Search

Objective: This study aimed to develop a deep learning model to predict skeletal malocclusions with an acceptable level of accuracy using airway and cephalometric landmark values obtained from analyzing different CBCT images. Background: In orthodontics, multitudinous studies have reported the correlation between orthodontic treatment and changes in the anatomy as well as the functioning of the airway. Typically, the values obtained from various measurements of cephalometric landmarks are used to determine skeletal class based on the interpretation an orthodontist experiences, which sometimes may not be accurate. Methods: Samples of skeletal anatomical data were retrospectively obtained and recorded in Digital Imaging and Communications in Medicine (DICOM) file format. The DICOM files were used to reconstruct 3D models using 3DSlicer (slicer.org) by thresholding airway regions to build up 3D polygon models of airway regions for each sample. The 3D models were measured for different landmarks that included measurements across the nasopharynx, the oropharynx, and the hypopharynx. Male and female subjects were combined as one data set to develop supervised learning models. These measurements were utilized to build 7 artificial intelligence-based supervised learning models. Results: The supervised learning model with the best accuracy was Random Forest, with a value of 0.74. All the other models were lower in terms of their accuracy. The recall scores for Class I, II, and III malocclusions were 0.71, 0.69, and 0.77, respectively, which represented the total number of actual positive cases predicted correctly, making the sensitivity of the model high. Conclusion: In this study, it is observed that the Random Forest model was the most accurate model for predicting the skeletal malocclusion based on various airway and cephalometric landmarks. [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]

Tree species classification using hyperspectral imagery shows incredible promise in developing a large-scale, high-resolution model for identifying tree species, providing unprecedented details on global tree species distribution. Many questions remain unanswered about the best practices for creating a global, general hyperspectral tree species classification model. This study aims to address three key issues in creating a hyperspectral species classification model. We assessed the effectiveness of three data-labeling methods to create training data, three data-splitting methods for training/validation/testing, and machine-learning and deep-learning (including semi-supervised deep-learning) models for tree species classification using hyperspectral imagery at National Ecological Observatory Network (NEON) Sites. Our analysis revealed that the existing data-labeling method using the field vegetation structure survey performed reasonably well. The random tree data-splitting technique was the most efficient method for both intra-site and inter-site classifications to overcome the impact of spatial autocorrelation to avoid the potential to create a locally overfit model. Deep learning consistently outperformed random forest classification; both semi-supervised and supervised deep-learning models displayed the most promising results in creating a general taxa-classification model. This work has demonstrated the possibility of developing tree-classification models that can identify tree species from outside their training area and that semi-supervised deep learning may potentially utilize the untapped terabytes of unlabeled forest imagery. [ABSTRACT FROM AUTHOR]

Detecting clouds, snow, and lakes in remote sensing images is vital due to their propensity to obscure underlying surface information and hinder data extraction. In this study, we utilize Sentinel-2 images to implement a two-stage random forest (RF) algorithm for image labeling and delve into the factors influencing neural network performance across six aspects: model architecture, encoder, learning rate adjustment strategy, loss function, input image size, and different band combinations. Our findings indicate the Feature Pyramid Network (FPN) achieved the highest MIoU of 87.14%. The multi-head self-attention mechanism was less effective compared to convolutional methods for feature extraction with small datasets. Incorporating residual connections into convolutional blocks notably enhanced performance. Additionally, employing false-color images (bands 12-3-2) yielded a 4.86% improvement in MIoU compared to true-color images (bands 4-3-2). Notably, variations in model architecture, encoder structure, and input band combination had a substantial impact on performance, with parameter variations resulting in MIoU differences exceeding 5%. These results provide a reference for high-precision segmentation of clouds, snow, and lakes and offer valuable insights for applying deep learning techniques to the high-precision extraction of information from remote sensing images, thereby advancing research in deep neural networks for semantic segmentation. [ABSTRACT FROM AUTHOR]

Skin cancer diagnosis greatly benefits from advanced machine learning techniques, particularly fine-tuned deep learning models. In our research, we explored the impact of traditional machine learning and fine-tuned deep learning approaches on prediction accuracy. Our findings reveal significant improvements in predictability and accuracy with fine-tuning, particularly evident in deep learning models. The CNN, SVM, and Random Forest Classifier achieved high accuracy. However, fine-tuned deep learning models such as EfficientNetB0, ResNet34, VGG16, Inception _v3, and DenseNet121 demonstrated superior performance. To ensure comparability, we fine-tuned these models by incorporating additional layers, including one flatten layer and three densely interconnected layers. These layers play a crucial role in enhancing model efficiency and performance. The flatten layer preprocesses multidimensional feature maps, facilitating efficient information flow, while subsequent dense layers refine feature representations, capturing intricate patterns and relationships within the data. Leveraging LeakyReLU activation functions in the dense layers mitigates the vanishing gradient problem and promotes stable training. Finally, the output dense layer with a sigmoid activation function simplifies decision making for healthcare professionals by providing binary classification output. Our study underscores the significance of incorporating additional layers in fine-tuned neural network models for skin cancer classification, offering improved accuracy and reliability in diagnosis. [ABSTRACT FROM AUTHOR]

Given the increasing competition among household appliance enterprises, accurately predicting household appliance demand is crucial for enterprise supply chain management and marketing. This paper proposes a combined model integrating deep learning and ensemble learning—LSTM-RF-XGBoost—to assist enterprises in identifying customer demand, thereby addressing the complexity and uncertainty of the household appliance market demand. In this study, Long Short-Term Memory Network (LSTM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) models are established separately. Then, the three individual algorithms are used as the base models in the first layer, with the multiple linear regression (MLR) algorithm serving as the meta-model in the second layer, merging the demand prediction model based on the hybrid model into the overall demand prediction model. This study demonstrates that the accuracy and stability of demand prediction using the LSTM–RF–XGBoost model significantly outperform traditional single models, highlighting the significant advantages of using a combined model. This research offers practical and innovative solutions for enterprises seeking rational resource allocation through demand prediction. [ABSTRACT FROM AUTHOR]

This paper proposes an advanced deep learning model that integrates the Diffusion-Transformer structure and parallel attention mechanism for the tasks of growth estimation and disease detection in jujube forests. Existing methods in forestry monitoring often fall short in meeting the practical needs of large-scale and highly complex forest areas due to limitations in data processing capabilities and feature extraction precision. In response to this challenge, this paper designs and conducts a series of benchmark tests and ablation experiments to systematically evaluate and verify the performance of the proposed model across key performance metrics such as precision, recall, accuracy, and F1-score. Experimental results demonstrate that compared to traditional machine learning models like Support Vector Machines and Random Forests, as well as common deep learning models such as AlexNet and ResNet, the model proposed in this paper achieves a precision of 95%, a recall of 92%, an accuracy of 93%, and an F1-score of 94% in the task of disease detection in jujube forests, showing similarly superior performance in growth estimation tasks as well. Furthermore, ablation experiments with different attention mechanisms and loss functions further validate the effectiveness of parallel attention and parallel loss function in enhancing the overall performance of the model. These research findings not only provide a new technical path for forestry disease monitoring and health assessment but also contribute rich theoretical and experimental foundations for related fields. [ABSTRACT FROM AUTHOR]

Brazil, a leading rice producer globally, faces challenges in systematically mapping its diverse rice fields due to varying cropping systems, climates, and planting calendars. Existing rice mapping methods often rely on complex techniques like deep learning or microwave imagery, posing limitations for large-scale mapping. This study proposes a novel approach utilizing Sentinel-2 spectral–temporal metrics (STMs) in conjunction with a random forest classifier for rice paddy mapping. By extracting diverse STMs and training both regional and global classifiers, we validated the method across independent areas. While regional models tended to overestimate rice areas, the global model effectively reduced discrepancies between our data and the reference maps, achieving an overall classifier accuracy exceeding 80%. Despite the need for further refinement to address confusion with other crops, STM exhibits promise for national-scale rice paddy mapping in Brazil. [ABSTRACT FROM AUTHOR]

Predicting phase stability in high entropy alloys (HEAs), such as phase fractions as functions of composition and temperature, is essential for understanding alloy properties and screening desirable materials. Traditional methods like CALPHAD are computationally intensive for exploring high-dimensional compositional spaces. To address such a challenge, this study explored and compared the effectiveness of random forests (RF) and deep neural networks (DNN) for accelerating materials discovery by building surrogate models of phase stability prediction. For interpolation scenarios (testing on the same order of system as trained), RF models generally produce smaller errors than DNN models. However, for extrapolation scenarios (training on lower-order systems and testing on higher order systems), DNNs generalize more effectively than traditional ML models. DNN demonstrate the potential to predict topologically relevant phase composition when data were missing, making it a powerful predictive tool in materials discovery frameworks. The study uses a CALPHAD dataset of 480 million data points generated from a custom database, available for further model development and benchmarking. Experiments show that DNN models are data-efficient, achieving similar performance with a fraction of the dataset. This work highlights the potential of DNNs in materials discovery, providing a powerful tool for predicting phase stability in HEAs, particularly within the Cr-Hf-Mo-Nb-Ta-Ti-V-W-Zr composition space. [ABSTRACT FROM AUTHOR]

Background: This study evaluates the efficacy of integrating MRI deep transfer learning, radiomic signatures, and clinical variables to accurately preoperatively differentiate between stage T2 and T3 rectal cancer. Methods: We included 361 patients with pathologically confirmed stage T2 or T3 rectal cancer, divided into a training set (252 patients) and a test set (109 patients) at a 7:3 ratio. The study utilized features derived from deep transfer learning and radiomics, with Spearman rank correlation and the Least Absolute Shrinkage and Selection Operator (LASSO) regression techniques to reduce feature redundancy. Predictive models were developed using Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM), selecting the best-performing model for a comprehensive predictive framework incorporating clinical data. Results: After removing redundant features, 24 key features were identified. In the training set, the area under the curve (AUC)values for LR, RF, DT, and SVM were 0.867, 0.834, 0.900, and 0.944, respectively; in the test set, they were 0.847, 0.803, 0.842, and 0.910, respectively. The combined model, using SVM and clinical variables, achieved AUCs of 0.946 in the trainingset and 0.920 in the test set. Conclusion: The study confirms the utility of a combined model of MRI deep transfer learning, radiomic features, and clinical factors for preoperative classification of stage T2 vs. T3 rectal cancer, offering significant technological support for precise diagnosis and potential clinical application. [ABSTRACT FROM AUTHOR]

BACKGROUND: The field of toxicology has witnessed substantial advancements in recent years, particularly with the adoption of new approach methodologies (NAMs) to understand and predict chemical toxicity. Class-based methods such as clustering and classification are key to NAMs development and application, aiding the understanding of hazard and risk concerns associated with groups of chemicals without additional laboratory work. Advances in computational chemistry, data generation and availability, and machine learning algorithms represent important opportunities for continued improvement of these techniques to optimize their utility for specific regulatory and research purposes. However, due to their intricacy, deep understanding and careful selection are imperative to align the adequate methods with their intended applications. OBJECTIVES: This commentary aims to deepen the understanding of class-based approaches by elucidating the pivotal role of chemical similarity (structural and biological) in clustering and classification approaches (CCAs). It addresses the dichotomy between general end point–agnostic similarity, often entailing unsupervised analysis, and end point–specific similarity necessitating supervised learning. The goal is to highlight the nuances of these approaches, their applications, and common misuses. DISCUSSION: Understanding similarity is pivotal in toxicological research involving CCAs. The effectiveness of these approaches depends on the right definition and measure of similarity, which varies based on context and objectives of the study. This choice is influenced by how chemical structures are represented and the respective labels indicating biological activity, if applicable. The distinction between unsupervised clustering and supervised classification methods is vital, requiring the use of end point–agnostic vs. end point–specific similarity definition. Separate use or combination of these methods requires careful consideration to prevent bias and ensure relevance for the goal of the study. Unsupervised methods use end point– agnostic similarity measures to uncover general structural patterns and relationships, aiding hypothesis generation and facilitating exploration of datasets without the need for predefined labels or explicit guidance. Conversely, supervised techniques demand end point–specific similarity to group chemicals into predefined classes or to train classification models, allowing accurate predictions for new chemicals. Misuse can arise when unsupervised methods are applied to end point–specific contexts, like analog selection in read-across, leading to erroneous conclusions. This commentary provides insights into the significance of similarity and its role in supervised classification and unsupervised clustering approaches. [ABSTRACT FROM AUTHOR]

With the ongoing challenge of air pollution posing serious health and environmental threats, particularly in rapidly industrializing regions, accurate forecasting and effective pollutant identification are crucial for enhancing public health and ecological stability. This study aimed to optimize air quality management through the prediction of the Air Quality Index (AQI) and identification of air pollutants. Our study spans nine representative cities (Hohhot, Yinchuan, Lanzhou, Beijing, Taiyuan, Xi'an, Shanghai, Nanjing, Wuhan) in China, with data collected from January 1, 2015, to November 30, 2021. We proposed a new model for daily AQI prediction, termed VMD-CSA-CNN-LSTM, which employed advanced machine learning techniques, including convolutional neural networks (CNN) and long short-term memory (LSTM) networks, and leveraged the chameleon swarm algorithm (CSA) for hyperparameter optimization, integrated through a variational mode decomposition approach. The model was developed using data from Lanzhou, with a split ratio of 8:1:1 into training, validation, and test sets, achieving an RMSE of 2.25, MAPE of 0.02, adjusted R-squared of 98.91%, and training efficiency of 5.31%. The model was further externally validated in the other eight cities, yielding comparable results, with an adjusted R-squared above 96%, MAPE below 0.1, and RMSE below 7.5. Additionally, we employed a random forest algorithm to identify the primary pollutants contributing to AQI levels. Our results indicated that PM2.5 was the most significant pollutant in Beijing, Taiyuan, and Xi'an, while PM10 was dominant in Hohhot, Yinchuan, and Lanzhou. In Shanghai, Nanjing, and Wuhan, both PM2.5 and PM10 were critical, with ozone also identified as a major air pollutant. This study not only advances the predictive accuracy of AQI models but also aids policymakers by providing a reliable tool for air quality management and strategic planning aimed at pollution reduction. The integration of these advanced computational techniques into environmental monitoring practices offers a promising avenue for enhancing air quality and mitigating pollution-related risks. [ABSTRACT FROM AUTHOR]

Site-specific weed management employs image data to generate maps through various methodologies that classify pixels corresponding to crop, soil, and weed. Further, many studies have focused on identifying specific weed species using spectral data. Nonetheless, the availability of open-access weed datasets remains limited. Remarkably, despite the extensive research employing hyperspectral imaging data to classify species under varying conditions, to the best of our knowledge, there are no open-access hyperspectral weed datasets. Consequently, accessible spectral weed datasets are primarily RGB or multispectral and mostly lack the temporal aspect, i.e., they contain a single measurement day. This paper introduces an open dataset for training and evaluating machine-learning methods and spectral features to classify weeds based on various biological traits. The dataset comprises 30 hyperspectral images, each containing thousands of pixels with 204 unique visible and near-infrared bands captured in a controlled environment. In addition, each scene includes a corresponding RGB image with a higher spatial resolution. We included three weed species in this dataset, representing different botanical groups and photosynthetic mechanisms. In addition, the dataset contains meticulously sampled labeled data for training and testing. The images represent a time series of the weed's growth along its early stages, critical for precise herbicide application. We conducted an experimental evaluation to test the performance of a machine-learning approach, a deep-learning approach, and Spectral Mixture Analysis (SMA) to identify the different weed traits. In addition, we analyzed the importance of features using the random forest algorithm and evaluated the performance of the selected algorithms while using different sets of features. [ABSTRACT FROM AUTHOR]

Several machine learning (ML) techniques have demonstrated efficacy in precisely forecasting HIV risk and identifying the most eligible individuals for HIV testing in various countries. Nevertheless, there is a data gap on the utility of ML algorithms in strengthening HIV testing worldwide. This systematic review aimed to evaluate how effectively ML algorithms can enhance the efficiency and accuracy of HIV testing interventions and to identify key outcomes, successes, gaps, opportunities, and limitations in their implementation. This review was guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. A comprehensive literature search was conducted via PubMed, Google Scholar, Web of Science, Science Direct, Scopus, and Gale OneFile databases. Out of the 845 identified articles, 51 studies were eligible. More than 75% of the articles included in this review were conducted in the Americas and various parts of Sub-Saharan Africa, and a few were from Europe, Asia, and Australia. The most common algorithms applied were logistic regression, deep learning, support vector machine, random forest, extreme gradient booster, decision tree, and the least absolute shrinkage selection operator model. The findings demonstrate that ML techniques exhibit higher accuracy in predicting HIV risk/testing compared to traditional approaches. Machine learning models enhance early prediction of HIV transmission, facilitate viable testing strategies to improve the efficiency of testing services, and optimize resource allocation, ultimately leading to improved HIV testing. This review points to the positive impact of ML in enhancing early prediction of HIV spread, optimizing HIV testing approaches, improving efficiency, and eventually enhancing the accuracy of HIV diagnosis. We strongly recommend the integration of ML into HIV testing programs for efficient and accurate HIV testing. [ABSTRACT FROM AUTHOR]

This study focuses on estimating the lead times of various processes in wind tower factories. Accurate estimation of these times allows for more efficient sequencing of activities, proper allocation of resources, and setting of realistic delivery dates, thus avoiding delays and bottlenecks in the production flow and improving process quality and efficiency. In addition, accurate estimation of these times contributes to a proper assessment of costs, overcoming the limitations of traditional techniques; this allows for the establishment of tighter quotations. The data used in this study were collected at wind tower manufacturing facilities in Spain and Brazil. Data preprocessing was conducted rigorously, encompassing cleaning, transformation, and feature selection processes. Following preprocessing, machine learning regression analysis was performed to estimate lead times. Nine algorithms were employed: decision trees, random forest, Ridge regression, Lasso regression, Elastic Net, support vector regression, gradient boosting, XGBoost, LightGBM, and multilayer perceptron. Additionally, the performance of two deep learning models, TabNet and NODE, designed specifically for tabular data, was evaluated. The results showed that gradient boosting-based algorithms were the most effective in predicting processing times and optimizing resource allocation. The system is designed to retrain models as new information becomes available. [ABSTRACT FROM AUTHOR]

This study addresses the growing concern of technostress, a condition caused by the overwhelming use of digital technologies, exacerbated by the COVID-19 pandemic. The researchers developed a predictive model using machine learning algorithms, Random Forest (RF) and Support Vector Machine (SVM), to assess and manage technostress levels. The model considers factors such as age, gender, technology usage hours, and technological experiences to classify stress levels into high, moderate, and low categories. The study collected data through a questionnaire administered to knowledgeable respondents, using a non-probabilistic sampling approach. The results showed that both RF and SVM algorithms achieved high accuracy in classifying technostress, with SVM performing slightly better (94.5% vs 84.50%). The model’s effectiveness in predicting stress levels for users with varying degrees of stress is a significant contribution to the field. The research also developed an interactive user interface to facilitate user engagement with the model, promoting stress management and well-being in a technology-driven society. The study’s findings provide valuable insights into the challenges posed by technostress and offer a solution for mitigating its effects. The use of machine learning algorithms to classify gender based on the dataset demonstrates the model’s potential applications in various areas. Overall, this study demonstrates the importance of addressing technostress in the digital age and provides a valuable tool for managing stress levels. The development of predictive models like this one can help individuals and organizations mitigate the negative impacts of technostress, promoting a healthier and more sustainable relationship with technology. [ABSTRACT FROM AUTHOR]

Poverty threatens human development especially for developing countries, so ending poverty has become one of the most important United Nations Sustainable Development Goals (SDGs). This study aims to explore China's progress in poverty reduction from 2016 to 2019 through time-series multi-source geospatial data and a deep learning model. The poverty reduction efficiency (PRE) is measured by the difference in the out-of-poverty rates (which measures the probability of being not poor) of 2016 and 2019. The study shows that the probability of poverty in all regions of China has shown an overall decreasing trend (PRE = 0.264), which indicates that the progress in poverty reduction during this period is significant. The Hu Huanyong Line (Hu Line) shows an uneven geographical pattern of out-of-poverty rate between Southeast and Northwest China. From 2016 to 2019, the centroid of China's out-of-poverty rate moved 105.786 km to the northeast while the standard deviation ellipse of the out-of-poverty rate moved 3 degrees away from the Hu Line, indicating that the regions with high out-of-poverty rates are more concentrated on the east side of the Hu Line from 2016 to 2019. The results imply that the government's future poverty reduction policies should pay attention to the infrastructure construction in poor areas and appropriately increase the population density in poor areas. This study fills the gap in the research on poverty reduction under multiple scales and provides useful implications for the government's poverty reduction policy. [ABSTRACT FROM AUTHOR]

Marine transportation accounts for approximately 90% of the total trade managed in international logistics and plays a vital role in many companies' supply chains. However, en-route factors like weather conditions or piracy incidents often delay scheduled arrivals at destination ports, leading to downstream inefficiencies. Due to the maritime industry's digital transformation, smart ports and vessels generate vast amounts of data, creating an opportunity to use the latest technologies, like machine and deep learning (ML/DL), to support terminals in their operations. This study proposes a data-driven solution for accurately predicting vessel arrival times using ML/DL techniques, including Deep Neural Networks, K-Nearest Neighbors, Decision Trees, Random Forest, and Extreme Gradient Boosting. This study collects real-world AIS data in the Eastern Mediterranean Sea from a network of public and private AIS base stations. The most relevant features are selected for training and evaluating the six ML/DL models. A comprehensive comparison is also performed against the estimated arrival time provided by shipping agents, a simple calculation-based approach, and four other ML/DL models proposed recently in the literature. The evaluation has revealed that Random Forest achieves the highest performance with an MAE of 99.9 min, closely followed by XGBoost, having an MAE of 105.0 min. [ABSTRACT FROM AUTHOR]

In recent years, machine learning (ML) algorithms have gained substantial recognition for ecological modeling across various temporal and spatial scales. However, little evaluation has been conducted for the prediction of soil organic carbon (SOC) on small data sets commonly inherent to long-term soil ecological research. In this context, the performance of ML algorithms for SOC prediction has never been tested against traditional process-based modeling approaches. Here, we compare ML algorithms, calibrated and uncalibrated process-based models as well as multiple ensembles on their performance in predicting SOC using data from five long-term experimental sites (comprising 256 independent data points) in Austria. Using all available data, the ML-based approaches using Random forest and Support vector machines with a polynomial kernel were superior to all process-based models. However, the ML algorithms performed similar or worse when the number of training samples was reduced or when a leave-one-site-out cross validation was applied. This emphasizes that the performance of ML algorithms is strongly dependent on the data-size related quality of learning information following the well-known curse of dimensionality phenomenon, while the accuracy of process-based models significantly relies on proper calibration and combination of different modeling approaches. Our study thus suggests a superiority of ML-based SOC prediction at scales where larger datasets are available, while process-based models are superior tools when targeting the exploration of underlying biophysical and biochemical mechanisms of SOC dynamics in soils. Therefore, we recommend applying ensembles of ML algorithms with process-based models to combine advantages inherent to both approaches. • We evaluated process-based (PB) and machine-learning (ML) models for SOC prediction. • Random forest & support vector machine predicted SOC superior to PB models. • Reduced data availability and quality significantly weakened ML model performance. • ML-assisted PB model ensembles strongly improved model performance. [ABSTRACT FROM AUTHOR]

Despite its proven success in various fields such as engineering, business, and healthcare, human–machine collaboration in education remains relatively unexplored. This study aims to highlight the advantages of human–machine collaboration for improving the efficiency and accuracy of decision-making processes in educational settings. High school dropout prediction serves as a case study for examining human–machine collaboration's efficacy. Unlike previous research prioritizing high accuracy with immutable predictors, this study seeks to bridge gaps by identifying actionable factors for dropout prediction through a framework of human–machine collaboration. Utilizing a large dataset from the High School Longitudinal Study of 2009 (HSLS:09), two machine learning models were developed to predict 9th-grade students' high school dropout history. Results indicated that the Random Forest algorithm outperformed the deep learning algorithm. Model explainability revealed the significance of actionable variables such as students' GPA in the 9th grade, sense of school belonging, self-efficacy in mathematics and science, and immutable variables like socioeconomic status in predicting high school dropout history. The study concludes with discussions on the practical implications of human–machine partnerships for enhancing student success. [ABSTRACT FROM AUTHOR]

In recent years, the semantic segmentation model has been widely applied in fields such as the extraction of crops due to its advantages such as strong discrimination ability, high accuracy, etc. Currently, there is no standard set of ground true label data for major crops in China, and the visual interpretation process is usually time-consuming and laborious. The sample size also makes it difficult to support the model to learn enough ground features, resulting in poor generalisation ability of the model, which in turn makes the model difficult to apply in fine extraction tasks of large-area crops. In this study, a method to establish a pseudo-label sample set based on the random forest algorithm to train a semantic segmentation model (U-Net) was proposed to perform winter wheat extraction. With the help of the GEE platform, Winter Wheat Canopy Index (WCI) indicators were employed in this method to initially extract winter wheat, and training samples (i.e., pseudo labels) were built for the semantic segmentation model through the iterative process of "generating random sample points—random forest model training—winter wheat extraction"; on this basis, the U-net model was trained with multi-time series remote sensing images; finally, the U-Net model was employed to obtain the spatial distribution map of winter wheat in Henan Province in 2022. The results illustrated that: (1) Pseudo-label data were constructed using the random forest model in typical regions, achieving an overall accuracy of 97.53% under validation with manual samples, proving that its accuracy meets the requirements for U-Net model training. (2) Utilizing the U-Net model, U-Net++ model, and random forest model constructed based on pseudo-label data for 2022, winter wheat mapping was conducted in Henan Province. The extraction accuracy of the three models is in the order of U-Net model > U-Net++ model > random forest model. (3) Using the U-Net model to predict the winter wheat planting areas in Henan Province in 2019, although the extraction accuracy decreased compared to 2022, it still exceeded that of the random forest model. Additionally, the U-Net++ model did not achieve higher classification accuracy. (4) Experimental results demonstrate that deep learning models constructed based on pseudo-labels exhibit higher classification accuracy. Compared to traditional machine learning models like random forest, they have higher spatiotemporal adaptability and robustness, further validating the scientific and practical feasibility of pseudo-labels and their generation strategies, which are expected to provide a feasible technical pathway for intelligent extraction of winter wheat spatial distribution information in the future. [ABSTRACT FROM AUTHOR]

This project employs artificial intelligence, including machine learning and deep learning, to assess COVID-19 readmission risk in Malaysia. It offers tools to mitigate healthcare resource strain and enhance patient outcomes. This study outlines a methodology for classifying COVID-19 readmissions. It starts with dataset description and pre-processing, while the data balancing was computed through Random Oversampling, Borderline SMOTE, and Adaptive Synthetic Sampling. Nine machine learning and ten deep learning techniques are applied, with five-fold cross-validation for evaluation. Optuna is used for hyperparameter selection, while the consistency in training hyperparameters is maintained. Evaluation metrics encompass accuracy, AUC, and training/inference times. Results were based on stratified five-fold cross-validation and different data-balancing methods. Notably, CatBoost consistently excelled in accuracy and AUC across all tables. Using ROS, CatBoost achieved the highest accuracy (0.9882 ± 0.0020) with an AUC of 1.0000 ± 0.0000. CatBoost maintained its superiority in BSMOTE and ADASYN as well. Deep learning approaches performed well, with SAINT leading in ROS and TabNet leading in BSMOTE and ADASYN. Decision Tree ensembles like Random Forest and XGBoost consistently showed strong performance. [ABSTRACT FROM AUTHOR]

Cardiovascular and neurological diseases are a major cause of mortality and morbidity worldwide. Such diseases require careful monitoring to effectively manage their progression. Artificial intelligence (AI) offers valuable tools for this purpose through its ability to analyse data and identify predictive patterns. This review evaluated the application of AI in cardiac and neurological diseases for their clinical impact on the general population. We reviewed studies on the application of AI in the neurological and cardiological fields. Our search was performed on the PubMed, Web of Science, Embase and Cochrane library databases. Of the initial 5862 studies, 23 studies met the inclusion criteria. The studies showed that the most commonly used algorithms in these clinical fields are Random Forest and Artificial Neural Network, followed by logistic regression and Support-Vector Machines. In addition, an ECG-AI algorithm based on convolutional neural networks has been developed and has been widely used in several studies for the detection of atrial fibrillation with good accuracy. AI has great potential to support physicians in interpretation, diagnosis, risk assessment and disease management. [ABSTRACT FROM AUTHOR]

The past few years have seen an emergence of interest in examining the significance of machine learning (ML) in the medical field. Diseases, health emergencies, and medical disorders may now be identified with greater accuracy because of technological advancements and advances in ML. It is essential especially to diagnose individuals with chronic diseases (CD) as early as possible. Our study has focused on analyzing ML's applicability to predict CD, including cardiovascular disease, diabetes, cancer, liver, and neurological disorders. This study offered a high-level summary of the previous research on ML-based approaches for predicting CD and some instances of their applications. To wrap things up, we compared the results obtained by various studies and the methodologies as well as tools employed by the researchers. The factors or parameters that are responsible for improving the accuracy of the predicting model for different previous works are also identified. For identifying significant features, most of the authors employed a variety of strategies, where least absolute shrinkage and selection (LASSO), minimal-redundancy-maximum-relevance (mRMR), and RELIEF are extensively used methods. It is seen that a wide range of ML approaches, including support vector machine (SVM), random forest (RF), decision tree (DT), naïve Bayes (NB), etc., have been widely used. Also, several deep learning techniques and hybrid models are employed to create CD prediction models, resulting in efficient and reliable clinical decision-making models. For the benefit of the whole healthcare system, we have also offered our suggestions for enhancing the prediction results of CD. [ABSTRACT FROM AUTHOR]

A complex AI system must be worked offline because the training and execution phases are processed separately. This process often requires different computer resources due to the high model requirements. A limitation of this approach is the convoluted training process that needs to be repeated to obtain models with new data continuously incorporated into the knowledge base. Although the environment may be not static, it is crucial to dynamically train models by integrating new information during execution. In this article, artificial neural networks (ANNs) are developed to predict risk levels in traffic accidents with relatively simpler configurations than a deep learning (DL) model, which is more computationally intensive. The objective is to demonstrate that efficient, fast, and comparable results can be obtained using simple architectures such as that offered by the Radial Basis Function neural network (RBFNN). This work led to the generation of a driving dataset, which was subsequently validated for testing ANN models. The driving dataset simulated the dynamic approach by adding new data to the training on-the-fly, given the constant changes in the drivers' data, vehicle information, environmental conditions, and traffic accidents. This study compares the processing time and performance of a Convolutional Neural Network (CNN), Random Forest (RF), Radial Basis Function (RBF), and Multilayer Perceptron (MLP), using evaluation metrics of accuracy, Specificity, and Sensitivity-recall to recommend an appropriate, simple, and fast ANN architecture that can be implemented in a secure alert traffic system that uses encrypted data. [ABSTRACT FROM AUTHOR]

Artificial intelligence algorithms have become extensively utilized in survival analysis for high-dimensional, multi-source data. However, due to their complexity, these methods often yield poorly interpretable outcomes, posing challenges in the analysis of several conditions. One of these conditions is obstructive sleep apnea, a sleep disorder characterized by the simultaneous occurrence of comorbidities. Survival analysis provides a potential solution for assessing and categorizing the severity of obstructive sleep apnea, aiding personalized treatment strategies. Given the critical role of time in such scenarios and considering limitations in model interpretability, time-dependent explainable artificial intelligence algorithms have been developed in recent years for direct application to basic Machine Learning models, such as Cox regression and survival random forest. Our work aims to enhance model selection in OSA survival analysis using time-dependent XAI for Machine Learning and Deep Learning models. We developed an end-to-end pipeline, training several survival models and selecting the best performers. Our top models—Cox regression, Cox time, and logistic hazard—achieved good performance, with C-index scores of 0.81, 0.78, and 0.77, and Brier scores of 0.10, 0.12, and 0.11 on the test set. We applied SurvSHAP methods to Cox regression and logistic hazard to investigate their behavior. Although the models showed similar performance, our analysis established that the results of the log hazard model were more reliable and useful in clinical practice compared to those of Cox regression in OSA scenarios. [ABSTRACT FROM AUTHOR]

Purpose: 123I-Ioflupane SPECT is an effective tool for the diagnosis and progression assessment of Parkinson's disease (PD). Radiomics and deep learning (DL) can be used to track and analyze the underlying image texture and features to predict the Hoehn-Yahr stages (HYS) of PD. In this study, we aim to predict HYS at year 0 and year 4 after the first diagnosis with combined imaging, radiomics and DL-based features using 123I-Ioflupane SPECT images at year 0. Methods: In this study, 161 subjects from the Parkinson's Progressive Marker Initiative database underwent baseline 3T MRI and 123I-Ioflupane SPECT, with HYS assessment at years 0 and 4 after first diagnosis. Conventional imaging features (IF) and radiomic features (RaF) for striatum uptakes were extracted from SPECT images using MRI- and SPECT-based (SPECT-V and SPECT-T) segmentations respectively. A 2D DenseNet was used to predict HYS of PD, and simultaneously generate deep features (DF). The random forest algorithm was applied to develop models based on DF, RaF, IF and combined features to predict HYS (stage 0, 1 and 2) at year 0 and (stage 0, 1 and ≥ 2) at year 4, respectively. Model predictive accuracy and receiver operating characteristic (ROC) analysis were assessed for various prediction models. Results: For the diagnostic accuracy at year 0, DL (0.696) outperformed most models, except DF + IF in SPECT-V (0.704), significantly superior based on paired t-test. For year 4, accuracy of DF + RaF model in MRI-based method is the highest (0.835), significantly better than DF + IF, IF + RaF, RaF and IF models. And DL (0.820) surpassed models in both SPECT-based methods. The area under the ROC curve (AUC) highlighted DF + RaF model (0.854) in MRI-based method at year 0 and DF + RaF model (0.869) in SPECT-T method at year 4, outperforming DL models, respectively. And then, there was no significant differences between SPECT-based and MRI-based segmentation methods except for the imaging feature models. Conclusion: The combination of radiomic and deep features enhances the prediction accuracy of PD HYS compared to only radiomics or DL. This suggests the potential for further advancements in predictive model performance for PD HYS at year 0 and year 4 after first diagnosis using 123I-Ioflupane SPECT images at year 0, thereby facilitating early diagnosis and treatment for PD patients. No significant difference was observed in radiomics results obtained between MRI- and SPECT-based striatum segmentations for radiomic and deep features. [ABSTRACT FROM AUTHOR]

Motivation Understanding the mechanisms and structural mappings between molecules and pathway classes are critical for design of reaction predictors for synthesizing new molecules. This article studies the problem of prediction of classes of metabolic pathways (series of chemical reactions occurring within a cell) in which a given biochemical compound participates. We apply a hybrid machine learning approach consisting of graph convolutional networks used to extract molecular shape features as input to a random forest classifier. In contrast to previously applied machine learning methods for this problem, our framework automatically extracts relevant shape features directly from input SMILES representations, which are atom-bond specifications of chemical structures composing the molecules. Results Our method is capable of correctly predicting the respective metabolic pathway class of 95.16% of tested compounds, whereas competing methods only achieve an accuracy of 84.92% or less. Furthermore, our framework extends to the task of classification of compounds having mixed membership in multiple pathway classes. Our prediction accuracy for this multi-label task is 95.62%. We analyze the relative importance of various global physicochemical features to the pathway class prediction problem and show that simple linear/logistic regression models can predict the values of these global features from the shape features extracted using our framework. Availability and implementation https://github.com/baranwa2/MetabolicPathwayPrediction. [ABSTRACT FROM AUTHOR]

Blockchain is a developing technology that promises advancements when it is applied to other fields. Applying blockchain to other systems requires a customized blockchain model to satisfy the requirements of different application fields. One important area is to integrate blockchain with smart spaces and the Internet of Things to process, manage, and store data. Actually, smart spaces and Internet of Things systems include various types of transactions in terms of sensitivity. The sensitivity can be considered as correctness sensitivity, time sensitivity, and specialization sensitivity. Correctness sensitivity means that the systems should accept precise or approximated data in some cases, whereas time sensitivity means that there are time bounds for each type of transaction, and specialization sensitivity applies when some transactions are processed only by specialized people. Therefore, this work introduces the smart partitioned blockchain model, where we use machine learning and deep learning models to classify transactions into different pools according to their sensitivity levels. Then, each pool is mapped to a specific part of the smart partitioned blockchain model. The parts can be permissioned or permissionless. The permissioned parts can have different sub-parts if needed. Consequently, the smart partitioned blockchain can be customized to meet application-field requirements. In the experimental results, we use bank and medical datasets with a predefined sensitivity threshold for classification accuracy in each system. The bank transactions are critical, whereas the classification of the medical dataset is speculative and less critical. The Random Forest model is used for bank-dataset classification, and its accuracy reaches 100%, whereas Sequential Deep Learning is used for the medical dataset, which reaches 91%. This means that all bank transactions are correctly mapped to the corresponding parts of the blockchain, whereas accuracy is lower for the medical dataset. However, acceptability is determined based on the predefined sensitivity threshold. [ABSTRACT FROM AUTHOR]

Airborne laser technology produces point clouds that can be used to build 3D models of buildings. However, the work is a laborious process that could benefit from automation. Artificial intelligence (AI) has been widely used in automating building segmentation as one of the initial stages in the 3D modeling process. The algorithms with a high success rate using point clouds for automatic semantic segmentation are random forest (RF) and PointNet++, with each algorithm having its own advantages and disadvantages. However, the training and testing data to develop and test the model usually share similar characteristics. Moreover, producing a good automation model requires a lot of training data, which may become an issue for users with a small amount of training data (limited data). The aim of this research is to test the performance of the RF and PointNet++ models in different regions with limited training and testing data. We found that the RF model developed from a small amount data, in different regions between the training and testing data, performs well compared to PointNet++, yielding an OA score of 73.01% for the RF model. Furthermore, several scenarios have been used in this research to explore the capabilities of RF in several cases. [ABSTRACT FROM AUTHOR]

Identifying fractures along a well trajectory is of immense significance in determining the subsurface fracture network distribution. Typically, conventional logs exhibit responses in fracture zones, and almost all wells have such logs. However, detecting fractures through logging responses can be challenging since the log response intensity is weak and complex. To address this problem, we propose a deep learning model for fracture identification using deep forest, which is based on a cascade structure comprising multi-layer random forests. Deep forest can extract complex nonlinear features of fractures in conventional logs through ensemble learning and deep learning. The proposed approach is tested using a dataset from the Oligocene to Miocene tight carbonate reservoirs in D oilfield, Zagros Basin, Middle East, and eight logs are selected to construct the fracture identification model based on sensitivity analysis of logging curves against fractures. The log package includes the gamma-ray, caliper, density, compensated neutron, acoustic transit time, and shallow, deep, and flushed zone resistivity logs. Experiments have shown that the deep forest obtains high recall and accuracy (>92%). In a blind well test, results from the deep forest learning model have a good correlation with fracture observation from cores. Compared to the random forest method, a widely used ensemble learning method, the proposed deep forest model improves accuracy by approximately 4.6%. [ABSTRACT FROM AUTHOR]

In this work, we present a novel methodology for performing the supervised classification of time-ordered noisy data; we call this methodology Entropic Sparse Probabilistic Approximation with Markov regularization (eSPA-Markov). It is an extension of entropic learning methodologies, allowing the simultaneous learning of segmentation patterns, entropy-optimal feature space discretizations, and Bayesian classification rules. We prove the conditions for the existence and uniqueness of the learning problem solution and propose a one-shot numerical learning algorithm that—in the leading order—scales linearly in dimension. We show how this technique can be used for the computationally scalable identification of persistent (metastable) regime affiliations and regime switches from high-dimensional non-stationary and noisy time series, i.e., when the size of the data statistics is small compared to their dimensionality and when the noise variance is larger than the variance in the signal. We demonstrate its performance on a set of toy learning problems, comparing eSPA-Markov to state-of-the-art techniques, including deep learning and random forests. We show how this technique can be used for the analysis of noisy time series from DNA and RNA Nanopore sequencing. [ABSTRACT FROM AUTHOR]

Many patients pursue attractive smiles, and surgical-orthodontic treatment is a common method. We aimed to analyze the changes in smile parameters after surgical-orthodontic treatment in patients with skeletal Class III pattern and identify factors influencing postoperative outcomes. This retrospective study comprised 34 patients with skeletal Class III malocclusion and pure mandible prognathism who received surgical-orthodontic treatment. Hard and soft tissue parameters were assessed through lateral cephalometry, and smile esthetics were evaluated through extraoral photography. Postoperative changes in smile parameters and between-parameter correlations were analyzed. Random forest and decision tree deep learning models were used to identify factors influencing postoperative changes. Substantial postoperative changes were observed in the buccal corridor, upper lip height, and smile index. Significant between-sex differences were noted in the upper midline and right chelion. Strong, positive correlations were found between upper lip height and upper lip ratio and between lower lip height and lower lip ratio. By contrast, strong negative correlations were observed between lower teeth exposure and smile index and between interlabial gap and smile index. The highest degrees of postoperative changes were noted in asymmetry-associated smile parameters: lower lip area, interlabial gap, smile index, buccal corridor, and arc ratio. Considerable changes were noted in skeletal, dental, and soft tissue parameters after surgical-orthodontic treatment. However, the changes in smile esthetics were less prominent from the frontal view. As for chin asymmetry, the most to least prominent changes were in the lower lip area, interlabial gap, smile index, buccal corridor, and arc ratio, respectively. [ABSTRACT FROM AUTHOR]

Synthesizing bare soil pictures in regions with complex vegetation is challenging, which hinders the accuracy of predicting soil organic carbon (SOC) in specific areas. An SOC prediction model was developed in this study by integrating the convolutional neural network and long and short-term memory network (CNN-LSTM) algorithms, taking into consideration soil-forming factors such as climate, vegetation, and topography in Hainan. Compared with common algorithmic models (random forest, CNN, LSTM), the SOC prediction model based on the CNN-LSTM algorithm achieved high accuracy (R2 = 0.69, RMSE = 6.06 g kg−1, RPIQ = 1.96). The model predicted that the SOC content ranged from 5.49 to 36.68 g kg−1, with Hainan in the central and southern parts of the region with high SOC values and the surrounding areas with low SOC values, and that the SOC was roughly distributed as follows: high in the mountainous areas and low in the flat areas. Among the four models, CNN-LSTM outperformed LSTM, CNN, and random forest models in terms of R2 accuracy by 11.3%, 23.2%, and 53.3%, respectively. The CNN-LSTM model demonstrates its applicability in predicting SOC content and shows great potential in complex areas where obtaining sample data is challenging and where SOC is influenced by multiple interacting factors. Furthermore, it shows significant potential for advancing the broader field of digital soil mapping. [ABSTRACT FROM AUTHOR]

Machine learning (ML) has been broadly applied for vadose zone applications in recent years. This article provides a comprehensive review of such developments. ML applications for variables corresponding to different complex vadose zone processes are summarized mostly in a prediction context. By analyzing and assessing these applications, we discovered extensive usages of classic ML models with relatively limited applications of deep learning (DL) approaches in general. We also recognized a lack of benchmark datasets for soil property research as well as limited integration of physics‐based vadose zone principles into the ML approaches. To facilitate this interdisciplinary research of ML in vadose zone characterization and processes, a paradigm of knowledge‐guided machine learning is suggested along with other data‐driven and ML model‐based research suggestions to advance future research. Core Ideas: Random forest and artificial neural network are two widely applied machine learning options for predicting vadose zone studies.A benchmark dataset is missing in soil property studies.We suggest vadose zone scientists explore more deep learning options and expand knowledge‐guided machine learning implementations. [ABSTRACT FROM AUTHOR]

The study uses machine learning and deep learning models to study the intricate relationship between viral genetic DNA sequences and host organisms. It uses a comprehensive dataset from databases like ExPASy and NCBI, which encodes crucial genetic information for viral replication. The study aimed to create a viral DNA dataset and develop robust machine learning and deep learning models to classify viruses into eight host categories. Despite extensive experimentation using various models, performance improvement was elusive due to genetic overlaps. Viral genomes from different classes had significant shared genetic sequences, making it difficult for these models to identify unique class-specific features, blurring the lines of differentiation. The study reduced the number of classes from eight to three, focusing on plants, animals, and microorganisms. This resulted in improved evaluation metrics, with the Random Forest Machine learning model reaching a maximum accuracy of 70% and the LSTM deep learning model surpassing 85%, overcoming earlier challenges. The discovery that viral genomes from different classes share significant genetic overlaps challenges conventional molecular distinctions, emphasizing the complexity of molecular differentiation in viral genomes. This pragmatic approach aligns molecular understanding with genetic data in viral host determination. [ABSTRACT FROM AUTHOR]

Tea, a commonly consumed beverage, is susceptible to being sold in adulterated or expired forms by third-party vendors. Hyperspectral imaging across different wavelength bands has proven to precisely assess the diverse types of tea and their corresponding financial gains. This study aims to employ a deep learning methodology in conjunction with hyperspectral imaging for efficiently classifying tea leaves. A novel approach is proposed, wherein a waveband convolutional neural network is utilized to generate hyper spectral images of tea leaf samples with enhanced resolution. The model known as optimized-convolutional neural network-random forest O-(ConvNet-RF) demonstrated exceptional performance, achieving high accuracy, impressive recall, F1 score, and notable sensitivity rate, outperforming existing alternative methods. The tea leaf types, namely green, yellow, and black, were accurately identified using a combination of the random forest (RF) model and the O-ConvNet-RF model. The tree-based classification method for the identification of tea leaves demonstrated superior performance as compared to alternative machine learning models. In general, this study presents a successful methodology for the classification of tea leaves, with potential implications for consumer processing and distributor profit analysis. [ABSTRACT FROM AUTHOR]

Virtual reality (VR) and immersive technology have emerged as powerful tools with numerous applications. VR technology creates a computer-generated simulation that immerses users in a virtual environment, providing a highly realistic and interactive experience. This technology finds applications in various fields, including gaming, healthcare, education, architecture, and training simulations. Understanding user immersion levels in VR is crucial and challenging for optimizing the design of VR applications. Immersion refers to the extent to which users feel absorbed and engrossed in the virtual environment. This research primarily aims to detect user immersion levels in VR using an efficient machine-learning model. We utilized a benchmark dataset based on user experiences in VR environments to conduct our experiments. Advanced deep and machine learning approaches are applied in comparison. We proposed a novel technique called Polynomial Random Forest (PRF) for feature generation mechanisms. The proposed PRF approach extracts polynomial and class prediction probability features to generate a new feature set. Extensive research experiments show that random forest outperformed state-of-the-art approaches, achieving a high immersion level detection rate of 98%, using the proposed PRF technique. We applied hyperparameter optimization and cross-validation approaches to validate the performance scores. Additionally, we utilized explainable artificial intelligence (XAI) to interpret the reasoning behind the decisions made by the proposed model for user immersion level detection in VR. Our research has the potential to revolutionize user immersion level detection in VR, enhancing the design process. [ABSTRACT FROM AUTHOR]

The fundamental method for pre-processing speech or text data that enables computers to comprehend human language is known as natural language processing. Numerous models have been developed to date to pre-process data in the English language; however, the Hindi language does not support these models. India's national tongue is Hindi. In order to help the locals, the authors of this study used supervised learning methods like Linear Regression, SVM, and Naive Bayes algorithm to investigate a dataset of complicated terms in the Hindi language. Additionally, a sophisticated Hindi word classification model is suggested employing several methods based on the forecasts as well as collective learning strategies like Random Forest, Adaboost, and Decision Tree. Depending on how well the user's language is understood, the suggested model will assist in simplifying Hindi text. Authors attempt to classify the uncharted dataset using deep learning algorithms like Bi-LSTM and GRU approaches in further processing. [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]

Increasing urban traffic and congestion have led to significant issues such as rising air pollution and wasted time, highlighting the need for an intelligent traffic light control (TLC) system to minimize vehicle waiting times. This paper presents a novel TLC system that leverages the Internet of Things (IoT) for data collection and employs the random forest algorithm for preprocessing and feature extraction. A deep belief network predicts future traffic conditions, and a support vector regression network is integrated to enhance prediction accuracy. Additionally, the traffic light control strategy is optimized using reinforcement learning. The proposed method is evaluated through two different scenarios. The first scenario is compared with fixed-time control and the double dueling deep neural network (3DQN) methods. The second scenario compares it with the SVM, KNN, and MAADAC approaches. Simulation results demonstrate that the proposed method significantly outperforms these alternative approaches, showing substantial improvements in average vehicle waiting times by more than 20%, 32%, and 45%, respectively. Using a deep belief network, supplemented by support vector regression, ensures high precision in forecasting traffic patterns. Furthermore, the reinforcement learning-based optimization of the traffic light control strategy effectively adapts to changing traffic conditions, providing superior traffic flow management. The results indicate that the proposed system can substantially reduce traffic congestion and improve urban traffic flow. [ABSTRACT FROM AUTHOR]

Deep learning is one of the emerging techniques that shows good failure modes classification prediction results due to its flexibility in recognizing patterns from raw sensor data. However, it requires complex hyperparameter optimization, high training time, and high computational hardware resources for neural network architecture. On the other hand, classical machine learning algorithms rely heavily on domain knowledge and manual feature engineering which is not always available in the industry. Therefore, we present an alternative method that learns characteristics of multivariate raw time series data to perform failure mode classification. The method is based on the deep forest algorithm, which is composed of two main processes: multi-grained scanning and cascade forest. The multi-grained scanning process windows the data and screens the times series to generate feature vectors automatically based on class probability distribution and hence recognize patterns from data. The cascade forest uses the output of the multi-grained scanning process and creates layers of random forests to make predictions. Each layer will perform fault classification, and the number of layers will increase until the accuracy of the classification does not improve. This layer-by-layer process is similar to deep learning, where the algorithm architecture is composed of different hidden layers. The presented methodology directly works with raw data in three domains: time, frequency, and time & frequency domain. Also, the method is validated using data provided by the Prognosis and Health Management (PHM) data challenge 2022 competition for hydraulic rock drill multiple failure mode classifications. The results show that the presented methodology is faster, less complex, and more accurate than deep learning algorithms. [ABSTRACT FROM AUTHOR]

Skin lesion classification plays a crucial role in the early detection and diagnosis of various skin conditions. Recent advances in computer-aided diagnostic techniques have been instrumental in timely intervention, thereby improving patient outcomes, particularly in rural communities lacking specialized expertise. Despite the widespread adoption of convolutional neural networks (CNNs) in skin disease detection, their effectiveness has been hindered by the limited size and data imbalance of publicly accessible skin lesion datasets. In this context, a two-step hierarchical binary classification approach is proposed utilizing hybrid machine and deep learning (DL) techniques. Experiments conducted on the International Skin Imaging Collaboration (ISIC 2017) dataset demonstrate the effectiveness of the hierarchical approach in handling large class imbalances. Specifically, employing DenseNet121 (DNET) as a feature extractor and random forest (RF) as a classifier yielded the most promising results, achieving a balanced multiclass accuracy (BMA) of 91.07% compared to the pure deep-learning model (end-to-end DNET) with a BMA of 88.66%. The RF ensemble exhibited significantly greater efficiency than other machine-learning classifiers in aiding DL to address the challenge of learning with limited data. Furthermore, the implemented predictive hybrid hierarchical model demonstrated enhanced performance while significantly reducing computational time, indicating its potential efficiency in real-world applications for the classification of skin lesions. [ABSTRACT FROM AUTHOR]

This study aims to establish a deep learning-based classification framework to efficiently and rapidly distinguish between coniferous and broadleaf forests across the Loess Plateau. By integrating the deep residual neural network (ResNet) architecture with transfer learning techniques and multispectral data from unmanned aerial vehicles (UAVs) and Landsat remote sensing data, the effectiveness of the framework was validated through well-designed experiments. The study began by selecting optimal spectral band combinations, using the random forest algorithm. Pre-trained models were then constructed, and model performance was optimized with different training strategies, considering factors such as image size, sample quantity, and model depth. The results indicated substantial improvements in the model's classification accuracy and efficiency for reasonable image dimensions and sample sizes, especially for an image size of 3 × 3 pixels and 2000 samples. In addition, the application of transfer learning and model fine-tuning strategies greatly enhanced the adaptability and universality of the model in different classification scenarios. The fine-tuned model achieved remarkable performance improvements in forest-type classification tasks, increasing classification accuracy from 85% to 93% in Zhengning, from 89% to 96% in Yongshou, and from 86% to 94% in Baishui, as well as exceeding 90% in all counties. These results not only confirm the effectiveness of the proposed framework, but also emphasize the roles of image size, sample quantity, and model depth in improving the generalization ability and classification accuracy of the model. In conclusion, this research has developed a technological framework for effective forest landscape recognition, using a combination of multispectral data from UAVs and Landsat satellites. This combination proved to be more effective in identifying forest types than was using Landsat data alone, demonstrating the enhanced capability and accuracy gained by integrating UAV technology. This research provides valuable scientific guidance and tools for policymakers and practitioners in forest management and sustainable development. [ABSTRACT FROM AUTHOR]

Intrusion Detection Systems (IDSs) play a crucial role in safeguarding network infrastructures from cyber threats and ensuring the integrity of highly sensitive data. Conventional IDS technologies, although successful in achieving high levels of accuracy, frequently encounter substantial model bias. This bias is primarily caused by imbalances in the data and the lack of relevance of certain features. This study aims to tackle these challenges by proposing an advanced machine learning (ML) based IDS that minimizes misclassification errors and corrects model bias. As a result, the predictive accuracy and generalizability of the IDS are significantly improved. The proposed system employs advanced feature selection techniques, such as Recursive Feature Elimination (RFE), sequential feature selection (SFS), and statistical feature selection, to refine the input feature set and minimize the impact of non-predictive attributes. In addition, this work incorporates data resampling methods such as Synthetic Minority Oversampling Technique and Edited Nearest Neighbor (SMOTE_ENN), Adaptive Synthetic Sampling (ADASYN), and Synthetic Minority Oversampling Technique–Tomek Links (SMOTE_Tomek) to address class imbalance and improve the accuracy of the model. The experimental results indicate that our proposed model, especially when utilizing the random forest (RF) algorithm, surpasses existing models regarding accuracy, precision, recall, and F Score across different data resampling methods. Using the ADASYN resampling method, the RF model achieves an accuracy of 99.9985% for botnet attacks and 99.9777% for Man-in-the-Middle (MITM) attacks, demonstrating the effectiveness of our approach in dealing with imbalanced data distributions. This research not only improves the abilities of IDS to identify botnet and MITM attacks but also provides a scalable and efficient solution that can be used in other areas where data imbalance is a recurring problem. This work has implications beyond IDS, offering valuable insights into using ML techniques in complex real-world scenarios. [ABSTRACT FROM AUTHOR]

Rail-fastening components are essential for ensuring the safety of urban rail systems by securing rails to sleepers. Traditional inspection methods rely heavily on manual labor and are inefficient. This paper introduces a novel approach to address these inefficiencies and the challenges faced by computer vision-based inspections, such as missed detections due to imbalanced samples and limitations in conventional image segmentation techniques. Our approach transitions the industry's focus from qualitative to a more precise quantitative analysis of rail-fastening components. We propose Mask-FRCN, an advanced image segmentation network that incorporates three key technological enhancements: the fully refined convolutional network module (FRCN),which refines the segmentation boundaries for SFC-type fasteners; the Channel-WiseKnowledge Distillation (CWD) algorithm, which boosts the model's inference efficiency; and the FCRM methodology, which enhances the extraction capabilities for features specific to SFC-type fasteners. Furthermore, we introduce a fastener system inspection and quantization method based on the Mask FRCN method (FIQ), a novel technique for quantifying the condition of components by using image features, template matching with random forests, and a clustering calculation method derived from segmentation results. Experimental results validate that our method significantly surpasses existing techniques in accuracy, thereby offering a more efficient solution for inspecting rail-fastening components. The enhanced Mask-FRCN achieves a segmentation accuracy of 96.01% and a reduced network size of 36.1 M. Additionally, the FIQ method improves fault detection accuracy for SFC-type fasteners to 95.13%, demonstrating the efficacy and efficiency of our innovative approach. [ABSTRACT FROM AUTHOR]

Glaucoma is a common eye disease that damages the optic nerve and leads to loss of vision. The disease shows few symptoms in the early stages, making its identification a complex task. To overcome the challenges associated with this task, this study aimed to tackle the localization and segmentation of the optic disc, as well as the classification of glaucoma. For the optic disc segmentation, we propose a novel metaheuristic approach called Grey Wolf Optimization (GWO). Two different approaches are used for glaucoma classification: a one-stage approach, in which the whole image without cropping is used for classification, and a two-stage approach. In the two-stage approach, the optic disc region is detected using the You Only Look Once (YOLO) detection algorithm. Once the optic disc region of interest (ROI) is identified, glaucoma classification is performed using pre-trained convolutional neural networks (CNNs) and vision transformation techniques. In addition, both the one-stage and the two-stage approaches are applied in combination with the pre-trained CNN using the Random Forest algorithm. In segmentation, GWO achieved an average sensitivity of 96.04%, a specificity of 99.58%, an accuracy of 99.39%, a DICE coefficient of 94.15%, and a Jaccard index of 90.4% on the Drishti-GS dataset. For classification, the proposed method achieved remarkable results with a high-test accuracy of 100% and 88.18% for hold-out validation and three-fold cross-validation for the Drishti-GS dataset, and 96.15% and 93.84% for ORIGA with hold-out and five-fold cross-validation, respectively. Comparing the results with previous studies, the proposed CNN model outperforms them. In addition, the use of the Swin transformer shows its effectiveness in classifying glaucoma in different subsets of the data. [ABSTRACT FROM AUTHOR]

Introduction: The identification of microbe-drug associations can greatly facilitate drug research and development. Traditional methods for screening microbe-drug associations are time-consuming, manpower-intensive, and costly to conduct, so computational methods are a good alternative. However, most of them ignore the combination of abundant sequence, structural information, and microbe-drug network topology. Methods: In this study, we developed a computational framework based on a modified graph attention variational autoencoder (MGAVAEMDA) to infer potential microbedrug associations by combining biological information with the variational autoencoder. In MGAVAEMDA, we first used multiple databases, which include microbial sequences, drug structures, and microbe-drug association databases, to establish two comprehensive feature matrices of microbes and drugs after multiple similarity computations, fusion, smoothing, and thresholding. Then, we employed a combination of variational autoencoder and graph attention to extract low-dimensional feature representations of microbes and drugs. Finally, the lowdimensional feature representation and graphical adjacency matrix were input into the random forest classifier to obtain the microbe-drug association score to identify the potential microbe-drug association. Moreover, in order to correct the model complexity and redundant calculation to improve efficiency, we introduced a modified graph convolutional neural network embedded into the variational autoencoder for computing low dimensional features. Results: The experiment results demonstrate that the prediction performance of MGAVAEMDA is better than the five state-of-the-art methods. For the major measurements (AUC =0.9357, AUPR =0.9378), the relative improvements of MGAVAEMDA compared to the suboptimal methods are 1.76 and 1.47%, respectively. Discussion: We conducted case studies on two drugs and found that more than 85% of the predicted associations have been reported in PubMed. The comprehensive experimental results validated the reliability of our models in accurately inferring potential microbe-drug associations. [ABSTRACT FROM AUTHOR]

Deep random forest (DRF), which combines deep learning and random forest, exhibits comparable accuracy, interpretability, low memory and computational overhead to deep neural networks (DNNs) in edge intelligence tasks. However, efficient DRF accelerator is lagging behind its DNN counterparts. The key to DRF acceleration lies in realizing the branch-split operation at decision nodes. In this work, we propose implementing DRF through associative searches realized with ferroelectric analog content addressable memory (ACAM). Utilizing only two ferroelectric field effect transistors (FeFETs), the ultra-compact ACAM cell performs energy-efficient branch-split operations by storing decision boundaries as analog polarization states in FeFETs. The DRF accelerator architecture and its model mapping to ACAM arrays are presented. The functionality, characteristics, and scalability of the FeFET ACAM DRF and its robustness against FeFET device non-idealities are validated in experiments and simulations. Evaluations show that the FeFET ACAM DRF accelerator achieves ~106x/10x and ~106x/2.5x improvements in energy and latency, respectively, compared to other DRF hardware implementations on state-of-the-art CPU/ReRAM. [ABSTRACT FROM AUTHOR]

The Yellow River Delta wetlands in China belong to the coastal wetland ecosystem, which is one of the youngest and most characteristic wetlands in the world. The Yellow River Delta wetlands are constantly changed by inland sediment and the influence of waves and storm surges, so the accurate classification of the coastal wetlands in the Yellow River Delta is of great significance for the rational utilization, development and protection of wetland resources. In this study, the Yellow River Delta sentinel-2 multispectral data were processed by super-resolution synthesis, and the feature bands were optimized. The optimal feature-band combination scheme was screened using the OIF algorithm. A deep learning model attention mechanism ResNet based on feature optimization with attention mechanism integration into the ResNet network is proposed. Compared with the classical machine learning model, the AM_ResNet model can effectively improve the classification accuracy of the wetlands in the Yellow River Delta. The overall accuracy was 94.61% with a Kappa of 0.93, and they were improved by about 6.99% and 0.1, respectively, compared with the best-performing Random Forest Classification in machine learning. The results show that the method can effectively improve the classification accuracy of the wetlands in the Yellow River Delta. [ABSTRACT FROM AUTHOR]