Correlation-based Feature Selection Research Articles

GAAMmf: genetic algorithm with aggressive mutation and decreasing feature set for feature selection

This paper introduces a modified version of a genetic algorithm with aggressive mutation (GAAM), one of the genetic algorithms (GAs) used for feature selection. The modification proposed in this study expands the original GAAM’s capabilities by allowing not only feature selection but also feature reduction. To obtain this effect, we applied the concept of ranks used in the non-dominated sorting genetic algorithm (NSGA) and the concept of penalty term used in the Holland genetic algorithm. With those two concepts, we managed to balance the importance of two competing criteria in the GAAM fitness function: classification accuracy and the feature subset’s size. To assess the algorithm’s effectiveness, we evaluated it on eleven datasets with different characteristics and compared the results with eight reference methods: GAAM, Melting GAAM, Holland GA with a penalty term, NSGA-II, Correlation-based Feature Selection, Lasso, Sequential Forward Selection, and IniPG (an algorithm for particle swarm optimisation). The main conclusion drawn from this study is that the genetic algorithm with aggressive mutation and decreasing feature set (GAAMmf) introduced in this paper returned feature sets with a significantly smaller number of features than almost all reference methods. Furthermore, GAAMmf outperformed most of the methods in terms of classification accuracy (except the original GAAM). In contrast to Holland GA and NSGA-II, GAAMmf was able to perform the feature reduction task for all datasets, regardless of the initial number of features.

Estimation of Winter Wheat SPAD Values Based on UAV Multispectral Remote Sensing

Unmanned aerial vehicle (UAV) multispectral imagery has been applied in the remote sensing of wheat SPAD (Soil and Plant Analyzer Development) values. However, existing research has yet to consider the influence of different growth stages and UAV flight altitudes on the accuracy of SPAD estimation. This study aims to optimize UAV flight strategies and incorporate multiple feature selection techniques and machine learning algorithms to enhance the accuracy of the SPAD value estimation of different wheat varieties across growth stages. This study sets two flight altitudes (20 and 40 m). Multispectral images were collected for four winter wheat varieties during the green-up and jointing stages. Three feature selection methods (Pearson, recursive feature elimination (RFE), and correlation-based feature selection (CFS)) and four machine learning regression models (elastic net, random forest (RF), backpropagation neural network (BPNN), and extreme gradient boosting (XGBoost)) were combined to construct SPAD value estimation models for individual growth stages as well as across growth stages. The CFS-RF (40 m) model achieved satisfactory results (green-up stage: R2 = 0.7270, RPD = 2.0672, RMSE = 1.1835, RRMSE = 0.0259; jointing stage: R2 = 0.8092, RPD = 2.3698, RMSE = 2.3650, RRMSE = 0.0487). For cross-growth stage modeling, the optimal prediction results for SPAD values were achieved at a flight altitude of 40 m using the Pearson-XGBoost model (R2 = 0.8069, RPD = 2.3135, RMSE = 2.0911, RRMSE = 0.0442). These demonstrate that the flight altitude of UAVs significantly impacts the estimation accuracy, and the flight altitude of 40 m (with a spatial resolution of 2.12 cm) achieves better SPAD value estimation than that of 20 m (with a spatial resolution of 1.06 cm). This study also showed that the optimal combination of feature selection methods and machine learning algorithms can more accurately estimate winter wheat SPAD values. In addition, this study includes multiple winter wheat varieties, enhancing the generalizability of the research results and facilitating future real-time and rapid monitoring of winter wheat growth.

Öznitelik Seçim Yöntemlerinin Toplam Ekipman Etkinliği Tahmin Başarısı Üzerindeki Etkisinin Araştırılması

Overall equipment effectiveness (OEE) describes production efficiency by combining availability, performance, and quality and is used to evaluate production equipment’s performance. This research’s aim is to investigate the potential of the feature selection techniques and the multiple linear regression method, which is one of the machine learning techniques, in successfully predicting the OEE of the corrugated department of a box factory. In the study, six different planned downtimes and information on seventeen different previously known concepts related to activities to be performed are used as input features. Moreover, backward elimination, forward selection, stepwise selection, correlation-based feature selection (CFS), genetic algorithm, random forest, extra trees, ridge regression, lasso regression, and elastic net feature selection methods are proposed to find the most distinctive feature subset in the dataset. As a result of the analyses performed on the data set consisting of 23 features, 1 output and 1204 working days of information, the elastic net - multiple linear regression model, which selects 19 attributes, gave the best average R2 value compared to other models developed. Occam's razor principle is taken into account since there is not a great difference between the average R2 values obtained. Among the models developed according to the principle, the stepwise selection - multiple linear regression model yielded the best R2 value among those that selected the fewest features.

An exploratory in N-doped carbon dots as green fluorescence probes for Hg(II) ions detection

ABSTRACT Carbon dots (CDs), as a fascinating carbon nanomaterial, have important applications in various fields due to their unique properties. The physical and chemical properties of CDs can be fine-tuned using heteroatom doping and surface functionalisation. Here, we synthesised N-doped carbon dots (N-CDs) by reacting Citric acid, which serve as the carbon core, with twenty amino acids under microwave irradiation. The fluorescence quenching of each amino acid doped CDs by Hg(II) ions was experimentally measured. Then the effect of the molecular features and chemical properties of amino acids on the fluorescence quenching of N-CDs by Hg(II) ions was investigated by using the quantitative structure–property relationship (QSPR) method. Applying different machine learning techniques including correlation-based and ReliefF algorithm feature selection approaches to choose relevant descriptors, multi-linear regression, and support vector machine to construct QSPR model, some reliable and predictive models were developed. Based on the variables used throughout the final QSPR models, hydrophobic interactions, in addition to hydrogen bonding interactions, can be considered a major factor governing the photoluminescence behaviour of different N-CDs quenched by Hg(II) ions. N-CDs derived from amino acids bearing larger hydrophobic surfaces show greater fluorescence quenching, indicating that a greater capacity to interact with Hg(II) metal ions resulting in further fluorescence quenching.

Experimental and data driven measurement of engine dynamometer bearing lifespan using acoustic emission

In this study, experimental studies are carried out to capture the lifespan of engine dynamometer bearing using acoustic emission signal. As there is not a through comparison of the usage of different novel neural networks for bearing remaining useful life prediction, here, different feedback neural networks namely Elman, Jordan and LSTM neural networks are applied for prediction of bearing lifespan based on acoustic emission waveforms. Different time–frequency features are presented and prognostic feature selection is used for features size reduction. Correlation-based feature selection (CFS) is used to identify the correlated features. Comparison of different neural networks showed that Jordan feedback neural network with Bayesian Regularization training algorithm has the least error in estimating the bearing lifespan and is therefore selected as the best neural network for this purpose. Also, it is shown that acoustic emission is a good method for bearing RUL prediction. The time to start prediction for the the definition of RUL based on the different tests was calculated about 13.4 h.

Toward the automatic detection of effective gerbil holes in desert grasslands through unmanned aerial vehicle imagery

Rapidly determining the density of effective gerbil holes is ecologically important but technically challenging. However, unmanned aerial vehicles (UAVs) offer new methods to identify effective gerbil holes and understand the spatial relationships between gerbils and grass coverage. In this study, we focused on Meriones unguiculatus, which live in desert grasslands of Ordos, and gathered UAV imagery to explore the performance of rule-based classification in object-based image analysis (OBIA) for identifying effective gerbil holes. To improve the classification accuracy and reduce the time cost of repeated ‘trial and error’, we propose a novel method to build rule sets. We adopted the estimation of scale parameter_2 (ESP2) method during the segmentation stage to enable fast and objective segmentation parameterization. For the classification stage, a correlation-based feature selection (CFS) algorithm was applied for feature selection and threshold prediction. Our analysis determined the following universally recommended rule sets for identifying effective gerbil holes using OBIA: scale parameter of 107, shape factor of 0.2, compactness value of 0.3, excess green value less than −5, brightness feature value in the 143–149 range and roundness feature less than 0.9. With these rule sets, OBIA exhibited higher classification accuracy than maximum likelihood (ML) classification, with an overall classification accuracy of 88.25%. We also found that the relationship between the area of effective gerbil holes (y) and the grass coverage (x) satisfied a quadratic function: This study provides practical guidance for grassland management and rodent infestation control.

Development of an online Nigella sativa inspection system equipped with machine vision technology and artificial neural networks

Aim of study: Nigella sativa L. seeds usually are mixed with impurities, which affect its quality and influences consumer acceptance in both raw seeds and the oil market. In this study, an intelligent system based on the combination of machine vision (MV) and artificial neural networks (ANN) was developed to classify and clean N. sativa seeds and its impurities. Area of study: Iran, Kurdistan province. Material and methods: For accurate detections we developed a robust image processing algorithm including image acquisition, image enhancement, segmentation, and feature extraction steps. Correlation-based Feature Selection method was used to select the superior features. Three methods of linear discriminant analysis, support vector machines, and ANN were used to classify the data. Main results: The statistical indices of sensitivity, specificity, and accuracy for N. sativa in the online phase were 90%, 98.93%, and 97.04%, respectively. The average of these measurements for the impurities class was 95.57%, 96.89%, and 96.58%, respectively. Research highlights: The results demonstrated the feasibility of suggested machine learning and image processing approaches in the real-time cleaning of N. sativa. The image acquisition and processing process, including selection of the best lighting methods to reduce the shadows, noise elimination and segmentation, provided precise results. The final results indicated the effectiveness of proposed machine learning algorithm in feature extraction, feature dimensionality reduction, and classification approaches. This methodology can be recommended for detection, classification and automatic cleaning of other similar seeds.

Gene Expression Classification for Biomarker Identification in Maize Subjected to Various Biotic Stresses.

Various diseases severely affect maize, leading to a significant reduction in yield and crop quality. Therefore, the identification of genes responsible for tolerance to biotic stress is important in maize breeding programs. In the present study, a meta-analysis on microarray gene expression of maize imposed to various biotic stresses, induced by fungal pathogens or pests, was performed to identify key tolerant genes. Correlation-based Feature Selection (CFS) was performed to attain fewer DEGs discriminating control and stress conditions. As a result, 44 genes were selected and their performance was confirmed in the Bayes Net, MLP, SMO, KStar, Hoeffding Tree, and Random Forest models. Bayes Net outperformed the other algorithms representing an accuracy level of 97.1831%. Pathogen recognition genes, decision tree models, co-expression analysis, and functional enrichment were implemented on these selected genes. A robust co-expression was observed among 11 genes responsible for defense response, diterpene phytoalexin biosynthetic process, and diterpenoid biosynthetic process in terms of biological process. This study could provide new information on the genes responsible for resistance to biotic stress in maize to be implicated in biology or maize breeding.

Investigating Feature Selection Techniques to Enhance the Performance of EEG-Based Motor Imagery Tasks Classification

Analyzing electroencephalography (EEG) signals with machine learning approaches has become an attractive research domain for linking the brain to the outside world to establish communication in the name of the Brain-Computer Interface (BCI). Many researchers have been working on developing successful motor imagery (MI)-based BCI systems. However, they still face challenges in producing better performance with them because of the irrelevant features and high computational complexity. Selecting discriminative and relevant features to overcome the existing issues is crucial. In our proposed work, different feature selection algorithms have been studied to reduce the dimension of multiband feature space to improve MI task classification performance. In the procedure, we first decomposed the MI-based EEG signal into four sets of the narrowband signal. Then a common spatial pattern (CSP) approach was employed for each narrowband to extract and combine effective features, producing a high-dimensional feature vector. Three feature selection approaches, named correlation-based feature selection (CFS), minimum redundancy and maximum relevance (mRMR), and multi-subspace randomization and collaboration-based unsupervised feature selection (SRCFS), were used in this study to select the relevant and effective features for improving classification accuracy. Among them, the SRCFS feature selection approach demonstrated outstanding performance for MI classification compared to other schemes. The SRCFS is based on the multiple k-nearest neighbour graphs method for learning feature weight based on the Laplacian score and then discarding the irrelevant features based on the weight value, reducing the feature dimension. Finally, the selected features are fed into the support vector machines (SVM), linear discriminative analysis (LDA), and multi-layer perceptron (MLP) for classification. The proposed model is evaluated with two benchmark datasets, namely BCI Competition III dataset IVA and dataset IIIB, which are publicly available and mainly used to recognize the MI tasks. The LDA classifier with the SRCFS feature selection algorithm exhibits better performance. It proves the superiority of our proposed study compared to the other state-of-the-art BCI-based MI task classification systems.

Development and validation of a diagnostic aid for convulsive epilepsy in sub-Saharan Africa: a retrospective case-control study.

Identification of convulsive epilepsy in sub-Saharan Africa relies on access to resources that are often unavailable. Infrastructure and resource requirements can further complicate case verification. Using machine-learning techniques, we have developed and tested a region-specific questionnaire panel and predictive model to identify people who have had a convulsive seizure. These findings have been implemented into a free app for health-care workers in Kenya, Uganda, Ghana, Tanzania, and South Africa. In this retrospective case-control study, we used data from the Studies of the Epidemiology of Epilepsy in Demographic Sites in Kenya, Uganda, Ghana, Tanzania, and South Africa. We randomly split these individuals using a 7:3 ratio into a training dataset and a validation dataset. We used information gain and correlation-based feature selection to identify eight binary features to predict convulsive seizures. We then assessed several machine-learning algorithms to create a multivariate prediction model. We validated the best-performing model with the internal dataset and a prospectively collected external-validation dataset. We additionally evaluated a leave-one-site-out model (LOSO), in which the model was trained on data from all sites except one that, in turn, formed the validation dataset. We used these features to develop a questionnaire-based predictive panel that we implemented into a multilingual app (the Epilepsy Diagnostic Companion) for health-care workers in each geographical region. We analysed epilepsy-specific data from 4097 people, of whom 1985 (48·5%) had convulsive epilepsy, and 2112 were controls. From 170 clinical variables, we initially identified 20 candidate predictor features. Eight features were removed, six because of negligible information gain and two following review by a panel of qualified neurologists. Correlation-based feature selection identified eight variables that demonstrated predictive value; all were associated with an increased risk of an epileptic convulsion except one. The logistic regression, support vector, and naive Bayes models performed similarly, outperforming the decision-tree model. We chose the logistic regression model for its interpretability and implementability. The area under the receiver operator curve (AUC) was 0·92 (95% CI 0·91-0·94, sensitivity 85·0%, specificity 93·7%) in the internal-validation dataset and 0·95 (0·92-0·98, sensitivity 97·5%, specificity 82·4%) in the external-validation dataset. Similar results were observed for the LOSO model (AUC 0·94, 0·93-0·96, sensitivity 88·2%, specificity 95·3%). On the basis of these findings, we developed the Epilepsy Diagnostic Companion as a predictive model and app offering a validated culture-specific and region-specific solution to confirm the diagnosis of a convulsive epileptic seizure in people with suspected epilepsy. The questionnaire panel is simple and accessible for health-care workers without specialist knowledge to administer. This tool can be iteratively updated and could lead to earlier, more accurate diagnosis of seizures and improve care for people with epilepsy. The Wellcome Trust, the UK National Institute of Health Research, and the Oxford NIHR Biomedical Research Centre.

Transcriptomic data in tumor-adjacent normal tissues harbor prognostic information on multiple cancer types.

In identifying prognostic markers in cancer, the roles of tumor-adjacent normal tissues are often confined to drawing expression differences between tumor and normal tissues rather than being treated as the main targets of investigations. Thus, differential expression analysis between tumors and adjacent normal tissues is performed prior to prognostic analysis in previous studies. However, recent studies have suggested that the prognostic relevance of differentially expressed genes (DEGs) is insignificant for some cancers, contradicting conventional approaches METHODS: This study investigated the prognostic efficacy of transcriptomic data from tumors and adjacent normal tissues using The Cancer Genome Atlas dataset. Prognostic analysis using Cox regression models and survival prediction using machine-learning models and feature selection methods were employed. The results revealed that for kidney, liver, and head and neck cancer, adjacent normal tissues harbored higher proportions of prognostic genes and exhibited better survival prediction performance than tumor tissues and DEGs in machine-learning models. Furthermore, the application of a distance correlation-based feature selection method to kidney and liver cancer using external datasets revealed that the selected genes for adjacent normal tissues exhibited higher prediction performance than those for tumor tissues. The study results suggest that the expression levels of genes in adjacent normal tissues are potential prognostic markers. The source code of this study is available at https://github.com/DMCB-GIST/Survival_Normal.

Empirical evaluation of the performance of data sampling and feature selection techniques for software fault prediction

Context:The application of Software Fault Prediction (SFP) in the software development life cycle to predict the faulty class at the early stage has piqued the interest of various scholars. In the SFP domain, during research analysis, it got realized that there has been very little work instigated on addressing both class imbalance and feature redundancy problems jointly to enhance the performance and prediction accuracy of SFP models. It has been perceived in the literature survey the study of droughts with the comprehensive comparative analysis of different sampling and feature selection strategies together. Objective:This research builds an extensive assessment of distinct combinations of different feature selection and sampling approaches, to effectively overcome the problems of class overlap, class imbalance, and feature redundancy. The objective is to determine the best combination that will produce results with a higher degree of accuracy and an effective SFP model. Method:Considering the above erudition, the study has applied 8 different sampling techniques along with 10 feature selection algorithms against 56 open-source projects. The comparative analysis is performed against 5346 variants of input datasets by applying 8 different classifiers to predict the faulty class. In addition, the research paper presents an intensive assessment and performance of these techniques individually against all the input projects. We have considered accuracy and Area Under the ROC (receiver operating characteristic curve) Curve (AUC) performance metrics to compare the performance of different models developed using the classification algorithm. Result:For each project in the proposed work, we evaluated a total of 792 combinations that were produced using 10 feature selection methods, 1 all metrics dataset, 8 sampling methods, 1 original, unsampled dataset, and 8 classifiers. The empirical result indicates that, against 21 projects out of 54 projects, Synthetic Minority Over Sampling Technique Edited (SMOTEE) with correlation-based feature selection (FS2) combination outperformed with the highest AUC value which is 38.89 % of projects. Additionally, according to experimental results, the highest AUC values were attained by 24.07 % of projects using the SMOTEE, FS2, and RF combination. Conclusion:The results of the statical analysis test reveal that 93.42 % of the combinational pairs of different sampling and feature selection approaches demonstrated a significant variance in the performance of the distinct combinations of sampling and feature selection techniques. The empirical result indicates the performance of the SFP Model is adversely impacted by class imbalance and irrelevance. The outcome indicates for more than 75% of projects, the performance of trained models improved with an AUC value between a range of 0.805 to 0.99 post-application of sampling and feature selection strategies, in comparison without the use of feature selection and sampling techniques.

A Multi-level Random Forest Model-Based Intrusion Detection Using Fuzzy Inference System for Internet of Things Networks

Intrusion detection (ID) methods are security frameworks designed to safeguard network information systems. The strength of an intrusion detection method is dependent on the robustness of the feature selection method. This study developed a multi-level random forest algorithm for intrusion detection using a fuzzy inference system. The strengths of the filter and wrapper approaches are combined in this work to create a more advanced multi-level feature selection technique, which strengthens network security. The first stage of the multi-level feature selection is the filter method using a correlation-based feature selection to select essential features based on the multi-collinearity in the data. The correlation-based feature selection used a genetic search method to choose the best features from the feature set. The genetic search algorithm assesses the merits of each attribute, which then delivers the characteristics with the highest fitness values for selection. A rule assessment has also been used to determine whether two feature subsets have the same fitness value, which ultimately returns the feature subset with the fewest features. The second stage is a wrapper method based on the sequential forward selection method to further select top features based on the accuracy of the baseline classifier. The selected top features serve as input into the random forest algorithm for detecting intrusions. Finally, fuzzy logic was used to classify intrusions as either normal, low, medium, or high to reduce misclassification. When the developed intrusion method was compared to other existing models using the same dataset, the results revealed a higher accuracy, precision, sensitivity, specificity, and F1-score of 99.46%, 99.46%, 99.46%, 93.86%, and 99.46%, respectively. The classification of attacks using the fuzzy inference system also indicates that the developed method can correctly classify attacks with reduced misclassification. The use of a multi-level feature selection method to leverage the advantages of filter and wrapper feature selection methods and fuzzy logic for intrusion classification makes this study unique.

Network intrusion detection using data dimensions reduction techniques

Due to the increasing growth of the Internet and its widespread application, the number of attacks on the network has also increased. Therefore, maintaining network security and using intrusion detection systems is of critical importance. The connection between devices leads to a large number of data being generated and saved. The era of “big data” emerges over time. This paper presents a new method for selecting effective features on network intrusion detection based on the concept of fuzzy numbers and scoring methods based on correlation feature selection for intrusion detection systems. The goal of this paper is to present a new approach for reducing data size using the concept of fuzzy numbers and scoring methods based on correlation feature selection for intrusion detection systems. In this method, to eliminate inefficient features and reduce data dimensions, number of features are defined as a fuzzy number, and the heuristic function of the correlation-based feature selection algorithm is expressed as a triangular fuzzy number membership function. To evaluate the proposed method, it is then compared to previous intrusion detection methods. The results show that the proposed method selects several features less than the conventional methods with a higher detection rate. The proposed method is compared with the correlation-based feature selection method on two datasets. The proposed method is evaluated and validated on KDD Cup, NSL-KDD and CICIDS datasets. The achieved accuracy is 99.9% which is 96.01% with CFS method.

Improved Stress Classification Using Automatic Feature Selection from Heart Rate and Respiratory Rate Time Signals

Time-series features are the characteristics of data periodically collected over time. The calculation of time-series features helps in understanding the underlying patterns and structure of the data, as well as in visualizing the data. The manual calculation and selection of time-series feature from a large temporal dataset are time-consuming. It requires researchers to consider several signal-processing algorithms and time-series analysis methods to identify and extract meaningful features from the given time-series data. These features are the core of a machine learning-based predictive model and are designed to describe the informative characteristics of the time-series signal. For accurate stress monitoring, it is essential that these features are not only informative but also well-distinguishable and interpretable by the classification models. Recently, a lot of work has been carried out on automating the extraction and selection of times-series features. In this paper, a correlation-based time-series feature selection algorithm is proposed and evaluated on the stress-predict dataset. The algorithm calculates a list of 1578 features of heart rate and respiratory rate signals (combined) using the tsfresh library. These features are then shortlisted to the more specific time-series features using Principal Component Analysis (PCA) and Pearson, Kendall, and Spearman correlation ranking techniques. A comparative study of conventional statistical features (like, mean, standard deviation, median, and mean absolute deviation) versus correlation-based selected features is performed using linear (logistic regression), ensemble (random forest), and clustering (k-nearest neighbours) predictive models. The correlation-based selected features achieved higher classification performance with an accuracy of 98.6% as compared to the conventional statistical feature’s 67.4%. The outcome of the proposed study suggests that it is vital to have better analytical features rather than conventional statistical features for accurate stress classification.

Photoplethysmography Signal Wavelet Enhancement and Novel Features Selection for Non-Invasive Cuff-Less Blood Pressure Monitoring.

In this paper, new features relevant to blood pressure (BP) estimation using photoplethysmography (PPG) are presented. A total of 195 features, including the proposed ones and those already known in the literature, have been calculated on a set composed of 50,000 pulses from 1080 different patients. Three feature selection methods, namely Correlation-based Feature Selection (CFS), RReliefF and Minimum Redundancy Maximum Relevance (MRMR), have then been applied to identify the most significant features for BP estimation. Some of these features have been extracted through a novel PPG signal enhancement method based on the use of the Maximal Overlap Discrete Wavelet Transform (MODWT). As a matter of fact, the enhanced signal leads to a reliable identification of the characteristic points of the PPG signal (e.g., systolic, diastolic and dicrotic notch points) by simple means, obtaining results comparable with those from purposely defined algorithms. For systolic points, mean and std of errors computed as the difference between the locations obtained using a purposely defined already known algorithm and those using the MODWT enhancement are, respectively, 0.0097 s and 0.0202 s; for diastolic points they are, respectively, 0.0441 s and 0.0486 s; for dicrotic notch points they are 0.0458 s and 0.0896 s. Hence, this study leads to the selection of several new features from the MODWT enhanced signal on every single pulse extracted from PPG signals, in addition to features already known in the literature. These features can be employed to train machine learning (ML) models useful for estimating systolic blood pressure (SBP) and diastolic blood pressure (DBP) in a non-invasive way, which is suitable for telemedicine health-care monitoring.

Quantitative Prediction of Inorganic Nanomaterial Cellular Toxicity via Machine Learning.

Organic chemistry has seen colossal progress due to machine learning (ML). However, the translation of artificial intelligence (AI) into materials science is challenging, where biological behavior prediction becomes even more complicated. Nanotoxicity is a critical parameter that describes their interaction with the living organisms screened in every bio-related research. To prevent excessive experiments, such properties have to be pre-evaluated. Several existing ML models partially fulfill the gap by predicting whether a nanomaterial is toxic or not. Yet, this binary categorization neglects the concentration dependencies crucial for experimental scientists. Here, an ML-based approach is proposed to the quantitative prediction of inorganic nanomaterial cytotoxicity achieving the precision expressed by 10-fold cross-validation (CV) Q2 = 0.86 with the root mean squared error (RMSE) of 12.2% obtained by the correlation-based feature selection and grid search-based model hyperparameters optimization. To provide further model flexibility, quantitative atom property-based nanomaterial descriptors are introduced allowing the model to extrapolate on unseen samples. Feature importance is calculated to find an interpretable model with optimal decision-making. These findings allow experimental scientists to perform primary in silico candidate screening and minimize the number of excessive, labor-intensive experiments enabling the rapid development of nanomaterials for medicinal purposes.

SMMO-CoFS: Synthetic Multi-minority Oversampling with Collaborative Feature Selection for Network Intrusion Detection System

Researchers publish various studies to improve the performance of network intrusion detection systems. However, there is still a high false alarm rate and missing intrusions due to class imbalance in the multi-class dataset. This imbalanced distribution of classes results in low detection accuracy for the minority classes. This paper proposes a Synthetic Multi-minority Oversampling (SMMO) framework by integrating with a collaborative feature selection (CoFS) approach in network intrusion detection systems. Our framework aims to increase the detection accuracy of the extreme minority classes (i.e., user-to-root and remote-to-local attacks) by improving the dataset’s class distribution and selecting relevant features. In our framework, SMMO generates synthetic data and iteratively over-samples multi-minority classes. And the collaboration of correlation-based feature selection with an evolutionary algorithm selects essential features. We evaluate our framework with a random forest, J48, BayesNet, and AdaBoostM1. In a multi-class NSL-KDD dataset, the experimental results show that the proposed framework significantly improves the detection accuracy of the extreme minority classes compared with other approaches.

Tree species classification in a typical natural secondary forest using UAV-borne LiDAR and hyperspectral data

ABSTRACT Recent growth in unmanned aerial vehicle (UAV) technology have promoted the detailed mapping of individual tree species. However, the in-depth mining and comprehending of the significance of features derived from high-resolution UAV data for tree species discrimination remains a difficult task. In this study, a state-of-the-art approach combining UAV-borne light detection and ranging (LiDAR) and hyperspectral was used to classify 11 common tree species in a typical natural secondary forest in Northeast China. First, comprehensive relevant structural and spectral features were extracted. Then, the most valuable feature sets were selected by using a hybrid approach combining correlation-based feature selection with the optimized recursive feature elimination algorithm. The random forest algorithm was used to assess feature importance and perform the classification. Finally, the robustness of features derived from point clouds with different structures and hyperspectral images with different spatial resolutions was tested. Our results showed that the best classification accuracy was obtained by combining LiDAR and hyperspectral data (75.7%) compared to that based on LiDAR (60.0%) and hyperspectral (64.8%) data alone. The mean intensity of single returns and the visible atmospherically resistant index for red-edge band were the most influential LiDAR and hyperspectral derived features, respectively. The selected features were robust in point clouds with a density not lower than 5% (~5 pts/m2) and a resolution not lower than 0.3 m in hyperspectral data. Although canopy surface features were slightly different from original LiDAR features, canopy surface information was also important for tree species classification. This study proved the capabilities of UAV-borne LiDAR and hyperspectral data in natural secondary forest tree species discrimination and the potential for this approach to be transferable to other study areas.

Comparison of Logistic Regression and Random Forest using Correlation-based Feature Selection for Phishing Website Detection

The world is currently experiencing mass developments in information technology, especially during the current pandemic, which requires all of us to learn and even work online. They are triggered much crime in the internet world. One of them is stealing internet user data through a fake website built like the original or called a phishing website. In this research , a classification model is needed to detect phishing websites using the best performance from one of the logistic regression and random forest classification algorithms to overcome the rise of phishing websites in cyberspace. Classification performance can be improved using the correlation-based feature selection (CFS) method to select the most influential attribute in detecting web phishing . Based on the test results, applying the logistic regression and random forest classification algorithm in the classification of web phishing resulted in an accuracy of 93.035% and 96.834%. After feature selection with CFS, the accuracy was 92.718% and 97.015%, respectively. On the Testing, There was an increase in accuracy in RandomForest by 0.181% and an insignificant decrease in logistic regression. The test results prove that feature selection with CFS can eliminate redundant attributes and the resulting classification algorithm accuracy is not much different when the details are complete and Random Forest has accuracy better than after using CSF . Keywords : website phis h ing, classification, logistic regression, random forest, correlation-based