Iterative Selection Research Articles

An efficient many objective optimization algorithm with few parameters

During the past two decades, numerous many-objective optimization evolutionary algorithms (MaOEAs) have been proposed to tackle the challenges traditional multi-objective evolutionary algorithms face, that is to deal with abundant non-dominated solutions and low selection pressure. Specifically, a series of sophisticated selection strategies have been adopted, some of which need additional pre-defined parameters or a significant amount of extra computation time, which retards their applications in real life. In this paper, we propose an efficient indicator-based MaOEA with few parameters, SDE+-MOEA, that uses an adaptive combination of commonly used selection methods to improve search efficiency based on SDE+. SDE+ addresses situations where SDE cannot distinguish individuals with the same SDE values. The adaptive selection method dynamically selects between one-time and iterative selection methods at different stages of evolution to improve the search efficiency. Furthermore, apart from the four parameters for generating offspring, our proposed SDE+-MOEA does not introduce additional parameters. We conduct experimental studies to compare SDE+-MOEA with 11 state-of-the-art algorithms, including 2REA, ISDE+, θ-DEA, LMPFE, CVEA3, SRA, MOEA/DD, IBEA, Two_Arch2, NSGA-III, and SPEA2SDE using four representative performance indicators (HV, SP, PD and GD) on MaF benchmark with 5, 8, 10, and 15 objectives. Experimental studies demonstrate that, compared to the algorithms, SDE+-MOEA achieves better HV and competitive convergence and uniformity performance, while requiring few parameters. It means that SDE+-MOEA can find a solution set with better convergence and uniformity to help decision-makers understand the solved problems. Furthermore, SDE+-MOEA loses little spreadability since a better convergence often leads to a worse spread.

Automated stenosis classification on invasive coronary angiography using modified dual cross pattern with iterative feature selection

Automated stenosis classification on invasive coronary angiography using modified dual cross pattern with iterative feature selection

Application of Multiple-Optimization Filtering Algorithm in Remote Sensing Image Denoising.

Denoising remote sensing images is crucial in the application and research of remote sensing imagery. Noise in remote sensing images originates from sensor characteristics, signal transmission, and environmental conditions, among which Gaussian noise is the most common type. In this paper, we proposed a multiple-optimization bilateral filtering (MOBF) algorithm based on edge detection and differential evolution (DE) methods. The proposed algorithm optimizes the spatial domain filtering kernel and the spatial domain Gaussian kernel by using the standard deviation and width of the edge response. By employing the DE algorithm, the individuals in the population based on the standard deviation of the gray value domain are subjected to iterative mutation, crossover, and selection operations to refine the latent solution vectors and determine the optimal color space for optimizing the standard deviation of the pixel range domain kernel. As a result, the MOBF algorithm, which does not require any parameter input, is realized. To verify the feasibility and effectiveness of the proposed algorithm, denoising experiments were conducted on remote sensing images by using evaluation metrics such as the mean squared error, peak signal-to-noise ratio, and structural similarity index. The experimental results revealed that the MOBF algorithm outperforms traditional algorithms for all three evaluation metrics.

Explainable attention ResNet18-based model for asthma detection using stethoscope lung sounds

This study proposes an accurate asthma detection model using an attention network and machine learning technique. The objective of this study is the automated detection of asthma using an attention network.The lung sounds from 203 subjects involving 767 segments from asthma and 722 segments from healthy subjects were collected using a stethoscope. A novel Attention ResNet18-based deep feature engineering model has been developed in five phases: preprocessing, training the Attention ResNet18 network, extracting deep features, iterative feature selection, and classification using k-nearest neighbor (kNN) or support vector machine (SVM). Gradient-weighted class activation mapping (Grad-CAM) was used to generate heat maps, effectively distinguishing asthma lung sounds from those of normal individuals. By using Grad-CAM, explainable results have been presented.Our proposed model obtained an accuracy of 99.73% using SVM with 10-fold cross-validation, surpassing the performance obtained by previous models. Hence, the developed model has the potential to detect asthma in the real-world scenario. scenario to detect.

Sistem Informasi Penjadwalan Mata Pelajaran Menggunakan Algoritma Artificial Bee Colony Berbasis Web

Course Scheduling Information System Using Web-Based Artificial Bee Colony AlgorithmOne of the educational institutions in Cicalengka District and Bandung Regency is SMK Yadika Cicalengka. has difficulties with scheduling and plotting. At SMK Yadika Cicalengka, the existing scheduling system is still done manually using Microsoft Excel. This becomes less effective because it takes quite a long time and requires an assessment of each teacher's teaching availability every day. This research aims to create a scheduling system that can optimize the time to create subject schedules and accurately divide teaching assignments. Using the artificial bee colony method, this research develops the system and achieves optimal results by imitating how bee colonies search and exploit food sources effectively. In the case of this research, iteration and solution selection will be performed to reduce the breadth of the problem. The results of this study show that the created system is more efficient in time scheduling, with an average value of 96%.

Efficient prediction of fog-related low-visibility events with Machine Learning and evolutionary algorithms

Low visibility events are a severe problem for road transport, causing accidents and major economic losses. Their accurate prediction may help prevent these problems. For that purpose, machine and deep learning techniques have been applied for fog prediction using in situ meteorological data and persistence variables as baseline predictors. These techniques have been evaluated for different prediction time-horizons: 1 h, 3 h and 6 h. The effect of including data extracted from ERA5 Reanalysis as predictive variables has been studied. A database, covering 23 months, has been used, which contains visibility and other meteorogical variables measured in Mondoñedo, Galicia, Spain. A 222000 km2 region around Mondoñedo has been delimited. Thus, a proposed iterative forward selection algorithm based on evolutionary algorithms has been applied to determine the optimal variables and nodes in the region for each regressor model. Both Differential Evolution and Particle Swarm Optimization have been used as optimization algorithms, and an improvement of up to 17.3% with respect to the baseline databases have been obtained. Finally, an analysis of the most frequently selected variables by the evolutionary algorithms has been conducted, leading us to conclude which variables and geographical nodes provide better information to the prediction models.

Prediction of high-grade soft-tissue sarcoma using a combined intratumoural and peritumoural MRI-based radiomics nomogram

To develop an intratumoural and peritumoural magnetic resonance imaging (MRI)-based radiomics nomogram for predicting tumour grade to improve clinical treatment and long-term prognosis. MRI (3 T) features and T2-weighted imaging with fat-saturation (T2WI-FS)-based radiomics features of 57 patients with soft-tissue sarcoma (STS) were analysed retrospectively. Tumour size, ratio of width and length, relative depth to the peripheral fascia, peritumoural oedema, heterogeneity on T2WI, necrosis signal, enhancement model, and peritumoural enhancement were obtained. Independent risk factors were screened to construct an MRI feature nomogram. Radiomics features were obtained from intratumoural and peritumoural images on T2WI-FS. The optimal radiomics model was selected by the four-step dimensionality reduction method of minimum and maximum normalisation, optimal feature selection, selection based on support vector machine with L1-norm regularisation model, and iterative feature selection. MRI features and optimal radiomics features were used to construct a radiomics nomogram. The MRI feature nomogram model, the radiomics model, and the radiomics nomogram model were assessed by receiver operating characteristic (ROC) curves and calibration curves of the training and validation sets. Heterogeneity on T2WI and peritumoural enhancement were independent risk factors for predicting high-grade STS. The areas under the curves of the training set and verification set of the three models were as follows: MRI feature nomogram, 0.86 and 0.83, respectively; intratumoural and peritumoural combined radiomics model, 0.99 and 0.86, respectively; and radiomics nomogram model, 0.98 and 0.96, respectively. The radiomics nomogram model based on MRI features and combined intratumoural and peritumoural radiomic features was best able to predict high-grade STS.

Development of prediction model for alanine transaminase elevations during the first 6 months of conventional synthetic DMARD treatment

Frequent laboratory monitoring is recommended for early identification of toxicity when initiating conventional synthetic disease-modifying antirheumatic drugs (csDMARDs). We aimed at developing a risk prediction model to individualize laboratory testing at csDMARD initiation. We identified inflammatory joint disease patients (N = 1196) initiating a csDMARD in Turku University Hospital 2013–2019. Baseline and follow-up safety monitoring results were drawn from electronic health records. For rheumatoid arthritis patients, diagnoses and csDMARD initiation/cessation dates were manually confirmed. Primary endpoint was alanine transaminase (ALT) elevation of more than twice the upper limit of normal (ULN) within 6 months after treatment initiation. Computational models for predicting incident ALT elevations were developed using Lasso Cox proportional hazards regression with stable iterative variable selection (SIVS) and were internally validated against a randomly selected test cohort (1/3 of the data) that was not used for training the models. Primary endpoint was reached in 82 patients (6.9%). Among baseline variables, Lasso model with SIVS predicted subsequent ALT elevations of > 2 × ULN using higher ALT, csDMARD other than methotrexate or sulfasalazine and psoriatic arthritis diagnosis as important predictors, with a concordance index of 0.71 in the test cohort. Respectively, at first follow-up, in addition to baseline ALT and psoriatic arthritis diagnosis, also ALT change from baseline was identified as an important predictor resulting in a test concordance index of 0.72. Our computational model predicts ALT elevations after the first follow-up test with good accuracy and can help in optimizing individual testing frequency.

Combined approximation algorithms for interactive design of road routes in CAD

Objectives. The aim of the work is to create algorithms for approximating a sequence of points on a plane by arcs of clothoids and circles. Such a problem typically arises in the design of railroad and highway routes. The plan (projection onto a horizontal plane) of the road route is a curve (spline) consisting of a repeating bundle of elements “straight line + clothoid arc + circle arc + clothoid arc + ...”. Such a combination of elements provides continuity not only for the curve and its tangent, but also for the curvature. Since the number of spline elements is not known in advance, and their parameters are subject to restrictions, there is no mathematically consistent algorithm for this problem. The two-stage scheme for solving the problem is developed at RTU MIREA only for a spline with lines and circles (i.e., without clothoid elements). At the first stage, the scheme uses dynamic programming to determine the number of spline elements. At the second stage, the scheme optimizes parameters of the spline using nonlinear programming. This scheme has yet to be implemented for a spline with clothoids due to a significantly more complicated nature of this problem. Therefore, the design of route plans in existing computer aided design (CAD) systems is carried out in interactive mode using iterative selection of elements. In this regard, it makes sense to develop mathematically consistent algorithms for element-by-element approximation.Methods. The problem of element-by-element approximation by a circle and a clothoid is formalized as a lowdimensional non-linear programming problem. The objective function is the sum of squared deviations from the original points. Since a clothoid can only be represented in Cartesian coordinates by power series, there are difficulties in calculating the derivatives of the objective function with respect to the desired parameters of the spline elements. The proposed mathematically consistent algorithm for calculating these derivatives is based on the integral representation of the Cartesian coordinates of the points of the clothoid as functions of its length.Results. A mathematical model and algorithms have been developed for approximating a sequence of points on a plane by clothoids and circles using the method of nonlinear programming. A second-order algorithm is implemented with the calculation and inversion of the matrix of second derivatives (Hesse matrix).Conclusions. For approximation by circles and clothoids using nonlinear programming, it is not necessary to have an analytical expression of the objective function in terms of the required variables. The proposed algorithms make it possible to calculate not only the first, but also the second derivatives in the absence of such expressions.

Feature extraction and fusion using deep convolutional neural networks for Covid-19 detection using CT and X-RAY images

COVID-19 represents a novel variant of the coronavirus disease, having rapidly disseminated across the globe. In recent studies pertaining to computer vision, image processing, and classification techniques, numerous methodologies have been introduced employing chest X-ray images and computerized tomography (CT) images. This investigation introduces novel fused deep features founded on CT and X-ray image classification, with the aim of detecting COVID-19 disease. The proposed approach encompasses three key phases: deep feature generation, iterative feature selection, and classification. During the feature generation phase, well-known pre-trained deep convolutional neural networks, namely DenseNet201, MobileNetV2, ResNet18, ResNet50, ResNet101, VGG16, and VGG19, were leveraged. Each network model generated 1000 features, which were subsequently fused, culminating in the acquisition of a final feature vector comprising 7000 dimensions. In order to distill the most pertinent information, the ReliefF and iterative maximum relevance minimum redundancy (RFImRMR) feature selection techniques were employed in the generation of the ultimate feature vector. To evaluate the performance of the proposed method, publicly available datasets of CT images and X-ray images were employed. Notably, the suggested deep learning approach attained accuracy rates of 99.33% and 93.10% for COVID-19 detection using CT and X-ray images, respectively. These achieved results serve as compelling evidence substantiating the efficacy of the proposed fused deep features and RFImRMR-based COVID-19 detection.

Forest Canopy Cover Inversion Exploration Using Multi-Source Optical Data and Combined Methods

An accurate estimation of canopy cover can provide an important basis for forest ecological management by understanding the forest status and change patterns. The aim of this paper is to investigate the four methods of the random forest (RF), support vector regression (SVR), k-nearest neighbor (KNN), and k-nearest neighbor with fast iterative features selection (KNN-FIFS) for modeling forest canopy cover, and to evaluate three mainstream optical data sources—Landsat8 OLI, Sentinel-2A, Gaofen-1 (GF-1)—and three types of data combined comparatively by selecting the optimal modeling method. The paper uses the Daxinganling Ecological Station of Genhe City, Inner Mongolia, as the research area, and is based on three types of multispectral remote sensing data, extracting spectral characteristics, textural characteristics, terrain characteristics; the Kauth–Thomas transform (K-T transform); and color transformation characteristics (HIS). The optimal combination of features was selected using three feature screening methods, namely stepwise regression, RF, and KNN-FIFS, and the four methods: RF, SVR KNN, and KNN-FIFS, were combined to carry out the evaluation analysis regarding the accuracy of forest canopy cover modeling: (1) In this study, a variety of remote sensing features were introduced, and the feature variables were selected by different parameter preference methods and then employed in modeling. Based on the four modeling inversion methods, the KNN-FIFS model achieves the best accuracy: the Landsat8 OLI with R2 = 0.60, RMSE = 0.11, and RMSEr = 14.64% in the KNN-FIFS model; the Sentinel-2A with R2 = 0.80, RMSE = 0.08, and RMSEr = 11.63% in the KNN-FIFS model; the GF-1 with R2 = 0.55, RMSE = 0.12, and RMSEr = 15.04% in the KNN-FIFS model; and the federated data with R2 = 0.82, RMSE = 0.08, and RMSEr = 10.40% in the KNN-FIFS model; (2) the three multispectral datasets have the ability to estimate forest canopy cover, and the modeling accuracy superior under the combination of multi-source data features; (3) under different optical data, KNN- FIFS achieves the best accuracy in the established nonparametric model, and its feature optimization method is better than that of the random forest optimization method. For the same model, the estimation result of the joint data is better than the single optical data; thus, the KNN-FIFS model, with specific parameters, can significantly improve the inversion accuracy and efficiency of forest canopy cover evaluation from different data sources.

Density-based one-shot active learning for image segmentation

Image segmentation is a key step in image processing tasks, which has significant applications in computer vision field such as medical image analysis, scene understanding and video monitoring, etc. However, image segmentation tasks usually require a large number of labeled samples to obtain great performance of convolutional neural networks (CNNs). Active learning (AL) can select valuable samples for annotation, so as to reduce the annotation cost as much as possible while maintaining the performance of CNNs. Further, one-shot AL can select valuable samples by once, which eliminates the need for iterative sample selection and annotation. However, existing one-shot AL approaches extremely rely on complex clustering algorithm, which brings a limitation in practice, i.e., we often do not know how to set the hyperparameters. In this paper, we propose a clustering-free one-shot AL framework, which is based on self-supervised feature learning and density-based query strategy. Our framework can select samples with high local density robustly against hyperparameters. The experimental results are impressive that state-of-the-art one-shot active learning performance can be achieved with simple density-based sampling.

Specific Clearance of Lipopolysaccharide from Blood Based on Peptide Bottlebrush Polymer for Sepsis Therapy.

Lipopolysaccharide (LPS) is the primary bacterial toxin that is vital to the pathogenesis and progression of sepsis associated with extremely high morbidity and mortality worldwide. However, specific clearance of LPS from circulating blood is highly challenging because of the structural complexity and its variation between/within bacterial species. Herein, a robust strategy based on phage display screening and hemocompatible peptide bottlebrush polymer design for specific clearance of targeted LPS from circulating blood is proposed. Using LPS extracted from Escherichia coli as an example, a novel peptide (HWKAVNWLKPWT) with high affinity (KD < 1.0 nм), specificity, and neutralization activity (95.9 ± 0.1%) against the targeted LPS is discovered via iterative affinity selection coupled with endotoxin detoxificationscreening. A hemocompatible bottlebrush polymer bearing the short peptide [poly(PEGMEA-co-PEP-1)] exhibits high LPS selectivity to reduce circulating LPS level from 2.63 ± 0.01 to 0.78 ± 0.05 EU mL-1 in sepsis rabbits via extracorporeal hemoperfusion (LPS clearance ratio > 70%), reversing the LPS-induced leukocytopenia and multiple organ damages significantly. This work provides a universal paradigm for developing a highly selective hemoadsorbent library fully covering the LPS family, which is promising to create a new era of precision medicine in sepsis therapy.

Optimal sensor placement for leak location in water distribution networks: A feature selection method combined with graph signal processing

Nowadays, real-time monitoring of smart water networks is essentially performed by Supervisory Control and Data Acquisition (SCADA) systems and through the use of sensors strategically positioned in the water distribution network (WDN). The purpose of sensor placement is to reasonably collect signals and thus improve the efficiency of subsequent leak diagnosis, while also limiting their deployment and operational costs. Most current sensor placement methods rely on well-calibrated hydraulic models for node selection and subsequent leak location evaluation. In this study, an efficient Optimal Sensor Placement (OSP) method for WDN is proposed, which avoids the reliance on the hydraulic model in the node selection step. It can be generalized as an optimization process, and the algorithm to solve the problem is a heuristic algorithm. We consider the user nodes in the WDN as features and propose a feature selection algorithm combined with graph signal processing. By this method, the importance of different nodes in the WDN is analyzed and the redundancy between different nodes is considered in the iterative selection process. A graph signal reconstruction method is applied to recover pressure data of all nodes using the data monitored by the selected nodes, and the relationship between the number of sensors and the reconstruction error is analyzed. The proposed method is tested on two benchmark networks of different sizes and types. A comparative analysis with other methods shows that the proposed OSP method can be easily extended to other WDNs. In addition, the proposed method achieves better monitoring results while selecting nodes quickly.

Lyophilization to enable distribution of ChAdOx1 and ChAdOx2 adenovirus-vectored vaccines without refrigeration

Distribution of vaccines which require refrigerated or frozen storage can be challenging and expensive. The adenovirus vector platform has been widely used for COVID-19 vaccines while several further candidate vaccines using the platform are in clinical development. In current liquid formulations, adenoviruses require distribution at 2–8 °C. The development of formulations suitable for ambient temperature distribution would be advantageous. Previous peer-reviewed reports of adenovirus lyophilization are relatively limited. Here, we report the development of a formulation and process for lyophilization of simian adenovirus-vectored vaccines based on the ChAdOx1 platform. We describe the iterative selection of excipients using a design of experiments approach, and iterative cycle improvement to achieve both preservation of potency and satisfactory cake appearance. The resulting method achieved in-process infectivity titre loss of around 50%. After drying, there was negligible further loss over a month at 30 °C. Around 30% of the predrying infectivity remained after a month at 45 °C. This performance is likely to be suitable for ‘last leg’ distribution at ambient temperature. This work may also facilitate the development of other product presentations using dried simian adenovirus-vectored vaccines.

On the optimal design of radial basis function neural networks for the analysis of nonlinear stochastic systems

In this paper, an iterative selection strategy of Gaussian neurons for radial basis function neural networks (RBFNN) is proposed when the RBFNN method is applied to obtain the steady-state solution of the Fokker–Planck–Kolmogorov (FPK) equation. A performance index is introduced to rank neurons. Top rank neurons are selected, leading to a RBFNN with optimal number and locations of Gaussian neurons for the FPK equation under consideration. The statistical properties of the performance index are studied. It is found that the index assigned to the jth neuron is proportional to the probability of the system falling into the small neighborhood of the mean of this neuron as well as proportional to the weight of the neuron. The RBFNN method with the optimally selected neurons is then applied to several challenging examples of nonlinear stochastic systems in 2, 3 and 4 dimensional state space. The RBFNN solutions are also compared with the results of extensive Monte Carlo simulations. It is observed that the RBFNN method with optimally selected neurons by the proposed iterative algorithm is much more efficient than the RBFNN method with uniformly distributed neurons, and is very accurate in terms of the root mean squared (RMS) errors of the FPK equation or the RMS errors of the PDF solution compared with simulation results.

Feature selection‐integrated classifier optimisation algorithm for network intrusion detection

SummaryIn the era of technology, information security has gained significant importance, as intruders constantly conduct attacks to breach information systems. Intelligent network intrusion detection systems (NIDS) are promising for detecting malicious activities; however, it is required to apply feature selection (FS) and classifier optimisation (CO) using cost‐effective algorithms to build an accurate and efficient system. Although classifier‐dependent FS (CDFS) techniques and CO algorithms have been shown to perform well, they suffer from computational complexity, and their interdependencies negatively affect model performance. This study proposes the FS‐integrated classifier optimisation algorithm that incorporates FS during CO, enhances optimisation, and tackles the interdependency problem. Furthermore, since this algorithm does not use an iterative feature selection process, such as forward selection or backward elimination, it provides relatively less complexity than other CDFS techniques. Moreover, an application of the proposed methodology (NIDS) was implemented using the designed framework to validate the model in this problem domain. The proposed methodology achieved accuracies of 85.10%, 73.24% with one feature for the NSLKDD datasets, 83.45% with 32 features for the UNSW‐NB15 dataset, 99.41% with eight features, and 99.63% with 16 features for the CIC‐IDS2017 datasets. The results showed that the FS‐integrated optimisation algorithm had improved the accuracy of the classifier with fewer features. Furthermore, the proposed methodology outperformed other FS, ensemble learning, and deep learning‐based methods regarding detection accuracy and false alarm rate. In conclusion, the developed NIDS is an accurate, efficient, straightforward, feasible, and easy‐to‐implement system that can be created using limited computing power and time as a promising solution to protect traditional and modern computer networks.

Waypoint selection for unmanned aerial vehicle‐aided calibration in wireless positioning networks

AbstractDeploying an unmanned aerial vehicle (UAV) to scatter positioning beacons and further calibrate their positions by obtaining range measurements enables the establishment of a wireless positioning network in GNSS‐denied environments where hand placement is not an option. The influence of the UAV trajectory on the calibration quality is investigated and methods to find optimal waypoints at which the UAV makes observations are determined. A Fisher information matrix‐based metric is devised and two waypoint selection algorithms are proposed to optimise calibration quality, one‐off waypoint selection, and iterative and incremental waypoint selection. Numerical results show that optimised waypoints provide more information about beacon positions and therefore produce a more accurate wireless positioning network.

A CsoR family transcriptional regulator, TTHA1953, controls the sulfur oxidation pathway in Thermus thermophilus HB8

Transcription regulation is a critical means by which microorganisms sense and adapt to their environments. Bacteria contain a wide range of highly conserved families of transcription factors that have evolved to regulate diverse sets of genes. It is increasingly apparent that structural similarities between transcription factors do not always equate to analogous transcription regulatory networks. For example, transcription factors within the copper-sensing operon repressor (CsoR)-resistance to cobalt and nickel repressor family have been found to repress a wide range of gene targets, including various metal efflux genes, as well as genes involved in sulfide and formaldehyde detoxification machinery. In this study, we identify the preferred DNA-binding sequence for the CsoR-like protein, TTHA1953, from the model extremophile Thermus thermophilus HB8 using the iterative selection approach, restriction endonuclease, protection, selection, and amplification. By mapping significant DNA motifs to the T.thermophilus HB8 genome, we identify potentially regulated genes that we validate with invitro and invivo methodologies. We establish TTHA1953 as a master regulator of the sulfur oxidation pathway, providing the first link between CsoR-like proteins and Sox regulation.

Characterization of breast lesions using multi-parametric diffusion MRI and machine learning

Objective. To investigate quantitative imaging markers based on parameters from two diffusion-weighted imaging (DWI) models, continuous-time random-walk (CTRW) and intravoxel incoherent motion (IVIM) models, for characterizing malignant and benign breast lesions by using a machine learning algorithm. Approach. With IRB approval, 40 women with histologically confirmed breast lesions (16 benign, 24 malignant) underwent DWI with 11 b-values (50 to 3000 s/mm2) at 3T. Three CTRW parameters, D m , α, and β and three IVIM parameters D diff, D perf, and f were estimated from the lesions. A histogram was generated and histogram features of skewness, variance, mean, median, interquartile range; and the value of the 10%, 25% and 75% quantiles were extracted for each parameter from the regions-of-interest. Iterative feature selection was performed using the Boruta algorithm that uses the Benjamin Hochberg False Discover Rate to first determine significant features and then to apply the Bonferroni correction to further control for false positives across multiple comparisons during the iterative procedure. Predictive performance of the significant features was evaluated using Support Vector Machine, Random Forest, Naïve Bayes, Gradient Boosted Classifier (GB), Decision Trees, AdaBoost and Gaussian Process machine learning classifiers. Main Results. The 75% quantile, and median of D m ; 75% quantile of f; mean, median, and skewness of β; kurtosis of D perf; and 75% quantile of D diff were the most significant features. The GB differentiated malignant and benign lesions with an accuracy of 0.833, an area-under-the-curve of 0.942, and an F1 score of 0.87 providing the best statistical performance (p-value < 0.05) compared to the other classifiers. Significance. Our study has demonstrated that GB with a set of histogram features from the CTRW and IVIM model parameters can effectively differentiate malignant and benign breast lesions.