, the dataset is re-evaluated and new labels are produced to minimize the impact of label flipping. OLR can be configured using different hyperparameters and we investigate how different values can improve the recovery procedure. The results obtained by evaluating Deep Learning (DL) models using a poisoned version of the CIC IoT Dataset 2022 demonstrate that training overlap needs to be controlled to maintain good performance and that the proposed strategy improves the overall profiling performance in all cases investigated. [ABSTRACT FROM AUTHOR]

The present work focuses on predicting the steel melt temperature following the vacuum treatment step in a vacuum tank degasser (VTD). The primary objective is to establish a comprehensive methodology for developing and validating machine learning (ML) models within this context. Another objective is to evaluate the model by analyzing the alignment of the SHAP values with metallurgical domain expectations, thereby validating the model's predictions from a metallurgical perspective. The proposed methodology employs a Random Forest model, incorporating a grid search with domain-informed variables grouped into batches, and a robust model-selection criterion that ensures optimal predictive performance, while keeping the model as simple and stable as possible. Furthermore, the Shapley Additive Explanations (SHAP) algorithm is employed to interpret the model's predictions. The selected model achieved a mean adjusted R 2 of 0.631 and a hit ratio of 75.3% for a prediction error within ±5 °C. Despite the moderate predictive performance, SHAP highlighted several aspects consistent with metallurgical domain expertise, emphasizing the importance of domain knowledge in interpreting ML models. Improving data quality and refining the model framework could enhance predictive performance. [ABSTRACT FROM AUTHOR]

Obtaining accurate basic parameters for long hole blasting is challenging, and the resulting vibration damage significantly impacts key surface facilities. Predicting ground vibration velocity accurately and mitigating the harmful effects of blasting are crucial aspects of controlled blasting technology. This study focuses on the prediction of ground vibration velocity induced by underground long hole blasting tests. Utilizing the fitting equation based on the US Bureau of Mines (USBM) formula as a baseline for predicting peak particle velocity, two machine learning models suitable for small sample data, Support Vector Regression (SVR) machine and Random Forest (RF), were employed. The models were optimized using the particle swarm optimization algorithm (PSO) to predict peak particle velocity with multiple parameters specific to long hole blasting. Mean absolute error (MAE), mean Squared error (MSE), and coefficient of determination (R2) were used to assess the model predictions. Compared with the fitting equation based on the USBM model, both the Support Vector Regression (SVR) and Random Forest (RF) models accurately and effectively predict peak particle velocity, enhancing prediction accuracy and efficiency. The SVR model exhibited slightly superior predictive performance compared to the RF model. [ABSTRACT FROM AUTHOR]

The design of geopolymer concrete must meet more stringent requirements for the landscape, so understanding and designing geopolymer concrete with a higher compressive strength challenging. In the performance prediction of geopolymer concrete compressive strength, machine learning models have the advantage of being more accurate and faster. However, only a single machine learning model is usually used at present, there are few applications of ensemble learning models, and model optimization processes is lacking. Therefore, this paper proposes to use the Firefly Algorithm (AF) as an optimization tool to perform hyperparameter tuning on Logistic Regression (LR), Multiple Logistic Regression (MLR), decision tree (DT), and Random Forest (RF) models. At the same time, the reliability and efficiency of four integrated learning models were analyzed. The model was used to analyze the influencing factors of geopolymer concrete and determine the strength of their influencing ability. According to the experimental data, the RF-AF model had the lowest RMSE value. The RMSE value of the training set and test set were 4.0364 and 8.7202, respectively. The R value of the training set and test set were 0.9774 and 0.8915, respectively. Therefore, compared with the other three models, RF-AF has a stronger generalization ability and higher prediction accuracy. In addition, the molar concentration of NaOH was the most important influencing factors, and its influence was far greater than the other possible factors including NaOH content. Therefore, it is necessary to pay more attention to NaOH molarity when designing geopolymer concrete. [ABSTRACT FROM AUTHOR]

Global volcanic and plutonic olivines record the compositional characteristics and physicochemical conditions of the parental magmas. Thus, they have significant potential for use as petrogenetic discriminators of the olivine formation environment and prospecting indicators for potential host rocks of magmatic sulfide deposits. Several data visualization approaches have been proposed by researchers to determine olivine origins. However, they can only discriminate specific olivine populations and require the incorporation of trace elements for which data are lacking globally. In this study, a machine-learning method consisting of the random forest algorithm and the synthetic minority oversampling technique (SMOTE) is used to discriminate the crystallization environments of olivine and predict the sulfide potential of olivine-bearing mafic-ultramafic intrusions. We employ a global data set of 24 341 olivine samples from 12 environments to determine the contents of MgO, FeO, Ni, Ca, Mn, and Cr and the Fo number [100 × Mg/(Mg+Fe)]. The results indicate that the proposed method can classify olivine into genetically distinct populations and distinguish olivine derived from mineralized intrusions from that derived from sulfide-barren intrusions with high accuracies (higher than 99% on average). We develop a dimensionality reduction algorithm to visualize the olivine classifications using low-dimensional vectors and an olivine classifier (accessible at http://101.33.204.62:8080/olivine%5fweb/main.html China University of Geosciences, Beijing). The model is used successfully to identify the contributions of distinct sources to regional magmatism using olivines from the late Permian picrite and basalt along the western margin of the Yangtze block (SW China) and to predict the sulfide potential of the newly discovered Qixin mafic-ultramafic complex in the southern Central Asian Orogenic Belt (NW China). The findings suggest that the proposed approach enables the accurate identification of olivine origins in diferent formation environments and is a reliable indicator suitable for global Ni-Cu-platinum group element (PGE) exploration. [ABSTRACT FROM AUTHOR]

As an indicator of the optical characteristics of perovskite materials, the band gap is a crucial parameter that impacts the functionality of a wide range of optoelectronic devices. Obtaining the band gap of a material via a labor-intensive, time-consuming, and inefficient high-throughput calculation based on first principles is possible. However, it does not yield the most accurate results. Machine learning techniques emerge as a viable and effective substitute for conventional approaches in band gap prediction. This paper collected 201 pieces of data through the literature and open-source databases. By separating the features related to bits A, B, and X, a dataset of 1208 pieces of data containing 30 feature descriptors was established. The dataset underwent preprocessing, and the Pearson correlation coefficient method was employed to eliminate non-essential features as a subset of features. The band gap was predicted using the GBR algorithm, the random forest algorithm, the LightGBM algorithm, and the XGBoost algorithm, in that order, to construct a prediction model for organic–inorganic hybrid perovskites. The outcomes demonstrate that the XGBoost algorithm yielded an MAE value of 0.0901, an MSE value of 0.0173, and an R2 value of 0.991310. These values suggest that, compared to the other two models, the XGBoost model exhibits the lowest prediction error, suggesting that the input features may better fit the prediction model. Finally, analysis of the XGBoost-based prediction model's prediction results using the SHAP model interpretation method reveals that the occupancy rate of the A-position ion has the greatest impact on the prediction of the band gap and has an A-negative correlation with the prediction results of the band gap. The findings provide valuable insights into the relationship between the prediction of band gaps and significant characteristics of organic–inorganic hybrid perovskites. [ABSTRACT FROM AUTHOR]

Accurately predicting the condition rating of a bridge deck is crucial for effective maintenance and repair planning. Despite significant research efforts to develop deterioration models, the efficacy of Random Forest, eXtreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN) in predicting the condition rating of the nation's bridge decks has remained unexplored. This study aims to assess the effectiveness of these algorithms for deck condition rating prediction at the national level. To achieve this, the study collected bridge data, which includes National Bridge Inventory (NBI), traffic, and climate regions gathered using Geospatial Information Science (GIS) and remote sensing techniques. Two datasets were collected: bridge data for a single year of 2020 and historical bridge data covering a five-year period from 2016 to 2020. Three models were trained using 319,404 and 1,246,261 bridge decks in the single-year bridge data and the five-year historical bridge data, respectively. Results show that the use of historical bridge data significantly improves the performance of the models compared to the single-year bridge data. Specifically, the Random Forest model achieved an overall accuracy of 83.4% and an average F1 score of 79.7%. In contrast, the XGBoost model achieved an overall accuracy of 79.4% and an average F1 score of 77.5%, while the ANN model obtained an overall accuracy of 79.7% and an average F1 score of 78.4%. Permutation-based variable importance reveals that NBI, traffic, and climate regions significantly contribute to model development. In conclusion, the Random Forest, XGBoost, and ANN models, trained using updated historical bridge data, provide useful tools for accurately predicting the condition rating of bridge decks in the United States, allowing infrastructure managers to efficiently schedule inspections and allocate maintenance resources. [ABSTRACT FROM AUTHOR]

This study aims to enhance additive manufacturing (AM) quality control. AM builds 3D objects layer by layer, potentially causing defects. High-resolution micrograph data capture internal material defects, e.g., pores, which are vital for evaluating material properties, but image acquisition and analysis are time-consuming. This study introduces a hybrid machine learning (ML) approach that combines model-based image processing and data-driven supervised ML to detect and classify different pore types in AM micrograph data. Pixel-based features are extracted using, e.g., Sobel and Gaussian filters on the input micrograph image. Standard image processing algorithms detect pore defects, generating labels based on different features, e.g., area, convexity, aspect ratio, and circularity, and providing an automated feature labeling for training. This approach achieves sufficient accuracy by training a Random Forest as a hybrid-model data-driven classifier, compared with a pure data-driven model such as a CNN. [ABSTRACT FROM AUTHOR]

Accurate spatial distribution of gridded gross domestic product (GDP) data is crucial for revealing regional disparities within administrative units, thus facilitating a deeper understanding of regional economic dynamics, industrial distribution, and urbanization trends. The existing GDP spatial models often rely on prediction residuals for model evaluation or utilize residual distribution to improve the final accuracy, frequently overlooking the modifiable areal unit problem within residual distribution. This paper introduces a hybrid downscaling model that combines random forest and area-to-area kriging to map gridded GDP. Employing Thailand as a case study, GDP distribution maps were generated at a 1 km spatial resolution for the year 2015 and compared with five alternative downscaling methods and an existing GDP product. The results demonstrate that the proposed approach yields higher accuracy and greater precision in detailing GDP distribution, as evidenced by the smallest mean absolute error and root mean squared error values, which stand at USD 256.458 and 699.348 ten million, respectively. Among the four different sets of auxiliary variables considered, one consistently exhibited a higher prediction accuracy. This particular set of auxiliary variables integrated classification-based variables, illustrating the advantages of incorporating such integrated variables into modeling while accounting for classification characteristics. [ABSTRACT FROM AUTHOR]

Accelerometers are powerful tools for behavioral ecologists studying wild animals, particularly species that are difficult to observe due to their cryptic nature or dense or difficult to access habitats. Using a supervised approach, e.g., by observing in detail with a detailed ethogram the behavior of an individual wearing an accelerometer, to train a machine learning algorithm and the accelerometer data of one individual from a wild population of Javan slow lorises (Nycticebus javanicus), we applied a Random Forest model (RFM) to classify specific behaviors and posture or movement modifiers automatically. We predicted RFM would identify simple behaviors such as resting with the greatest accuracy while more complex behaviors such as feeding and locomotion would be identified with lower accuracy. Indeed, resting behaviors were identified with a mean accuracy of 99.16% while feeding behaviors were identified with a mean accuracy of 94.88% and locomotor behaviors with 85.54%. The model identified a total of 21 distinct combinations of six behaviors and 18 postural or movement modifiers in this dataset showing that RFMs are effective as a supervised approach to classifying accelerometer data. The methods used in this study can serve as guidelines for future research for slow lorises and other ecologically similar wild mammals. These results are encouraging and have important implications for understanding wildlife responses and resistance to global climate change, anthropogenic environmental modification and destruction, and other pressures. [ABSTRACT FROM AUTHOR]

In this paper, an approach to perform leak state detection and size identification for industrial fluid pipelines with an acoustic emission (AE) activity intensity index curve (AIIC), using b-value and a random forest (RF), is proposed. Initially, the b-value was calculated from pre-processed AE data, which was then utilized to construct AIICs. The AIIC presents a robust description of AE intensity, especially for detecting the leaking state, even with the complication of the multi-source problem of AE events (AEEs), in which there are other sources, rather than just leaking, contributing to the AE activity. In addition, it shows the capability to not just discriminate between normal and leaking states, but also to distinguish different leak sizes. To calculate the probability of a state change from normal condition to leakage, a changepoint detection method, using a Bayesian ensemble, was utilized. After the leak is detected, size identification is performed by feeding the AIIC to the RF. The experimental results were compared with two cutting-edge methods under different scenarios with various pressure levels and leak sizes, and the proposed method outperformed both the earlier algorithms in terms of accuracy. [ABSTRACT FROM AUTHOR]

In recent years, a new discipline known as Explainable Artificial Intelligence (XAI) has emerged, which has followed the growing trend experienced by Artificial Intelligence over the last decades. There are, however, important gaps in the adoption of XAI in hydrology research, in terms of application studies in the southern hemisphere, or in studies associated with snowmelt-driven streamflow prediction in arid regions, to mention a few. This paper seeks to contribute to filling these knowledge gaps through the application of XAI techniques in snowmelt-driven streamflow prediction in a basin located in the arid region of north-central Chile in South America. For this, two prediction models were built using the Random Forest algorithm, for one and four months in advance. The models show good prediction performance in the training set for one (RMSE:1.33, R2: 0.94, MAE:0.55) and four (RMSE: 5.67, R2:0.94, MAE: 1.51) months in advance. The selected interpretation techniques (importance of the variable, partial dependence plot, accumulated local effects plot, Shapley values and local interpretable model-agnostic explanations) show that hydrometeorological variables in the vicinity of the basin are more important than climate variables and this occurs both for the dataset level and for the months with the lowest streamflow records. The importance of the XAI approach adopted in this study is discussed in terms of its contribution to the understanding of hydrological processes, as well as its role in high-stakes decision-making. [ABSTRACT FROM AUTHOR]

Wetlands provide important ecosystem services, such as water conservation, biodiversity protection, and carbon sequestration. The Zoige alpine wetland is the largest high-altitude swamp in the world and plays a critical role in regional ecological balance and climate change. However, little is known about the fate of its soil organic carbon (SOC) storage. In this study, we estimated the degradation status of the wetland over the past 35 years and used machine learning to investigate the dynamics and driving factors of SOC at different soil depths of the Zoige wetland in 1985, 2000, and 2020. We also simulated the future SOC balance under different scenarios. The results showed that the area of Zoige wetland has degraded by 378.71 km2 in the past 35 years. Increased precipitation and solar radiation offset the adverse effects of global warming, making the soil act as a carbon sink in the past 35 years. The total SOC storage of the wetland soils in 1985, 2000, and 2020 was estimated to be 2.03 Pg, 2.05 Pg, and 2.21 Pg, respectively, with 46.95% of SOC distributed in the subsoil layers. Climate change was the most important driving factor controlling the SOC storage of the Zoige wetland, explaining 51.33% of the SOC changes in the soil. Temperature change was always the most important factor controlling wetland SOC, and precipitation had a greater impact on the topsoil. Under the temperature control targets of 1.5 °C and 2 °C, the SOC pool of the Zoige wetland will decrease by 60.21 Tg C and 69.19 Tg C, respectively. Under scenarios of a 10% and 20% increase in precipitation, the wetland soil will accumulate an additional 46.53 Tg C and 118.89 Tg C, respectively. The study results provide important references for the sustainable management of the Zoige wetland under the background of global climate change. [ABSTRACT FROM AUTHOR]

Accurate information on snow cover extent plays a crucial role in understanding regional and global climate change, as well as the water cycle, and supports the sustainable development of socioeconomic systems. Remote sensing technology is a vital tool for monitoring snow cover' extent, but accurate identification of shallow snow cover on the Tibetan Plateau has remained challenging. Focusing on the Three-Rivers Headwater Region (THR), this study addressed this issue by developing a snow cover discrimination model (SCDM) using a random forests (RF) algorithm. Using daily observed snow depth (SD) data from 15 stations in the THR during the period 2001–2013, a comprehensive analysis was conducted, considering various factors influencing regional snow cover distribution, such as land surface reflectance, land surface temperature (LST), Normalized Difference Snow Index (NDSI), Normalized Difference Vegetation Index (NDVI), and Normalized Difference Forest Snow Index (NDFSI). The key results were as follows: (1) Optimal model performance was achieved with the parameters Ntree, Mtry, and ratio set to 1000, 2, and 19, respectively. The SCDM outperformed other snow cover products in both pixel-scale and local spatial-scale discrimination. (2) Spectral information of snow cover proved to be the most influential auxiliary variable in discrimination, and the combined inclusion of NDVI and LST improved model performance. (3) The SCDM achieved accuracy of 99.04% for thick snow cover (SD > 4 cm) and 98.54% for shallow snow cover (SD ≤ 4 cm), significantly (p < 0.01) surpassing the traditional dynamic threshold method. This study can offer valuable reference for monitoring snow cover dynamics in regions with limited data availability. [ABSTRACT FROM AUTHOR]

This study considers the problem of approximating the temporal dynamics of the urban-rural temperature difference (ΔT) in Moscow megacity using machine learning (ML) models and predictors characterizing large-scale weather conditions. We compare several ML models, including random forests, gradient boosting, support vectors, and multi-layer perceptrons. These models, trained on a 21-year (2001–2021) dataset, successfully capture the diurnal, synoptic-scale, and seasonal variations of the observed ΔT based on predictors derived from rural weather observations or ERA5 reanalysis. Evaluation scores are further improved when using both sources of predictors simultaneously and involving additional features characterizing their temporal dynamics (tendencies and moving averages). Boosting models and support vectors demonstrate the best quality, with RMSE of 0.7 K and R2 > 0.8 on average over 21 years. For three selected summer and winter months, the best ML models forced only by reanalysis outperform the comprehensive hydrodynamic mesoscale model COSMO, supplied by an urban canopy scheme with detailed city-descriptive parameters and forced by the same reanalysis. However, for a longer period (1977–2023), the ML models are not able to fully reproduce the observed trend of ΔT increase, confirming that this trend is largely (by 60–70%) driven by megacity growth. Feature importance assessment indicates the atmospheric boundary layer height as the most important control factor for the ΔT and highlights the relevance of temperature tendencies as additional predictors. [ABSTRACT FROM AUTHOR]

Simple Summary: Cancer treatments often have side effects that may impair patients' quality of life. Our research aimed to create a predictive tool able to foresee the likelihood of these severe complications. We used medical data from 267 gastrointestinal cancer patients, applied a particular type of computer model known as a Bayesian network, and evaluated its predictions against real outcomes. The model accurately predicted the risk of developing severe haematological toxicity in 80–85% of cases. This tool, if further validated and refined, may help to identify a vulnerable subset of patients who might benefit from personalized treatment plans. Purpose: Severe toxicity is reported in about 30% of gastrointestinal cancer patients receiving 5-Fluorouracil (5-FU)-based chemotherapy. To date, limited tools exist to identify at risk patients in this setting. The objective of this study was to address this need by designing a predictive model using a Bayesian network, a probabilistic graphical model offering robust, explainable predictions. Methods: We utilized a dataset of 267 gastrointestinal cancer patients, conducting preprocessing, and splitting it into TRAIN and TEST sets (80%:20% ratio). The RandomForest algorithm assessed variable importance based on MeanDecreaseGini coefficient. The bnlearn R library helped design a Bayesian network model using a 10-fold cross-validation on the TRAIN set and the aic-cg method for network structure optimization. The model's performance was gauged based on accuracy, sensitivity, and specificity, using cross-validation on the TRAIN set and independent validation on the TEST set. Results: The model demonstrated satisfactory performance with an average accuracy of 0.85 (±0.05) and 0.80 on TRAIN and TEST datasets, respectively. The sensitivity and specificity were 0.82 (±0.14) and 0.87 (±0.07) for the TRAIN dataset, and 0.71 and 0.83 for the TEST dataset, respectively. A user-friendly tool was developed for clinical implementation. Conclusions: Despite several limitations, our Bayesian network model demonstrated a high level of accuracy in predicting the risk of developing severe haematological toxicity in gastrointestinal cancer patients receiving 5-FU-based chemotherapy. Future research should aim at model validation in larger cohorts of patients and different clinical settings. [ABSTRACT FROM AUTHOR]

Cryptocurrencies are rapidly growing and are increasingly accepted by major commercial vendors. However, along with their rising popularity, they have also become the go-to currency for illicit activities driven by the anonymity they provide. Cryptocurrencies such as the one on the Ethereum blockchain provide a way for entities to hide their real-world identities behind pseudonyms, also known as addresses. Hence, the purpose of this work is to uncover the level of anonymity in Ethereum by investigating multiclass classification models for Externally Owned Accounts (EOAs) of Ethereum. The researchers aim to achieve this by examining patterns of transaction activity associated with these addresses. Using a labelled Ethereum address dataset from Kaggle and the Ethereum crypto dataset by Google BigQuery, an address profiles dataset was compiled based on the transaction history of the addresses. The compiled dataset, consisting of 4371 samples, was used to tune and evaluate the Random Forest, Gradient Boosting and XGBoost classifier for predicting the category of the addresses. The best-performing model found for the problem was the XGBoost classifier, achieving an accuracy of 75.3% with a macro-averaged F1-Score of 0.689. Following closely was the Random Forest classifier, with an accuracy of 73.7% and a macro-averaged F1-Score of 0.641. Gradient Boosting came in last with 73% accuracy and a macro-averaged F1-Score of 0.659. Owing to the data limitations in this study, the overall scores of the best model were weaker in comparison to similar research, with the exception of precision, which scored slightly higher. Nevertheless, the results proved that it is possible to predict the category of an Ethereum wallet address such as Phish/Hack, Scamming, Exchange and ICO wallets based on its transaction behaviour. [ABSTRACT FROM AUTHOR]

For decades, humans have been confronted with numerous pest species, with the desert locust being one of the most damaging and having the greatest socio-economic impact. Trying to predict the occurrence of such pests is often complicated by the small number of records and observations in databases. This paper proposes a methodology based on a combination of classification and regression techniques to address not only the problem of locust sightings prediction, but also the number of locust individuals that may be expected. For this purpose, we apply different machine learning (ML) and related techniques, such as linear regression, Support Vector Machines, decision trees, random forests and neural networks. The considered ML algorithms are evaluated in three different scenarios in Western Africa, mainly Mauritania, and for the elaboration of the forecasting process, a number of meteorological variables obtained from the ERA5 reanalysis data are used as input variables for the classification–regression machines. The results obtained show good performance in terms of classification (appearance or not of desert locust), and acceptable regression results in terms of predicting the number of locusts, a harder problem due to the small number of samples available. We observed that the RF algorithm exhibited exceptional performance in the classification task (presence/absence) and achieved noteworthy results in regression (number of sightings), being the most effective machine learning algorithm among those used. It achieved classification results, in terms of F-score, around the value of 0.9 for the proposed Scenario 1. [ABSTRACT FROM AUTHOR]

The normalized difference vegetation index (NDVI) is one of the most common metrics used to describe vegetation dynamics. Unfortunately, low-quality pixels resulting from contamination (by features including clouds, snow, aerosols, and mixed factors) have impeded NDVI products' widespread application. Researchers have thought of several ways to improve NDVI quality when contamination occurs. However, most of these algorithms are based on the noise-negative deviation principle, which aligns low-value NDVI products to an upper line but ignores cases where absolute surface values are low. Consequently, to fill in these research gaps, in this article, we use the random forest model to produce a set of high-quality NDVI products to represent actual surface characteristics more accurately and naturally. Climate and geographical products are used as model inputs to describe environmental factors. They represent the random forest (RF) model that establishes relationships between MODIS NDVI products and meteorological products in high-quality areas. In addition, auxiliary data and empirical knowledge are employed to meet filling requirements. Notably, the random forest (RF) algorithm exhibits a mean absolute error (MAE) of 0.024 and a root mean squared error (RMSE) of 0.034, in addition to a coefficient of determination (R2) value of 0.974. Furthermore, the MAE and RMSE of the RF-based method decreased by 0.014 and 0.019, respectively, when compared to those of the STSG (spatial–temporal Savitzky–Golay) plan and by 0.013 and 0.015, respectively, when compared to the LSTM (long short-term memory) method. R2 increased by 0.039 and 0.027, respectively, compared to the STSG and LSTM methods. We introduced a novel series of NDVI products that demonstrated consistent spatial and temporal connectivity. The novel product exhibits enhanced adaptability to intricate environmental conditions and promises the potential for utilization in investigating vegetation dynamics within the Chinese region. [ABSTRACT FROM AUTHOR]

Particulate matter (PM) in the air can cause various health problems and diseases in humans. In particular, the smaller size of PM 2.5 enable them to penetrate deep into the lungs, causing severe health impacts. Exposure to PM 2.5 can result in respiratory, cardiovascular, and allergic diseases, and prolonged exposure has also been linked to an increased risk of cancer, including lung cancer. Therefore, forecasting the PM 2.5 concentration in the surrounding is crucial for preventing these adverse health effects. This paper proposes a method for forecasting the PM 2.5 concentration after 1 h using bidirectional long short-term memory (Bi-LSTM). The proposed method involves selecting input variables based on the feature importance calculated by random forest, classifying the data to assign weight variables to reduce bias, and forecasting the PM 2.5 concentration using Bi-LSTM. To compare the performance of the proposed method, two case studies were conducted. First, a comparison of forecasting performance according to preprocessing. Second, forecasting performance between deep learning (long short-term memory, gated recurrent unit, and Bi-LSTM) and conventional machine learning models (multi-layer perceptron, support vector machine, decision tree, and random forest). In case study 1, The proposed method shows that the performance indices (RMSE: 3.98%p, MAE: 5.87%p, RRMSE: 3.96%p, and R 2 :0.72%p) are improved because weights are given according to the input variables before the forecasting is performed. In case study 2, we show that Bi-LSTM, which considers both directions (forward and backward), can effectively forecast when compared to conventional models (RMSE: 2.70, MAE: 0.84, RRMSE: 1.97, R 2 : 0.16). Therefore, it is shown that the proposed method can effectively forecast PM 2.5 even if the data in the high-concentration section is insufficient. [ABSTRACT FROM AUTHOR]

Accurate high-spatial-resolution precipitation is significantly important in hydrological and meteorological modelling, especially in rain-gauge-sparse areas. Some methods and strategies have been applied for satellite-based precipitation downscaling, residual correction and precipitation calibration. However, which downscaling scheme can provide reliable high-resolution precipitation efficiently remains unanswered. To address this issue, this study aimed to present a framework combining the machine learning downscaling algorithm and post-process procedures. Firstly, four ML-based models, namely support vector regression, random forest, spatial random forest (SRF) and eXtreme gradient boosting (XGBoost), were tested for downscaling and compared with conventional downscaling methods. Then, the effectiveness of the residual correction process using ordinary Kriging and the calibration process using the geographical difference analysis (GDA) method was investigated. The results showed that the ML-based methods had better performance than the conventional regression and interpolation approaches. The SRF and XGBoost outperformed others in generating accurate precipitation estimation with a high resolution. The GDA calibration process significantly improved the downscaled results. However, the residual correction process decreased the downscaling performance of the ML-based models. Combining the SRF or XGBoost downscaling algorithm with the GDA calibration method could be a promising downscaling scheme for precipitation data. The scheme could be used to generate high-resolution precipitation, especially in areas urgently requiring data, which would benefit regional water resource management and hydrological disaster prevention. [ABSTRACT FROM AUTHOR]

This paper presents a new two-step approach for record linkage, focusing on the creation of high-quality training data in the first step. The approach employs the unsupervised random forest model as a similarity measure to produce a similarity score vector for record matching. Three constructions were proposed to select non-match pairs for the training data, with both balanced (symmetry) and imbalanced (asymmetry) distributions tested. The top and imbalanced construction was found to be the most effective in producing training data with 100% correct labels. Random forest and support vector machine classification algorithms were compared, and random forest with the top and imbalanced construction produced an F1-score comparable to probabilistic record linkage using the expectation maximisation algorithm and EpiLink. On average, the proposed approach using random forests and the top and imbalanced construction improved the F1-score by 1% and recall by 6.45% compared to existing record linkage methods. By emphasising the creation of high-quality training data, this new approach has the potential to improve the accuracy and efficiency of record linkage for a wide range of applications. [ABSTRACT FROM AUTHOR]

Simple Summary: The objective of the present study was to develop a tool to detect mildly lame cows by combining already existing data from sensors, automated milking systems (AMSs), routinely recorded animal and farm data and other phenotypes. Ten dairy farms were visited every 30–42 days from January 2020 to May 2021, and locomotion scores (LCSs) and body condition scores (BCSs) were assessed at each visit. For each farm, a lameness incidence risk was calculated. Further, the impact of lameness on the derived sensor parameters was inspected. Finally, random forest models for lameness detection were fit by including different combinations of influencing variables and compared for best results. The best performing model achieved an accuracy of 0.75 with a sensitivity of 0.72 and specificity of 0.78 for predicting an LCS ≥ 2. We conclude that the combination of data from an available sensor device with routinely available AMS data, animal and farm information, and performance records can provide promising results for the detection of mild lameness in dairy cattle. This study aimed to develop a tool to detect mildly lame cows by combining already existing data from sensors, AMSs, and routinely recorded animal and farm data. For this purpose, ten dairy farms were visited every 30–42 days from January 2020 to May 2021. Locomotion scores (LCS, from one for nonlame to five for severely lame) and body condition scores (BCS) were assessed at each visit, resulting in a total of 594 recorded animals. A questionnaire about farm management and husbandry was completed for the inclusion of potential risk factors. A lameness incidence risk (LCS ≥ 2) was calculated and varied widely between farms with a range from 27.07 to 65.52%. Moreover, the impact of lameness on the derived sensor parameters was inspected and showed no significant impact of lameness on total rumination time. Behavioral patterns for eating, low activity, and medium activity differed significantly in lame cows compared to nonlame cows. Finally, random forest models for lameness detection were fit by including different combinations of influencing variables. The results of these models were compared according to accuracy, sensitivity, and specificity. The best performing model achieved an accuracy of 0.75 with a sensitivity of 0.72 and specificity of 0.78. These approaches with routinely available data and sensor data can deliver promising results for early lameness detection in dairy cattle. While experimental automated lameness detection systems have achieved improved predictive results, the benefit of this presented approach is that it uses results from existing, routinely recorded, and therefore widely available data. [ABSTRACT FROM AUTHOR]

Accurate high-resolution soil moisture mapping is critical for surface studies as well as climate change research. Currently, regional soil moisture retrieval primarily focuses on a spatial resolution of 1 km, which is not able to provide effective information for environmental science research and agricultural water resource management. In this study, we developed a quantitative retrieval framework for high-resolution (250 m) regional soil moisture inversion based on machine learning, multisource data fusion, and in situ measurement data. Specifically, we used various data sources, including the normalized vegetation index, surface temperature, surface albedo, soil properties data, precipitation data, topographic data, and soil moisture products from passive microwave data assimilation as input parameters. The soil moisture products simulated based on ground model simulation were used as supplementary data of the in situ measurements, together with the measured data from the Maqu Observation Network as the training target value. The study was conducted in the Zoige region of the Tibetan Plateau during the nonfreezing period (May–October) from 2009 to 2018, using random forests for training. The random forest model had good accuracy, with a correlation coefficient of 0.885, a root mean square error of 0.024 m³/m³, and a bias of −0.004. The ground-measured soil moisture exhibited significant fluctuations, while the random forest prediction was more accurate and closely aligned with the field soil moisture compared to the soil moisture products based on ground model simulation. Our method generated results that were smoother, more stable, and with less noise, providing a more detailed spatial pattern of soil moisture. Based on the permutation importance method, we found that topographic factors such as slope and aspect, and soil properties such as silt and sand have significant impacts on soil moisture in the southeastern Tibetan Plateau. This highlights the importance of fine-scale topographic and soil property information for generating high-precision soil moisture data. From the perspective of inter-annual variation, the soil moisture in this area is generally high, showing a slow upward trend, with small spatial differences, and the annual average value fluctuates between 0.3741 m3/m3 and 0.3943 m3/m3. The intra-annual evolution indicates that the monthly mean average soil moisture has a large geographical variation and a small multi-year linear change rate. These findings can provide valuable insights and references for regional soil moisture research. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) has become widespread these days all over the world. PD affects the nervous system of the human and also affects a lot of human body parts that are connected via nerves. In order to make a classification for people who suffer from PD and who do not suffer from the disease, an advanced model called Bayesian Optimization-Support Vector Machine (BO-SVM) is presented in this paper for making the classification process. Bayesian Optimization (BO) is a hyperparameter tuning technique for optimizing the hyperparameters of machine learning models in order to obtain better accuracy. In this paper, BO is used to optimize the hyperparameters for six machine learning models, namely, Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Naive Bayes (NB), Ridge Classifier (RC), and Decision Tree (DT). The dataset used in this study consists of 23 features and 195 instances. The class label of the target feature is 1 and 0, where 1 refers to the person suffering from PD and 0 refers to the person who does not suffer from PD. Four evaluation metrics, namely, accuracy, F1-score, recall, and precision were computed to evaluate the performance of the classification models used in this paper. The performance of the six machine learning models was tested on the dataset before and after the process of hyperparameter tuning. The experimental results demonstrated that the SVM model achieved the best results when compared with other machine learning models before and after the process of hyperparameter tuning, with an accuracy of 92.3% obtained using BO. [ABSTRACT FROM AUTHOR]

The spatial and temporal variation analysis of land cover classification is important for studying the distribution and transformation of regional land cover changes. The Qilian Mountain National Park (QMNP), an important ecological barrier in northwestern China, has lacked land cover products for long time series. The Landsat images available on the Google Earth Engine (GEE) make it possible to analyze the land cover changes over the past three decades. The purpose of this study was to generate a long time series of datasets of land cover classification based on the method of sample migration in the QMNP in Northwest China. The Landsat 5, 7, and 8 images and field sample data were combined with multiple image features and the random forest algorithm to complete the land cover classification of the QMNP from 1990 to 2020. The results indicate that (1) the method of Jeffries–Matusita (J-M) distance can reduce image feature redundancy and show that elevation and phenological features have good differentiability among land cover types that were easy to mix with feature classes; (2) the spatial distribution of land cover every 10 years between 1990 and 2020 was consistent in the QMNP, and there were obvious differences in land cover from the east to the west part of the QMNP, with a large area of vegetation distribution in Sunan county in the central part and Tianzhu county in the east part of the QMNP; (3) over the past 30 years, forests and grasslands decreased by 62.2 km2 and 794.7 km2, respectively, while shrubs increased by 442.9 km2 in the QMNP. The conversion of bare land to grassland and the interconversion between different vegetation types were the main patterns of land cover changes, and the land cover changes were mainly concentrated in pastoral areas, meaning that human activity was the main factor of land cover changes; and (4) when the samples of 2020 were migrated to 2010, 2000, and 1990, the overall classification accuracies were 89.7%, 88.0%, 86.0%, and 83.9%, respectively. The results show that the vegetation conservation process in the QMNP was closely related to human activities. [ABSTRACT FROM AUTHOR]

Using traditional tea frost hazard risk assessment results as sample data, the four indicators of minimum temperature, altitude, tea planting area, and tea yield were selected to consider the risk of hazard-causing factors, the exposure of hazard-bearing bodies, and the vulnerability of hazard-bearing bodies. The random forest algorithm was used to construct the frost hazard risk assessment model of Hangzhou tea, and hazard risk assessment was carried out on tea with different cold resistances in Hangzhou. The model's accuracy reached 93% after training, and the interpretation reached more than 0.937. According to the risk assessment results of tea with different cold resistance, the high-risk areas of weak cold resistance tea were the most, followed by medium cold resistance and the least strong cold resistance. Compared with the traditional method, the prediction result of the random forest model has a deviation of only 1.57%. Using the random forest model to replace the artificial setting of the weight factor in the traditional method has the advantages of simple operation, high time efficiency, and high result accuracy. The prediction results have been verified by the existing hazard data. The model conforms to the actual situation and has certain guiding for local agricultural production and early warning of hazards. [ABSTRACT FROM AUTHOR]

Odor is a very serious problem worldwide. Thus, odor prediction research has been conducted consistently to help prevent odor. Odor substances that are complex odors are known, but complex odors and odor substances do not have a linear dependence. In addition, depending on the combination of odor substances, the causal relationships, such as synergy and antagonism, are different for complex odors. Research is needed to know this, but the situation is incomplete. Therefore, in this study, research was conducted through data-based research. The complex odor was predicted using various machine learning methods, and the effect of odor substances on the complex odor was verified using an explainable artificial intelligence method. In this study, according to the Malodor Prevention Act in Korea, complex odors are divided into two categories: acceptable and unacceptable. Analysis of variance and correlation analysis were used to determine the relationships between variables. Six machine learning methods (k-nearest neighbor, support vector classification, random forest, extremely randomized tree, eXtreme gradient boosting, and light gradient boosting machine) were used as predictive classification models, and the best predictive method was chosen using various evaluation metrics. As a result, the support vector machine that performed best in five out of six evaluation metrics was selected as the best model (f1-score = 0.7722, accuracy = 0.8101, sensitivity = 0.7372, specificity = 0.8656, positive predictive value = 0.8196, and negative predictive value = 0.8049). In addition, the partial dependence plot method from explainable artificial intelligence was used to understand the influence and interaction effects of odor substances. [ABSTRACT FROM AUTHOR]

Global solar irradiation is an important variable that can be used to determine the suitability of an area to install solar systems; nevertheless, due to the limitations of requiring measurement stations around the entire world, it can be correlated with different meteorological parameters. To confront this issue, different locations in Rias Baixas (Autonomous Community of Galicia, Spain) and combinations of parameters (month and average temperature, among others) were used to develop various machine learning models (random forest -RF-, support vector machine -SVM- and artificial neural network -ANN-). These three approaches were used to model and predict (one month ahead) monthly global solar irradiation using the data from six measurement stations. Afterwards, these models were applied to seven different measurement stations to check if the knowledge acquired could be extrapolated to other locations. In general, the ANN models offered the best results for the development and testing phases of the model, as well as for the phase of knowledge extrapolation to other locations. In this sense, the selected ANNs obtained a mean absolute percentage error (MAPE) value between 3.9 and 13.8% for the model development and an overall MAPE between 4.1 and 12.5% for the other seven locations. ANNs can be a capable tool for modelling and predicting monthly global solar irradiation in areas where data are available and for extrapolating this knowledge to nearby areas. [ABSTRACT FROM AUTHOR]

Even though Industrial Kitchens (IKs) are among the highest energy intensity spaces, very little work has been done to forecast their consumption. This work explores the possibility of increasing the accuracy of the consumption forecast in an IK by forecasting disaggregated appliance consumption and comparing these results with the forecast of the total consumption of these appliances (Virtual Aggregate—VA). To do so, three different methods are used: the statistical method (Prophet), classic Machine Learning (ML) method such as random forest (RF), and deep learning (DL) method, namely long short-term memory (LSTM). This work uses individual appliance electricity consumption data collected from a Portuguese restaurant over a period of four consecutive weeks. The obtained results suggest that Prophet and RF are the more viable options. The former achieved the best performance in aggregated data, whereas the latter showed better forecasting results for most of the individual loads. Regarding the performance of the VA against the sum of individual appliance forecasts, all models perform better in the former. However, the very small difference across the results shows that this is a viable alternative to forecast aggregated consumption when only individual appliance consumption data are available. [ABSTRACT FROM AUTHOR]

In recent years, CO2 flooding has emerged as an efficient method for improving oil recovery. It also has the advantage of storing CO2 underground. As one of the promising types of CO2 enhanced oil recovery (CO2-EOR), CO2 water-alternating-gas injection (CO2-WAG) can suppress CO2 fingering and early breakthrough problems that occur during oil recovery by CO2 flooding. However, the evaluation of CO2-WAG is strongly dependent on the injection parameters, which in turn renders numerical simulations computationally expensive. So, in this work, machine learning is used to help predict how well CO2-WAG will work when different injection parameters are used. A total of 216 models were built by using CMG numerical simulation software to represent CO2-WAG development scenarios of various injection parameters where 70% of them were used as training sets and 30% as testing sets. A random forest regression algorithm was used to predict CO2-WAG performance in terms of oil production, CO2 storage amount, and CO2 storage efficiency. The CO2-WAG period, CO2 injection rate, and water–gas ratio were chosen as the three main characteristics of injection parameters. The prediction results showed that the predicted value of the test set was very close to the true value. The average absolute prediction deviations of cumulative oil production, CO2 storage amount, and CO2 storage efficiency were 1.10%, 3.04%, and 2.24%, respectively. Furthermore, it only takes about 10 s to predict the results of all 216 scenarios by using machine learning methods, while the CMG simulation method spends about 108 min. It demonstrated that the proposed machine-learning method can rapidly predict CO2-WAG performance with high accuracy and high computational efficiency under conditions of various injection parameters. This work gives more insights into the optimization of the injection parameters for CO2-EOR. [ABSTRACT FROM AUTHOR]

Noisy environments, changes and variations in the volume of speech, and non-face-to-face conversations impair the user experience with hearing aids. Generally, a hearing aid amplifies sounds so that a hearing-impaired person can listen, converse, and actively engage in daily activities. Presently, there are some sophisticated hearing aid algorithms available that operate on numerous frequency bands to not only amplify but also provide tuning and noise filtering to minimize background distractions. One of those is the BioAid assistive hearing system, which is an open-source, freely available downloadable app with twenty-four tuning settings. Critically, with this device, a person suffering with hearing loss must manually alter the settings/tuning of their hearing device when their surroundings and scene changes in order to attain a comfortable level of hearing. However, this manual switching among multiple tuning settings is inconvenient and cumbersome since the user is forced to switch to the state that best matches the scene every time the auditory environment changes. The goal of this study is to eliminate this manual switching and automate the BioAid with a scene classification algorithm so that the system automatically identifies the user-selected preferences based on adequate training. The aim of acoustic scene classification is to recognize the audio signature of one of the predefined scene classes that best represent the environment in which it was recorded. BioAid, an open-source biological inspired hearing aid algorithm, is used after conversion to Python. The proposed method consists of two main parts: classification of auditory scenes and selection of hearing aid tuning settings based on user experiences. The DCASE2017 dataset is utilized for scene classification. Among the many classifiers that were trained and tested, random forests have the highest accuracy of 99.7%. In the second part, clean speech audios from the LJ speech dataset are combined with scenes, and the user is asked to listen to the resulting audios and adjust the presets and subsets. A CSV file stores the selection of presets and subsets at which the user can hear clearly against the scenes. Various classifiers are trained on the dataset of user preferences. After training, clean speech audio was convolved with the scene and fed as input to the scene classifier that predicts the scene. The predicted scene was then fed as input to the preset classifier that predicts the user's choice for preset and subset. The BioAid is automatically tuned to the predicted selection. The accuracy of random forest in the prediction of presets and subsets was 100%. This proposed approach has great potential to eliminate the tedious manual switching of hearing assistive device parameters by allowing hearing-impaired individuals to actively participate in daily life by automatically adjusting hearing aid settings based on the acoustic scene. [ABSTRACT FROM AUTHOR]

Stress echocardiography (SE) is based on regional wall motion abnormalities and coronary flow velocity reserve (CFVR). Their independent prognostic capabilities could be better studied with a machine learning (ML) approach. The study aims to assess the SE outcome data by conducting an analysis with an ML approach. We included 6881 prospectively recruited and retrospectively analyzed patients with suspected (n = 4279) or known (n = 2602) coronary artery disease submitted to clinically driven dipyridamole SE. The outcome measure was all-cause death. A random forest survival model was implemented to model the survival function according to the patient's characteristics; 1002 patients recruited by a single, independent center formed the external validation cohort. During a median follow-up of 3.4 years (IQR 1.6–7.5), 814 (12%) patients died. The mortality risk was higher for patients aged >60 years, with a resting ejection fraction < 60%, resting WMSI, positive stress-rest WMSI scores, and CFVR < 3.The C-index performance was 0.79 in the internal and 0.81 in the external validation data set. Survival functions for individual patients were easily obtained with an open access web app. An ML approach can be fruitfully applied to outcome data obtained with SE. Survival showed a constantly increasing relationship with a CFVR < 3.0 and stress-rest wall motion score index > Since processing is largely automated, this approach can be easily scaled to larger and more comprehensive data sets to further refine stratification, guide therapy and be ultimately adopted as an open-source online decision tool. [ABSTRACT FROM AUTHOR]

Customer churn is a critical issue impacting enterprises and organizations, particularly in the emerging and highly competitive telecommunications industry. It is important to researchers and industry analysts interested in projecting customer behavior to separate churn from non-churn consumers. The fundamental incentive is a firm's intent desire to keep current consumers, along with the exorbitant expense of gaining new ones. Many solutions have been developed to address customer churn prediction (CCP), such as rule-based and machine learning (ML) solutions. However, the issue of scalability and robustness of rule-based customer churn solutions is a critical drawback, while the imbalanced nature of churn datasets has a detrimental impact on the prediction efficacy of conventional ML techniques in CCP. As a result, in this study, we developed intelligent decision forest (DF) models for CCP in telecommunication. Specifically, we investigated the prediction performances of the logistic model tree (LMT), random forest (RF), and Functional Trees (FT) as DF models and enhanced DF (LMT, RF, and FT) models based on weighted soft voting and weighted stacking methods. Extensive experimentation was performed to ascertain the efficacy of the suggested DF models utilizing publicly accessible benchmark telecom CCP datasets. The suggested DF models efficiently distinguish churn from non-churn consumers in the presence of the class imbalance problem. In addition, when compared to baseline and existing ML-based CCP methods, comparative findings showed that the proposed DF models provided superior prediction performances and optimal solutions for CCP in the telecom industry. Hence, the development and deployment of DF-based models for CCP and applicable ML tasks are recommended. [ABSTRACT FROM AUTHOR]

Soil moisture is one of the core hydrological and climate variables that crucially influences water and energy budgets. The spatial resolution of available soil moisture products is generally coarser than 25 km, which limits their hydro-meteorological and eco-hydrological applications and the management of water resources at watershed and agricultural scales. A feasible solution to overcome these limitations is to downscale coarse soil moisture products with the support of higher-resolution spatial information. Although many auxiliary variables have been used for this purpose, few studies have analyzed their applicability and effectiveness in arid regions. To this end, we comprehensively evaluated four commonly used auxiliary variables, including NDVI (Normalized Difference Vegetation Index), LST (Land Surface Temperature), TVDI (Temperature Vegetation Dryness Index), and SEE (Soil Evaporative Efficiency), against ground-based soil moisture observations during the vegetation growing season in the Heihe River Basin, China. Performance metrics indicated that SEE is most sensitive (R2 ≥ 0.67) to soil moisture because it is controlled by soil evaporation limited by the available soil moisture. The similarity of spatial patterns also showed that SEE best captures soil moisture changes, with the STD (standard deviation) of the HD (Hausdorff Distance) less than 0.058 when compared with PLMR (Polarimetric L-band Multi-beam Radiometer) soil moisture products. In addition, soil moisture was mapped by RF (Random Forests) using both single auxiliary variables and 11 types of multiple auxiliary variable combinations. SEE was found to be the best auxiliary variable for scaling and mapping soil moisture with accuracy of 0.035 cm3/cm3. Among the multiple auxiliary variables, the combination of LST, NDVI, and SEE was found to best enhance the scaling and mapping accuracy of soil moisture with 0.034 cm3/cm3. [ABSTRACT FROM AUTHOR]

Machine learning-based methods are commonly used for landslide susceptibility mapping. Most of the recent publications focused on quantitative analysis, i.e., improving data processing methods, comparing and perfecting the data-driven model itself, but rarely taking the qualitative aspects of the local landslide occurrences into consideration and the further analysis of the key features was always lacking. This study aims to combine qualitative and quantitative analysis and examine its effect on mapping accuracy; based on the feature importance ranks and the related literature, the key features for identifying landslide/non-landslide points of different sub-zones were further analyzed. Before modeling, the study area Yunyang County, Chongqing City, China, was manually divided into four sub-zones based on the information from geological hazards exploration in Chongqing, including the mechanism of landslide formation and sliding failure and geomorphic unit characteristics. Upon the qualitative analysis basis, five grid searches tuned random forest models (one for the whole region and four for the sub-zones independently) were established by 1654 data points and 20 conditioning features. Compared with the conventional data-driven method, the integrated quantitative evaluation based on the qualitative analysis results showed higher reliability, which not only improved the mapping accuracy but also increased the AUC values of all four sub-models, which were 8.8%, 2.3%, 1.9% and 9.1% higher than that of the parent model. Moreover, the quantitative evaluation based on the qualitative analysis revealed the key factors affecting local landslide formation. Therefore, qualitative analysis is recommended in future landslide susceptibility modeling with the additional combination of data-driven methods. [ABSTRACT FROM AUTHOR]

EISCAT VHF radar data are used for observing, monitoring, and understanding Earth's upper atmosphere. This paper presents an approach to segment Polar Mesospheric Summer Echoes (PMSE) from datasets obtained from EISCAT VHF radar data. The data consist of 30 observations days, corresponding to 56,250 data samples. We manually labeled the data into three different categories: PMSE, Ionospheric background, and Background noise. For segmentation, we employed random forests on a set of simple features. These features include: altitude derivative, time derivative, mean, median, standard deviation, minimum, and maximum values corresponding to neighborhood sizes ranging from 3 by 3 to 11 by 11 pixels. Next, in order to reduce the model bias and variance, we employed a method that decreases the weight applied to pixel labels with large uncertainty. Our results indicate that, first, it is possible to segment PMSE from the data using random forests. Second, the weighted-down labels technique improves the performance of the random forests method. [ABSTRACT FROM AUTHOR]

Feature selection (FS) is a vital step in data mining and machine learning, especially for analyzing the data in high-dimensional feature space. Gene expression data usually consist of a few samples characterized by high-dimensional feature space. As a result, they are not suitable to be processed by simple methods, such as the filter-based method. In this study, we propose a novel feature selection algorithm based on the Explosion Gravitation Field Algorithm, called EGFAFS. To reduce the dimensions of the feature space to acceptable dimensions, we constructed a recommended feature pool by a series of Random Forests based on the Gini index. Furthermore, by paying more attention to the features in the recommended feature pool, we can find the best subset more efficiently. To verify the performance of EGFAFS for FS, we tested EGFAFS on eight gene expression datasets compared with four heuristic-based FS methods (GA, PSO, SA, and DE) and four other FS methods (Boruta, HSICLasso, DNN-FS, and EGSG). The results show that EGFAFS has better performance for FS on gene expression data in terms of evaluation metrics, having more than the other eight FS algorithms. The genes selected by EGFAGS play an essential role in the differential co-expression network and some biological functions further demonstrate the success of EGFAFS for solving FS problems on gene expression data. [ABSTRACT FROM AUTHOR]

Solar irradiance forecasting has been an essential topic in renewable energy generation. Forecasting is an important task because it can improve the planning and operation of photovoltaic systems, resulting in economic advantages. Traditionally, single models are employed in this task. However, issues regarding the selection of an inappropriate model, misspecification, or the presence of random fluctuations in the solar irradiance series can result in this approach underperforming. This paper proposes a heterogeneous ensemble dynamic selection model, named HetDS, to forecast solar irradiance. For each unseen test pattern, HetDS chooses the most suitable forecasting model based on a pool of seven well-known literature methods: ARIMA, support vector regression (SVR), multilayer perceptron neural network (MLP), extreme learning machine (ELM), deep belief network (DBN), random forest (RF), and gradient boosting (GB). The experimental evaluation was performed with four data sets of hourly solar irradiance measurements in Brazil. The proposed model attained an overall accuracy that is superior to the single models in terms of five well-known error metrics. [ABSTRACT FROM AUTHOR]

In most countries, freight is predominantly transported by road cargo trucks. We present a new satellite remote sensing method for detecting moving trucks on roads using Sentinel-2 data. The method exploits a temporal sensing offset of the Sentinel-2 multispectral instrument, causing spatially and spectrally distorted signatures of moving objects. A random forest classifier was trained (overall accuracy: 84%) on visual-near-infrared-spectra of 2500 globally labelled targets. Based on the classification, the target objects were extracted using a developed recursive neighbourhood search. The speed and the heading of the objects were approximated. Detections were validated by employing 350 globally labelled target boxes (mean F 1 score: 0.74). The lowest F 1 score was achieved in Kenya (0.36), the highest in Poland (0.88). Furthermore, validated at 26 traffic count stations in Germany on in sum 390 dates, the truck detections correlate spatio-temporally with station figures (Pearson r-value: 0.82, RMSE: 43.7). Absolute counts were underestimated on 81% of the dates. The detection performance may differ by season and road condition. Hence, the method is only suitable for approximating the relative truck traffic abundance rather than providing accurate absolute counts. However, existing road cargo monitoring methods that rely on traffic count stations or very high resolution remote sensing data have limited global availability. The proposed moving truck detection method could fill this gap, particularly where other information on road cargo traffic are sparse by employing globally and freely available Sentinel-2 data. It is inferior to the accuracy and the temporal detail of station counts, but superior in terms of spatial coverage. [ABSTRACT FROM AUTHOR]

In this work, we use a copula-based approach to select the most important features for a random forest classification. Based on associated copulas between these features, we carry out this feature selection. We then embed the selected features to a random forest algorithm to classify a label-valued outcome. Our algorithm enables us to select the most relevant features when the features are not necessarily connected by a linear function; also, we can stop the classification when we reach the desired level of accuracy. We apply this method on a simulation study as well as a real dataset of COVID-19 and for a diabetes dataset. [ABSTRACT FROM AUTHOR]

Energy being a precious resource needs to be mindfully utilized, so that efficiency is achieved and its wastage is curbed. Globally, multi-storeyed buildings are the biggest energy consumers. A large portion of energy within a building is consumed to maintain the desired temperature for the comfort of occupants. For this purpose, heating load and cooling load requirements of the building need to be met. These requirements should be minimized to reduce energy consumption and optimize energy usage. Some characteristics of buildings greatly affect the heating load and cooling load requirements. This paper presented a systematic approach for analysing various factors of a building playing a vital role in energy consumption, followed by the algorithmic approaches of traditional machine learning and modern ensemble learning for energy consumption prediction in residential buildings. The results revealed that ensemble techniques outperform machine learning techniques with an appreciable margin. The accuracy of predicting heating load and cooling load, respectively, with multiple linear regression was 88.59% and 85.26%, with support vector regression was 82.38% and 89.32%, with K-nearest neighbours was 91.91% and 94.47%. The accuracy achieved with ensemble techniques was comparatively better—99.74% and 94.79% with random forests, 99.73% and 96.22% with gradient boosting machines, 99.75% and 95.94% with extreme gradient boosting. [ABSTRACT FROM AUTHOR]

The random forest, a powerful machine learning algorithm, is introduced to improve the performance of silicon arrayed waveguide grating (AWG)‐based fibre Bragg grating (FBG) wavelength interrogation. The experimental results show the proposed method has high interrogation accuracy with the root mean squared error (RMSE) of 0.73 pm in the whole demodulation range. [ABSTRACT FROM AUTHOR]

Eutrophication is severely affecting species distributions and ecosystem functioning in coastal areas. Targets for eutrophication reduction have been set in the Baltic Sea Action Plan ( BSAP) using Secchi depth, a measure of water transparency, as the main status indicator. Despite the high economic costs involved, the potential effects of this political decision on key species and habitats have not been assessed., In a case study including species central to coastal ecosystem functioning, we modelled the effects of changing Secchi depth on the distribution of bladderwrack Fucus vesiculosus and eelgrass Zostera marina vegetation as well as recruitment areas of the main predatory fish species, perch Perca fluviatilis and pikeperch Sander lucioperca. Specifically, we explored the effects of changing Secchi depth on species distributions under a set of scenarios based on the BSAP, using three fundamentally different modelling techniques: maximum entropy, generalized additive and random forest modelling., Improved Secchi depth (reduced eutrophication) was predicted to cause a substantial increase in the distribution of bladderwrack, while the distribution of eelgrass remained largely unaffected. For the fish, a large increase in perch recruitment areas was predicted and a concurrent decrease in recruitment areas of pikeperch. These changes are likely to have effects on biodiversity and ecosystem services., The three modelling methods exposed differences in the quantitative predictions for species with a weaker coupling to Secchi depth. Qualitatively, however, the results were consistent for all species., Synthesis and applications. We show how ecological effects of environmental policies can be evaluated in an explicit spatial context using species distribution modelling. The model-specific responses to changes in eutrophication status emphasize the importance of using ensemble modelling for exploring how species distributions may respond to alternative management regimes. A pronounced difference in response between species suggests that eutrophication mitigation will have consequences for ecosystem functioning, and thus ecosystem goods and services, by inducing changes in the simple food webs of the Baltic Sea. These model predictions form a basis for spatially explicit cost-benefit estimates under different scenarios, providing valuable information for both decision-makers and the wider society. [ABSTRACT FROM AUTHOR]

Audio classification algorithms for hearing aids require excellent classification accuracy. To achieve effective performance, we first present a novel supervised method, involving a spectral entropy-based magnitude feature with a random forest classifier (SEM-RF). A novel-feature SEM based on the similarity and stability of band signals is introduced to improve the classification accuracy of each audio environment. The random forest (RF) model is applied to perform the classification process. Subsequently, to resolve the problem of decreasing classification accuracy of the SEM-RF algorithm in mixed speech environments, an improved algorithm, ImSEM-RF, is proposed. The SEM features and corresponding phase features are fused on multiple time resolutions to form a robust multi-time resolution magnitude and phase (multi-MP) feature, which improves the stability of the feature with which the speech signal interferes. The RF model is improved using the linear discriminant analysis (LDA) method to form a linear discriminant analysis-random forest (LDA-RF) joint classification model, which performs model acceleration. Through experiments on hearing aid research data sets for acoustic environment recognition, the effectiveness of the SEM-RF algorithm was confirmed on a background audio signal dataset. The classification accuracy increased by approximately 7% compared with the background noise classification algorithm using an RF tree classifier. The validity of the ImSEM-RF algorithm in speech-interference environments was confirmed using the speech in the background audio signal dataset. Compared with the SEM-RF algorithm, the classification accuracy was improved by approximately 2%. The LDA-RF reduced the program's running time by >80% with multi-MP features compared with RF. [ABSTRACT FROM AUTHOR]