Wrapper Method Research Articles

Expecting individuals’ body reaction to Covid-19 based on statistical Naïve Bayes technique

Covid-19, what a strange, unpredictable mutated virus. It has baffled many scientists, as no firm rule has yet been reached to predict the effect that the virus can inflict on people if they are infected with it. Recently, many researches have been introduced for diagnosing Covid-19; however, none of them pay attention to predict the effect of the virus on the person's body if the infection occurs but before the infection really takes place. Predicting the extent to which people will be affected if they are infected with the virus allows for some drastic precautions to be taken for those who will suffer from serious complications, while allowing some freedom for those who expect not to be affected badly. This paper introduces Covid-19 Prudential Expectation Strategy (CPES) as a new strategy for predicting the behavior of the person's body if he has been infected with Covid-19. The CPES composes of three phases called Outlier Rejection Phase (ORP), Feature Selection Phase (FSP), and Classification Phase (CP). For enhancing the classification accuracy in CP, CPES employs two proposed techniques for outlier rejection in ORP and feature selection in FSP, which are called Hybrid Outlier Rejection (HOR) method and Improved Binary Genetic Algorithm (IBGA) method respectively. In ORP, HOR rejects outliers in the training data using a hybrid method that combines standard division and Binary Gray Wolf Optimization (BGWO) method. On the other hand, in FSP, IBGA as a hybrid method selects the most useful features for the prediction process. IBGA includes Fisher Score (FScore) as a filter method to quickly select the features and BGA as a wrapper method to accurately select the features based on the average accuracy value from several classification models as a fitness function to guarantee the efficiency of the selected subset of features with any classifier. In CP, CPES has the ability to classify people based on their bodies’ reaction to Covid-19 infection, which is built upon a proposed Statistical Naïve Bayes (SNB) classifier after performing the previous two phases. CPES has been compared against recent related strategies in terms of accuracy, error, recall, precision, and run-time using Covid-19 dataset [1]. This dataset contains routine blood tests collected from people before and after their infection with covid-19 through a Web-based form created by us. CPES outperforms the competing methods in experimental results because it provides the best results with values of 0.87, 0.13, 0.84, and 0.79 for accuracy, error, precision, and recall.

Prediction of polarities of online hotel reviews: an improved stacked decision tree (ISD) approach

PurposeThere is a need to predict whether the consumers liked the stay in the hotel rooms or not, and to remove the aspects the customers did not like. Many customers leave a review after staying in the hotel. These reviews are mostly given on the website used to book the hotel. These reviews can be considered as a valuable data, which can be analyzed to provide better services in the hotels. The purpose of this study is to use machine learning techniques for analyzing the given data to determine different sentiment polarities of the consumers.Design/methodology/approachReviews given by hotel customers on the Tripadvisor website, which were made available publicly by Kaggle. Out of 10,000 reviews in the data, a sample of 3,000 negative polarity reviews (customers with bad experiences) in the hotel and 3,000 positive polarity reviews (customers with good experiences) in the hotel is taken to prepare data set. The two-stage feature selection was applied, which first involved greedy selection method and then wrapper method to generate 37 most relevant features. An improved stacked decision tree (ISD) classifier) is built, which is further compared with state-of-the-art machine learning algorithms. All the tests are done using R-Studio.FindingsThe results showed that the new model was satisfactory overall with 80.77% accuracy after doing in-depth study with 50–50 split, 80.74% accuracy for 66–34 split and 80.25% accuracy for 80–20 split, when predicting the nature of the customers’ experience in the hotel, i.e. whether they are positive or negative.Research limitations/implicationsThe implication of this research is to provide a showcase of how we can predict the polarity of potentially popular reviews. This helps the authors’ perspective to help the hotel industries to take corrective measures for the betterment of business and to promote useful positive reviews. This study also has some limitations like only English reviews are considered. This study was restricted to the data from trip-adviser website; however, a new data may be generated to test the credibility of the model. Only aspect-based sentiment classification is considered in this study.Originality/valueStacking machine learning techniques have been proposed. At first, state-of-the-art classifiers are tested on the given data, and then, three best performing classifiers (decision tree C5.0, random forest and support vector machine) are taken to build stack and to create ISD classifier.

Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer

PurposeThis study aims to evaluate the potential of machine learning algorithms built with radiomics features from computed tomography urography (CTU) images that classify RB1 gene mutation status in bladder cancer. MethodThe study enrolled CTU images of 18 patients with and 54 without RB1 mutation from a public database. Image and data preprocessing were performed after data augmentation. Feature selection steps were consisted of filter and wrapper methods. Pearson’s correlation analysis was the filter, and a wrapper-based sequential feature selection algorithm was the wrapper. Models with XGBoost, Random Forest (RF), and k-Nearest Neighbors (kNN) algorithms were developed. Performance metrics of the models were calculated. Models’ performances were compared by using Friedman’s test. Results8 features were selected from 851 total extracted features. Accuracy, sensitivity, specificity, precision, recall, F1 measure and AUC were 84%, 80%, 88%, 86%, 80%, 0.83 and 0.84, for XGBoost; 72%, 80%, 65%, 67%, 80%, 0.73 and 0.72 for RF; 66%, 53%, 76%, 67%, 53%, 0.60 and 0.65 for kNN, respectively. XGBoost model had outperformed kNN model in Friedman’s test (p = 0.006). ConclusionsMachine learning algorithms with radiomics features from CTU images show promising results in classifying bladder cancer by RB1 mutation status non-invasively.

Novel Machine Learning Algorithms for Predicting Early Right Heart Failure Post Left Ventricular Assist Device Implantation

<h3>Purpose</h3> Right heart failure is a major contributor to mortality and morbidity after left ventricular assist device implantation (LVAD). Previously our group developed a logistic regression-based model to predict right heart failure (RHF)after LVAD implantation, the EUROMACS RHF Risk Score, with currently the best but yet moderate discriminative ability. However, identification of patients prone to develop RHF after LVAD implantation using traditional statistical models has important limitations. Due to the exponential increase of computational power in the last decade, novel machine learning algorithms have emerged as a powerful tool in prediction modelling. Large international multicenter registries containing thousands of patients like the European Registry for patients with Mechanical Circulatory Support (the EUROMACS Registry) database are particularly suitable for these novel machine learning models. In this study, we aim to use the EUROMACS Registry database, to train and test novel machine learning algorithms predicting RHF after LVAD implantation, holding our previous model as benchmark. The results of this study may facilitate more accurate prediction of early RHF post LVAD implantation. <h3>Methods</h3> The EUROMACS registry will be used to develop different machine learning models, including Random Forests, AdaBoost, XGBoost, Neural networks and Support Vector Machines, to predict postoperative RHF after LVAD implantation. Baseline variables collected in EUROMACS will serve as potential predictors. Both wrapper methods and filter methods will be used for predictor selection. The whole dataset will be used as training set and internal performance of the models will be assessed using resampling methods based upon k-fold cross validation or bootstrapping to limit overfitting. Performance measures that will be used include Area Under the Curve (discrimination), calibration intercepts/slope (calibration), Brier score (discrimination/calibration) and Net benefit curves. <h3>Endpoints</h3> The primary endpoint of this study is early postoperative RHF using the following definitions: the need for temporary or durable right ventricular assist device, or need of inotropic support for ≥14 days, and/or NO ventilation for ≥48 hours.

Classifying the difficulty levels of working memory tasks by using pupillary response.

Knowing the difficulty of a given task is crucial for improving the learning outcomes. This paper studies the difficulty level classification of memorization tasks from pupillary response data. Developing a difficulty level classifier from pupil size features is challenging because of the inter-subject variability of pupil responses. Eye-tracking data used in this study was collected while students solved different memorization tasks divided as low-, medium-, and high-level. Statistical analysis shows that values of pupillometric features (as peak dilation, pupil diameter change, and suchlike) differ significantly for different difficulty levels. We used a wrapper method to select the pupillometric features that work the best for the most common classifiers; Support Vector Machine (SVM), Decision Tree (DT), Linear Discriminant Analysis (LDA), and Random Forest (RF). Despite the statistical difference, experiments showed that a random forest classifier trained with five features obtained the best F1-score (82%). This result is essential because it describes a method to evaluate the cognitive load of a subject performing a task using only pupil size features.

A flexible zinc-air battery using fiber absorbed electrolyte

The rise of soft electronic devices has promoted the development and application of flexible metal-air batteries (MABs) with deformable properties. Most traditional flexible batteries are made of gel electrolyte. The complicated process, high cost and many limitations hinder the promotion of flexible MABs. In order to improve the structure and performance of flexible zinc-air batteries (ZABs) and hope to provide new ideas and methods for future research and development. Herein, a distinctive cable-type zinc-air battery (ZAB) is proposed. The composite fiber soaked in KOH solution is used as the electrolyte material of ZAB, which not only avoids the complex process of preparing flexible-based electrolyte, but also realizes the transformation from aqueous battery to flexible battery. Benefiting from the high water absorption and excellent flexibility of fiber electrolyte, the assembled cable-type ZAB can operate under various deformation conditions. When the battery performance deteriorates or fails due to water dissipation in the electrolyte, the performance can be recovered by replenishing electrolyte/water. The service life and performance of battery are improved by reducing water evaporation through the outer wrapping method. The successful application of such batteries in various electronic devices guides the future way.

A wrapper method based on a modified two-step league championship algorithm for detecting botnets in IoT environments

A wrapper method based on a modified two-step league championship algorithm for detecting botnets in IoT environments

Gene selection using pyramid gravitational search algorithm.

Genetics play a prominent role in the development and progression of malignant neoplasms. Identification of the relevant genes is a high-dimensional data processing problem. Pyramid gravitational search algorithm (PGSA), a hybrid method in which the number of genes is cyclically reduced is proposed to conquer the curse of dimensionality. PGSA consists of two elements, a filter and a wrapper method (inspired by the gravitational search algorithm) which iterates through cycles. The genes selected in each cycle are passed on to the subsequent cycles to further reduce the dimension. PGSA tries to maximize the classification accuracy using the most informative genes while reducing the number of genes. Results are reported on a multi-class microarray gene expression dataset for breast cancer. Several feature selection algorithms have been implemented to have a fair comparison. The PGSA ranked first in terms of accuracy (84.5%) with 73 genes. To check if the selected genes are meaningful in terms of patient’s survival and response to therapy, protein-protein interaction network analysis has been applied on the genes. An interesting pattern was emerged when examining the genetic network. HSP90AA1, PTK2 and SRC genes were amongst the top-rated bottleneck genes, and DNA damage, cell adhesion and migration pathways are highly enriched in the network.

Feature Selection for Supervised Learning and Compression

ABSTRACT Supervised feature selection aims to find the signals that best predict a target variable. Typical approaches use measures of correlation or similarity, as seen in filter methods, or predictive power in learned models, as seen in wrapper methods. In both approaches, the selected features often have high entropies and are not suitable for compression. This is a particular drawback in the automotive domain where fast communication and archival of vehicle telemetry data is increasingly important, especially with technologies such as V2V and V2X (vehicle-to-vehicle and vehicle-to-everything communication). This paper aims to select features with good predictive performances and good compression by introducing a compressibility factor into several existing feature selection approaches. Where appropriate, performance guarantees are provided for greedy searches based on monotonicity and submodularity. Using the language of entropy, the relationship between relevance, redundancy, and compressibility is discussed from the perspective of signal selection. The approaches are then demonstrated in selecting features from a vehicle Controller Area Network for use in SVMs in a regression task, namely predicting fuel consumption, and a classification task, namely identifying Points of Interest. We show that while predictive performance is slightly lower when compression is considered, the compressibility of the selected features is significantly improved.

Electrodermal activity based autonomic sleep staging using wrist wearable

Autonomic sleep staging refers to sleep characterization using autonomic physiological signals. This paper focuses on utilizing electrodermal activity (EDA), an autonomic signal that reflects the activity of sympathetic nerves on sweat glands, for characterizing wake and three sleep stages viz., light, deep, and rapid eye movement (REM) sleep. The study also investigates whether skin temperature (ST) measured from the same skin site as EDA can enhance the performance of EDA-based sleep staging. EDA and ST during sleep were recorded overnight to generate 118 datasets with an average duration of 6.2 h. Recordings were done from the dominant ventral wrist of all subjects using a GEN II wrist wearable vital signs monitor (VSM) from Analog Devices. WatchPAT, an FDA-approved, portable sleep monitor was used as a reference to generate the ground truth. 204 features were extracted from 30-s epochs of raw and preprocessed EDA and ST signals. Feature selection using a novel ensemble wrapper method was adopted to identify the best feature subset. User-specific, general, and non-intersecting ordinal models based on 7 classifiers were investigated, concerning their utility for sleep staging. While the EDA-based scheme using the non-intersecting ordinal random forest classifier yielded the highest training accuracy of 88.11% for females and 88.75% for males, the addition of ST enhanced it to 96.29% and 95.06%, respectively. The scheme exhibited good generalizability on a new dataset, yielding an accuracy of 94.11% for females and 92.92% for males. The duration of wake, light, deep, and REM was estimated as a percentage of total sleep duration and was validated against the reference. The sleep estimates showed a positive correlation with Pearson’s r of 0.97, 0.96, 0.96, and 0.98 respectively for %Wake, %Light, %Deep, and %REM. The Bland–Altman analysis done on estimates also indicated similarity with minimal bias.

Prediction of Chronic Kidney Disease-A Machine Learning Perspective

Chronic Kidney Disease is one of the most critical illnesses nowadays and proper diagnosis is required as soon as possible. Machine learning technique has become reliable for medical treatment. With the help of a machine learning classifier algorithms, the doctor can detect the disease on time. For this perspective, Chronic Kidney Disease prediction has been discussed in this article. Chronic Kidney Disease dataset has been taken from the UCI repository. Seven classifier algorithms have been applied in this research such as artificial neural network, C5.0, Chi-square Automatic interaction detector, logistic regression, linear support vector machine with penalty L1 &amp; with penalty L2 and random tree. The important feature selection technique was also applied to the dataset. For each classifier, the results have been computed based on the following factors given below: (i) full features, (ii) correlation-based feature selection, (iii) Wrapper method feature selection, (iv)Least absolute shrinkage and selection operator regression, (v) synthetic minority over- sampling technique with least absolute shrinkage and selection operator regression selected features, (vi) synthetic minority oversampling technique with full features. From the results, it is marked that LSVM with penalty L2 is giving the highest accuracy of 98.86% in synthetic minority over-sampling technique with full features. Along with accuracy, precision, recall, F- measure, area under the curve and GINI coefficient have been computed and compared results of various algorithms have been shown in the graph. Least absolute shrinkage and selection operator regression selected features with synthetic minority over-sampling technique gave the best after synthetic minority over-sampling technique with full features. In the synthetic minority over-sampling technique with least absolute shrinkage and selection operator selected features, again linear support vector machine gave the highest accuracy of 98.46%. Along with machine learning models one deep neural network has been applied on the same dataset and it has been noted that deep neural network achieved the highest accuracy of 99.6%.

Prediction of Chronic Kidney Disease Using Machine Learning

Chronic Kidney Disease is one of the most serious illnesses nowadays, and it is vital to have a good diagnosis as soon as possible. Machine learning has proven to be effective in medical therapy. The doctor can diagnose the ailment early with the use of machine learning classifier algorithms. This article has examined Chronic Kidney Disease prediction from this standpoint. The Chronic Kidney Disease dataset was obtained from the University of California at Irvine's repository. The artificial neural network, C5.0, Chi-square Automatic interaction detector, logistic regression, linear support vector machine with penalty L1 &amp; with penalty L2, and random forest classifier techniques were used in this study. The dataset was also subjected to the significant feature selection technique. The results were computed for each classifier using I full features, (ii) correlation-based feature selection, (iii) Wrapper method feature selection, (iv) Least absolute shrinkage and selection operator regression, (v) synthetic minority over-sampling technique with least absolute shrinkage and selection operator regression selected features, and (vi) synthetic minority over-sampling technique with full features. The results show that in synthetic minority over-sampling technique with full features, LSVM with penalty L2 has the maximum accuracy of 98.86 percent. Along with precision, recall, F-measure, and area, accuracy, precision, recall, and area. The GINI coefficient and beneath the curve have been computed, and the results of various algorithms have been compared in the graph. After synthetic minority over-sampling technique with full features, the least absolute shrinkage and selection operator regression selected features with synthetic minority over-sampling approach produced the best results. Again, the linear support vector machine had the maximum accuracy of 98.46 percent in the synthetic minority over-sampling technique with the least absolute shrinkage and selection operator selected features. Along with machine learning models, a deep neural network was used on the same dataset, and the deep neural network was found to have the greatest accuracy of 99.6%.

Predictive model for construction labour productivity using hybrid feature selection and principal component analysis

Construction labour productivity (CLP) is affected by numerous variables made up of subjective and objective factors. Thus, CLP modelling and prediction are a complex task, leading to high computational cost and the risk of overfitting of data. This paper proposes a predictive model for CLP by integrating hybrid feature selection (HFS), as a combination of filter and wrapper methods, with principal component analysis (PCA). This developed HFS-PCA method reduces the dimensionality and complexity of CLP data and obtains better prediction performance by identifying the most predictive factors. Identified factors are utilized as inputs for various classification methods to predict CLP. Finally, prediction errors of the classification methods with and without using the proposed HFS-PCA method are compared, and the most accurate classification method is selected to develop the CLP predictive model. Experimental results show that using HFS-PCA for CLP prediction leads to better performances compared with past studies.

Novel Improved Salp Swarm Algorithm: An Application for Feature Selection.

We live in a period when smart devices gather a large amount of data from a variety of sensors and it is often the case that decisions are taken based on them in a more or less autonomous manner. Still, many of the inputs do not prove to be essential in the decision-making process; hence, it is of utmost importance to find the means of eliminating the noise and concentrating on the most influential attributes. In this sense, we put forward a method based on the swarm intelligence paradigm for extracting the most important features from several datasets. The thematic of this paper is a novel implementation of an algorithm from the swarm intelligence branch of the machine learning domain for improving feature selection. The combination of machine learning with the metaheuristic approaches has recently created a new branch of artificial intelligence called learnheuristics. This approach benefits both from the capability of feature selection to find the solutions that most impact on accuracy and performance, as well as the well known characteristic of swarm intelligence algorithms to efficiently comb through a large search space of solutions. The latter is used as a wrapper method in feature selection and the improvements are significant. In this paper, a modified version of the salp swarm algorithm for feature selection is proposed. This solution is verified by 21 datasets with the classification model of K-nearest neighborhoods. Furthermore, the performance of the algorithm is compared to the best algorithms with the same test setup resulting in better number of features and classification accuracy for the proposed solution. Therefore, the proposed method tackles feature selection and demonstrates its success with many benchmark datasets.

Tremor-related feature engineering for machine learning based Parkinson’s disease diagnostics

Growing research interest has arisen towards the possibility to automatically discriminate between the patients with neurodegenerative disease and healthy controls based on the information extracted from the digital drawing tests.In this paper, we propose novel higher-order derivative based, angular-type and integral-like features extracted from the Archimedean spiral drawing tests for machine learning based Parkinson’s disease diagnostics. The proposed features describe micro-changes in the handwriting trajectory, which are hard or impossible to detect with visual observation. However, they may hold valuable information in terms of tremor-like symptom analysis.Two datasets are considered in this study: DraWritePD (acquired by the authors) and PaHaW (well known from the literature). A filter (Fisher’s score) and wrapper (Recursive Feature Elimination) methods were used for feature selection. Six classifiers were trained and evaluated in a nested cross-validated loop to discriminate between healthy controls and Parkinson’s patients.A nested wrapper-type feature selection method combined with the ensemble classifiers predicted a disease with an accuracy of 84.33%, sensitivity of 70.00% and specificity of 93.20% (DraWritePD), and accuracy of 73.71%, sensitivity of 75.00% and specificity of 71.43% (PaHaW). The non-nested feature selection showed an over-optimistically high performance for both datasets: an accuracy of 92.16% (DraWritePD) and 84.86% (PaHaW).The proposed novel tremor-related features were among the best performing predictors in the case of both datasets. Furthermore, the results indicate that the nested feature selection procedure plays a significant part in the classification performance.

A Novel Feature Selection Method Based on MRMR and Enhanced Flower Pollination Algorithm for High Dimensional Biomedical Data

Background: The massive amount of biomedical data accumulated in the past decades can be utilized for diagnosing disease. Objective: However, the high dimensionality, small sample sizes, and irrelevant features of data often have a negative influence on the accuracy and speed of disease prediction. Some existing machine learning models cannot capture the patterns on these datasets accurately without utilizing feature selection. Methods: Filter and wrapper are two prevailing feature selection methods. The filter method is fast but has low prediction accuracy, while the latter can obtain high accuracy but has a formidable computation cost. Given the drawbacks of using filter or wrapper individually, a novel feature selection method, called MRMR-EFPATS, is proposed, which hybridizes filter method Minimum Redundancy Maximum Relevance (MRMR) and wrapper method based on an improved Flower Pollination Algorithm (FPA). First, MRMR is employed to rank and screen out some important features quickly. These features are further chosen for individual populations following the wrapper method for faster convergence and less computational time. Then, due to its efficiency and flexibility, FPA is adopted to further discover an optimal feature subset. Result: FPA still has some drawbacks, such as slow convergence rate, inadequacy in terms of searching new solutions, and tends to be trapped in local optima. In our work, an elite strategy is adopted to improve the convergence speed of the FPA. Tabu search and Adaptive Gaussian Mutation are employed to improve the search capability of FPA and escape from local optima. Here, the KNN classifier with the 5-fold-CV is utilized to evaluate the classification accuracy. Conclusion: Extensive experimental results on six public high dimensional biomedical datasets show that the proposed MRMR-EFPATS has achieved superior performance compared to other state-of-theart methods.

Hybrid Symmetrical Uncertainty and Reference Set Harmony Search Algorithm for Gene Selection Problem

Selecting the most miniature possible set of genes from microarray datasets for clinical diagnosis and prediction is one of the most challenging machine learning tasks. A robust gene selection technique is required to identify the most significant subset of genes by removing spurious or non-predictive genes from the original dataset without sacrificing or reducing classification accuracy. Numerous studies have attempted to address this issue by implementing either a filter or a wrapper. Although the filter approaches are computationally efficient, they are completely independent of the induction algorithm. On the other hand, wrapper approaches outperform filter approaches but are computationally more expensive. Therefore, this study proposes an enhanced gene selection method that uses a hybrid technique that combines the Symmetrical Uncertainty (SU) filter and Reference Set Harmony Search Algorithm (RSHSA) wrapper method, known as SU-RSHSA. The framework to develop the proposed SU-RSHSA includes numerous stages: (1) investigate a novel gene selection method based on the HSA and will then determine appropriate values for the HSA’s parameters, (2) enhance the construction process of the initial harmony memory while satisfying the diversity of the solution by embedding a reference set within the HSA (RSHSA), and (3) investigates the effect of integrating Symmetrical Uncertainty (SU) as a filter and RSHSA as a wrapper (SU-RSHSA) to maximize classification accuracy by leveraging their respective advantages. The results demonstrate that the SU-RSHSA outperforms the original HSA and SU-HSA in terms of classification accuracy, a small number of selected relevant genes, and reduced computational time. More importantly, the proposed SU-RSHSA gene selection method effectively generates a small subset of salient genes with high classification accuracy.

Generalization enhancement of artificial neural network for turbulence closure by feature selection

Feature selection targets for selecting relevant and useful features, and is a vital challenge in turbulence modeling by machine learning methods. In this paper, a new posterior feature selection method based on validation dataset is proposed, which is an efficient and universal method for complex systems including turbulence. Different from the priori feature importance ranking of the filter method and the exhaustive search for feature subset of the wrapper method, the proposed method ranks the features according to the model performance on the validation dataset, and generates the feature subsets in the order of feature importance. Using the features from the proposed method, a black-box model is built by artificial neural network (ANN) to reproduce the behavior of Spalart-Allmaras (S-A) turbulence model for high Reynolds number (Re) airfoil flows in aeronautical engineering. The results show that compared with the model without feature selection, the generalization ability of the model after feature selection is significantly improved. To some extent, it is also demonstrated that although the feature importance can be reflected by the model parameters during the training process, artificial feature selection is still very necessary.

Efficient weakly supervised LIBS feature selection method in quantitative analysis of iron ore slurry

On-stream analysis of the element content in ore slurry plays an important role in the control of the mineral flotation process. Therefore, our laboratory developed a LIBS-based slurry analyzer named LIBSlurry, which can monitor the iron content in slurries in real time. However, achieving high-precision quantitative analysis results of the slurries is challenging. In this paper, a weakly supervised feature selection method named spectral distance variable selection was proposed for the raw spectral data. This method utilizes the prior information that multiple spectra of the same slurry sample have the same reference concentration to assess the important weight of spectral features, and features selected by this prior can avoid over-fitting compared with a traditional wrapper method. The spectral data were collected on-stream of iron ore concentrate slurry samples during the mineral flotation process. The results show that the prediction accuracy is greatly improved compared with the full-spectrum input and other feature selection methods; the root mean square error of the prediction of iron content can be decreased to 0.75%, which helps to realize the successful application of the analyzer.

In-Depth Feature Selection for the Statistical Machine Learning-Based Botnet Detection in IoT Networks

The attackers compromise insecure IoT devices to enlarge their botnets for the purpose of launching more influential attacks against their victims. In various studies, it is demonstrated that machine learning can be utilized for the detection of IoT botnet attacks. In this paper, we focus on the minimization of feature sets for machine learning tasks that are formulated as six different binary and multi-class classification problems based on the stages of the botnet life-cycle. More specifically, we apply filter and wrapper methods with some machine learning methods and derived the optimal feature sets for each classification problem. The experimental results show that it is possible to achieve very high detection rates with very limited number of features. Some wrapper methods guarantee an optimal feature set regardless of the problem formulation but filter methods do not achieve that in all cases. The feature selection methods more prefer channel-based features for the detection at post-attack and communication & control stages whereas host-based features are more influential for identifying the attacks originating from the bots.