Search

Machine learning classifiers are increasingly widely used. This research note explores how a particular widely used classifier, the Random Forest, performs when faced with samples which are imbalanced and noisy data. Both are known to affect accuracy, but if their effects are independent or not has not been explored. Based on an experiment using synthetic data generated for the study we find that the effects of noise and sample balance interact with each other; classification accuracy is worse when faced with both noisy data and sample imbalance. This has implications for the use of RF in market research, but also for how methods to address either sample imbalance or noise are assessed. [ABSTRACT FROM AUTHOR]

The competition among Food & Beverage companies has substantially increased in today's age of digitization. Sales forecasting is one of their main challenges. Due to space limitations, employee shortages, and rising online demand, retail sales forecasting became extremely important for Food and Beverage companies. This research analyzed the sales data of a multinational Food & Beverage Company. It proposed a framework using Gaussian Mixture Model (GMM) clustering, Hierarchical Agglomerative Clustering (HAC), and Random Forest algorithm for forecasting sales. This model analyzes the impact of the weekends, holidays, promotional activities, customer sentiments, festivals, and socio-economic situations in sales data and is able to forecast sales ranging from one to 15 months. An investigation of the suggested model's performance compared to numerous cutting-edge sales forecasting techniques is carried out to show its efficacy. Here, we demonstrate that the proposed hybrid model surpasses current predicting and computing efficiency methods. The results of this study can help retail managers to allocate resources and manage inventories in well-informed ways. The findings suggest that combining many strategies may produce the most precise forecasts. [ABSTRACT FROM AUTHOR]

In the era of advanced cyber developments, intrusions becomes a common event in any network. Although there are research studies and developers found ways to improve the detection models, there is some problem that persists in the intrusion models such as extracting key features from a large dataset, and delayed detection is a critical issue that needs to be addressed. Hence the proposed study aimed to develop a model that could extract key features from the dataset and use them effectively in the detection of threats. The study incorporates two approaches, one is feature extraction by the K-Nearest Neighbourhood, and feature selection by the K-Best approach. And the other is the balanced Gini-Entropy approach for the Random Forest (RF) classifier. This combined approach by KNN, K-best, and RF is referred to as (KK-RF). This combined approach of feature extraction, selection, and classification results in an effective threat detection model with high accuracy of about 99.61%. Moreover the proposed model has achieved precision and the recall rates of 97.3 and 96.6% respectively. Concurrently, the model attained markable F1-score of 96.6 respectively. Also, from the comparison results, it is observed that the proposed model had higher performance. [ABSTRACT FROM AUTHOR]

Understanding the intricate pathways of protein secretion in bacteria is crucial for advancing research on bacterial diseases and their potential treatments, particularly in the case of non-classical protein secretion pathways. These pathways pose unique challenges due to the complex signaling mechanisms involved. To address this, we employed advanced machine learning techniques and gathered physical–chemical characteristics of amino acids from the AA index site. Through a meticulous six-step methodology, we curated a comprehensive dataset by filtering raw genome data and juxtaposing it with a positive dataset comprising 141 proteins from authoritative literature sources. Leveraging a conventional Random Forest machine learning algorithm, we achieved an impressive accuracy rate of approximately 91% in classifying non-classical secreted proteins. This validation was conducted on a dataset of 14 positive and 92 negative proteins, resulting in a sensitivity of 91% and a specificity of 86%. Notably, our study distinguishes itself by its rapid execution of non-classical secretion pathway analyses, rendering it particularly suitable for large datasets. This speed does not compromise accuracy, allowing for comprehensive Omics analyses. Consequently, our research underscores the significance of carefully selecting appropriate descriptors and constructing a robust training dataset to enhance Omics analyses of bacterial protein secretion via non-classical pathways. For further details, please refer to the complete study available at https://github.com/santosardr/non-CSPs. [ABSTRACT FROM AUTHOR]

Background: Colorectal cancer (CRC) is a common cancer that causes millions of deaths worldwide each year. At present, numerous studies have confirmed that intestinal microbes play a crucial role in the process of CRC. Additionally, studies have shown that CRC can be divided into several consensus molecular subtypes (CMS) based on tumor gene expression, and CRC microbiomes have been reported related to CMS. However, most previous studies on intestinal microbiome of CRC have only compared patients with healthy controls, without classifying of CRC patients based on intestinal microbial composition. Results: In this study, a CRC cohort including 339 CRC samples and 333 healthy controls was selected as the discovery set, and the CRC samples were divided into two subgroups (234 Subgroup1 and 105 Subgroup2) using PAM clustering algorithm based on the intestinal microbial composition. We found that not only the microbial diversity was significantly different (Shannon index, p-value < 0.05), but also 129 shared genera altered (p-value < 0.05) between the two CRC subgroups, including several marker genera in CRC, such as Fusobacterium and Bacteroides. A random forest algorithm was used to construct diagnostic models, which showed significantly higher efficiency when the CRC samples were divided into subgroups. Then an independent cohort including 187 CRC samples (divided into 153 Subgroup1 and 34 Subgroup2) and 123 healthy controls was chosen to validate the models, and confirmed the results. Conclusions: These results indicate that the divided CRC subgroups can improve the efficiency of disease diagnosis, with various microbial composition in the subgroups. [ABSTRACT FROM AUTHOR]

As a crucial node in the East Asia–Australasia migratory bird network, the Liaohe River Estuary Wetland (LREW) contributes significantly to coastal ecological balance and biodiversity. Accurate and timely mapping of the LREW is essential for monitoring ecological changes and understanding shifts in the wetland's ecosystem structure and functions. In this study, an innovative approach that integrates radar (Sentinel-1), optical (Sentinel-2), and DEM data on Google Earth Engine (GEE) is proposed to achieve a more optimized and accurate wetland mapping. Recursive Feature Elimination (RFE) is employed to improve feature collection, facilitating the construction of an optimal feature set for Random Forest (RF) classification to extract detailed LREW information. Mapping conducted from 2017 to 2023 using the proposed approach demonstrates its effectiveness and stability in mapping the LREW, achieving overall accuracies ranging from 89.84% to 93.73% and Kappa from 0.85 to 0.91. Compared to single-source methods, the integration of multi-source data substantially enhances mapping accuracy, while RF-RFE effectively eliminates redundant features, further refining classification precision. Texture features (Sum Average, SAVG) and the Water Index 2019 (WI2019) were found to significantly influence wetland mapping. The importance of different feature types is ranked as follows: spectral features > vegetation/water body index > PCA features > SAR texture features > red-edge index > other spectral index > spectral texture features > backscatter coefficient > H-Alpha. During the study period, the wetland area increased from 849.60 km2 to 979.49 km2. This expansion was caused primarily by wetland protection policies that led to the dismantling of coastal aquaculture ponds, resulting in a reduction of 90.28 km2 in waterbodies over 7 years, with many areas transitioning to tidal flats and Suaeda salsa habitats. In conclusion, the proposed method is effective in mapping the LRE wetlands and provides reliable data support for wetland ecological protection and restoration. [ABSTRACT FROM AUTHOR]

Metamaterial absorbers (MMAs) have tremendous potential for controlling and modulating Terahertz electromagnetic (EM) waves. It is challenging to design MMAs for optimal performance using conventional methods due to their time-consuming and computationally demanding nature. Machine learning (ML) regressor approaches have emerged as potential tools for optimizing the predictive modeling of MMAs in recent years. This article examined different regression techniques, such as Decision Tree, k-Nearest Neighbors, Random Forest, Extra Trees (ET), Extreme Gradient Boosting, Bagging, and Categorical Boosting. The primary goal is to assess the effectiveness of each regressor technique in forecasting the performance of MMAs using various performance metrics. The study focuses on a representative spectrum of MMAs, chosen for its key features that are common across a wide range of MMAs. The extra tree Regressor outperforms other models in the comparative analysis due to its capacity to integrate multiple decision trees and include randomness into the feature selection process, resulting in improved predictive skills. The ET regressor forecasts MMA performance remarkably well for a 70 % test size, with a Root Mean Squared Error of 0.0251, a Mean Absolute Error of 0.0074, a Mean Squared Error of 0.006, and an Adjusted R-squared of 0.9873. These findings can assist researchers in optimizing metamaterial absorber designs for Terahertz applications using ML regressor techniques and provide insights into how these methods can be generalized to other spectra with similar characteristics. [ABSTRACT FROM AUTHOR]

Word recognition has garnered significant attention due to its wide-ranging real-time applications, including postal automation, signature verification, bank check processing and writer identification. Handwritten word recognition poses a formidable challenge in computer vision, primarily due to the diverse writing styles exhibited by individuals. Presently, researchers are increasingly focused on developing holistic word recognition approaches. This holistic approach treats entire words as single, indivisible entities for the purpose of feature extraction and recognition, rendering it well-suited for identifying words with overlapping characters. In this study, authors have proposed a holistic approach for recognizing offline handwritten words in the Devanagari script, employing VGG16 (Visual Geometry Group) as a versatile feature extractor. Three classifiers, namely Gaussian Naive Bayes (Gaussian NB), eXtreme Gradient Boosting (XGBoost) and Random Forest (RF), are considered for classifying these word images. Based on the extracted features and the aforementioned classifiers, words are categorized into one of 50 distinct word classes. Various performance evaluation metrics, including Accuracy, Precision, Recall, F1-score and Area Under the Curve (AUC), are employed to assess the effectiveness of the proposed system. It is worth noting that the Random Forest (RF) based classification technique achieved exceptional accuracy, with impressive recall, high precision and a remarkable F1-score. Additionally, the XGBoost based classification exhibited comparable performance, achieving the highest possible AUC in this study. Furthermore, to underscore the significance of this work, authors have presented a comparative analysis of the proposed approach with existing state-of-the-art methodologies. [ABSTRACT FROM AUTHOR]

Recently, every human being has been busy keeping pace with fast changes and is unable to put his attention on a healthy lifestyle. This unhealthy lifestyle leads to several fatal diseases like heart disease (HD), cancer disease, allergies, asthma, breast cancer, etc. These diseases are increasing the morbidity and mortality rate every year, and out of these HD is more fetal. Earlier/Timely prediction of HD is regarded as one of the most crucial tasks in the medical field. In the healthcare industry, a big collection of datasets is available free of cost. Motivated by existing challenges, the authors proposed two intelligent models i.e., HyOPTRF (Model 1), and HyOPTXGBoost Classifier (Model 2), implemented on the Statlog HD dataset with default and hyper-tuned parameters. Both the models recorded maximum Accuracy of 92.59%, Specificity 100%, Precision 100%, Negative Predicted Value 100%, Geometric mean 93.93% F1 Score 93.75%, Training Time 0.02s, and Testing Time 0.005s for the HyOPTRF on Trial no. 2nd and Accuracy of 96.30%, Specificity 100%, Precision 100%, Negative Predicted Value 100%, Geometric mean 96.82%, F1 Score 96.77%, Training Time 0.009s, and Testing Time 0.002s for the HyOPTXGBoost Classifier on Trial no. 33rd. The proposed models were validated by the Stratify Kfold Cross-Validation technique and compared with the other existing models. [ABSTRACT FROM AUTHOR]

Case-based reasoning (CBR) is widely used in medical decision support systems because of its similarity to human reasoning. Despite the effectiveness of the latter, its performance can be improved when reinforced by other automatic learning techniques. This is what induced us to propose a hybrid model 3FS-CBR-IRF (Three feature selection- Case based reasoning- Improved random forest) that combines case-based reasoning and random forests. Firstly, a feature selection step is used by three techniques such as: Correlation, Dropping Constant Features and Chi-square to select the relevant features. Secondly, we have modeled the retrieval phase of the CBR system by the modified random forests; in this step two pruning methods (Pre-pruning and Post-pruning) are applied only to the highly ranked features to improve the performance of the CBR system. Thirdly, the adaptation phase of the retrieval cases based on the adaptation rules is proposed. The developed approach is evaluated on 13 medical databases using the precision and several other performance criteria, the results obtained are satisfactory with an average precision of 91% for the first model (CBR-FS-RF) which improves the CBR system by feature selection techniques with classic random forest, 97% for the model (CBR-FS-IRF) which improve the CBR system by feature selection techniques with improved random forests and 98% for the second model (CBR-FS-IRF) with adaptation. The results showed that the proposed pruning method selects the best tree in less time and with better precision than hybridization with classical random forest that means an improvement of the performance of the CBR system. [ABSTRACT FROM AUTHOR]

Bridge construction collapse is one of the most common bridge safety accidents. At present, evaluation results are often affected by the ability and experience of the assessor. Therefore, it is difficult to quickly, accurately and effectively evaluate the risk in the process of bridge construction. Moreover, key factors that can prevent accidents can hardly find from the existing bridge construction safety management and evaluation method. This paper analyzes and classifies the artificial and environmental risk factors that affect the bridge construction stage, and establishes 26 risk factors in 5 categories according to the characteristics of bridge construction and the actual situation of the project. Random forest (RF) algorithm is a non-parametric machine learning method based on decision tree, which does not need to be scored by experts in advance and avoids the influence of subjective factors. Compared with other analysis methods, random forest algorithm has the advantages of accurate and robust risk assessment results. Based on the advantages of random forest algorithm and the characteristics of bridge construction risk, this paper uses random forest algorithm to evaluate the bridge construction risk, and ranks the importance of indicators, and identify the index that has a greater influence on the risk. In order to verify the applicability and feasibility of the proposed method, a typical urban complex pedestrian bridge was taken as an example for actual engineering evaluation and verification. The results obtained are basically consistent with the actual risk assessment results of the pedestrian bridge. [ABSTRACT FROM AUTHOR]

Many species of fishes around the world are soniferous. The types of sounds fishes produce vary among species and regions but consist typically of low-frequency (< 1.5 kHz) pulses and grunts. These sounds can potentially be used to monitor fishes non-intrusively and could complement traditional monitoring techniques. However, the significant time required for human analysts to manually label fish sounds in acoustic recordings does not yet allow passive acoustics to be used as a viable tool for monitoring fishes. In this paper, we compare two different approaches to automatically detect fish sounds. One is a more traditional machine learning technique based on the detection of acoustic transients in the spectrogram and the classification using Random Forest (RF). The other is using a deep learning approach and is based on the classification of overlapping segments (0.2 s) of spectrogram using a ResNet18 Convolutional Neural Network (CNN). Both algorithms were trained using 21,950 manually annotated fish and non-fish sounds collected from 2014 to 2019 at five different locations in the Strait of Georgia, British Columbia, Canada. The performance of the detectors was tested on part of the data from the Strait of Georgia that was withheld from the training phase, data from Barkley Sound, British Columbia, and data collected in the Port of Miami, Florida, United States. The CNN performed up to 1.9 times better than the RF (F1 score: 0.82 vs. 0.43). In some cases, the CNN was able to find more faint fish sounds than the analyst and performed well in environments different from the one it was trained in (Miami F1 score: 0.88). Noise analysis in the 20--1,000 Hz frequency band shows that the CNN is still reliable in noise levels greater than 130 dB re 1 μPa in the Port of Miami but becomes less reliable in Barkley Sound past 100 dB re 1 μPa due to mooring noise. The proposed approach can efficiently monitor (unidentified) fish sounds in a variety of environments and can also facilitate the development of species-specific detectors. We provide the software FishSound Finder, an easy-to-use open-source implementation of the CNN detector with detailed documentation. [ABSTRACT FROM AUTHOR]

Machine learning has gained attention due to its ongoing advancements and diverse applications. Within the field of homogeneous catalysis, a prominent area of research in machine learning revolves around predicting reaction yield in Pd‐catalyzed Buchwald–Hartwig amination reactions. This study sought to determine the optimal descriptors for representing the both structural and physical information associated with the reaction, particularly focusing on product details. To achieve this, we assessed the utilization of product extended molecular fingerprints (PEMF) and selected physical parameters (SPP). The utilization of a random forest model incorporating these descriptors yielded promising results in the prediction of reaction yields in Pd‐catalyzed Buchwald–Hartwig amination reactions. The model achieved an impressive R2 value of 0.943. Data preprocessing on PEMF and sorting preprocessing on physical parameters resulted in a significant reduction in data size to 259 bits PEMF+2 SPPs per prediction, much less than the two previous random forest models which utilized 480 physical parameters and 21,073 bits molecular fingerprints. Although establishing definitive correlations between SPPs and reaction yield presented challenges, our findings indicate that the presence of heavier atoms in the aryl halides may have a beneficial impact within the examined Pd‐catalyzed Buchwald–Hartwig amination reactions, as compared to their analogues. [ABSTRACT FROM AUTHOR]

Introduction Musculoskeletal injuries are one of the primary causes of Soldiers' inability to be medically ready, comprising over 80% of such causes. The electronic profile (e-Profile) is the way that musculoskeletal injuries are documented so that commanders will know the type of injury as well as the length of the time that the Soldier will need limited duty. A previous study of e-Profiles in an Army MTF Integrated Pain Management Center showed that the median length of an e-Profile was 30 days. It is in the best interest of the Army to have the Soldier out of the fight the minimum amount of time for recovery to ensure the unit readiness. The goal of this study was to utilize e-Profile data to see if a machine learning model can be developed to determine the appropriate time a Soldier needs to be on profile for a given diagnoses. Materials and Methods Institutional Review Board approval was obtained from the USAMRDC (protocol #M-10966). The initial dataset provided to the research team consisted of a single pipe delimited ("|") text file containing 2.9 million rows of e-Profile data. Linear regression, decision trees, and random forests (RFs) were evaluated to see which model would best predict the number of days needed for an e-Profile. Results Linear regression had an adjusted R-squared of 0.165. The positive predictive value of decision trees (0-to-30-day range of e-Profiles) was 73.6%, and the negative predictive value (30-90 days) was 60.9% with an area under the receiver operating characteristic curve (AUC) of 0.694 for the model. The positive predictive value of RFs was 85.3% (for the 0-30 range), and the negative predictive value was 58.7% (for the 30-90 range) with an AUC of 0.794. An AUC that approaches 1 indicates a more accurate prediction. Conclusions The 3 models (linear regression, decision trees, and RF) studied as part of this project did not predict the days on e-Profile with a high degree of certainty. Future research will focus on adding additional data to the e-Profile dataset in order to improve model accuracy. [ABSTRACT FROM AUTHOR]

Groundwater is a primary source of drinking water for billions worldwide. It plays a crucial role in irrigation, domestic, and industrial uses, and significantly contributes to drought resilience in various regions. However, excessive groundwater discharge has left many areas vulnerable to potable water shortages. Therefore, assessing groundwater potential zones (GWPZ) is essential for implementing sustainable management practices to ensure the availability of groundwater for present and future generations. This study aims to delineate areas with high groundwater potential in the Bankura district of West Bengal using four machine learning methods: Random Forest (RF), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), and Voting Ensemble (VE). The models used 161 data points, comprising 70% of the training dataset, to identify significant correlations between the presence and absence of groundwater in the region. Among the methods, Random Forest (RF) and Extreme Gradient Boosting (XGBoost) proved to be the most effective in mapping groundwater potential, suggesting their applicability in other regions with similar hydrogeological conditions. The performance metrics for RF are very good with a precision of 0.919, recall of 0.971, F1-score of 0.944, and accuracy of 0.943. This indicates a strong capability to accurately predict groundwater zones with minimal false positives and negatives. Adaptive Boosting (AdaBoost) demonstrated comparable performance across all metrics (precision: 0.919, recall: 0.971, F1-score: 0.944, accuracy: 0.943), highlighting its effectiveness in predicting groundwater potential areas accurately; whereas, Extreme Gradient Boosting (XGBoost) outperformed the other models slightly, with higher values in all metrics: precision (0.944), recall (0.971), F1-score (0.958), and accuracy (0.957), suggesting a more refined model performance. The Voting Ensemble (VE) approach also showed enhanced performance, mirroring XGBoost's metrics (precision: 0.944, recall: 0.971, F1-score: 0.958, accuracy: 0.957). This indicates that combining the strengths of individual models leads to better predictions. The groundwater potentiality zoning across the Bankura district varied significantly, with areas of very low potentiality accounting for 41.81% and very high potentiality at 24.35%. The uncertainty in predictions ranged from 0.0 to 0.75 across the study area, reflecting the variability in groundwater availability and the need for targeted management strategies. In summary, this study highlights the critical need for assessing and managing groundwater resources effectively using advanced machine learning techniques. The findings provide a foundation for better groundwater management practices, ensuring sustainable use and conservation in Bankura district and beyond. [ABSTRACT FROM AUTHOR]

To reveal the evolution characteristics of vegetation cover in Nanchang City and identify the main climate drivers affecting its change trends, in order to provide guidance for its long-term stable and benign development and active response to the subsequent climate change. In this paper, NDVI monthly data and ten meteorological driving factors such as temperature, precipitation and pressure of Nanchang City from 2000 to 2020 were used to study the importance of different drivers by using single sample K-S test, Friedmann test, Kendall harmony coefficient test and random forest analysis. The results showed that, 1) the NDVI of Nanchang City showed a fluctuating downward trend from 2000 to 2020, the peak appeared in 2000, while the trough occurred in 2010. 2) The overall vegetation cover of the city showed a spatial distribution pattern of high perimeter and low center, with the NDVI values in the north and the west being relatively high and decreasing at a slow rate, and the NDVI values of the central areas of the city such as the East Lake District and the Castle Peak Lake District being relatively low and with an obvious downward trend. 3) The great average value of the vegetation cover appeared in August each year, which was most significantly affected by temperature and least affected by wind direction, with a certain time lag influenced by precipitation, so the study of vegetation cover change should be determined by combining the driving effect of multiple elements. [ABSTRACT FROM AUTHOR]

Visual information affects static postural control, but how it affects dynamic postural control still needs to be fully understood. This study investigated the effect of proprioception weighting, influenced by the presence or absence of visual information, on dynamic posture control during voluntary trunk movements. We recorded trunk movement angle and angular velocity, center of pressure (COP), electromyographic, and electroencephalography signals from 35 healthy young adults performing a standing trunk flexion–extension task under two conditions (Vision and No-Vision). A random forest analysis identified the 10 most important variables for classifying the conditions, followed by a Wilcoxon signed-rank test. The results showed lower maximum forward COP displacement and trunk flexion angle, and faster maximum flexion angular velocity in the No-Vision condition. Additionally, the alpha/beta ratio of the POz during the switch phase was higher in the No-Vision condition. These findings suggest that visual deprivation affects cognitive- and sensory-integration-related brain regions during movement phases, indicating that sensory re-weighting due to visual deprivation impacts motor control. The effects of visual deprivation on motor control may be used for evaluation and therapeutic interventions in the future. [ABSTRACT FROM AUTHOR]

A common challenge for exoskeleton control is discerning operator intent to provide seamless actuation of the device with the operator. One way to accomplish this is with joint angle estimation algorithms and multiple sensors on the human–machine system. However, the question remains of what can be accomplished with just one sensor. The objective of this study was to deploy a modular testing approach to test the performance of two joint angle estimation models—a kinematic extrapolation algorithm and a Random Forest machine learning algorithm—when each was informed solely with kinematic gait data from a single potentiometer on an ankle exoskeleton mock-up. This study demonstrates (i) the feasibility of implementing a modular approach to exoskeleton mock-up evaluation to promote continuity between testing configurations and (ii) that a Random Forest algorithm yielded lower realized errors of estimated joint angles and a decreased actuation time than the kinematic model when deployed on the physical device. [ABSTRACT FROM AUTHOR]

Land-use and land-cover change (LULCC) is a critical environmental issue that has significant effects on biodiversity, ecosystem services, and climate change. This study examines the land-use and land-cover (LULC) spatiotemporal dynamics across a three-decade period (1998–2023) in a district area. In order to forecast the LULCC patterns, this study suggests a hybrid strategy that combines the random forest method with multi-layer perceptron (MLP) and Markov chain analysis. To predict the dynamics of LULC changes for the year 2035, a hybrid technique based on multi-layer perceptron and Markov chain model analysis (MLP-MCA) was employed. The area of developed land has increased significantly, while the amount of bare land, vegetation, and forest cover have all decreased. This is because the principal land types have changed due to population growth and economic expansion. This study also discovered that between 1998 and 2023, the built-up area increased by 468 km2 as a result of the replacement of natural resources. It is estimated that 25.04% of the study area's urbanization will increase by 2035. The performance of the model was confirmed with an overall accuracy of 90% and a kappa coefficient of around 0.89. It is important to use advanced predictive models to guide sustainable urban development strategies. The model provides valuable insights for policymakers, land managers, and researchers to support sustainable land-use planning, conservation efforts, and climate change mitigation strategies. [ABSTRACT FROM AUTHOR]

Building Performance Simulation extensively uses statistical learning techniques for quicker insights and improved accessibility. These techniques help understand the relationship between input variables and the desired outputs, and they can predict unknown observations. Prediction becomes more informative with uncertainty quantification, which involves computing prediction intervals. Conformal prediction has emerged over the past 25 years as a flexible and rigorous method for estimating uncertainty. This approach can be applied to any pre-trained model, creating statistically rigorous uncertainty sets or intervals for model predictions. This study uses data from simulated buildings to demonstrate the powerful applications of conformal prediction in Building Performance Simulation (BPS) and, consequently, to the broader energy sector. Results show that conformal prediction can be applied when any assumptions about input and output variables are made, enhancing understanding and facilitating informed decision-making in energy system design and operation. [ABSTRACT FROM AUTHOR]

Soil nutrient content varies spatially across agricultural fields in hard-to-predict ways, particularly in floodplains with complex fluvial depositional history. Satellite reflectance data from the Sentinel-2 (S2) mission provides spatially continuous land reflectance data that can aid model development when used with point observations of nutrients. Reflectance from vegetation is assumed to obstruct land reflectance of bare soil, such that researchers have masked vegetation in models. We developed a routine for masking vegetation within Google Earth Engine (GEE) using Random Forest classification for iterative application to libraries of S2-images. Using gradient boosting, we then developed soil nutrient models for surface soils at a 250-ha agricultural site using S2 images. Soils were sampled at 2145 point locations to a 23-cm depth and analyzed for Ca, K, Mg, P, pH, S, and Zn. Results showed that masking vegetation improved model performance for models from subsets of the data (80% of samples used for model development, 20% validation), but full data sets did not require masking to achieve accuracy. Models of Ca, K, Mg, and S were successful (validation R2 > 0.60 to 0.96), but models for pH, P, and Zn failed. Bare soil composite images from S2 data are helpful in predicting soil fertility in low-relief floodplains. [ABSTRACT FROM AUTHOR]

Accurate prediction of lake surface water temperature (LSWT) is essential for understanding the impacts of climate change on aquatic ecosystems and for guiding environmental management strategies. Predictions of LSWT for two prominent lakes in northern China, Qinghai Lake and Hulun Lake, under various future climate scenarios, were conducted in the present study. Utilizing historical hydrometeorological data and MODIS satellite observations (MOD11A2), we employed three advanced machine learning models—Random Forest (RF), XGBoost, and Multilayer Perceptron Neural Network (MLPNN)—to predict monthly average LSWT across three future climate scenarios (ssp119, ssp245, ssp585) from CMIP6 projections. Through the comparison of training and validation results of the three models across both lake regions, the RF model demonstrated the highest accuracy, with a mean MAE of 0.348 °C and an RMSE of 0.611 °C, making it the most optimal and suitable model for this purpose. With this model, the predicted LSWT for both lakes reveals a significant warming trend in the future, particularly under the high-emission scenario (ssp585). The rate of increase is most pronounced under ssp585, with Hulun Lake showing a rise of 0.55 °C per decade (R2 = 0.72) and Qinghai Lake 0.32 °C per decade (R2 = 0.85), surpassing trends observed under ssp119 and ssp245. These results underscore the vulnerability of lake ecosystems to future climate change and provide essential insights for proactive climate adaptation and environmental management. [ABSTRACT FROM AUTHOR]

Accurate river ice mapping is crucial for predicting and managing floods caused by ice jams and for the safe operation of hydropower and water resource facilities. Although satellite multispectral images are widely used for river ice mapping, atmospheric contamination limits their effectiveness. This study developed river ice mapping models for the Han River in South Korea using atmospherically uncorrected Landsat-8 Operational Land Imager (OLI) multispectral reflectance data, addressing atmospheric influences with a Random Forest (RF) classification approach. The RF-based river ice mapping models were developed by implementing various combinations of input variables, incorporating the Landsat-8 multispectral top-of-atmosphere (TOA) reflectance, normalized difference indices for snow, water, and bare ice, and atmospheric factors such as aerosol optical depth, water vapor content, and ozone concentration from the Moderate Resolution Imaging Spectroradiometer observations, as well as surface elevation from the GLO-30 digital elevation model. The RF model developed using all variables achieved excellent performance in the classification of snow-covered ice, snow-free ice, and water, with an overall accuracy and kappa coefficient exceeding 98.4% and 0.98 for test samples, and higher than 83.7% and 0.75 when compared against reference river ice maps generated by manually interpreting the Landsat-8 images under various atmospheric conditions. The RF-based river ice mapping model for the atmospherically corrected Landsat-8 multispectral surface reflectance was also developed, but it showed very low performance under atmospheric conditions heavily contaminated by aerosol and water vapor. Aerosol optical depth and water vapor content were identified as the most important variables. This study demonstrates that multispectral reflectance data, despite atmospheric contamination, can be effectively used for river ice monitoring by applying machine learning with atmospheric auxiliary data to mitigate atmospheric effects. [ABSTRACT FROM AUTHOR]

Global warming and climate change are significantly impacting local climates, causing more intense heat during the summer season, which poses risks to individuals with pre-existing health conditions and negatively affects overall human health. While various studies have examined the Surface Urban Heat Island (SUHI) phenomenon, these studies often focus on small to large geographic regions using low-to-moderate-resolution data, highlighting general thermal trends across large administrative areas. However, there is a growing need for methods that can detect microscale thermal patterns in environments familiar to urban residents, such as streets and alleys. The temperature-humidity index (THI), which incorporates both temperature and humidity data, serves as a critical measure of human-perceived heat. However, few studies have explored microscale THI variations within urban settings and identified potential THI hotspots at a local level where SUHI effects are pronounced. This research aims to address this gap by estimating THI at a finer resolution scale using data from multiple sensor platforms. We developed a model with the random forest algorithm to assess THI trends at a resolution of 0.5 m, utilizing various variables from different sources, including Landsat 8 land surface temperature (LST), unmanned aerial system (UAS)-derived LST, Sentinel-2 NDVI and NDMI, a wind exposure index, solar radiation modeled from aircraft and UAS-derived Digital Surface Models, and vehicle density and building floor area from social big data. Two models were constructed with different variables: Modelnatural, which includes variables related to only natural factors, and Modelmix, which includes all variables, including anthropogenic factors. The two models were compared to reveal how each source contributes to the model development and SUHI effects. The results show significant improvements, as Modelnatural had a fitting R2 = 0.5846, a root mean square error (RMSE) = 0.5936 and a mean absolute error (MAE) = 0.4294. Moreover, when anthropogenic factors were introduced, Modelmix performed even better, with R2 = 0.9638, RMSE = 0.1751, and MAE = 0.1065 (n = 923). This study contributes to the future of microscale SUHI analysis and offers important insights into urban planning and smart city development. [ABSTRACT FROM AUTHOR]

Background: Mild cognitive impairment (MCI) patients are at a high risk of developing Alzheimer's disease and related dementias (ADRD) at an estimated annual rate above 10%. It is clinically and practically important to accurately predict MCI-to-dementia conversion time. Objective: It is clinically and practically important to accurately predict MCI-to-dementia conversion time by using easily available clinical data. Methods: The dementia diagnosis often falls between two clinical visits, and such survival outcome is known as interval-censored data. We utilized the semi-parametric model and the random forest model for interval-censored data in conjunction with a variable selection approach to select important measures for predicting the conversion time from MCI to dementia. Two large AD cohort data sets were used to build, validate, and test the predictive model. Results: We found that the semi-parametric model can improve the prediction of the conversion time for patients with MCI-to-dementia conversion, and it also has good predictive performance for all patients. Conclusions: Interval-censored data should be analyzed by using the models that were developed for interval- censored data to improve the model performance. [ABSTRACT FROM AUTHOR]

Introduction: The purpose of our report was to use a Random Forest classification approach to predict the association between transcutaneous electrical nerve stimulation (TENS) and walking kinematics at the stride level when middle-aged and older adults performed the 6-min test of walking endurance. Methods: Data from 41 participants (aged 64.6 ± 9.7 yr) acquired in two previously published studies were analyzed with a Random Forest algorithm that focused on upper and lower limb, lumbar, and trunk kinematics. The four most predictive kinematic features were identified and utilized in separate models to distinguish between three walking conditions: burst TENS, continuous TENS, and control. SHAP analysis and linear mixed models were used to characterize the differences among these conditions. Results: Modulation of four key kinematic features--toe-out angle, toe-off angle, and lumbar range of motion (ROM) in coronal and sagittal planes--accurately predicted walking conditions for the burst (82%accuracy) and continuous (77% accuracy) TENS conditions compared with control. Linear mixed models detected a significant difference in lumbar sagittal ROM between the TENS conditions. SHAP analysis revealed that burst TENS was positively associated with greater lumbar coronal ROM, smaller toe-off angle, and less lumbar sagittal ROM. Conversely, continuous TENS was associated with less lumbar coronal ROM and greater lumbar sagittal ROM. Conclusions: Our approach identified four kinematic features at the stride level that could distinguish between the three walking conditions. These distinctions were not evident in average values across strides. [ABSTRACT FROM AUTHOR]

Rainfall-triggered landslides pose a significant threat to both infrastructure and human lives, making it crucial to comprehend the factors that contribute to their occurrence. Specifically, understanding the relationship between these factors and the amount of rain that is necessary for triggering such events is essential for effective prediction and mitigation strategies. To address this issue, our study proposes a statistical modelling approach using machine learning, specifically the Random Forest algorithm, to investigate the connection between landslide predisposing factors and the daily rainfall intensity threshold necessary for the initiation of shallow landslides in Portugal. By leveraging a comprehensive dataset comprising historical landslide events, associated critical rainfall, and ten distinct landslide predisposing factors, we developed several models and used cross-validation technique to evaluate their performance. Our findings demonstrate that the Random Forest model effectively captures a relationship among landslide predisposing factors, critical daily rainfall intensity, and landslide occurrences. The models exhibit a satisfactory accuracy in assessing the spatial variation of critical daily rainfall intensity based on the predisposing factors, with a mean absolute percentage error (MAPE) of around 17%. Furthermore, the models provide valuable insights into the relative importance of various predisposing factors in landslide triggering, highlighting the significance of each factor. It was found that it takes higher rainfall intensity to trigger shallow landslides in the north region of Portugal when considering critical rainfall events of 3 and 13 days. Slope aspect, slope angle, and clay content in the soil are among the main predisposing factors used for defining the spatial variation of the daily rainfall intensity threshold. [ABSTRACT FROM AUTHOR]

Most data-driven landslide-susceptibility assessment models heavily rely on statistical analyses based on geological and environmental similarity principles. These models often struggle to establish connections with landslide destruction processes and mechanisms effectively. In response to this challenge, this study introduces a hybrid approach that combines the transient rainfall infiltration, regional slope-stability physics–based model (TRIGRS) and the random forest (RF) model. Initially, to calculate the safety coefficients of the study area, the TRIGRS model was employed, and appropriate non-landslide samples were selected based on these coefficients. Subsequently, to enable learning and fitting of the nonlinear relationships between sample points and geological environmental factors, historical landslide data and safety coefficient-filtered non-landslide point data were input into the RF model, ultimately generating landslide probability values that represent the magnitude of landslide occurrences. The coupled model demonstrated excellent predictive performance using the landslides induced by the 2019 "Lekima" typhoon in Yongjia, Zhejiang Province, as a case study. The results indicated that the evaluation effect of the TRIGRS and RF coupled model was satisfactory, achieving an accuracy (ACC) rate of 77.6% and an area under the curve (AUC) of 0.873. Furthermore, the ACC and AUC of the TRIGRS and RF coupled model increased by 8.22% and 9.20%, respectively, compared with those of the traditional buffering sampling method. Therefore, the TRIGRS and RF coupled model better evaluates regional landslide susceptibility than the traditional buffering sampling method. [ABSTRACT FROM AUTHOR]

The eastern Himalayan syntaxis (EHS) region is characterized by steep topography, strong tectonic activity, and strong disaster activity, and the disaster activity has a temporal correlation with the change of seasonal climate factors. Different from other disaster-prone areas, the disasters in the EHS area are more destructive and more susceptible to changes in climate factors. However, previous studies on disaster susceptibility in the region mainly focused on geohazard samples, regional topography, and geological conditions and seldom considered the characteristics of disaster activity and the characteristics of seasonal temperature and rainfall changes, which often led to an underestimation of disaster susceptibility in this region. Therefore, in this study, SBAS-InSAR technology and the GEE (Google Earth Engine) platform were used to identify 317 geological disasters and construct the spatial–temporal motion field and spatial-temporal background information of disasters in the last 5 years. Based on the random forest and optimized evaluation data model, the disaster susceptibility in the EHS area was quantitatively evaluated. The AUC value of the model was 0.89, indicating that the results have high reliability. The results showed that the high-susceptibility areas were mainly distributed in the riverbank and high-altitude areas. The SHAP model revealed that the factors of temperature, precipitation, slope, and elevation in the EHS area had a great negative influence on the disaster. The quantitative results of the influence of seasonal temperature and precipitation on disaster susceptibility showed that the area of susceptibility in summer was significantly higher than that in winter, and the area of high and very high susceptibility increased by about 13%. Finally, the dynamic failure process of typical landslide and glacier disasters in highly susceptible areas was quantitatively predicted, which provides a scientific basis for disaster prevention. [ABSTRACT FROM AUTHOR]

China's unsustainable agricultural production activities have caused severe agricultural non-point source pollution (ANPSP), particularly nitrogen source pollution (NSP), which impacts farmland ecological environments. Understanding NSP is important for managing ANPSP and improving environmental water quality. Thus, inventory analysis methods were used to assess county-level total nitrogen (TN) loads in large-scale agricultural areas, analyze spatial and temporal variations in TN loads, examine the major sources of TN loads and identify the driving factors of DITN using Pearson correlation and random forest (RF) methods. The results showed that (1) TN loads and discharge intensity decreased by 4.59% and 12.7%, respectively, increasing and then decreasing via market regulations, policy incentives, and policy constraints. The eastern and northern Henan Province plain areas were highly discharged. (2) The major pollution sources varied, with the total contributions of mineral fertilizers and livestock and poultry breeding to TN being 73.53% and 81.78%, respectively. Farmland solid waste contributed minimally but increased yearly from 10.84 to 19.74%. (3) The discharge intensity of TN was highly significantly negatively correlated with the urbanization rate, economic development and slope; neither was significantly correlated with arable land. The RF results showed that total mineral fertilizer consumption and total livestock and poultry production were the major factors controlling the NSP in Henan Province. China's agricultural policies have slightly reduced pollutant discharge intensities, but the situation remains grim. This study provides a scientific basis for the development of differentiated TN control measures in Henan Province, which is important for improving pollution prevention and control capabilities. [ABSTRACT FROM AUTHOR]

In ordinal classification problems, the class value exhibits a natural order. Usually, these problems are solved as multiclass classification problems while discarding the ordering form of the class. Recently, several research studies have proposed novel methods for ordinal classification problems while aiming to predict a predefined objective value. These methods are based on modification of the splitting criteria of decision tree-based algorithms. These methods consider the ordinal nature of the data and the magnitude of the potential classification error from a predefined predicted objective. This research aims to consolidate these methods and generalize them for any decision tree-based method while constructing decision trees according to any predefined objective value calculated from the training dataset. Furthermore, to evaluate the proposed method, a comprehensive experimental study is performed based on known ordinal datasets. The proposed method is found to significantly outperform its counterpart nonordinal models. This observation confirms that ordering information benefits ordinal methods and improves their performance. Additionally, the ordinal decision tree-based methods achieved competitive performance compared to state-of-the-art ordinal techniques. The results are validated with various performance measures that are commonly used for ordinal and non-ordinal classification problems. [ABSTRACT FROM AUTHOR]

Urban national parks (UNPs) provide tourism services in cities worldwide. However, the factors affecting tourist distributions in UNP activity and path spaces remain uncertain. Using Web crawler technology, location big data were tracked and sampled in Donghu National Park in Wuhan, China, and 12 predictor variables were analyzed using a machine-learning method (i.e., random forest). The consistency of the big data compared to the population census and tourist observations was determined at 79.5% and 77.8%, respectively. The tourist number (p) and tourist density (p/ha) per day in the park space in Donghu National Park were 0–2,531 p and 0–198.0 p/ha, respectively. Peak tourist periods showed pressure flows of 0.3–34.5‰ between scenic areas in the park. An analytical framework was formulated for UNPs to link the urban environment, park attributes, and configurational attributes, which here explained 66.4%–72.5% of the tourist distribution in the path and activity spaces. Random forest models performed better than geographically weighted regression (GWR) or ordinary least squares (OLS) models, indicating a complex nonlinear relationship between the independent variables and tourist distribution in UNP spaces, rather than the linear relationship that has previously been found in urban parks. First, both activity and path spaces near developed urban environments or park entrances bore higher tourism pressure. Second, winding routes attracted tourists to path spaces, while water landscapes attracted tourists to both path and activity spaces. Third, tourism pressure in path spaces was determined by configurational attributes. These results are important reference points for the planning and management of UNPs. [ABSTRACT FROM AUTHOR]

The influence of ionic liquid (IL) characteristics, lignocellulosic biomass (LCB) properties, and process conditions on LCB pretreatment is not well understood. In this study, a total of 129 experimental data on LCB (grass, agricultural, and forest residues) pretreatment using imidazolium, triethylamine, and choline-amino acid ILs were compiled to develop machine learning (ML) models for cellulose, hemicellulose, lignin, and solid recovery. Following data imputation, a bilayer artificial neural network (ANN) and random forest (RF) regression, the two most widely adopted ML models, were developed. The full-featured ANN following Bayesian hyperparameter (HP) optimisation offered excellent fit on training (R2: 0.936–0.994), though cross-validation (R2CV) performance remained marginally poor, i.e. between 0.547 and 0.761. The fitness of HP-optimised RF models varied between 0.824 and 0.939 for regression, and between 0.383 and 0.831 in cross-validation. Temperature and pretreatment time had been the most important predictors, except for hemicellulose recovery. Bayesian predictor selection combined with HP optimisation improved the R2CV boundary for ANN (0.555–0.825), as well as for RF models (0.474–0.824). As predictive performance of the models varied depending on target response, use of a larger homogeneous dataset may be warranted. The predictive modelling framework for LCB pretreatment, developed in this study, can be extended to similar biochemical process systems. [ABSTRACT FROM AUTHOR]

Fiber-reinforced polymer (FRP) is an excellent building material for strengthening concrete structures, but it is difficult to accurately evaluate the bond strength of FRP-to-concrete due to the influence of various parameters. In this study, a novel hybrid model which combines particle swarm optimization (PSO) with random forest (RF) was proposed to predict the bond strength of FRP-to-concrete. The PSO algorithm was used to optimize the hyperparameters of the RF model. A total of 749 specimens collected from the literature were used to develop the proposed PSO-RF model. Each sample contains 11 parameters required for the model. These 11 parameters are (1) the compressive strength of concrete, (2) the tensile strength of concrete, (3) the width of concrete specimen, (4) the maximum aggregate size of concrete, (5) the tensile strength of FRP, (6) the thickness of FRP, (7) the elastic modulus of FRP, (8) the tensile strength of adhesive, (9) the bond length of FRP, (10) the bond width of FRP, and (11) the bond strength of FRP-to-concrete. The proposed PSO-RF model was compared with other machine learning models as well as ten empirical equations. Six statistical indices, namely root mean squared error (RMSE), mean absolute error (MAE), coefficient of determination (R2), Nash-Sutcliffe efficiency coefficient (NSE), Willmott's Index of Agreement (WIA), and Legates-McCabe's Index (LM) were used to evaluate the prediction performance of the abovementioned models. The results show that the RMSE, MAE, R2, NSE, WIA and LM values of the PSO-RF model are 1.529 kN, 0.942 kN, 0.986, 0.984, 0.996 and 0.892, respectively, for the training datasets and 2.672 kN, 1.967 kN, 0.963, 0.961, 0.989 and 0.761, respectively, for the test datasets. It can be concluded that the proposed PSO-RF model has the best comprehensive performance in predicting the bond strength of FRP-to-concrete. In addition, the sensitivity analysis of the PSO-RF model was also conducted in this study. [ABSTRACT FROM AUTHOR]

In forensic practice, determining the postmortem submersion interval (PMSI) and cause-of-death of cadavers in aquatic ecosystems has always been challenging task. Traditional approaches are not yet able to address these issues effectively and adequately. Our previous study proposed novel models to predict the PMSI and cause-of-death based on metabolites of blood from rats immersed in freshwater. However, with the advance of putrefaction, it is hardly to obtain blood samples beyond 3 days postmortem. To further assess the feasibility of PMSI estimation and drowning diagnosis in the later postmortem phase, gastrocnemius, the more degradation-resistant tissue, was collected from drowned rats and postmortem submersion model in freshwater immediately after death, and at 1 day, 3 days, 5 days, 7 days, and 10 days postmortem respectively. Then the samples were analyzed with liquid chromatography–tandem mass spectrometry (LC–MS/MS) to investigate the dynamic changes of the metabolites. A total of 924 metabolites were identified. Similar chronological changes of gastrocnemius metabolites were observed in the drowning and postmortem submersion groups. The difference in metabolic profiles between drowning and postmortem submersion groups was only evident in the initial 1 day postmortem, which was faded as the PMSI extension. Nineteen metabolites representing temporally-dynamic patterns were selected as biomarkers for PMSI estimation. A regression model was built based on these biomarkers with random forest algorithm, which yielded a mean absolute error (± SE) of 5.856 (± 1.296) h on validation samples from an independent experiment. These findings added to our knowledge of chronological changes in muscle metabolites from submerged vertebrate remains during decomposition, which provided a new perspective for PMSI estimation. [ABSTRACT FROM AUTHOR]

To date South African forensic anthropologists are only able to successfully apply a metric approach to estimate population affinity when constructing a biological profile from skeletal remains. While a non-metric, or macromorphoscopic approach exists, limited research has been conducted to explore its use in a South African population. This study aimed to explore 17 cranial macromorphoscopic traits to develop improved methodology for the estimation of population affinity among black, white and coloured South Africans and for the method to be compliant with standards of best practice. The trait frequency distributions revealed substantial group variation and overlap, and not a single trait can be considered characteristic of any one population group. Kruskal-Wallis and Dunn's tests demonstrated significant population differences for 13 of the 17 traits. Random forest modelling was used to develop classification models to assess the reliability and accuracy of the traits in identifying population affinity. Overall, the model including all traits obtained a classification accuracy of 79% when assessing population affinity, which is comparable to current craniometric methods. The variable importance indicates that all the traits contributed some information to the model, with the inferior nasal margin, nasal bone contour, and nasal aperture shape ranked the most useful for classification. Thus, this study validates the use of macromorphoscopic traits in a South African sample, and the population-specific data from this study can potentially be incorporated into forensic casework and skeletal analyses in South Africa to improve population affinity estimates. [ABSTRACT FROM AUTHOR]

The limitations of Content Based Video Retrieval (CBVR), such as large pools of video data, selection of features, limited processing capacity, and content-related issues, can be overcome by Deep Belief Neural Networks (DBNs). The search engine does the processing, and the results are effectively returned to the users. The deep learning model also has some comparable challenges to be solved at various levels. Typically, the selection of frames is one of the most essential tasks for a face retrieval system which is efficiently accomplished by using deep learning models. Also, the performance of recognition models highly depends on the selection of frames that include both low-level and high-level features from the given video sequence. This paper proposes ALPHA-TO-OMEGA (ALMEGA-VIR) Visual Information Retrieval scheme that analyzes the contents of the video file for a particular face and retrieves the user's relevant videos. VIR aims to solve the challenge of locating relevant pictures and videos based on a query. VIR can be based on text-based search, content-based search, and Mixed based search. VIR here focuses on content-based search approach. The YouTube Celebrities (YTC) dataset, the Youtube Face (YTF) dataset, and Honda / UCSD dataset are used in this work. The used dataset addresses issues such as illumination changes, occlusion, rotation, and scale. We propose an ALMEGA-VIR framework for visual novelty face identification for specific investigation and evaluation. The classification accuracy of the proposed ALMEGA-VIR model shows that 4% is more effective than traditional classifier algorithms such as SVM, Naïve Bayesian classifier, MLP and Random Forest classifier. A comparative study is also implemented with other existing works to check the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Background: To develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors. Materials and Methods: In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third, the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach. Results: A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The "original_shape_Flatness" feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method. Conclusions: The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature-based RF model displaying the best performance. [ABSTRACT FROM AUTHOR]

The punctuality of vessel arrival at port is a crucial issue in contemporary port operations. Uncertainties in vessel arrival can lead to port handling inefficiency and result in economic losses. Although vessels typically report their estimated time of arrival (ETA) en-route to the destination port, their actual time of arrival (ATA) often differs from the reported ETA due to various factors. To address this issue and enhance terminal operational efficiency, we first quantitatively evaluate vessel arrival uncertainty in different time slides prior to arrival at the port using 2021 vessel arrival data for Hong Kong port (HKP). Our results confirm that the overall vessel arrival uncertainty decreases as vessels approach the HKP. Then, we implement a random forest (RF) approach to predict vessel arrival time. Our model reduces the error in ship ATA data prediction by approximately 40% (from 25.5 h to 15.5 h) using the root mean squared error metric and 20% (from 13.8 h to 11.0 h) using the mean absolute error metric compared with the reported ETA data. The proposed vessel arrival time evaluation and prediction models are applicable to port management and operation, laying the foundation for future research on port daily operations. [ABSTRACT FROM AUTHOR]

The information on land use/land cover (LULC) is indispensable in regional planning, policy formulation and tracking land use/land cover changes (LULCC). The rapid urbanization of hilly terrains, driven by population growth, has significant implications for landslide risk reduction. Recognizing the need for an innovative approach for extracting LULC information, the present study uses a random forest (RF) classifier to develop a novel, pre-trained and universal tool that automatically generates LULC classification maps based on natural colour satellite imagery without any training input from the end-user. The proposed framework with an overall accuracy of 0.75 and an area under the curve (AUC) score of 0.95 in the receiver operating characteristic curve (ROC) approach was used for mapping built-up area expansion in regions susceptible to rainfall-induced landslides in Idukki block panchayat (administrative division), Kerala, India. By comparing the LULC information for the years 2012 and 2022, it was understood that the built-up area in the location has increased from 12.76% of the total area in 2012 to 26.48% in 2022. It is important to consider the rapid increase in built-up area expansion in the 'very high' landslide susceptibility zones in the study area. This clearly demonstrates the need for hazard inclusive planning and tracking of LULCC, for disaster risk reduction. Research Highlights: A pre-trained Land Use/Land Cover (LULC) classification tool is developed using the Random Forest (RF) classifier. Based on natural colour satellite imagery, the tool automatically generates LULC maps for various landscapes worldwide. The tool demonstrates a satisfactory performance, achieving an overall accuracy of 0.75 and an overall ROC AUC score of 0.95. The tool was used to understand the LULC changes in Idukki block panchayat between 2012 and 2022. [ABSTRACT FROM AUTHOR]

Identification of landslide susceptible zones is the preliminary step to plan mitigation measures in landslide-prone mountainous terrains. The use of various machine learning (ML) algorithms has proven their superiority in terms of enhancing the success rate in susceptibility studies. Therefore, the present study focuses on spatial prediction of landslides using integrated supervised and unsupervised machine learning (ML) techniques with reference to Bhagirathi Valley, NW Himalaya. A landslide inventory of 514 landslides and 14 viable causative factors of landslides in the study area have been selected for the analysis. Three efficient supervised ML techniques, i.e., random forest (RF), extreme gradient boosting (XGBoost), and k-nearest neighbour (KNN), have been integrated with an unsupervised ISODATA cluster classification technique to prepare the landslide susceptible maps (LSM) of the study area. All the models depict that the greater part of the high and very high landslide hazard zones lie in the Main Central Thrust zone and its vicinity in the Bhagirathi Valley. The accuracy of each model was determined and compared using several statistical signifiers like sensitivity, specificity, area under curve, accuracy, and Kappa index. The results show that XGBoost and RF models exhibit higher performance accuracy than KNN. The quantitative assessment of prepared LSMs of the study area was also done using frequency ratio (FR) and frequency density (FD). The results indicate the consistency of each model in the prediction of landslide zones in the study area as FR and FD both increase with the increase of landslide susceptibility levels from very low to very high in all the models. [ABSTRACT FROM AUTHOR]

The study aims to report empirical findings of quantitative research investigating what variables are significant leading proxies of fraudulent financial reporting (FFR) and the performance of the fraud detection model. The paper used financial and non-financial proxies as indicators to detect FFR with the panel data of 2235 observations of listed companies on the Vietnamese Stock Exchange from 2014 to 2020. Based on the materiality principle in auditing, the study divided the profit variance ratio into four material fraud thresholds of over 5%, 10%, 20%, and 50%. Two data mining techniques were employed: random forest for the classification model and an artificial neural network for building the best fraud prediction model. The findings show that the average accuracy of the prediction results of the random forest algorithm (RFA) reaches 91% for a material fraud threshold of 5%; when the materiality of fraud increases to above 50% of profit variance, the predictability is 98%. The average prediction accuracy of an artificial neural network (ANN) for the training set is 99%, and the test set is 97% at different fraud thresholds. These results confirm that RFA and ANN give a high accuracy in predicting fraud, and the determinants of firms committing to FFR are proxies of financial stability, followed by cash in the business and the nature of the industry. Notably, the three most important proxies related to FFR include return on total assets, return on equity, and EBT on total assets. The findings have practical implications: to identify fraudulent firms, creditors, analysts, and other stakeholders should use financial and non-financial ratios and employ data mining techniques instead of traditional fraud detection methods. [ABSTRACT FROM AUTHOR]

The characteristics of the vegetation fire (VF) regime are strongly influenced by geographical variables such as regional physiographic settings, location, and climate. Understanding the VF regime is extremely important for managing and mitigating the impacts of fires on ecosystems, communities, and human activities in forest fire-prone regions. The present study thereby aimed to explore the potential effects of the confounding factors on VF in India to offer actionable and achievable solutions for mitigating this concurring environmental issue sustainably. A global burn area (250 m) data (Fire-CCIv5.1) and fire radiative power (FRP) were used to investigate the dynamics of VF across seven different divisions in India. The study also used the maximum and minimum temperatures, precipitation, population density, and intensity of human modification to model forest burn areas (including grassland). The Coupled Model Intercomparison Project-6 (CMIP6) was used to predict the burn area for 2030 and 2050 future climate scenarios. The present study accounted for a sizable increasing trend of VF during 2001–2019 period. The highest increasing trend was found in central India (513 and 343 km2 year−1 in the forest and crop fire, respectively), followed by southern India (364 km2 year−1 in forest fire), and upper Indo-Gangetic plain (128 km2 year−1 in crop fire). The FRP has varied significantly across the divisions, with the north-eastern Himalayas exhibiting the highest FRP hotspot. The maximum and minimum temperatures have the greatest influence on forest fires, according to Random Forest (RF) modeling. The estimated pre-monsoonal burn area for 2050 and 2050 future scenarios suggested a more frequent forest fire occurrence across India, particularly in southern and central India. A comprehensive forest fire control policy is therefore essential to safeguard and conserve forest cover in the regions, affected by forest fire periodically. [ABSTRACT FROM AUTHOR]

Supply of water is one of the most significant determinants of regional crop production and human food security. To promote sustainable management of agricultural water, the crop water requirement assessment (CropWRA) model was introduced as a tool for the assessment of satisfied degree of crop water requirements (CWR). Crop combination, water availability for agricultural production, water accessibility, and other indices were calculated considering the DEM, hydrological and climatic data, and crop properties for measuring the agricultural water requirement and satisfied degree in Bansloi River basin using the CropWRA model. Advanced machine learning model random forest was used to calculate the soil moisture considering the atmospheric variable, Landsat indices, and energy balance components for calculating the crop water satisfied degree and water requirement. The average crop water demand is 1.92 m, and it ranges from 1.58 to 2.26 m. The demand of crop water is more in the western part of the basin than the eastern part. The CropWSD (crop water satisfied degree) ranges from 17 to 116% due to variation in topography, river system, crop combination, land use, water uses, etc. The average crop water satisfied degree is 59%. About 71% of the total area is under 40% to 60% CropWSD level. CropWRA model can be applied for the sustainable water resource management, irrigation infrastructure development, and use of other modern technologies. [ABSTRACT FROM AUTHOR]

Machine learning (ML) models, particularly decision tree (DT)-based algorithms, are being increasingly utilized for flood susceptibility mapping. To evaluate the advantages of DT-based ML models over traditional statistical models on flood susceptibility assessment, a comparative study is needed to systematically compare the performances of DT- based ML models with that of traditional statistical models. New Orleans, which has a long history of flooding and is highly susceptible to flooding, is selected as the test bed. The primary purpose of this study is to compare the performance of multiple DT-based ML models namely DT, Adaptive Boosting (AdaBoost), Gradient Boosting (GdBoost), Extreme Gradient Boosting (XGBoost) and Random Forest (RF) models with a traditional statistical model known as Frequency Ratio (FR) model in New Orleans. This study also aims to identify the main drivers contributing to flooding in New Orleans using the best performing model. Based on the most recent Hurricane Ida-induced flood inventory map and nine crucial flood conditioning factors, the models' accuracies are tested and compared using multiple evaluation metrics. The findings of this study indicate that all DT-based ML models perform better compared to FR. The RF model emerges as the best model (AUC = 0.85) among all DT-based ML models in every evaluation metrics. This study then adopts the RF model to simulate flood susceptibility map (FSM) of New Orleans and compares it with the prediction of FR model. The RF model also demonstrates that low elevation and higher precipitation are the main factors responsible for flooding in New Orleans. Therefore, this comparative approach offers a significant understanding about the advantages of advanced ML models over traditional statistical models in local flood susceptibility assessment. [ABSTRACT FROM AUTHOR]

Communication networks are crucial components of the underlying digital infrastructure in any smart city setup. The increasing usage of computer networks brings additional cyber security concerns, and every organization has to implement preventive measures to protect valuable data and business processes. Due to the inherent distributed nature of the city infrastructures as well as the critical nature of its resources and data, any solution to the attack detection calls for distributed, efficient and privacy preserving solutions. In this paper, we extend the evaluation of our federated learning framework for network attacks detection and classification based on random forest. Previously the framework was evaluated only for attack detection using four well-known intrusion detection datasets (KDD, NSL-KDD, UNSW-NB15, and CIC-IDS-2017). In this paper, we extend the evaluation for attack classification. We also evaluate how adding differential privacy into random forest, as an additional protective mechanism, affects the framework performances. The results show that the framework outperforms the average performance of independent random forests on clients for both attack detection and classification. Adding differential privacy penalizes the performance of random forest, as expected, but the use of the proposed framework still brings benefits in comparison to the use of independent local models. The code used in this paper is publicly available, to enable transparency and facilitate reproducibility within the research community. [ABSTRACT FROM AUTHOR]

Modern manufacturing and quality monitoring involve multi-class out-of-control (OOC) information from the training sample. It is essential to use such information during online monitoring of data streams from complex processes. In this paper, a monitoring framework is designed by combining the random forest technique with the exponentially weighted moving average method for monitoring complex processes with multi-class OOC information. To be specific, a process surveillance technique in the form of a control chart is proposed based on the probability that the online data is classified as an in-control (IC) sample, and the control chart triggers an alarm when the probability is lower than the control limit. Our numerical findings based on the Monte–Carlo simulation show that the proposed control chart performs more effectively than its competitors under various distributions and data types, especially for high-dimensional cases when multi-class OOC information is known in advance. Moreover, the proposed method is illustrated with an application using the data related to the hard disk manufacturing processes. [ABSTRACT FROM AUTHOR]

Imbalanced graph node classification is a highly relevant and challenging problem in many real-world applications. The inherent data scarcity, a central characteristic of this task, substantially limits the performance of neural classification models driven solely by data. Given the limited instances of relevant nodes and complex graph structures, current methods fail to capture the distinct characteristics of node attributes and graph patterns within the underrepresented classes. In this article, we propose REFUEL—a novel approach for highly imbalanced node classification problems in graphs. Whereas symbolic and neural methods have complementary strengths and weaknesses when applied to such problems, REFUEL combines the power of symbolic and neural learning in a novel neural rule-extraction architecture. REFUEL captures the class semantics in the automatically extracted rule vectors. Then, REFUEL augments the graph nodes with the extracted rules vectors and adopts a Graph Attention Network-based neural node embedding, enhancing the downstream neural node representation. Our evaluation confirms the effectiveness of the proposed REFUEL approach for three real-world datasets with different minority class sizes. REFUEL achieves at least a 4% point improvement in precision on the minority classes of 1.5–2% compared to the baselines. [ABSTRACT FROM AUTHOR]

Surface waters are essential for meeting the needs of the world. In many regions, stream water quality is a major concern due to contamination from multiple sources. Stream water is also susceptible to climatic events and land-use practices influencing its catchment. Understanding the impact of such events on stream water quality is crucial for managing and protecting aquatic ecosystems and providing safe drinking water to communities that rely on these streams. Hence, monitoring and evaluating stream water quality holds significance in identifying potential hazards and implementing suitable management strategies. In this paper, a novel effort was made to determine the relative feature importance of a set of watershed characteristics (precipitation, temperature, urban land use, agricultural land use, and forest land-use factors) on four important water quality parameters (WQPs): fecal coliforms (FC), turbidity, pH, and conductivity of the Upper Green River watershed, Kentucky, USA. Random forest (RF), an ensemble learning method, was used to predict the WQPs from the causal parameters and determine the feature importance characteristics of the four WQPs previously mentioned. This model demonstrated that precipitation and temperature are the most influential factors on FC, turbidity, and pH. Forest land use and temperature are the two most important factors for conductivity. The novel feature importance factors of the RF model have likewise been confirmed for each WQP. In modeling stream WQPs, the developed the RF model outperformed the artificial neural network (ANN) model. Using the RF model, we obtain regression coefficients of (0.93, 0.74, and 0.94) for pH in training, testing, and overall. We obtain regression coefficients of (0.60, 0.64, and 0.61) using the ANN model. ⁠⁠⁠⁠⁠⁠⁠Overall, the RF model was more effective than the ANN model in modeling stream WQPs. The model identified precipitation and temperature as the most influential factors on FC, turbidity, and pH, while forest land use and temperature were the most important factors in determining conductivity. It is also found that land use factors are important to improve the accuracy of WQPs predictions from climate variables. The results of this study can be used by authorities to better understand and control pollution at the watershed scale. [ABSTRACT FROM AUTHOR]

The world was affected by a novel coronavirus in December 2019 that changed human life. Several types of research have been done, substantial scientific advances have been made, and millions of dollars have been spent on bringing scholars and scientists to one platform to end this critical pandemic. Ascertaining COVID-19 diagnoses in the initial stage of the pandemic was critical, specifically for patients with no manifestations. In this case, artificial intelligence-based systems were proposed to identify the virus at an earlier phase. Thus, the present study suggests a machine vision scheme to identify COVID-19 from chest X-ray images. Three machine learning approaches, such as logistic regression (LR), decision tree (DT), and random forest (RF), were implemented with more than 95% accuracy. The deep convolutional neural network (CNN) architecture was also proposed and implemented with a 99.99% detection rate. Therefore, the present work can effectively detect COVID-19 cases in the early stages. [ABSTRACT FROM AUTHOR]