Effective Feature Selection Method Research Articles

Feature Selection and Regression Models for Multisource Data-Based Soil Salinity Prediction: A Case Study of Minqin Oasis in Arid China

(1) Monitoring salinized soil in saline–alkali land is essential, requiring regional-scale soil salinity inversion. This study aims to identify sensitive variables for predicting electrical conductivity (EC) in soil, focusing on effective feature selection methods. (2) The study systematically selects a feature subset from Sentinel-1 C SAR, Sentinel-2 MSI, and SRTM DEM data. Various feature selection methods (correlation analysis, LASSO, RFE, and GRA) are employed on 79 variables. Regression models using random forest regression (RF) and partial least squares regression (PLSR) algorithms are constructed and compared. (3) The results highlight the effectiveness of the RFE algorithm in reducing model complexity. The model incorporates significant environmental factors like soil moisture, topography, and soil texture, which play an important role in modeling. Combining the method with RF improved soil salinity prediction (R2 = 0.71, RMSE = 1.47, RPD = 1.84). Overall, salinization in Minqin oasis soils was evident, especially in the unutilized land at the edge of the oasis. (4) Integrating data from different sources to construct characterization variables overcomes the limitations of a single data source. Variable selection is an effective means to address the redundancy of variable information, providing insights into feature engineering and variable selection for soil salinity estimation in arid and semi-arid regions.

Improve the prediction in the digital Era: Causal feature selection with minimum redundancy

Effective decision-making in complex environments requires discerning the relevant from the irrelevant, a challenge that becomes pronounced with large multivariate time-series data. However, existing feature selection algorithms often suffer from complexity and a lack of interpretability, making it difficult for decision-makers to extract value, manage risks, and adhere to compliance regulations in a thoroughly explainable way. To address these challenges, we propose a novel causality-based feature selection technique that embeds an explainable unsupervised feature selection algorithm. We refer to our proposed method as Causal Feature Selection with Minimum Redundancy (CFSMR). Our method yields a minimum viable feature set without compromising model performance while ensuring interpretability. We conduct an experimental study to compare the proposed technique with conventional feature selection techniques. Our results demonstrate that our proposed method outperforms or performs on par with existing techniques, making it a promising approach for decision-makers seeking an effective and interpretable feature selection method.

Predicting lodging severity in dry peas using UAS-mounted RGB, LIDAR, and multispectral sensors

This study investigated the feasibility of using data collected by sensors mounted onto unmanned aerial systems (UASs) and traditional classification methods (Maximum Likelihood, Mahalanobis Distance, Minimum Distance, and Adaptive Coherence Estimator) and four machine learning models (Random Forest [RF], Support Vector Machine [SVM], K-Nearest Neighbor [KNN], and Extreme Gradient Boosting [XGBOOST]) to predict the severity of dry pea lodging. Data were collected in two environments in North Dakota during the 2022 crop season, where lodging was visually estimated at the plot level using a lodging scale range of 0 to 9. Aerial images were collected using two UASs (DJI Matrice 200 and 300) during early, mid, and late stages of growth. Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors (SMOTE-ENN) was used to balance the imbalanced dataset. Different feature selection models (recursive feature elimination, lasso regression, principal component analysis, and correlation-based methods) were used and compared to identify the most important features in the dataset. Our study found that similar channels can be used interchangeably for analyzing lodging without compromising accuracy, simplifying data acquisition, and saving time and resources. The maximum plant height values obtained from LiDAR and RGB sensors showed a strong correlation with actual values. Recursive feature elimination was the most effective feature selection method for handling high-dimensional datasets. The XGBOOST model outperformed all traditional and machine learning classification models, with the lowest variation in precision values. RF showed the most pronounced overfitting among the machine learning models, while Mahalanobis distance showed the least overfitting among all traditional classification models. Overall, the study demonstrated the potential of UAS and machine learning models for predicting lodging severity in dry peas, with XGBOOST being the best-performing model.

Thorough Assessment of Machine Learning Techniques for Predicting Protein-Nucleic Acid Binding Hot Spots

Background: Proteins and nucleic acids are vital biomolecules that contribute significantly to biological life. The precise and efficient identification of hot spots at protein-nucleic acid interfaces is crucial for guiding drug development, advancing protein engineering, and exploring the underlying molecular recognition mechanisms. As experimental methods like alanine scanning mutagenesis prove to be time-consuming and expensive, a growing number of machine learning techniques are being employed to predict hot spots. However, the existing approach is distinguished by a lack of uniform standards, a scarcity of data, and a wide range of attributes. Currently, there is no comprehensive overview or evaluation of this field. As a result, providing a full overview and review is extremely helpful. Methods: In this study, we present an overview of cutting-edge machine learning approaches utilized for hot spot prediction in protein-nucleic acid complexes. Additionally, we outline the feature categories currently in use, derived from relevant biological data sources, and assess conventional feature selection methods based on 600 extracted features. Simultaneously, we create two new benchmark datasets, PDHS87 and PRHS48, and develop distinct binary classification models based on these datasets to evaluate the advantages and disadvantages of various machine-learning techniques. Results: Prediction of protein-nucleic acid interaction hotspots is a challenging task. The study demonstrates that structural neighborhood features play a crucial role in identifying hot spots. The prediction performance can be improved by choosing effective feature selection methods and machine learning methods. Among the existing prediction methods, XGBPRH has the best performance. Conclusion: It is crucial to continue studying hot spot theories, discover new and effective features, add accurate experimental data, and utilize DNA/RNA information. Semi-supervised learning, transfer learning, and ensemble learning can optimize predictive ability. Combining computational docking with machine learning methods can potentially further improve predictive performance.

Detecting cyberthreats in Metaverse learning platforms using an explainable DNN

The rapid integration of the Internet of Artificial Intelligence and Internet of Things (AI-IoT) technologies has given rise to a pivotal element of the upcoming digital era, the Metaverse. This confluence has significantly impacted virtual learning platforms by introducing enhanced, immersive, and interactive environments for learners, educators, and institutions. However, the growing reliance on Metaverse necessitates robust cybersecurity measures to detect and mitigate cyber threats and ensure the safety of users. This paper proposes an explainable deep neural network (DNN) designed to identify and address network intrusion attacks within Metaverse learning environments. By leveraging the latest cybersecurity IoT datasets and employing an effective feature selection method, this study provides a visually interpretable, trustworthy, and quantitative explanation of the network intrusion detection system (NIDS) model using Shapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanation (LIME) explainability methods. The adopted explainable DNN, capable of processing network traffic features from interconnected Metaverse devices and IoT sensors, can facilitate accurate and comprehensible remediation of anomalous from benign activities within Metaverse. The NIDS model yields a high performing accuracy of 99.9% for establishing a more secure and trustworthy metaverse learning environment.

A comparative study on deep feature selection methods for skin lesion classification

AbstractMelanoma, a widespread and hazardous form of cancer, has prompted researchers to prioritize dermoscopic image‐based algorithms for classifying skin lesions. Recently, there has been a growing trend in using pre‐trained convolutional neural networks for detecting skin lesions. However, the features extracted from these classifiers may include irrelevant elements, emphasizing the importance of implementing effective feature selection methods. Nevertheless, there has not been a comprehensive study on feature selection methods to enhance the performance of skin lesion detection to date. To identify the most efficient methods, a diverse set of feature selection techniques, including filter, wrapper, embedded, and dimensionality reduction, were applied to images from two well‐known datasets, namely ISIC 2017 and ISIC 2018. According to the results, models trained with features chosen by wrapper techniques outperformed those trained with features chosen by filter and embedded methods. Achieving an accuracy of 0.8333 and an F1‐Score of 0.8291 for the ISIC 2017 dataset, and an F1‐Score of 0.9324 and an accuracy of 0.9350 for the ISIC 2018 dataset, the classification using features obtained via the GWO feature selection technique performed the best.

Neighborhood multigranulation rough sets for cost-sensitive feature selection on hybrid data

Feature selection is a vital preprocessing step in real applications of data mining and machine learning. With the prevalence of high-dimensional hybrid data sets in real-world scenarios, along with the presence of test costs and misclassification costs, the need for effective feature selection methods has become more prominent. However, existing feature selection approaches mainly focus on cost-sensitive data from a single granularity perspective, and they are primarily applicable to single-typed data sets. To address these limitations, this paper presents a novel feature selection approach specifically designed for hybrid data, considering variable test costs and misclassification costs. The proposed method is based on neighborhood multigranulation rough sets (NMRS), which provides more comprehensive and multi-angle data analysis for cost-sensitive hybrid data. First, a novel multigranulation model is developed to effectively process cost-sensitive hybrid data. Building upon this model, a cost-based multi-criteria measure is proposed to evaluate the significance of features. This measure takes into account the comprehensive information of candidate features, including their power in algebraic view, information view, and associated costs. Furthermore, a heuristic feature selection algorithm based on NMRS is proposed to handle hybrid data with the test costs and misclassification costs. This algorithm leverages the benefits of the proposed multigranulation model and cost-based measure to identify the most discriminative features efficiently. Finally, the experimental results on twelve different datasets show that the proposed heuristic algorithm outperforms other compared algorithms, especially in total cost and classification accuracy.

A Comparative Study Of Algorithmic Efficiency Of Feature Selection Algorithm On Microarray

A key challenge before classification can take place is feature selection. An effective feature selection method would increase classification accuracy and simultaneously reduce computation costs and time. A variety of filter approaches, along with different search algorithms, were considered in this study. Five traditional classifiers were evaluated on the selected gene subsets: Random Forest, Sequential minimal optimization algorithm, Naive Bayes, Decision Trees, and K-Nearest Neighbour. The datasets chosen for this analysis are the microarray gene expression data of two types of cancers: Acute Lymphocytic Leukaemia (ALL)/Acute Myeloid Leukaemia (AML) and Lung cancer. According to the experimental results, a fuzzy rough subset combined with Genetic Search selects optimal relevant gene subsets and produces significantly good classifier accuracy. Compared to classical classifiers described here, this research finds that Random Forest classifiers yield 94.33% on the raw dataset and 100% classifier accuracy after applying feature selection methods. Utilizing conventional methods like Precision, Recall, F-Score, and Region of Characteristics, MCC Matthews correlation coefficient, results are validated.

An effective hybrid feature selection using entropy weight method for automatic sleep staging

Objective. Sleep staging is the basis for sleep quality assessment and diagnosis of sleep-related disorders. In response to the inadequacy of traditional manual judgement of sleep stages, using machine learning techniques for automatic sleep staging has become a hot topic. To improve the performance of sleep staging, numerous studies have extracted a large number of sleep-related characteristics. However, there are redundant and irrelevant features in the high-dimensional features that reduce the classification accuracy. To address this issue, an effective hybrid feature selection method based on the entropy weight method is proposed in this paper for automatic sleep staging. Approach. Firstly, we preprocess the four modal polysomnography (PSG) signals, including electroencephalogram (EEG), electrooculogram (EOG), electrocardiogram (ECG) and electromyogram (EMG). Secondly, the time domain, frequency domain and nonlinear features are extracted from the preprocessed signals, with a total of 185 features. Then, in order to acquire characteristics of the multi-modal signals that are highly correlated with the sleep stages, the proposed hybrid feature selection method is applied to choose effective features. This method is divided into two stages. In stage I, the entropy weight method is employed to combine two filter methods to build a subset of features. This stage evaluates features based on information theory and distance metrics, which can quickly obtain a subset of features and retain the relevant features. In stage II, Sequential Forward Selection is used to evaluate the subset of features and eliminate redundant features. Further more, to achieve better performance of classification, an ensemble model based on support vector machine, K-nearest neighbor, random forest and multilayer perceptron is finally constructed for classifying sleep stages. Main results. The experiment using the Cyclic Alternating Pattern (CAP) sleep database is performed to assess the performance of the method proposed in this paper. The proposed hybrid feature selection method chooses only 30 features highly correlated to sleep stages. The accuracy, F1 score and Kappa coefficient of 6 class sleep staging reach 88.86%, 83.15% and 0.8531%, respectively. Significance. Experimental results show the effectiveness of the proposed method compared to the existing state-of-the-art studies. It greatly reduces the number of features required while achieving outstanding auto-sleep staging results.

Machine learning (ML) techniques to predict breast cancer in imbalanced datasets: a systematic review.

Knowledge discovery in databases (KDD) is crucial in analyzing data to extract valuable insights. In medical outcome prediction, KDD is increasingly applied, particularly in diseases with high incidence, mortality, and costs, like cancer. ML techniques can develop more accurate predictive models for cancer patients' clinical outcomes, aiding informed healthcare decision-making. However, cancer prediction modeling faces challenges because of the unbalanced nature of the datasets, where there is a small minority category of patients with a cancer diagnosis compared to a majority category of cancer-free patients. Imbalanced datasets pose statistical hurdles like bias and overfitting when developing accurate prediction models. This systematic review focuses on breast cancer prediction articles published from 2008 to 2023. The objective is to examine ML methods used in three critical steps of KDD: preprocessing, data mining, and interpretation which address the imbalanced data problem in breast cancer prediction. This work synthesizes prior research in ML methods for breast cancer prediction. The findings help identify effective preprocessing strategies, including balancing and feature selection methods, robust predictive models, and evaluation metrics of those models. The study aims to inform healthcare providers and researchers about effective techniques for accurate breast cancer prediction.

Nested ensemble selection: An effective hybrid feature selection method

It has been shown that while feature selection algorithms are able to distinguish between relevant and irrelevant features, they fail to differentiate between relevant and redundant and correlated features. To address this issue, we propose a highly effective approach, called Nested Ensemble Selection (NES), that is based on a combination of filter and wrapper methods. The proposed feature selection algorithm differs from the existing filter-wrapper hybrid methods in its simplicity and efficiency as well as precision. The new algorithm is able to separate the relevant variables from the irrelevant as well as the redundant and correlated features. Furthermore, we provide a robust heuristic for identifying the optimal number of selected features which remains one of the greatest challenges in feature selection. Numerical experiments on synthetic and real-life data demonstrate the effectiveness of the proposed method. The NES algorithm achieves perfect precision on the synthetic data and near optimal accuracy on the real-life data. The proposed method is compared against several popular algorithms including mRMR, Boruta, genetic, recursive feature elimination, Lasso, and Elastic Net. The results show that NES significantly outperforms the benchmarks algorithms especially on multi-class datasets.

Cardiovascular Disorder Detection with a PSO-Optimized Bi-LSTM Recurrent Neural Network Model

The medical community is facing ever-increasing difficulties in identifying and treating cardiovascular diseases. The World Health Organization (WHO) reports that despite the availability of numerous high-priced medical remedies for persons with heart problems, CVDs continue to be the main cause of mortality globally, accounting for over 21 million deaths annually. When cardiovascular diseases are identified and treated early on, they cause far fewer deaths. Deep learning models have facilitated automated diagnostic methods for early detection of these diseases. Cardiovascular diseases often present insidious symptoms that are difficult to identify in a timely manner. Prompt diagnosis of individuals with CVD and related conditions, such as high blood pressure or high cholesterol, is crucial to initiate appropriate treatment. Recurrent neural networks (RNNs) with gated recurrent units (GRUs) have recently emerged as a more advanced variant, capable of surpassing Long Short-Term Memory (LSTM) models in several applications. When compared to LSTMs, GRUs have the advantages of faster calculation and less memory usage. When it comes to CVD prediction, the bio-inspired Particle Swarm Optimization (PSO) algorithm provides a straightforward method of getting the best possible outcomes with minimal effort. This stochastic optimization method requires neither the gradient nor any differentiated form of the objective function and emulates the behaviour and intelligence of swarms. PSO employs a swarm of agents, called particles, that navigate the search space to find the best prediction type.This study primarily focuses on predicting cardiovascular diseases using effective feature selection and classification methods. For CVD forecasting, we offer a GRU model built on recurrent neural networks and optimized with particle swarms (RNN-GRU-PSO). We find that the proposed model significantly outperforms the state-of-the-art models (98.2% accuracy in predicting cardiovascular diseases) in a head-to-head comparison.

A COPRAS-based Approach to Multi-Label Feature Selection for Text Classification

In this article, we present a novel approach for text classification feature selection using a pseudo-relation matrix constructed with ridge regression. This approach involves generating a matrix that captures the relationship between features and target variables and then using that matrix to create a multi-criteria decision making (MCDM) problem. We then utilize the Complex Proportional Assessment (COPRAS) method to rank features in order of importance. To assess the performance of our proposed algorithm, we conduct tests on ten real-world text datasets and compare our results to the existing methods. Our findings indicate that the proposed approach outperforms other methods, and we provide statistical significance to support our claims. Our proposed algorithm provides a viable answer for researchers looking for efficient and effective feature selection methods for text data analysis, which can lead to a better understanding and interpretation of the underlying text.

An optimized machine learning method for predicting wogonin therapy for the treatment of pulmonary hypertension

Human health is at risk from pulmonary hypertension (PH), characterized by decreased pulmonary vascular resistance and constriction of the pulmonary vessels, resulting in right heart failure and dysfunction. Thus, preventing PH and monitoring its progression before treating it is vital. Wogonin, derived from the leaves of Scutellaria baicalensis Georgi, exhibits remarkable pharmacological activity. In this study, we examined the effectiveness of wogonin in mitigating the progression of PH in mice using right heart catheterization and hematoxylin-eosin (HE) staining. As an alternative to minimize the possibility of harming small animals, we present a scientifically effective feature selection method (BSCDWOA-KELM) that will allow us to develop a novel simpler noninvasive prediction method for wogonin in treating PH. In this method, we use the proposed enhanced whale optimizer (SCDWOA) in conjunction with the kernel extreme learning machine (KELM). Initially, we let SCDWOA perform global optimization experiments on the IEEE CEC2014 benchmark function set to verify its core advantages. Lastly, 12 public and PH datasets are examined for feature selection experiments using BSCDWOA-KELM. As shown in the experimental results for global optimization, the proposed SCDWOA has better convergence performance. Meanwhile, the proposed binary SCDWOA (BSCDWOA) significantly improves the ability of KELM to classify data. By utilizing the BSCDWOA-KELM, key indicators such as the Red blood cell (RBC), the Haemoglobin (HGB), the Lymphocyte percentage (LYM%), the Hematocrit (HCT), and the Red blood cell distribution width-size distribution (RDW-SD) can be efficiently screened in the Pulmonary hypertension dataset, and one of its most essential points is its accuracy of greater than 0.98. Consequently, the BSCDWOA-KELM introduced in this study can be used to predict wogonin therapy for treating pulmonary hypertension in a simple and noninvasive manner.

ADscreen: A speech processing-based screening system for automatic identification of patients with Alzheimer's disease and related dementia

Alzheimer's disease and related dementias (ADRD) present a looming public health crisis, affecting roughly 5 million people and 11 % of older adults in the United States. Despite nationwide efforts for timely diagnosis of patients with ADRD, >50 % of them are not diagnosed and unaware of their disease. To address this challenge, we developed ADscreen, an innovative speech-processing based ADRD screening algorithm for the protective identification of patients with ADRD. ADscreen consists of five major components: (i) noise reduction for reducing background noises from the audio-recorded patient speech, (ii) modeling the patient's ability in phonetic motor planning using acoustic parameters of the patient's voice, (iii) modeling the patient's ability in semantic and syntactic levels of language organization using linguistic parameters of the patient speech, (iv) extracting vocal and semantic psycholinguistic cues from the patient speech, and (v) building and evaluating the screening algorithm. To identify important speech parameters (features) associated with ADRD, we used the Joint Mutual Information Maximization (JMIM), an effective feature selection method for high dimensional, small sample size datasets. Modeling the relationship between speech parameters and the outcome variable (presence/absence of ADRD) was conducted using three different machine learning (ML) architectures with the capability of joining informative acoustic and linguistic with contextual word embedding vectors obtained from the DistilBERT (Bidirectional Encoder Representations from Transformers). We evaluated the performance of the ADscreen on an audio-recorded patients' speech (verbal description) for the Cookie-Theft picture description task, which is publicly available in the dementia databank. The joint fusion of acoustic and linguistic parameters with contextual word embedding vectors of DistilBERT achieved F1-score = 84.64 (standard deviation [std] = ±3.58) and AUC-ROC = 92.53 (std = ±3.34) for training dataset, and F1-score = 89.55 and AUC-ROC = 93.89 for the test dataset. In summary, ADscreen has a strong potential to be integrated with clinical workflow to address the need for an ADRD screening tool so that patients with cognitive impairment can receive appropriate and timely care.

Feasibility of local interpretable model-agnostic explanations (LIME) algorithm as an effective and interpretable feature selection method: comparative fNIRS study.

Many feature selection methods have been evaluated in functional near-infrared spectroscopy (fNIRS)-related studies. The local interpretable model-agnostic explanation (LIME) algorithm is a feature selection method for fNIRS datasets that has not yet been validated; the demand for its validation is increasing. To this end, we assessed the feature selection performance of LIME for fNIRS datasets in terms of classification accuracy. A comparative analysis was conducted for the benchmark (classification accuracy obtained without applying any feature selection method), LIME, two filter-based methods (minimum-redundancy maximum-relevance and t-test), and one wrapper-based method (sequential forward selection). To ensure the fairness and reliability of the performance evaluation, several open-access fNIRS datasets were used. The analysis revealed that LIME greatly outperformed the other feature selection methods in most cases and could achieve a statistically significantly better classification accuracy than that of the benchmark methods. These findings implied the effectiveness of LIME as a feature selection approach for fNIRS datasets.

Series Arc Fault Detection Based on Dual Filtering Feature Selection and Improved Hierarchical Clustering Sensitive Component Selection

Affected by the downstream load of the line, the low-voltage AC series arc fault signal presents nonlinear, non-stationary and random characteristics, which bring great difficulties to the extraction of arc fault features and lead to low arc detection accuracy. To solve this problem, a low-voltage AC series arc fault detection method based on strong discriminative features and sensitive components is proposed. In this work, firstly, the arc fault current signal is collected based on the self-built experimental platform, and the arc fault current components are obtained by the complete ensemble empirical mode decomposition with the adaptive noise (CEEMDAN) method. Secondly, 16 feature indexes based on time window are used to describe the component signals, and an effective feature selection method based on the maximum mutual information coefficient and the significance of feature changes is proposed to realize the mining of highly identifiable features. Then, an improved hierarchical clustering algorithm and a sensitive component selection strategy combining the saliency of feature changes are proposed to eliminate the interference of redundant components. Finally, a strong discriminative feature library of sensitive components of current signal is constructed, and series arc fault detection is realized based on support vector machine. Experimental results show that the proposed method is feasible and effective in arc current feature extraction and fault detection, and provides a reference for low-voltage AC series arc fault detection.

IOFS-SA: An interactive online feature selection tool for survival analysis

Background:Survival analysis is a primary problem before clinical treatments to cancer patients after their operations. In order to make this kind of analysis simple, many corresponding tools have been proposed. Though these tools are easy to use, there exist still two fatal flaws. One is that sample grouping is commonly empirical and wrongly based on original gene expressions or survival time. The other is that their feature selection methods mostly depend univariate semi-supervised regression or the multivariate one without considering the small sample size compared with the high dimension. Objective:In order to solve the two problems, we design an automatic feature selection web tool which can also satisfy interactive sample grouping. Methods:An automatic feature selection is performed on user-defined data or TCGA data. users can also perform manual feature selection. Then, hierarchical clustering is used and an automatic re-clustering strategy is proposed after interactive risk score split. Kaplan–Meier survival curve and log-rank test are utilized as the measurement. Results:Experimental results on 53 datasets from TCGA demonstrate the effectiveness of our method. The tree view, heat map and scatter map can intuitively display the result of the selected genes to the doctors for further research. Conclusions:This method is suitable for survival analysis of high-dimensional small sample data sets. At the same time, it also provides a platform for researchers to analyze custom data. It solves the problems of the existing web tools and provides an effective feature selection method for survival analysis. Availability:The full code package is freely available and can be downloaded at https://github.com/Yuan-23/IOFS-SA-ecp-data-main, and the online version at https://bioinfor.nefu.edu.cn/IOFS-SA/ is ready for use freely.

Multi-dimensional variables and feature parameter selection for aboveground biomass estimation of potato based on UAV multispectral imagery.

Aboveground biomass (AGB) is an essential assessment of plant development and guiding agricultural production management in the field. Therefore, efficient and accurate access to crop AGB information can provide a timely and precise yield estimation, which is strong evidence for securing food supply and trade. In this study, the spectral, texture, geometric, and frequency-domain variables were extracted through multispectral imagery of drones, and each variable importance for different dimensional parameter combinations was computed by three feature parameter selection methods. The selected variables from the different combinations were used to perform potato AGB estimation. The results showed that compared with no feature parameter selection, the accuracy and robustness of the AGB prediction models were significantly improved after parameter selection. The random forest based on out-of-bag (RF-OOB) method was proved to be the most effective feature selection method, and in combination with RF regression, the coefficient of determination (R2) of the AGB validation model could reach 0.90, with root mean square error (RMSE), mean absolute error (MAE), and normalized RMSE (nRMSE) of 71.68 g/m2, 51.27 g/m2, and 11.56%, respectively. Meanwhile, the regression models of the RF-OOB method provided a good solution to the problem that high AGB values were underestimated with the variables of four dimensions. Moreover, the precision of AGB estimates was improved as the dimensionality of parameters increased. This present work can contribute to a rapid, efficient, and non-destructive means of obtaining AGB information for crops as well as provide technical support for high-throughput plant phenotypes screening.

Drug-target interaction prediction using reliable negative samples and effective feature selection methods

Machine learning-based approaches in the field of drug discovery have dramatically reduced the time and cost of the laboratory process of detecting potential drug-target interactions (DTIs). Standard binary classifiers require both positive and negative samples in the training and validation phases. One of the major challenges in the DTI context is the lack of access to non-interacting pairs as negative samples in the learning process. Many recent studies in this field have randomly selected negative samples from unlabeled drug-target pairs. Therefore, due to the probability of the presence of unknown positive samples in a set considered as negative samples, the model results may be affected and appear with a high rate of false positive. In this study, an algorithm called Reliable Non-Interacting Drug-Target Pairs (RNIDTP) is proposed to select reliable negative samples and an efficient algorithm to select relevant features for drug-target interaction prediction. To validate the performance of the proposed RNIDTP algorithm in the selection of negative samples, a benchmark drug-target interactions dataset is used. The results demonstrate the superiority of the proposed algorithm compared with other algorithms in most cases. The results also indicate that by using an appropriate algorithm for the selection of negative samples, the performance of the learning process is significantly increased compared to random selection.