Search

Context: Artificial Intelligence (AI) has rapidly developed over the past several decades. Several related AI approaches, such as Machine Learning (ML), have been applied to research on landscape patterns and ecological processes. Objectives: Our goal was to review the methods of AI, particularly ML, used in studies related to landscape ecology and the main topics addressed. We aimed to assess the trend in the number of ML papers and the methods used therein, and provide a synopsis and prospectus of current use and future applications of ML in landscape ecology. Methods: We conducted a systematic literature search and selected 125 papers for review. These were examined and scored according to multiple criteria regarding methods and topic. We applied quantitative statistical methods, including cluster analysis based on titles, abstracts, and keywords and a non-metric multidimensional scaling based on attributes assigned during the review. We used Random Forests machine learning to describe the differences between identified clusters in terms of the topics and methods they included. Results: The most frequent method found was Random Forests, but it is noteworthy to mention the increasing popularity of tools related to Deep Learning. The topics cover both ecologically oriented issues and the landscape-human interface. There has been a rapid increase in ML and AI methods in landscape ecology research, with Deep Learning and complex multi-step pipeline AI methods emerging in the last several years. Conclusions: The rapid increase in the number of ML papers in landscape ecology research, and the range of methods employed in them, suggest explosive growth in application of these methods in landscape ecology. The increase of Deep Learning approaches in the most recent years suggest a major change in analytical paradigms and methodologies that we feel may transform the field and enable analyses of more complex pattern process relationships across vaster data sets than has been possible previously. [ABSTRACT FROM AUTHOR]

In most biomedical research paper corpus, document classification is a crucial task. Even due to the global epidemic, it is a crucial task for researchers across a variety of fields to figure out the relevant scientific research papers accurately and quickly from a flood of biomedical research papers. It can also assist learners or researchers in assigning a research paper to an appropriate category and also help to find the relevant research paper within a very short time. A biomedical document classifier needs to be designed differently to go beyond a "general" text classifier because it's not dependent only on the text itself (i.e. on titles and abstracts) but can also utilize other information like entities extracted using some medical taxonomies or bibliometric data. The main objective of this research was to find out the type of information or features and representation method creates influence the biomedical document classification task. For this reason, we run several experiments on conventional text classification methods with different kinds of features extracted from the titles, abstracts, and bibliometric data. These procedures include data cleaning, feature engineering, and multi-class classification. Eleven different variants of input data tables were created and analyzed using ten machine learning algorithms. We also evaluate the data efficiency and interpretability of these models as essential features of any biomedical research paper classification system for handling specifically the COVID-19 related health crisis. Our major findings are that TF-IDF representations outperform the entity extraction methods and the abstract itself provides sufficient information for correct classification. Out of the used machine learning algorithms, the best performance over various forms of document representation was achieved by Random Forest and Neural Network (BERT). Our results lead to a concrete guideline for practitioners on biomedical document classification. [ABSTRACT FROM AUTHOR]

In this paper, we modify the proof methods of some previously weakly consistent variants of random forest into strongly consistent proof methods, and improve the data utilization of these variants in order to obtain better theoretical properties and experimental performance. In addition, we propose the Data-driven Multinomial Random Forest (DMRF) algorithm, which has the same complexity with BreimanRF (proposed by Breiman) while satisfying strong consistency with probability 1. It has better performance in classification and regression tasks than previous RF variants that only satisfy weak consistency, and in most cases even surpasses BreimanRF in classification tasks. To the best of our knowledge, DMRF is currently a low-complexity and high-performing variation of random forest that achieves strong consistency with probability 1. [ABSTRACT FROM AUTHOR]

Gastric Cancer is the most common malignancy of the digestive tract, which is the third leading cause of cancer-related mortality worldwide. The early prognosis methods, especially Machine Learning (ML)-based approaches are one of the main strategies against GC, which have become a necessity to identify and prognosticate the factors that affect the GC. They enable the specialists to accelerate the subsequent clinical management of patients, who suffer from the GC. This paper aims at creating an Ensemble Method inspired from ML to predict the most significant factors of the GC occurrence. The main objective of this research is to predict the probabilities of the GC occurrence and its associated deaths. To achieve this goal, the created EM benefits from some ML-based methods, including Least Absolute Shrinkage and Selection Operator (LASSO)/Ridge Regression, Elastic Net, Logistic Regression (LR), Random Forest (RF), Gradient Boosting Decision Trees (GBDTs), and Deep Neural Network (DNN). The purpose of the provided EM is to lessen the prediction errors for the large number of the patients' features. The main novelties of this research include: (i) A sequential EM created by a Stacking method to predict the probability of the GC and associated deaths; (ii) Benefiting from the significance level to make an accurate prediction; (iii) Employing two Chi-square tests to select the influent features; (iv) Tuning the parameters of the applied ML models to avoid over-fitting and intensifying the errors; (v) Applying different kinds of the regression methods to treat hyper-dimension cases; (vi) A new model for weighting the applied ML models. The outcomes of the implementation of the created EM in seven pioneer hospitals in the field of GC show that the designed EM generates more precise predictions with an accuracy of 97.9% and 76.3% to predict the GC and its associated deaths, respectively. Moreover, the obtained results from the Area Under Curve (AUC) validates and confirms the capability of the created EM to predict the probability of the GC and its related deaths with an accuracy of 98% and 90% to predict the GC and its associated deaths, respectively. [ABSTRACT FROM AUTHOR]

This paper promotes better life quality and lifestyle for patients. We attain this goal by creating a mobile application that analyses patient's medical records, such as diabetes, hypertension, and chronic kidney diseases. Then, we implement the system to diagnose patients with chronic conditions using machine learning techniques. Machine learning classifiers are used in this paper to decide whether a person has any chronic diseases. The investigated diseases are hypertension, diabetes, and chronic kidney disease. Four datasets were used to build the classifying models. Orange3 from Anaconda-Navigator, a data mining tool, was used to test machine learning algorithms. The study findings revealed the superiority of the tree algorithm with 100% accuracy for hypertension; it was the highest outcome for both males and females using Orange3. The highest precision, which is 100%, is observed by SVM, k-NN, decision trees, logistic regression, and CART for hypertension males' data collection. In comparison, the highest precision is 100% in SVM, MLP, decision tree, random forest, logistic regression, and CART for the female dataset. We conclude that the two datasets for the same diseases share mostly the same algorithm accuracy. For kidneys, the Random Forest algorithm produced 100% accuracy, which is the highest value among other algorithms. For diabetes, neural networks have attested the best accuracy. It was 76.3%, yet the accuracy increased slightly as the kNN algorithm showed 83% accuracy. [ABSTRACT FROM AUTHOR]

Automated disease diagnosis and prediction, powered by AI, play a crucial role in enabling medical professionals to deliver effective care to patients. While such predictive tools have been extensively explored in resource-rich languages like English, this manuscript focuses on predicting disease categories automatically from symptoms documented in the Afaan Oromo language, employing various classification algorithms. This study encompasses machine learning techniques such as support vector machines, random forests, logistic regression, and Naïve Bayes, as well as deep learning approaches including LSTM, GRU, and Bi-LSTM. Due to the unavailability of a standard corpus, we prepared three data sets with different numbers of patient symptoms arranged into 10 categories. The two feature representations, TF-IDF and word embedding, were employed. The performance of the proposed methodology has been evaluated using accuracy, recall, precision, and F1 score. The experimental results show that, among machine learning models, the SVM model using TF-IDF had the highest accuracy and F1 score of 94.7%, while the LSTM model using word2vec embedding showed an accuracy rate of 95.7% and F1 score of 96.0% from deep learning models. To enhance the optimal performance of each model, several hyper-parameter tuning settings were used. This study shows that the LSTM model verifies to be the best of all the other models over the entire dataset. [ABSTRACT FROM AUTHOR]

Spectroscopy is a methodology for gaining knowledge of particles, especially biomolecules, by quantifying the interactions between matter and light. By examining the level of light absorbed, reflected or released by a specimen, its constituents, properties, and volume can be determined. Spectra obtained through spectroscopy procedures are quick, harmless and contactless; hence nowadays preferred in chemometrics. Due to the high dimensional nature of the spectra, it is challenging to build a robust classifier with good performance metrics. Many linear and nonlinear dimensionality reduction-based classification models have been previously implemented to overcome this issue. However, they lack in capturing the subtle details of the spectra into the low dimension space or cannot efficiently handle the nonlinearity present in the spectral data. We propose a graph-based neural network embedding approach to extract appropriate features into latent space and circumvent the spectrums' nonlinearity problem. Our approach performs dimensionality reduction into two phases: constructing a nearest neighbor graph and producing almost linear embedding using a fully connected neural network. Further, the low dimensional embedding is subjected to classification using the Random Forest algorithm. In this paper, we have implemented and compared our technique with four nonlinear dimensionality techniques widely used for spectral data analysis. In this study, we have considered five different spectral datasets belonging to specific applications. The various classification performance metrics of all the techniques are evaluated. The proposed approach is able to perform competitively well on six different low-dimensional spaces for each dataset with an accuracy score above 95% and Matthew's correlation coefficient value close to 1. The trustworthiness score of almost 1 show that the presented dimensionality reduction approach preserves the closest neighbor structure of high dimensional spectral inputs into latent space. [ABSTRACT FROM AUTHOR]

Classification is a widely used supervised learning technique that enables models to discover the relationship between a set of features and a specified label using available data. Its applications span various fields such as engineering, telecommunication, astronomy, and medicine. In this paper, we propose a novel rule-based classifier called RUCIB (RUle-based Classifier Inspired by BRADO), which draws inspiration from the socio-inspired swarm intelligence algorithm known as BRADO. RUCIB introduces two key aspects: the ability to accommodate multiple values for features within a rule and the capability to explore all data features simultaneously. To evaluate the performance of RUCIB, we conducted experiments using ten databases sourced from the UCI machine learning database repository. In terms of classification accuracy, we compared RUCIB to ten well-known classifiers. Our results demonstrate that, on average, RUCIB outperforms Naive Bayes, SVM, PART, Hoeffding Tree, C4.5, ID3, Random Forest, CORER, CN2, and RACER by 9.32%, 8.97%, 7.58%, 7.4%, 7.34%, 7.34%, 7.22%, 5.06%, 5.01%, and 1.92%, respectively. [ABSTRACT FROM AUTHOR]

Network Intrusion Detection (NID) is an important domain of research and as the network traffic is growing enormously, new challenges are emerging forth in terms of quality of service and security thus a reliable and robust network intrusion detection system (NIDS) has become an inevitable requirement. Researchers have developed and implemented many rule-based and statistical-based techniques, as well as machine learning (ML) approaches such as K-Nearest Neighbour (K-NN), Decision Tree (DT), Random Forest (RF), Multi-Layer Perceptron (MLP) and Naive-Bayes for this pursuit. But, a method is still in need that entails certain required characteristics like low computational cost, high classification accuracy, able to deal efficiently with large datasets having redundant data and high dimensionality. In this paper, a novel method is proposed that includes all these characteristics. Further, the proposed method is based on the rule induction technique using separate and-conquer algorithm known as CN2 for a network intrusion detection system. The performance of the proposed CN2 rule induction algorithm is also compared experimentally with K-NN, DT, RF, MLP and Naive-Bayes classifiers for the Kddcup99 dataset and it has been observed that the performance of the CN2 rule induction algorithm is better in comparison to other classifiers considered in this experimentation. [ABSTRACT FROM AUTHOR]

Predictive maintenance refers to predicting malfunctions using data from monitoring equipment and process performance measurements. Machine learning algorithms and techniques are often used to analyze equipment monitoring data. Machine learning is the process in which a computer can work more precisely by collecting and analyzing data. It is often the case that machine learning algorithms use supervised learning, in which labelled data is used to feed the algorithm. However, there are many supervised machine learning algorithms available. Therefore, choosing the best-supervised machine learning algorithm to resolve predictive maintenance issues is not trivial. This paper aims to increase the performance of predictive maintenance and achieve its goals by selecting the most suitable supervised machine learning algorithm. Based on the most commonly used criteria in research articles, we selected three supervised machine learning algorithms from a comparative study: Random forest, Decision tree and KNN. We then tested selected algorithms on data from real-world and simulation scenarios. Finally, we conducted the experiment based on vibration analysis and reliability evaluation. We noticed that Random forests and Decision trees obtained slightly the same performance. KNN is a better classification algorithm for extensive volumes of data; on the contrary, Random forest performs better in the case of small datasets. [ABSTRACT FROM AUTHOR]

In recent years, the gastronomy industry has increased the demand for rigorous and reliable tools to evaluate culinary creativity; but conceptually, creativity is difficult to define and even more difficult to measure. In this paper, we propose an AI-based method for assessing culinary product creativity by using the renowned high cuisine restaurant elBulli as a case study to understand the proliferation and scale of an entity's creativity and innovation. To achieve so, we trained a Random Forest Classifier to assess the level of creativity within the restaurant's recipes. The application of this model to elBulli's recipes allowed us to answer the following questions: how can creativity in a culinary product be characterized? Is there a single trait that is the key to culinary creativity? Is the creative culinary product a truly original outcome? Our key findings are (1) although ingredients and preparation techniques prove to be suitable attributes to characterize creativity in a recipe, none of them nor an elite subset clearly identifies creative cuisine, (2) new products are not radically novel with respect to previous creations, (3) creativity is more related to new uses and combinations of existing ingredients and techniques rather than to new ingredients or techniques. We believe that our method can find practical applications in supporting and guiding the creation of culinary products, identifying their strengths and weaknesses, and helping restaurants maintain a sustainable competitive advantage. [ABSTRACT FROM AUTHOR]

While Vehicular Ad-hoc Network (VANET) is developed to enable effective vehicle communication and traffic information exchange, VANET is also vulnerable to different security attacks, such as DOS attacks. The usage of an intrusion detection system (IDS) is one possible solution for preventing attacks in VANET. However, dealing with a large amount of vehicular data that keep growing in the urban environment is still an critical challenge for IDSs. This paper, therefore, proposes a new machine learning model to improve the performance of IDSs by using Random Forest and a posterior detection based on coresets to improve the detection accuracy and increase detection efficiency. The experimental results show that the proposed machine learning model can significantly enhance the detection accuracy compared to classical application of machine learning models. [ABSTRACT FROM AUTHOR]

In today's world, the growth of computer networks is exponential as networking is an essential part of the latest technologies like Internet of Things (IoT), cloud computing, edge computing, etc., with the adoption of new technologies; security has become an important issue for such techniques. These networks need to be saved from a wide range of available attacks. In the literature, many intrusion detection systems (IDS) are used to detect such attacks. IDS can be signature based or anomaly based. The signature-based method can only detect a well-known attack while anomaly-based methods can detect new attacks but suffers from low performance. IDS with a potential anomaly detection mechanism to improve the performance is highly desirable. For the reasons mentioned above, this paper proposed an anomaly-based IDS with novel hybrid ensemble classification method based on grouping of the network traffic. The groups are created based on the services or protocol used by the network traffic. After grouping of network traffic, wrapper-based sequential feature selection (SFS) with random forest (RF) classifier is used to select optimal features and perform classification in each group. Furthermore, to validate the performance of the proposed model for service-based and protocol-based grouping approach, UNSW-NB15 and NSL-KDD datasets are used, respectively. The result shows that the proposed approach outperforms the existing feature selection approaches with high accuracy, precision, and F-score for both the datasets. [ABSTRACT FROM AUTHOR]

In tourism-dependent cities, investigating the spatiotemporal distribution and dynamics of tourist flows is crucial for better urban planning in both steady and perturbed states. In recent years, researchers have started relying more on photo-based, geotagged social data, which offer insights about tourists, popular hotspots, and mobility patterns. However, distinguishing between tourists and locals from this data is problematic since residence information is often not provided. While previous studies rely on heuristic (e.g., period of stay) and probabilistic (Shannon entropy) approaches, this paper proposes a method for classifying tourists and residents based on machine learning (ML) algorithms and considering parameters that could explain the variability between the two (e.g., weather, mobility, and photo content). This approach was applied to Flickr users' geotagged photos taken in Tokyo's 23 special wards from July 2008 to December 2019. The results show that stacked ensemble (SE) models are superior to models based on five supervised-learning algorithms, including gradient boosting machine (GBM), generalized linear model (GLM), distributed random forest (DRF), deep learning (DL), and extremely randomized trees (XRT). Temporal entropy (TEN), mobility on workdays, and frequent visits to amusement venues and crowded places influenced how users were classified. While temporal distribution showed similar monthly/hourly patterns, spatial distribution varied. The proposed approach might pave the way for scholars to carry out future tourism research on different topics and subsequently support policymakers in the decision-making process, specifically in urban settings. [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]

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]

Machine learning(ML) based techniques for Land Use Land Cover(LULC) classification is crucial for extracting valuable insights from satellite imagery. The impact of severe class imbalance problems on LULC datasets, added to the limited temporal coverage, incomplete spectral information, spatial resolution constraints, and limitations due to sensor characteristics of a single satellite, hinder the efficient capturing of complex image features. The object-based classification using Gray-level co-occurrence matrix(GLCM) and Simple Non-Iterative Clustering(SNIC) captures the textural and spectral information, respectively, to enhance the accuracy in heterogeneous landscapes and overcome the limitations of pixel-based classification, such as the sensitivity towards noise and spectral confusion in mixed pixels at the cost of increased additional computational steps. In this context, the proposed study leverages high-quality fused images with diverse temporal, spectral, and spatial information obtained by fusing Landsat-8 and Sentinel-2 satellite imageries using Spatial-and-Temporal-Adaptive-Reflectance-Fusion-Model(STARFM). Further, to solve the class imbalance problem, a Granular Computing(GrC) based Segmentation and Textural Analysis(GrCSTA) framework is proposed for reducing the number of image primitives and computations required for subsequent image analysis processes in the object-based classification. The GrCSTA framework focuses on extracting the Spatial Granules(Gs) from the fused imagery using Spatial neighborhood Granulation(SNGr), textural indices of the Gs using GLCM, and reduced textural indices using Principal Component Analysis(PCA). Gs and its reduced textural indices are input features to train the Random Forest(RF) classifier. Experimental results demonstrate that the proposed GrCSTA framework achieves comparably higher accuracy than the state-of-the-art models. [ABSTRACT FROM AUTHOR]

The Q-matrix, which specifies the relationship between items and attributes, is a crucial component of cognitive diagnostic models (CDMs). A precisely specified Q-matrix allows for valid cognitive diagnostic assessments. In practice, a Q-matrix is usually developed by domain experts, and noted as being subjective and potentially containing misspecifications which can decrease the classification accuracy of examinees. To overcome this, some promising validation methods have been proposed, such as the general discrimination index (GDI) method and the Hull method. In this article, we propose four new methods for Q-matrix validation based on random forest and feed-forward neural network techniques. Proportion of variance accounted for (PVAF) and coefficient of determination (i.e., the McFadden pseudo-R2) are used as input features for developing the machine learning models. Two simulation studies are carried out to examine the feasibility of the proposed methods. Finally, a sub-dataset of the PISA 2000 reading assessment is analyzed as illustration. [ABSTRACT FROM AUTHOR]

The surfaces produced by the machining process are sensitive to the type of machining process and the conditions under which it is performed. Thus, surface texture identification is crucial in quality assurance, as it acts as a feedback to the machining process. Machined surface identification using image processing and machine learning (ML)-based techniques is gaining much importance due to industrial automation. This investigation addresses the development of ML models using gray-level co-occurrence matrices (GLCM) features to classify the machined (turned, ground and shaped) surfaces. The influence of distance-based dimensionality reduction techniques (DRT) viz., Fisher's criterion, Separation index and Bhattacharya distance on the performance of the ML-based image classifiers is explored. The GLCM features extracted from the machined surface images are used as inputs to ML classifiers. A threshold criterion function (TCF) is used to select the sensitive features in the DRT. Among all the classifiers, the (Random Forest) RAF model could produce a better classification accuracy as high as 95.3%. Also, analysis results show that the proposed dimensionality reduction methodology with TCF effectively identifies the most sensitive features. A maximum dimensionality reduction of 62% is achieved. The proposed methodology showed a 7.2% improvement in classification accuracy over the techniques reported in the previous study. Thus, developed ML models successfully classify the machined surface images with a minimum time and computational burden on the computer. [ABSTRACT FROM AUTHOR]

Ensemble methods are supervised learning algorithms that provide highly accurate solutions by training many models. Random forest is probably the most widely used in regression and classification problems. It builds decision trees on different samples and takes their majority vote for classification and average in case of regression. However, such an algorithm suffers from a lack of explainability and thus does not allow users to understand how particular decisions are made. To improve on that, we propose a new way of interpreting an ensemble tree structure. Starting from a random forest model, our approach is able to explain graphically the relationship structure between the response variable and predictors. The proposed method appears to be useful in all real-world cases where model interpretation for predictive purposes is crucial. The proposal is evaluated by means of real data sets. [ABSTRACT FROM AUTHOR]

In the evolution of digital technology, e-commerce sectors are gradually changing to realize customers' demands and supply required things with low cost and due time. Recently, various machine learning techniques have been used to investigate different activities of customers and estimate different characteristics and requirements of customers. The goal of this work is to propose a machine-learning model that employs multiple data analytics and machine learning techniques to manipulate customer records and predict their buying intention more precisely. In this study, we collected an online shoppers' purchasing intention dataset from a public data repository. Different feature transformation methods were employed in the primary dataset and generated its transformed datasets. Besides, we balanced the transformed datasets and detected outliers from them. Then, we applied different feature selection methods into primary and transformed-balanced datasets and again generated several feature subsets. Finally, various state-of-the-art classifiers were employed in primary, transformed, and all of their generated subsets. Then, different outcomes of the proposed model were analyzed and Random Forest was found as the stable classifier that produces more feasible results for any online shoppers' buying instances. In this work, this classifier provided the best accuracy of 92.39% and f-score of 0.924 for the Z-Score and Gain Ratio transformed subset. In addition, it gave the highest AUROC of 0.975 for the Square Root and Information Gain subset. We also found Z-Score transformation and Information Gain more reliable methods to convert online shoppers' customer intention dataset and get more feasible results from different classifiers. [ABSTRACT FROM AUTHOR]

The dimensions of microarray datasets are very large, containing noise and redundancy. The problem with microarray datasets is the presence of more features compared to the number of samples, which adversely affects algorithm performance. In other words, the number of columns exceeds the number of rows. Therefore, to extract precise information from microarray datasets, a robust technique is required. Microarray datasets play a critical role in detecting various diseases, including cancer and tumors. This is where feature selection techniques come into play. In recent times, feature selection (FS) has gained significant importance as a data preparation method, particularly for high-dimensional data. It is preferable to address classification problems with fewer features while maintaining high accuracy, as not all features are necessary to achieve this goal. The primary objective of feature selection is to identify the optimal subset of features. In this context, we will employ the Differential Evolution (DE) algorithm. DE is a population-based stochastic search approach that has found widespread use in various scientific and technical domains to solve optimization problems in continuous spaces. In our approach, we will combine DE with three different classification algorithms: Random Forest (RF), Decision Tree (DT), and Logistic Regression (LR). Our analysis will include a comparison of the accuracy achieved by each algorithmic model on each dataset, as well as the fitness error for each model. The results indicate that when feature selection was used the results were better compared to the results where the feature selection was not used. [ABSTRACT FROM AUTHOR]

Few-shot imbalanced classification tasks are commonly faced in the real-world applications due to the unbalanced data distribution and few samples of rare classes. As known, the traditional machine learning algorithms perform poorly on the imbalanced classification, usually ignoring the few samples in the minority class to achieve a good overall accuracy. To solve this few-shot problem, a novel data augmentation method was proposed in this study, called H-SMOTE, to rebalance the original imbalanced data in a stable and reasonable way. Extensive experiments were carried out on 12 open datasets covering a wide range of imbalance rate from 3.8 to 16.4. Moreover, two typical classifiers SVM and Random Forest were selected to testify the performance and generalization of proposed H-SMOTE. Further, the typical data oversampling algorithm SMOTE was adopted as the baseline of comparison. The average experimental results show that the proposed H-SMOTE method outperforms the typical SMOTE in terms of accuracy (2.58%), recall (0.67%), F-measure (2.33%), G-mean (2.58%), and AUC (2.5%). Besides, the distribution of augmented dataset by H-SMOTE is more uniform and stable. Thus, this work provides a useful data augmentation method to solve the few-shot imbalanced classification, which can also be generalized to many areas in multimedia systems. [ABSTRACT FROM AUTHOR]

Email is a useful communication medium for better reach. There are two types of emails, those are ham or legitimate email and spam email. Spam is a kind of bulk or unsolicited email that contains an advertisement, phishing website link, malware, Trojan, etc. This research aims to classify spam emails using machine learning classifiers and evaluate the performance of classifiers. In the pre-processing step, the dataset has been analyzed in terms of attributes and instances. In the next step, thirteen machine learning classifiers are implemented for performing classification. Those classifiers are Adaptive Booster, Artificial Neural Network, Bootstrap Aggregating, Decision Table, Decision Tree, J48, K-Nearest Neighbor, Linear Regression, Logistic Regression, Naïve Bayes, Random Forest, Sequential Minimal Optimization and, Support Vector Machine. In terms of accuracy, the Random Forest classifier performs best and the performance of the Naïve Bayes classifier is substandard compared to the rest of the classifiers. Random Forest classifier had the accuracy of 99.91% and 99.93% for the Spam Corpus and Spambase datasets respectively. The naïve Bayes classifier had the accuracy of 87.63% and 79.53% for the Spam Corpus and Spambase datasets respectively. [ABSTRACT FROM AUTHOR]

This study investigates the feasibility of using texture radiomics features extracted from mammography images to distinguish between benign and malignant breast lesions and to classify benign lesions into different categories and determine the best machine learning (ML) model to perform the tasks. Six hundred and twenty-two breast lesions from 200 retrospective patient data were segmented and analysed. Three hundred fifty radiomics features were extracted using the Standardized Environment for Radiomics Analysis (SERA) library, one of the radiomics implementations endorsed by the Image Biomarker Standardisation Initiative (IBSI). The radiomics features and selected patient characteristics were used to train selected machine learning models to classify the breast lesions. A fivefold cross-validation was used to evaluate the performance of the ML models and the top 10 most important features were identified. The random forest (RF) ensemble gave the highest accuracy (89.3%) and positive predictive value (66%) and likelihood ratio of 13.5 in categorising benign and malignant lesions. For the classification of benign lesions, the RF model again gave the highest likelihood ratio of 3.4 compared to the other models. Morphological and textural radiomics features were identified as the top 10 most important features from the random forest models. Patient age was also identified as one of the significant features in the RF model. We concluded that machine learning models trained against texture-based radiomics features and patient features give reasonable performance in differentiating benign versus malignant breast lesions. Our study also demonstrated that the radiomics-based machine learning models were able to emulate the visual assessment of mammography lesions, typically used by radiologists, leading to a better understanding of how the machine learning model arrive at their decision. [ABSTRACT FROM AUTHOR]

In precision manufacturing, tool condition monitoring is critical for improving surface finish, increasing efficiency, and lowering manufacturing costs. The present work discusses a complete workflow to accurately predict the tool condition based on vibration data obtained during the turning operation performed on a lathe. An image processing methodology is applied to compute the tool wear area. A specialized misclassification cost matrix is used to train the random forests algorithm to improve the classification of tool conditions. This model can correctly classify tool condition from vibration signals of 0.5 s with an accuracy of 97%. Furthermore, this investigation can be modified to suit the real-world classification of the tool condition based on tool wear requirements. [ABSTRACT FROM AUTHOR]

Automated classification of corn is important for corn sorting in intelligent agriculture. Corn classification process is a necessary and accurate process in many places in the world today. Correct corn classification is important to identify product quality and to distinguish good from bad. In this study, a hybrid model was proposed to classify the 3 corn species belonging to the Zea mays family. In the hybrid model, 12 different morphological features of corn were obtained. These morphological features were used for the classification process in the hybrid model created using machine learning (ML) algorithms. When morphological features were given as input to ML algorithms for normal classification, the test score was 96.66% for Decision Tree (DT), 97.32% for Random Forest (RF) and 96.66% for Naive Bayes (NB). With the proposed hybrid model, this rate has reached 100% test score in all three algorithms. Test processes were measured by statistical models. While Accuracy was 97.67% as a result of normal classification, this rate was 100% in hybrid model. The experimental results demonstrated the effectiveness of the proposed corn classification system. [ABSTRACT FROM AUTHOR]

Feature selection is a major process in data mining and classification process. It improves the classifier performance and reduces the computation time by removing the redundant and irrelevant information from the dataset. Initially, all variables from 10 to 100 were processed for classification process. It consumes more time and the efficiency of classifier is minimum. The best features can be selected from the following three methods: wrapper selection, filter and embedded method. In wrapper method, the feature selection method is based on two methods namely sequential searching method and heuristic approach. In sequential searching method, the subset of features is determined by processing from empty set. In heuristic approach, the feature is determined by subset of features by achieving the objective function. Some of the heuristic approaches are optimization algorithms like genetic algorithm, particle swarm and so on. Only few works were suggested the random forest classifier due to the hierarchical arrangements of data. Among the three filter techniques, the wrapper-based selection technique able to produce high accuracy. It is due to the attribute selection method. This problem is overcome with the proposed global sensitivity analysis approach. In this, an optimized filter technique is proposed for the feature selection for classification process. Here, the selection of attributes for the classification is performed in two stages. In the first stage, the filter selection is approach is based on the global sensitivity analysis. In the second stage, the dominant attribute from the first stage is determined though the wrapper approach using particle swarm optimization. Due to this multistage feature selection, the proposed approach can be applied to any type of machine learningapplication. The proposed particle swarm optimization based global sensitivity analysis (PSO-GSA) is performed on the Cleveland dataset using MATLAB. Its performance is evaluated in terms of accuracy, sensitivity and specificity and it is compared with the wrapper selection method. The proposed PSO-GSA able to outperform the wrapper selection by high accuracy of 90% and sensitivity of 94.74%. The computational time for the proposed GSA based classification of heart disease using random forest classifier is 0.7689 s, which is less when it iscompared with the computational time of classifiers with bagging and boosting technique. [ABSTRACT FROM AUTHOR]

This study aims to assess dengue fever risk using Machine Learning techniques, such as logistic regressions, linear discriminant analyses, Naive Bayes, decision tree, and random forest classifiers. This kind of approach to epidemiological problems has been developed to detect risks for diseases occurrence and allows to create public policies based on mathematical models to prevent public health problems. In this study, the models were trained with data from the municipality of São Luís do Maranhão, state of Maranhão, Brazil. The majority of related works analyze states, countries, or continental levels, with greater availability of data. To apply the approach to such a small region, some oversampling techniques were used. The number of cases per neighborhood from 2014 to and 2020 and climatic, territorial, and environmental data was used as input variables to estimate the probability of dengue occurrence in the municipality. Due to the unbalanced database, we used the SMOTE, ADASYN, and DBSMOTE oversampling techniques. The DBSMOTE-trained Random Forest classifier achieved the best results with a 75.1% AUC, 75.43% sensitivity and a 60.53% specificity. [ABSTRACT FROM AUTHOR]

The identification of unusual data in computer networks is a critical task for intrusion detection systems. In this study, a novel approach has been proposed for improving intrusion detection system performance by finding multivariate outliers and optimal feature selection. The NSL-KDD dataset consisting of 41 features has been utilized to create and test the system. Firstly, the ReliefF Feature Selection approach has been employed to identify the best features that maintain the classification performance at a high level and 20 features have been determined. Then, to find outliers in the dataset, the Mahalanobis Distance and Chi-Square approaches have been applied. After that, various machine learning methods have been applied to the dataset, and the results have been compared. According to the results, higher classification success has been reached in nearly half the time as a consequence of 20 features obtained from the feature selection and outlier identification processes, compared to the classification done using 41 features. With 99.2187% accuracy, the Random Forest Algorithm has achieved the best classification success. Finally, it has been observed that the suggested approach provides statistically significant results with a quick detection time and higher classification accuracy. [ABSTRACT FROM AUTHOR]

Ransomware is a subcategory of malware whose specific goal is to hold the victim's data by using encryption techniques until a ransom is paid. With mainstream usage of the Windows platform, Windows-based ransomware has become a great threat. With the rise of new malware categories and the huge volume of big data emerging, it has now become difficult to identify ransomware from benign applications. At the same time, ransomware detection and classification play a crucial role in computer security. Therefore, it is essential to analyze the behavior of ransomware samples to know their malicious nature that differs from clean applications. Due to the shortcomings of static analysis, we propose BigRC-EML for ransomware detection and classification based on several static and dynamic features. We use ensemble machine learning methods on big data to enhance the accuracy of the ransomware detection. Although, many machine learning models have been used in the detection of ransomware, yet, the evaluation of ensemble methods has not been investigated. Moreover, a new feature selection approach based on Principle Component Analysis (PCA) is presented to decrease the dimensions of the features. The datasets employed in the study comprised of two types: the first one is dynamic that comprises of 582 ransomware and 942 clean applications while the second one is hybrid that comprises of 500 applications. The classification models used are SVM, Random Forests, KNN, XGBoost, and Neural Network. Our experimental results show that Neural Network outperforms the other models and that BigRC-EML achieves an accuracy of 98% as well as can work under all types of data i.e. balanced, imbalanced, static, and dynamic. The experimental results successfully validate the effectiveness of the proposed approach by improving the classification accuracy of new ransomware. [ABSTRACT FROM AUTHOR]

Monitoring the balance conditions and physical abilities of athletes is important to track their current situations which enables us to apply appropriate training programs for recovery. For different branches of sports, there are three main balance board types to be used; not swaying board (i.e. Wii board), semi-spherical fulcrum (i.e. Wobble board), and springboard (i.e. Spring Balance Board). In this study, the Balance springboard, which is new to the literature, is used. The springboard equipped with sensors uses Bluetooth technology to transmit collected balance data. There are various previous studies developed for assessing the balance performance of athletes regarding the first two types of balance-boards. Most of them are based on statistical analysis and machine learning (ML) techniques. In this study, the usage of a shallow deep learning model trained with the balance data, which is a contribution to the literature, gathered from the springboard is introduced. This model (DDSS, Denge Decision Support System) is compared with the base ANN model -which leads the study to tend our DDSS model- and ML techniques. Our DDSS model outperforms when compared with the base ANN and ML techniques, Sequential Minimal Optimization and Random Forest, and offers appropriate training program suggestions with a success rate of 92.11%. [ABSTRACT FROM AUTHOR]

Innovation and adoption of new technologies in health care industries produce vast data every day. The diverse data in health care include clinical data, health history, and genetic data. Also, real-time monitoring in health care generates huge data, and efficiently examining these big data is a challenging task. Analysis of health care data becomes more important so that proper medications can be provided and issues can be reduced by taking proper precautions based on the history. Data analysis becomes efficient because of automation, however, due to data integrity, data diversity, and inconsistency, the performance gets lagged. Various machine learning models are introduced to handle big data management; however, researchers are still working to attain a better model with improved accuracy. So with the objective to attain maximum classification accuracy, fuzzy c means clustering and generative adversarial network are employed in this research work for health care data clustering and classification. Benchmark lung cancer dataset and Arrhythmia dataset are used in the experimentation. The proposed model exhibits the maximum accuracy of 97.8% for dataset 1 and 98.6% for dataset 2 compared to existing techniques like support vector machine, decision tree, and random forest algorithms. [ABSTRACT FROM AUTHOR]

Strengthening production plants and process control functions contribute to a global improvement of manufacturing systems because of their cross-functional characteristics in the industry. Companies established various innovative and operational strategies; there is increasing competitiveness among them and increasing companies' value. Machine learning (ML) techniques become an intelligent enticing option to address industrial issues in the current manufacturing sector since the emergence of Industry 4.0 and the extensive integration of paradigms such as big data and high computational power. Implementing a system able to identify faults early to avoid critical situations in the production line and its environment is crucial. Therefore, powerful machine learning algorithms are performed for fault diagnosis, real-time data classification, and predicting the state of functioning of the production line. Random forests proved to be a better classifier with an accuracy of 97%, compared to the SVM model's accuracy which is 94.18%. However, the K-NN model's accuracy is about 93.83%. An accuracy of 80.25% is achieved by the logistic regression model. About 83.73% is obtained by the decision tree's model. The excellent experimental results reached on the random forest model demonstrated the merits of this implementation in the production performance, ensuring predictive maintenance and avoiding wasting energy. [ABSTRACT FROM AUTHOR]

We examine whether corporate bankruptcy predictions can be improved by utilizing the recurrent neural network (RNN) and long short-term memory (LSTM) algorithms, which can process sequential data. Employing the RNN and LSTM methodologies improves bankruptcy prediction performance relative to using other classification techniques, such as logistic regression, support vector machine, and random forest methods. Because performance indicators, such as sensitivity and specificity, differ depending on the methodology, selecting a model that suits the purpose of the bankruptcy predictions is necessary. Our ensemble model, a synthesis of all methodologies, exhibits the best forecasting performance. In the test sample for the ensemble model, none of the observations with a default probability of less than 10% defaults within one year. [ABSTRACT FROM AUTHOR]

Random Forest (RF) is composed of decision trees as base classifiers. In general, a decision tree recursively partitions the feature space into two disjoint subspaces using a single feature as axis-parallel splits for each internal node. The oblique decision tree uses a linear combination of features (to form a hyperplane) to partition the feature space in two subspaces. The later approach is an NP-hard problem to compute the best-suited hyperplane. In this work, we propose to use multiple features at a node for splitting the data as in axis parallel method. Each feature independently divides into two subspaces and this process is done by multiple features at one node. Hence, the given space is divided into multiple subspaces simultaneously, and in turn, to construct the M-ary trees. Hence, the forest formed is named as M-ary Random Forest (MaRF). To measure the performance of the task in MaRF, we have extended the notion of tree strength of the regression tree. We empirically prove that the performance of the MaRF improves due to the improvement in the strength of the M-ary trees. We have shown the performance to wide range of datasets ranging from UCI datasets, Hyperspectral dataset, MNIST dataset, Caltech 101 and Caltech 256 datasets. The efficiency of the MaRF approach is found satisfactory as compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Goal: To evaluate the ability of radiomic feature extraction and a machine learning algorithm to differentiate between benign and malignant indeterminate adrenal lesions on contrast-enhanced computed tomography (CT) studies. Background: Adrenal "incidentalomas" are adrenal lesions that are accidentally discovered during workup not related to the adrenal glands; they have an incidence as high as 5%. Small adrenal incidentalomas (< 4 cm) with high attenuation values on pre-contrast CT(> 10 HU) need further evaluation to calculate the absolute percentage of washout (APW). If the APW is < 60%, these lesions are considered non-adenomas and commonly classified as indeterminate adrenal lesions. Further workup for indeterminate lesions includes more complicated and expensive radiological studies or invasive procedures like biopsy or surgical resection. Methods: We searched our institutional database for indeterminate adrenal lesions with the following characteristics: < 4 cm, pre-attenuation value > 10 HU, and APW < 60%. Exclusion criteria included pheochromocytoma and no histopathological examination. CT images were converted to Nifti format, and adrenal tumors were segmented using Amira software. Radiomic features from the adrenal mask were extracted using PyRadiomics software after removing redundant features (highly pairwise correlated features and low-variance features) using recursive feature extraction to select the final discriminative set of features. Lastly, the final features were used to build a binary classification model using a random forest algorithm, which was validated and tested using leave-one-out cross-validation, confusion matrix, and receiver operating characteristic curve. Results: We found 40 indeterminate adrenal lesions (21 benign and 19 malignant). Feature extraction resulted in 3947 features, which reduced down to 62 features after removing redundancies. Recursive feature elimination resulted in the following top 4 discriminative features: gray-level size zone matrix-derived size zone non-uniformity from pre-contrast and delayed phases, gray-level dependency matrix-derived large dependence high gray-level emphasis from venous-phase, and gray-level co-occurrence matrix-derived cluster shade from delayed-phase. A binary classification model with leave-one-out cross-validation showed AUC = 0.85, sensitivity = 84.2%, and specificity = 71.4%. Conclusion: Machine learning and radiomic features extraction can differentiate between benign and malignant indeterminate adrenal tumors and can be used to direct further workup with high sensitivity and specificity. [ABSTRACT FROM AUTHOR]