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 primary goal of the present research work is to build machine learning based classification model for classifying an individual with different degrees of autism that can yield better performance than traditional autism assessment scale used in India. The study aimed to find how significant are the selected additional 6 attributes for better identification and understanding of Autism spectrum disorder (ASD). This work focuses on a unique screening tool developed for the Indian population –Indian Scale for assessment of Autism(ISAA) to build the classification model. For better performance few additional significant features are also considered following proper procedure. Selective machine learning models are built and finally performance evaluation is done on all classifier results. As an alternative approach, a binary classifier multi-layer perceptron (MLP) model has also been trained on both the data sets to distinguish between people with autism who need less attention and those who need more attention for assessment and further intervention. Overall performance of 3 best classifiers (KNN, Random Forest, SVM) suggests that after considering additional 6 attributes SVM produced better efficacy in identification of degree of autism over conventional ISAA parameters with higher weighted F1 score of 85.7% and accuracy of 90% respectively. It is also reconfirmed with the results of the MLP model. The basic model converges after 71 epochs with training accuracy 97.78% wherein the extended model converges after 61 epochs with training accuracy 98.89%. The best model functions better than conventional scale of assessment which also made the screening task unbiased, accurate and time efficient. [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: Predicting mortality and relapse in children with acute lymphoblastic leukemia (ALL) is crucial for effective treatment and follow-up management. ALL is a common and deadly childhood cancer that often relapses after remission. In this study, we aimed to apply and evaluate machine learning-based models for predicting mortality and relapse in pediatric ALL patients. Methods: This retrospective cohort study was conducted on 161 children aged less than 16 years with ALL. Survival status (dead/alive) and patient experience of relapse (yes/no) were considered as the outcome variables. Ten machine learning (ML) algorithms were used to predict mortality and relapse. The performance of the algorithms was evaluated by cross-validation and reported as mean sensitivity, specificity, accuracy and area under the curve (AUC). Finally, prognostic factors were identified based on the best algorithms. Results: The mean accuracy of the ML algorithms for prediction of patient mortality ranged from 64 to 74% and for prediction of relapse, it varied from 64 to 84% on test data sets. The mean AUC of the ML algorithms for mortality and relapse was above 64%. The most important prognostic factors for predicting both mortality and relapse were identified as age at diagnosis, hemoglobin and platelets. In addition, significant prognostic factors for predicting mortality included clinical side effects such as splenomegaly, hepatomegaly and lymphadenopathy. Conclusions: Our results showed that artificial neural networks and bagging algorithms outperformed other algorithms in predicting mortality, while boosting and random forest algorithms excelled in predicting relapse in ALL patients across all criteria. These results offer significant clinical insights into the prognostic factors for children with ALL, which can inform treatment decisions and improve patient outcomes. [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]

Spherical data arise widely in various settings. Spherical statistics is an analysis of data on a unit hyper-spherical domain. In this paper, we mainly consider the local kernel estimators for regression models with a binary response and the predictors including spherical variables. We apply the random forests kernel to nonparametric binary regression models with spherical predictors. Simulation experiments and real examples are used to validate the performance of the new models. Compared with the classical von Mises–Fisher kernel and the linear-spherical kernel, the random forests kernel has better fitting effect and faster computation speed. Compared with other classifiers, the models proposed in this paper have better classification performance in both low and high dimensional cases. [ABSTRACT FROM AUTHOR]

This work proposed a liver cancer classification scheme that includes Preprocessing, Feature extraction, and classification stages. The source images are pre-processed using Gaussian filtering. For segmentation, this work proposes a LUV transformation-based adaptive thresholding-based segmentation process. After the segmentation, certain features are extracted that include multi-texon based features, Improved Local Ternary Pattern (LTP-based features), and GLCM features during this phase. In the Classification phase, an improved Deep Maxout model is proposed for liver cancer detection. The adopted scheme is evaluated over other schemes based on various metrics. While the learning rate is 60%, an improved deep maxout model achieved a higher F-measure value (0.94) for classifying liver cancer; however, the previous method like Support Vector Machine (SVM), Random Forest (RF), Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), K-Nearest Neighbor (KNN), Deep maxout, Convolutional Neural Network (CNN), and DL model holds less F-measure value. An improved deep maxout model achieved minimal False Positive Rate (FPR), and False Negative Rate (FNR) values with the best outcomes compared to other existing models for liver cancer classification. [ABSTRACT FROM AUTHOR]

LiDAR-unmanned aerial system (LiDAR-UAS) technology can accurately and efficiently obtain detailed and accurate three-dimensional spatial information of objects. The classification of objects in estuarine areas is highly important for management, planning, and ecosystem protection. Owing to the presence of slopes in estuarine areas, distinguishing between dense vegetation (lawns and trees) on slopes and the ground at the tops of slopes is difficult. In addition, the imbalance in the number of point clouds also poses a challenge for accurate classification directly from point cloud data. A multifeature-assisted and multilayer fused neural network (MLF-PointNet++) is proposed for LiDAR-UAS point cloud classification in estuarine areas. First, the 3D shape features that characterize the geometric characteristics of targets and the visible-band difference vegetation index (VDVI) that can characterize vegetation distribution are used as auxiliary features to enhance the distinguishability of dense vegetation (lawns and trees) on slopes and the ground at the tops of slopes. Second, to enhance the extraction of target spatial information and contextual relationships, the feature vectors output by different layers of set abstraction in the PointNet++ model are fused to form a combined feature vector that integrates low and high-level information. Finally, the focal loss function is adopted as the loss function in the MLF-PointNet++ model to reduce the effect of imbalance in the number of point clouds in each category on the classification accuracy. A classification evaluation was conducted using LiDAR-UAS data from the Moshui River estuarine area in Qingdao, China. The experimental results revealed that MLF-PointNet++ had an overall accuracy (OA), mean intersection over union (mIOU), kappa coefficient, precision, recall, and F1-score of 0.976, 0.913, 0.960, 0.953, 0.953, and 0.953, respectively, for object classification in the three representative areas, which were better than the corresponding values for the classification methods of random forest, BP neural network, Naive Bayes, PointNet, PointNet++, and RandLA-Net. The study results provide effective methodological support for the classification of objects in estuarine areas and offer a scientific basis for the sustainable development of these areas. [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]

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]

Automated sandbox-based analysis systems are dominantly focused on sequences of API calls, which are widely acknowledged as discriminative and easily extracted features. In this paper, we argue that an extension of the feature set beyond API calls may improve the malware detection performance. For this purpose, we apply the Cuckoo open-source sandbox system, carefully configured for the production of a novel dataset for dynamic malware analysis containing 22,200 annotated samples (11,735 benign and 10,465 malware). Each sample represents a full-featured report generated by the Cuckoo sandbox when a corresponding binary file is submitted for analysis. To support our position that the discriminative power of the full-featured sandbox reports is greater than the discriminative power of just API call sequences, we consider samples obtained from binary files whose execution induced API calls. In addition, we derive an additional dataset from samples in the full-featured dataset, whose samples contain only information on API calls. In a three-way factorial design experiment (considering the feature set, the feature representation technique, and the random forest model hyperparameter settings), we trained and tested a set of random forest models in a two-class classification task. The obtained results demonstrate that resorting to full-featured sandbox reports improves malware detection performance. The accuracy of 95.56 percent obtained for API call sequences was increased to 99.74 percent when full-featured sandbox reports were considered. [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]

Machine learning methods have improved in recent years and provide increasingly powerful tools for understanding landscape evolution. In this study, we used the random forest method based on Google Earth Engine to evaluate the desertification dynamics in northern China from 1995 to 2020. We selected Landsat series image bands, remote sensing inversion data, climate baseline data, land use data, and soil type data as variables for majority voting in the random forest method. The method's average classification accuracy was 91.6% ± 5.8 [mean ± SD], and the average kappa coefficient was 0.68 ± 0.09, suggesting good classification results. The random forest classifier results were consistent with the results of visual interpretation for the spatial distribution of different levels of desertification. From 1995 to 2000, the area of aeolian desertification increased at an average rate of 9977 km2 yr−1, and from 2000 to 2005, from 2005 to 2010, from 2010 to 2015, and from 2015 to 2020, the aeolian desertification decreased at an average rate of 2535, 3462, 1487, and 4537 km2 yr−1, respectively. [ABSTRACT FROM AUTHOR]

A baby's first spoken communication comes through crying. Before learning to convey their psychological/physiological needs or feelings using language, babies typically express how they feel by crying. Crying is a reaction to an inducement like pain, discomfort or hunger. Nevertheless, it is difficult sometimes to understand why a baby is crying. This will be annoying for a parents/guardian/caretaker, and therefore in this work, we are proposing an infant cry analysis and classification system to classify the kinds of crying of babies to assist parents/guardian/caretaker and attend to the needs of the babies. Presently, five distinct kinds of infant cries are identified: hunger (Neh), belly pain (Eairh), tiredness (Owh), discomfort (Heh) and burping (Eh). The database of this study consists of 456 audio recordings of 7 s each of 0–22-week-old babies. Feature extraction from each crying frame is carried out using Mel-frequency cepstral coefficients and the sequential forward floating selection is later used to choose highly discriminative features. Support Vector Machine and Random Forest classifiers are used for classification of infant crying. The results of the experiments has shown the performance of the proposed system with a accuracy of classification of 78% and 90.8% for Support Vector Machine and Random forest classifiers respectively. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has profoundly impacted our daily lives, disrupting the usual course of life as we know it. The persistent and unpredictable nature of the virus outbreak, coupled with the challenges in finding effective treatments and a satisfactory cure rate, has given rise to an environment that significantly affects our mental well-being. This article focuses on analyzing sentiments expressed in thousands of tweets related to the COVID-19 pandemic. To accomplish automated tweet sentiment classification, a novel deep learning model called CovDLCNet is introduced. This model is based on the classical Long Short-Term Memory (LSTM) network, which has proven to be effective in sequence analysis tasks. By employing Python-based libraries, the necessary data acquisition, data pre-processing, and data analysis processes are carried out. As a data preprocessing task tweets are initially cleaned and for removing the duplicate (redundant) and similar types of tweets one graph theoretic approach is proposed. Further by calculating the polarity score, sentiment of the tweets are categorized into three groups (viz., negative, neutral and positive). Thereafter, by applying the proposed model classifications of the tweets are evaluated. Experimental results show that the proposed model outperforms all other compared models by achieving a 99.23% classification accuracy score. Henceforth, the results suggest that the proposed model performed better than other six compared models viz., LSTM-M1, LSTM-M2, CNN-LSTM, Bernoulli Naïve Bayes (BNB), Logistic regression (LR) and Random forest (RF) for classifying the sentiment of the tweets into negative, neutral and positive categories. [ABSTRACT FROM AUTHOR]

In order to increase the likelihood of obtaining treatment and achieving a complete recovery, early illness identification and diagnosis are crucial. Artificial intelligence is helpful with this process by allowing us to rapidly start the necessary protocol for treatment in the early stages of disease development. Artificial intelligence is a major contributor to the improvement of medical treatment for patients. In order to prevent and foresee this problem on the individual, family, and generational levels, Monitoring the patient's therapy and recovery is crucial. This study's objective is to outline a non-invasive method for using mammograms to detect breast abnormalities, classify breast disorders, and identify cancerous or benign tumor tissue in the breast. We used classification models on a dataset that has been pre-processed so that the number of samples is balanced, unlike previous work on the same dataset. Identifying cancerous or benign breast tissue requires the use of supervised learning techniques and algorithms, such as random forest (RF) and decision tree (DT) classifiers, to examine up to thirty features, such as breast size, mass, diameter, circumference, and the nature of the tumor (solid or cystic). To ascertain if the tissue is malignant or benign, the examination's findings are employed. These features are mostly what determines how effectively anything may be categorized. The DT classifier was able to get a score of 95.32%, while the RF satisfied a far higher 98.83 percent. [ABSTRACT FROM AUTHOR]

This study introduces an innovative scheme for classifying uncrewed aerial vehicle (UAV)-derived vehicle trajectory behaviors by employing machine learning (ML) techniques to transform original trajectories into various sequences: space–time, speed–time, and azimuth–time. These transformed sequences were subjected to normalization for uniform data analysis, facilitating the classification of trajectories into six distinct categories through the application of three ML classifiers: random forest, time series forest (TSF), and canonical time series characteristics. Testing was performed across three different intersections to reveal an accuracy exceeding 90%, underlining the superior performance of integrating azimuth–time and speed–time sequences over conventional space–time sequences for analyzing trajectory behaviors. This research highlights the TSF classifier's robustness when incorporating speed data, demonstrating its efficiency in feature extraction and reliability in intricate trajectory pattern handling. This study's results indicate that integrating direction and speed information significantly enhances predictive accuracy and model robustness. This comprehensive approach, which leverages UAV-derived trajectories and advanced ML techniques, represents a significant step forward in understanding vehicle trajectory behaviors, aligning with the goals of enhancing traffic control and management strategies for better urban mobility. [ABSTRACT FROM AUTHOR]

Movie Recommender systems are frequently used in academics and industry to give users with relevant, engaging material based on their rating history. However, most traditional methods suffer from the cold-start problem, which is the initial lack of item ratings and data sparsity. The Hybrid Machine Learning (ML) technique is proposed for a movie recommendation system. Demographic data is collected from the Movie Lens dataset, and attributes are evaluated using the Attribute Analysis module. The Aquila Optimization Algorithm is used to select the best attributes, while Random Forest classifier is used for classification. Data is clustered using Fuzzy Probabilistic Cmeans Clustering Algorithm (FPCCA), and the Correspondence Index Assessment Phase (CIAP) uses Bhattacharyya Coefficient in Collaborative Filtering (BCCF) for similarity index calculation. The Outcomes gives the proposed method obtained low error, such as MAE has 0.44, RMSE has 0.63 compared with the baseline methods. [ABSTRACT FROM AUTHOR]

Early diagnosis of potentially malignant disorders, such as oral epithelial dysplasia, is the most reliable way to prevent oral cancer. Computational algorithms have been used as an auxiliary tool to aid specialists in this process. Usually, experiments are performed on private data, making it difficult to reproduce the results. There are several public datasets of histological images, but studies focused on oral dysplasia images use inaccessible datasets. This prevents the improvement of algorithms aimed at this lesion. This study introduces an annotated public dataset of oral epithelial dysplasia tissue images. The dataset includes 456 images acquired from 30 mouse tongues. The images were categorized among the lesion grades, with nuclear structures manually marked by a trained specialist and validated by a pathologist. Also, experiments were carried out in order to illustrate the potential of the proposed dataset in classification and segmentation processes commonly explored in the literature. Convolutional neural network (CNN) models for semantic and instance segmentation were employed on the images, which were pre-processed with stain normalization methods. Then, the segmented and non-segmented images were classified with CNN architectures and machine learning algorithms. The data obtained through these processes is available in the dataset. The segmentation stage showed the F1-score value of 0.83, obtained with the U-Net model using the ResNet-50 as a backbone. At the classification stage, the most expressive result was achieved with the Random Forest method, with an accuracy value of 94.22%. The results show that the segmentation contributed to the classification results, but studies are needed for the improvement of these stages of automated diagnosis. The original, gold standard, normalized, and segmented images are publicly available and may be used for the improvement of clinical applications of CAD methods on oral epithelial dysplasia tissue images. [ABSTRACT FROM AUTHOR]

Marine transport is still famous and claimed to be part of human civilization, but in practice, marine vessels still experience accidents quite frequently, which can result in large losses. Therefore, this research aims to integrate multiple data sources on marine accidents, classify them to identify patterns, and create a model to forecast and prevent future accidents. The first step in the methodology is to connect several variables from multiple data sources and generate target variables. We then feed this ready data set into 10 machine learning algorithms to determine which one best suit the data type and quality. The training results provided four algorithms with the best performance, namely label spreading, label propagation, random forest, and XGB classifier algorithms. After comparing the training and testing results, we found that XGB performed slightly better than the other three models, where the developed model and dataset only had a performance of 70%-74% in predicting marine accidents in the corresponding class. [ABSTRACT FROM AUTHOR]

This study aims to improve the performance of classification algorithms in dealing with unbalanced and high-dimensional health in stroke prediction by integrating correlation feature selection and hybrid sampling techniques. Several previous studies that used machine learning methods to predict stroke still had less than optimal accuracy. This is because stroke data has several problems, including missing values, many attributes, and data imbalance can cause a decrease in the performance of the classification method. Therefore, this research uses an integrated approach to feature selection and hybrid sampling. The objective of the feature selection technique is to identify important attributes within stroke data. After that, the SMOTE-Enn hybrid sampling approach is utilized to address data imbalance. The research findings indicate that employing correlation-based feature selection along with SMOTE-Enn and the Random Forest algorithm leads to improved performance compared to no sampling with the SVM and XGBoost methods, with an increase in accuracy of 3%, recall of 91.3%, and AUC of 45.2%. Thus, the proposed method performed better than recent stroke classification studies. [ABSTRACT FROM AUTHOR]

Honey authentication is a complex process which traditionally requires costly and time-consuming analytical techniques not readily available to the producers. This study aimed to develop non-invasive sensor methods coupled with a multivariate data analysis to detect the type and percentage of exogenous sugar adulteration in UK honeys. Through-container spatial offset Raman spectroscopy (SORS) was employed on 17 different types of natural honeys produced in the UK over a season. These samples were then spiked with rice and sugar beet syrups at the levels of 10%, 20%, 30%, and 50% w/w. The data acquired were used to construct prediction models for 14 types of honey with similar Raman fingerprints using different algorithms, namely PLS-DA, XGBoost, and Random Forest, with the aim to detect the level of adulteration per type of sugar syrup. The best-performing algorithm for classification was Random Forest, with only 1% of the pure honeys misclassified as adulterated and <3.5% of adulterated honey samples misclassified as pure. Random Forest was further employed to create a classification model which successfully classified samples according to the type of adulterant (rice or sugar beet) and the adulteration level. In addition, SORS spectra were collected from 27 samples of heather honey (24 Calluna vulgaris and 3 Erica cinerea) produced in the UK and corresponding subsamples spiked with high fructose sugar cane syrup, and an exploratory data analysis with PCA and a classification with Random Forest were performed, both showing clear separation between the pure and adulterated samples at medium (40%) and high (60%) adulteration levels and a 90% success at low adulteration levels (20%). The results of this study demonstrate the potential of SORS in combination with machine learning to be applied for the authentication of honey samples and the detection of exogenous sugars in the form of sugar syrups. A major advantage of the SORS technique is that it is a rapid, non-invasive method deployable in the field with potential application at all stages of the supply chain. [ABSTRACT FROM AUTHOR]

Combining an Internet of Things-driven approach with machine learning algorithms holds great promise in discerning pure gases across various applications. Interconnecting gas sensors within a network allows for continuous monitoring and real-time environmental analysis, producing valuable data for machine learning models. Utilizing supervised learning algorithms, like random forests, enables the creation of accurate classification models that can effectively distinguish between different pure gases based on their distinct features, such as spectral signatures or sensor responses. This groundbreaking integration of the Internet of Things and Machine Learning fosters the development of robust, automated gas detection systems, ensuring high accuracy and minimal delay in recognizing pure gases. Consequently, it opens avenues for enhanced safety, efficiency, and environmental sustainability in numerous industrial and commercial scenarios. [ABSTRACT FROM AUTHOR]

Predicting hotel ratings from reviews involves natural language processing techniques to extract sentiment and features from text data, then applying machine learning (ML) models like regression or classification to estimate the corresponding rating based on these features. This study proposes an ensemble learning approach for predicting hotel ratings from user reviews. By integrating multiple ML algorithms trained on various textual features, including linguistic, semantic, and sentiment-based attributes, our model achieves superior predictive accuracy. The primary aim of this study is to predict user experience ratings with high accuracy. To achieve this, this research utilizes an Ensemble learning approach known as majority voting to make these predictions effectively. In this investigation, initially, the dataset undergoes cleaning and is subsequently subjected to a series of pre-processing steps using Natural Language Processing (NLP) techniques. The research includes a comparative analysis of various classifiers along with different embedding methods. Seven different types of classifiers are used alongside three embedding techniques i.e., Term Frequency-Inverse Document Frequency (TF-IDF), Bag of Words (BoW), and Word2Vec. The classifiers include, Logistic Regression without Cross Validation (LR), LR with Cross Validation (LRCV), Decision Tree Classifier (DTC), Stochastic Gradient Descent Classifier (SGDC), Random Forest Classifier (RFC), Support Vector Classifier (SVC) and K-Nearest Neighbour (KNN). Our proposed methodology demonstrates higher accuracy and robust performance. Accuracy and frequency are utilized as performance metrics for assessing and validating both classifiers and embedding techniques. As per the simulation results, TF-IDF in combination with LRCV achieves an accuracy rate of 61%. [ABSTRACT FROM AUTHOR]

Image recognition and classification in the domain of cultural heritage is a complex task that usually requires good image quality and a large dataset. Small dataset is an apparent problem when data availability is limited, often resulting in poor classification performance. The aim of this study is to analyze and compare the performance of four machine learning algorithms, namely random forest, multilayer perceptron classifier, Naïve Bayes, and decision tree, that are used to classify features extracted using eleven pre-trained deep learning architectures from a small set of images representing cultural heritage. The findings imply that random forest and multilayer perceptron classifiers are the most appropriate for the task of image classification of small cultural heritage datasets, as they obtained the highest performance compared to the other two algorithms, particularly when DenseNet121, EfficientNetB0 and NASNetMobile architectures are used for feature extraction. In addition, for the classification of features extracted using NASNetMobile all the four utilized machine learning algorithms obtained high accuracy ranging from 88.89 to 95.56%. [ABSTRACT FROM AUTHOR]

ALS (Amyotrophic Lateral Sclerosis) is a fatal neurodegenerative disease of the human motor system. It is a group of progressive diseases that affects the nerve cells in the brain and spinal cord that control the muscle movement of the body hence, detection and classification of ALS at the right time is considered to be one of the vital aspects that can save the life of humans. Therefore, in various studies, different AI techniques are used for the detection of ALS, however, these methods are considered to be ineffectual in terms of identifying the disease due to the employment of ineffective algorithms. Hence, the proposed model utilizes Modified Principal Component Analysis (MPCA) and Modified Random Forest (MRF) for performing dimensionality reduction of all the potential features considered for effective classification of the ALS presence and absence of ALS causing mutation in the corresponding gene. The MPCA is adapted for capturing all the Low-Importance Data transformation. Furthermore, The MPCA is objected to performing three various approaches: Covariance Matrix Correlation, Eigen Vector- Eigenvalue decomposition, and selecting the desired principal components. This is done in aspects of implying the LI (Lower-Importance) Data Transformation. By choosing these potential components without any loss of features ensures better viability of selecting the attributes for ALS-causing gene classification. This is followed by the classification of the proposed model by using Modified RF by updating the clump detector technique. The clump detector is proceeded by clustering approach using K-means, and the data reduced by their dimension are grouped accordingly. These clustered data are analyzed either for ALS causing or devoid of causing ALS. Finally, the model's performance is assessed using different evaluation metrics like accuracy, recall, F1 score, and precision, and the proposed model is further compared with the existing models to assess the efficacy of the proposed model. [ABSTRACT FROM AUTHOR]

In healthcare, observing the features and areas of malaria in microscopic images is crucial for the diagnosis and treatment of plasmodium malaria parasites for automated detection. The classification of malaria parasites can be challenging due to factors such as limited training data, class imbalance, and variability in parasite stages. Moreover, the parasites often belong to similar classes, and the quality of malaria blood cell smears is often poor. To address this issue, a Deep Convolutional Neural Network (Deep-CNN) model is combined with Random Forest (RF) for the detection of plasmodium malaria parasites. The Deep-CNN-RF approach leverages domain-specific expertise for improved learning. Moreover, a novel modification is applied to the pooling layer by incorporating the Global Average-Pooling layer (GAP) without an additional flattening layer, enhancing parasite area visualization. Additionally, Canny edge detection is employed for precise parasite boundary edge detection. The experimental performance of the Deep-CNN-RF model is evaluated using a malaria cell dataset from the National Library of Medicine (NLM), Kaggle, and the National Institutes of Health (NIH). The proposed scheme effectiveness is assessed through performance metrics, including accuracy, precision, recall, Mean Square Error (MSE), and F1-Score. The results demonstrate that the proposed technique outperforms state-of-the-art classification models on malaria parasite datasets. [ABSTRACT FROM AUTHOR]

Recent advances in sequencing, mass spectrometry, and cytometry technologies have enabled researchers to collect multiple 'omics data types from a single sample. These large datasets have led to a growing consensus that a holistic approach is needed to identify new candidate biomarkers and unveil mechanisms underlying disease etiology, a key to precision medicine. While many reviews and benchmarks have been conducted on unsupervised approaches, their supervised counterparts have received less attention in the literature and no gold standard has emerged yet. In this work, we present a thorough comparison of a selection of six methods, representative of the main families of intermediate integrative approaches (matrix factorization, multiple kernel methods, ensemble learning, and graph-based methods). As non-integrative control, random forest was performed on concatenated and separated data types. Methods were evaluated for classification performance on both simulated and real-world datasets, the latter being carefully selected to cover different medical applications (infectious diseases, oncology, and vaccines) and data modalities. A total of 15 simulation scenarios were designed from the real-world datasets to explore a large and realistic parameter space (e.g. sample size, dimensionality, class imbalance, effect size). On real data, the method comparison showed that integrative approaches performed better or equally well than their non-integrative counterpart. By contrast, DIABLO and the four random forest alternatives outperform the others across the majority of simulation scenarios. The strengths and limitations of these methods are discussed in detail as well as guidelines for future applications. [ABSTRACT FROM AUTHOR]

Objectives: Women's attendance to cervical cancer screening (CCS) is a major concern for healthcare providers in community. This study aims to use the various algorithms that can accurately predict the most barriers of women for nonattendance to CS. Design: The real‐time data were collected from women presented at OPD of primary health centers (PHCs). About 1046 women's data regarding attendance and nonattendance to CCS were included. In this study, we have used three models, classification, ensemble, and deep learning models, to compare the specific accuracy and AU‐ROC for predicting non‐attenders for CC. Results: The current model employs 22 predictors, with soft voting in ensemble models showing slightly higher specificity (96%) and sensitivity (93%) than weighted averaging. Bagging excels with the highest accuracy (98.49%), specificity (97.3%), and ideal sensitivity (100%) with an AUC of 0.99. Classification models reveal Naive Bayes with higher specificity (97%) but lower sensitivity (91%) than Logistic Regression. Random Forest and Neural Network achieve the highest accuracy (98.49%), with an AUC of 0.98. In deep learning, LSTM has an accuracy of 95.68%, higher specificity (97.60%), and lower sensitivity (93.42%) compared to other models. MLP and NN showed the highest AUC values of 0.99. Conclusion: Employing ensemble and deep learning models proved most effective in predicting barriers to nonattendance in cervical screening. [ABSTRACT FROM AUTHOR]

The advent of Blockchain and its subsequent application in creating Bitcoin has changed the world of finance. The peer-to-peer Blockchain networks, lack a third-party intermediary authority to regulate the transactions, making it vulnerable to various forms of stings. One of the most proliferate uses of crypto transactions is for the ransom payment made by victims of ransomware attacks. Owing to the varied nature of the ransomware attacks, coupled with the decentralized nature of Blockchain, tracking and guarding against such attacks is still a challenge. One way to prevent ransomware attackers from easily benefitting from such crypto transactions is to identify them and avert any payment to those attackers. In this paper, the impact of three ensemble classification algorithms – Random Forest, XGBoost and Balanced Bagging are studied to correctly classify ransomware payments from existing Bitcoin transaction data, to identify the attackers’ addresses and possibly suspend them from taking part in any transactions. The outcomes of the three algorithms are compared with each other based on various indicators. From the experimental results, it could be concluded that Balanced Bagging Classifier demonstrated better performance with an accuracy of 98.41%. [ABSTRACT FROM AUTHOR]

Jilin Province is located in the northeast of China, and has fragile ecosystems, and a vulnerable environment. Large-scale, long time series, high-precision land-use/cover change (LU/CC) data are important for spatial planning and environmental protection in areas with high surface heterogeneity. In this paper, based on the high temporal and spatial fusion data of Landsat and MODIS and the Google Earth Engine (GEE), long time series LU/CC mapping and spatio-temporal analysis for the period 2000–2023 were realized using the random forest remote sensing image classification method, which integrates remote sensing indices. The prediction results using the OL-STARFM method were very close to the real images and better contained the spatial image information, allowing its application to the subsequent classification. The average overall accuracy and kappa coefficient of the random forest classification products obtained using the fused remote sensing index were 95.11% and 0.9394, respectively. During the study period, the area of cultivated land and unused land decreased as a whole. The area of grassland, forest, and water fluctuated, while building land increased to 13,442.27 km2 in 2023. In terms of land transfer, cultivated land was the most important source of transfers, and the total area share decreased from 42.98% to 38.39%. Cultivated land was mainly transferred to grassland, forest land, and building land, with transfer areas of 7682.48 km2, 8374.11 km2, and 7244.52 km2, respectively. Grassland was the largest source of land transfer into cultivated land, and the land transfer among other feature types was relatively small, at less than 3300 km2. This study provides data support for the scientific management of land resources in Jilin Province, and the resulting LU/CC dataset is of great significance for regional sustainable development. [ABSTRACT FROM AUTHOR]

A set of quantum chemical descriptors (molecular polarization, heat capacity, entropy, Mulliken net charge of the most positive hydrogen atom, APT charge of the most negative atom and APT charge of the most positive atom with hydrogen summed into heavy atoms) was successfully used to establish the classification models for the toxicity pLC50 of pesticides in Americamysis bahia. The optimal random forest model (Class Model A) yielded predictive accuracy of 100% (training set of 217 pesticides), 95.8% (test set of 72 pesticides) and 99.0% (total set of 289 pesticides), which were very satisfactory, compared with previous classification models reported for the toxicity of compounds in aquatic organisms. Therefore, it is reasonable to apply the quantum chemical descriptors associated with molecular structural information on molecular bulk, chemical reactivity and weak interactions, to develop classification models for the toxicity pLC50 of pesticides in A. bahia. [ABSTRACT FROM AUTHOR]

The proliferation of malware gravely threatens the security of computer systems and sensitive data. This work aims to improve malware detection by using advanced feature selection techniques. The study utilizes the Firefly Algorithm (FA) for feature selection in binary and multiclass classifications to enhance the discrimination capabilities of selected features. The selected features from the binary and multiclass classifications are combined to generate a comprehensive feature set. The Obfuscated-MalMem2022 dataset is employed in the experimental evaluation. The Random Forest (RF) method completes the classification problem. Remarkably, the results demonstrate that RF performs better with the combined feature set than with features chosen separately from the binary and multiclass classifications by the FA method. RF attains a remarkable 99.983% accuracy in binary classification, demonstrating the potency of the selected features in differentiating between malicious and benign data. Moreover, RF demonstrates an impressive accuracy of 87.304% in multiclass classification, highlighting the strength of the proposed methodology. [ABSTRACT FROM AUTHOR]

One of the most common causes of blindness, particularly in the elderly, is cataracts. Nearly half of India's elderly population has cataracts by the age of 80 or has had surgery to treat them. According to surveys conducted by the WHO and NPCB, there are over 12 million blind persons in India, and 80.1% of them are blind due to cataracts. Early detection of cataract cases is necessary to prevent total blindness. The World Health Organization (WHO) states that cataracts are the most frequent cause of blindness and visual loss. The risk of blindness among cataract patients can be decreased with prompt detection and treatment. On the other hand, clinical cataract identification requires the expertise of ophthalmologists. Therefore, the broad adoption of cataract detection to avert blindness may be hampered by the prospective expenses. Researchers are becoming more and more interested in artificial intelligence assisted diagnosis based on medical imagery. This study suggests an automated cataract detection procedure built on image processing and machine learning methods. A set of fundus retinal images serves as the input for the suggested model. The image dataset includes two kinds of images: healthy and images with cataracts to train the algorithm. This research consists of three primary phases: pre-processing, feature extraction and classification. The initial step of the method involves pre-processing the images to make them easier to process by extract the gray scale from the input image, then contrast-limited adaptive histogram equalization (CLAHE) is applied to improve the image and minimize noise, Finally ROI has been extracted. The second phase is feature extraction; by extract four kinds of texture features: (I) grey-level co-occurrence matrix (GLCM) to extract 11 features: 1) difference variance, 2) inverse difference moment, 3,4) information1\2, 5) entropy, 6) difference entropy, 7) correlation, 8) sum entropy, 9) maximal correlation coefficient, 10) contrast, and 11) angular second moment. (II) First Order Statistics (FOS) to extract 5 features: 1) entropy, 2) maximal gray level, 3) kurtosis, 4) skewness, and 5) energy. (III) Statistical Feature Matrix (SFM) to extract 4 features: 1) coarseness, 2) periodicity, 3) contrast, and 4) roughness. And finally (IV) Neighborhood Gray Tone Difference Matrix (NGTDM) to extract 4 features: 1) complexity, 2) coarseness, 3) strength, and 4) contrast. In the last phases, the extracted 24 features are put as input to the classifier, the classification was done by using Random Forest, support vector machines (SVM), Logistic Regression, K Neighbors (KNN), Decision Tree, and Naive Base Classifier. Classifies the retinal fundus images into two classes Cataracts or normal image. When compared to other current approaches, the experimental results of the suggested method show that its accuracy is 95%. [ABSTRACT FROM AUTHOR]

One expanding area of bioinformatics is medical diagnosis through the categorization of biomedical characteristics. Automatic medical strategies to boost the diagnostic through machine learning (ML) methods are challenging. They require a formal examination of their performance to identify the best conditions that enhance the ML method. This work proposes variants of the Voting and Stacking (VC and SC) ensemble strategies based on diverse auto-tuning supervised machine learning techniques to increase the efficacy of traditional baseline classifiers for the automatic diagnosis of vertebral column orthopedic illnesses. The ensemble strategies are created by first combining a complete set of auto-tuned baseline classifiers based on different processes, such as geometric, probabilistic, logic, and optimization. Next, the three most promising classifiers are selected among k-Nearest Neighbors (kNN), Naïve Bayes (NB), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Decision Tree (DT). The grid-search K-Fold cross-validation strategy is applied to auto-tune the baseline classifier hyperparameters. The performances of the proposed ensemble strategies are independently compared with the auto-tuned baseline classifiers. A concise analysis evaluates accuracy, precision, recall, F1-score, and ROC-ACU metrics. The analysis also examines the misclassified disease elements to find the most and least reliable classifiers for this specific medical problem. The results show that the VC ensemble strategy provides an improvement comparable to that of the best baseline classifier (the kNN). Meanwhile, when all baseline classifiers are included in the SC ensemble, this strategy surpasses 95% in all the evaluated metrics, standing out as the most suitable option for classifying vertebral column diseases. [ABSTRACT FROM AUTHOR]

As a popular nutraceutical, collagen powder is the target of adulteration like other high-value food products, therefore detection of adulteration in collagen powder is of great practical significance to ensure market order and the health of the people. To achieve accurate detection of adulterants in collagen powder, a modeling method of fluorescence hyperspectral technology combined with machine learning algorithm was proposed. This study employed various preprocessing methods for denoising and spectral correction to enhance the effective spectral data. Principal component analysis was used to visualize the spectral data and initially revealed the spatial distribution of adulterated collagen powder. Genetic algorithm-k nearest neighbor, particle swarm optimization-support vector machine, and gradient boosting decision tree were used to construct classification models to identify adulterated collagen powder, with the best 2-class discriminant model accuracy, 4-class discriminant model accuracy, and 5-class discriminant model accuracy reaching 99%, 94%, and 98%, respectively. In the quantitative detection models of adulteration level, the random forest model performed best with correlation coefficient (R2) of 0.95 to 0.99. These results suggested that fluorescence hyperspectral technology combined with machine learning algorithm can be effectively used to detect adulterated collagen powder. [ABSTRACT FROM AUTHOR]

Levels of a predictor variable that are absent when a classification tree is grown can not be subject to an explicit splitting rule. This is an issue if these absent levels are present in a new observation for prediction. To date, there remains no satisfactory solution for absent levels in random forest models. Unlike missing data, absent levels are fully observed and known. Ordinal encoding of predictors allows absent levels to be integrated and used for prediction. Using a case study on source attribution of Campylobacter species using whole genome sequencing (WGS) data as predictors, we examine how target-agnostic versus target-based encoding of predictor variables with absent levels affects the accuracy of random forest models. We show that a target-based encoding approach using class probabilities, with absent levels designated the highest rank, is systematically biased, and that this bias is resolved by encoding absent levels according to the a priori hypothesis of equal class probability. We present a novel method of ordinal encoding predictors via principal coordinates analysis (PCO) which capitalizes on the similarity between pairs of predictor levels. Absent levels are encoded according to their similarity to each of the other levels in the training data. We show that the PCO-encoding method performs at least as well as the target-based approach and is not biased. [ABSTRACT FROM AUTHOR]

Rice plays an essential role in ensuring the food security of Indonesia. Hence, rice (paddy) field monitoring using synthetic aperture radar (SAR) satellite data is critical, particularly in tropical regions. This study presents a new algorithm to detect paddy fields in Subang, West Java, using Sentinel-1 SAR with a 12-day revisit acquisition. Three temporal phenological features of paddy growth were used, namely, the minimum and maximum backscatter, as well as their differences. Paddy fields were discriminated from other land covers using a simple thresholding algorithm based on their specific pattern of low minimum, high maximum, and high difference of vertical transmithorizontal receive polarization (VH) backscatter on a 2-dimensional (2D) scatter plot. The results showed that the proposed algorithm had an accuracy of 94.02%, comparable to that of the random forest algorithm and other studies using 3-dimensional (3D) parameters. The proposed algorithm reduces the dimensionality from 3D to 2D and is practical for mapping and monitoring paddy fields. In this context, the application of the algorithm to the surrounding regions of Karawang, Indramayu, and Bekasi achieved high accuracy rates of 93.37%, 92.87%, and 88.13%, respectively. [ABSTRACT FROM AUTHOR]

Recently, the Internet of Things (IoT) has become a buzzword in various technology fields because of its many applications. Healthcare is one of the most important fields in daily life and holds significant interest for IoT and artificial intelligence researchers. In the area of healthcare, the mental healthcare field has attracted many researchers and funding organizations for various reasons. Among those reasons are the adverse impact of mental conditions on both individuals and society, the high costs of mental care, the nature of mental conditions and their hidden and unclear symptoms, and the stigma associated with them. In this work, an approach to building an IoT mental health monitoring and detection system has been proposed. The depression problem is used as a case study for the mental conditions. The proposed approach involves data collection, data pre-processing, feature extraction, feature selection, and model building. Machine learning (ML) and data mining techniques, along with different data types for training and testing the models, have been utilized to accomplish the tasks of the proposed approach. Four ML algorithms have been investigated to detect and predict the diagnosis of the mental state. These algorithms are random forest, decision tree, support vector machine (SVM) and k-nearest neighbors (KNN). Our ML detection model has achieved a high detection accuracy of 95% using the random forest algorithm. Comparisons in different aspects with other works are presented. Our work has the advantages of using ML, adopting different data types, and therefore achieving better classification. [ABSTRACT FROM AUTHOR]

Object detection plays an important role in various fields. Developing detection models for 2D objects that experience rotation and texture variations is a challenge. In this research, the initial stage of the proposed model integrates the gray-level co-occurrence matrix (GLCM) and local binary patterns (LBP) texture feature extraction to obtain feature vectors. The next stage is classifying features using k-nearest neighbors (KNN) and random forest (RF), as well as voting ensemble (VE). System testing used a dataset of 4,437 2D images, the results for KNN accuracy were 92.7% and F1-score 92.5%, while RF performance was lower. Although GLCM features improve performance on both algorithms, KNN is more consistent. The VE approach provides the best performance with an accuracy of 93.9% and an F1-score of 93.8%, this shows the effectiveness of the ensemble technique in increasing object detection accuracy. This study contributes to the field of object detection with a new approach combining GLCM and LBP as feature vectors as well as VE for classification. [ABSTRACT FROM AUTHOR]

Machine learning (ML) techniques empower computers to learn from data and make predictions or decisions in various domains, while preprocessing methods assist in cleaning and transforming data before it can be effectively utilized by ML. Feature selection in ML is a critical process that significantly influences the performance and effectiveness of models. By carefully choosing the most relevant and informative attributes from the dataset, feature selection enhances model accuracy, reduces overfitting, and minimizes computational complexity. In this study, we leverage the UAH-DriveSet dataset to classify driver behavior, employing Filter, embedded, and wrapper methods encompassing 10 distinct feature selection techniques. Through the utilization of diverse ML algorithms, we effectively categorize driver behavior into normal, drowsy, and aggressive classes. The second objective is to employ feature selection techniques to pinpoint the most influential features impacting driver behavior. As a results, random forest emerges as the top-performing classifier, achieving an impressive accuracy of 96.4% and an F1-score of 96.36% using backward feature selection in 7.43 s, while K-nearest neighbour (K-NN) attains an accuracy of 96.29% with forward feature selection in 0.05 s. Following our comprehensive results, we deduce that the primary influential features for studying driver behavior include speed (km/h), course, yaw, impact time, road width, distance to the ahead vehicle, vehicle position, and number of detected vehicles. [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]

The seasonal temperature trends and ice phenology in the Great Slave Lake (GSL) are significantly influenced by inflow from the Slave River. The river undergoes a sequence of mechanical break-ups all the way to the GSL, initiating the GSL break-up process. Additionally, upstream water management practices impact the discharge of the Slave River and, consequently, the ice break-up of the GSL. Therefore, monitoring the break-up process at the Slave River Delta (SRD), where the river meets the lake, is crucial for understanding the cascading effects of upstream activities on GSL ice break-up. This research aimed to use Random Forest (RF) models to monitor the ice break-up processes at the SRD using a combination of satellite images with relatively high spatial resolution, including Landsat-5, Landsat-8, Sentinel-2a, and Sentinel-2b. The RF models were trained using selected training pixels to classify ice, open water, and cloud. The onset of break-up was determined by data-driven thresholds on the ice fraction in images with less than 20% cloud coverage. Analysis of break-up timing from 1984 to 2023 revealed a significant earlier trend using the Mann–Kendall test with a p-value of 0.05. Furthermore, break-up data in recent years show a high degree of variability in the break-up rate using images in recent years with better temporal resolution. [ABSTRACT FROM AUTHOR]

PURPOSE: Rare cancers constitute over 20% of human neoplasms, often affecting patients with unmet medical needs. The development of effective classification and prognostication systems is crucial to improve the decision-making process and drive innovative treatment strategies. We have created and implemented MOSAIC, an artificial intelligence (AI)–based framework designed for multimodal analysis, classification, and personalized prognostic assessment in rare cancers. Clinical validation was performed on myelodysplastic syndrome (MDS), a rare hematologic cancer with clinical and genomic heterogeneities. METHODS: We analyzed 4,427 patients with MDS divided into training and validation cohorts. Deep learning methods were applied to integrate and impute clinical/genomic features. Clustering was performed by combining Uniform Manifold Approximation and Projection for Dimension Reduction + Hierarchical Density-Based Spatial Clustering of Applications with Noise (UMAP + HDBSCAN) methods, compared with the conventional Hierarchical Dirichlet Process (HDP). Linear and AI-based nonlinear approaches were compared for survival prediction. Explainable AI (Shapley Additive Explanations approach [SHAP]) and federated learning were used to improve the interpretation and the performance of the clinical models, integrating them into distributed infrastructure. RESULTS: UMAP + HDBSCAN clustering obtained a more granular patient stratification, achieving a higher average silhouette coefficient (0.16) with respect to HDP (0.01) and higher balanced accuracy in cluster classification by Random Forest (92.7% ± 1.3% and 85.8% ± 0.8%). AI methods for survival prediction outperform conventional statistical techniques and the reference prognostic tool for MDS. Nonlinear Gradient Boosting Survival stands in the internal (Concordance-Index [C-Index], 0.77; SD, 0.01) and external validation (C-Index, 0.74; SD, 0.02). SHAP analysis revealed that similar features drove patients' subgroups and outcomes in both training and validation cohorts. Federated implementation improved the accuracy of developed models. CONCLUSION: MOSAIC provides an explainable and robust framework to optimize classification and prognostic assessment of rare cancers. AI-based approaches demonstrated superior accuracy in capturing genomic similarities and providing individual prognostic information compared with conventional statistical methods. Its federated implementation ensures broad clinical application, guaranteeing high performance and data protection. MOSAIC: AI-based Framework for Multi-Modal Analysis, Classification and Prognostic Assessment in Rare Cancers. [ABSTRACT FROM AUTHOR]

Material science is a fast-growing research field where artificial intelligence is applied in a variety of applications to provide accurate solutions to the problem. Due to its generalizability, noise tolerance, and fast computation, machine learning algorithms have emerged in recent years as a potent tool for creating correlations between data, and are finding use in materials science. In this research work electric vehicle chassis material selection is done based on the mechanical properties of the material and this is done using machine learning techniques. Machine learning techniques, like logistic regression, K-Nearest Neighbor, Decision Tree, Random Forest, Naïve Base, XGBoost and AdaBoost techniques are used for the same. The stacking technique is also used which combines a variety of ML algorithms for enhanced performance and is observed that the stacking technique gives better accuracy compared to other classifiers. Binary class, as well as multiclass problems, are taken that will give solutions to the electric vehicle chassis selection material. Accuracy scores of different algorithms are compared and found that stacking works reasonably better compared to others. [ABSTRACT FROM AUTHOR]