Final Subset Research Articles

Application of best subset method for river water quality modeling: A study on Godavari River, India

AbstractThe utilization of water quality analysis to inform optimal decision‐making is imperative to achieve sustainable management of river water quality. A multitude of research works in the past has focused on river water quality modeling. Despite being a precise statistical regression technique that allows for fitting separate models for all potential combinations of predictors and selecting the optimal subset model, the application of best subset method in river water quality modeling is not widely adopted. The current research aims to validate the use of best subset method in evaluating the water quality parameters of the Godavari River, one of the largest rivers in India, by developing regression equations for different combinations of its physicochemical parameters. The study involves in formulating best subset regression equations to estimate the concentrations of river water quality parameters while also identifying and quantifying their variations. A total of 17 water quality parameters are analyzed at 13 monitoring sites using 13 years (1993–2005) of observed data for the monsoon (June–October) period and post‐monsoon (November–February) period. The final subset model is selected among model combinations that are developed for each year's dataset through widely used statistical criteria such as R2, F value, adjusted R2a, AICc, and RSS. The final best subset model across all parameters exhibits R2 values surpassing 0.8, indicating that the models possess the ability to account for over 80% of the variations in the concentrations of dependent parameters. Therefore, the findings demonstrated the appropriateness of this method in evaluating the water quality parameters in extensive rivers. This work is very useful for decision‐making and in the management of river water quality for its sustainable use in the study area.

Comparison of wellbeing structures based on survey responses and social media language: A network analysis.

Wellbeing is predominantly measured through surveys but is increasingly measured by analysing individuals' language on social media platforms using social media text mining (SMTM). To investigate whether the structure of wellbeing is similar across both data collection methods, we compared networks derived from survey items and social media language features collected from the same participants. The dataset was split into an independent exploration (n = 1169) and a final subset (n = 1000). After estimating exploration networks, redundant survey items and language topics were eliminated. Final networks were then estimated using exploratory graph analysis (EGA). The networks of survey items and those from language topics were similar, both consisting of five wellbeing dimensions. The dimensions in the survey- and SMTM-based assessment of wellbeing showed convergent structures congruent with theories of wellbeing. Specific dimensions found in each network reflected the unique aspects of each type of data (survey and social media language). Networks derived from both language features and survey items show similar structures. Survey and SMTM methods may provide complementary methods to understand differences in human wellbeing.

Selecting a PRO-CTCAE-based subset for patient-reported symptom monitoring in prostate cancer patients: a modified Delphi procedure

Clinician-based reporting of adverse events leads to underreporting and underestimation of the impact of adverse events on prostate cancer patients. Therefore, interest has grown in capturing adverse events directly from patients using the Patient-Reported Outcomes (PROs) version of the Common Terminology Criteria for Adverse Events (CTCAE). We aimed to develop a standardized PRO-CTCAE subset tailored to adverse event monitoring in prostate cancer patients. We used a mixed-method approach based on the 'phase I guideline for developing questionnaire modules' by the European Organization for Research and Treatment of Cancer (EORTC) Quality of Life group, including a literature review, and interviews with patients (n= 30) and health care providers (HCPs, n= 16). A modified Delphi procedure was carried out to reach consensus on the final subset selected from the complete PRO-CTCAE item library. Fourteen multidisciplinary HCPs and 12 patients participated in the Delphi rounds. Ninety percent agreed on the final subset, consisting of: 'ability to achieve and maintain erection', 'decreased libido', 'inability to reach orgasm', 'urinary frequency', 'urinary urgency', 'urinary incontinence', 'painful urination', 'fecal incontinence', 'fatigue', 'hot flashes', 'feeling discouraged', 'sadness', and 'concentration'. From 16 articles identified in the literature review, the following adverse events for which no PRO-CTCAE items are available, were included to the recommendation section: 'nocturia', 'blood and/or mucus in stool', 'hemorrhoids', 'hematuria', 'cystitis', 'neuropathy', and 'proctitis'. The obtained PRO-CTCAE-subset can be used for multidisciplinary adverse event monitoring in prostate cancer care. The described method may guide development of future PRO-CTCAE subsets.

S-40-3: MEMORY GAMMA DELTA T CELLS PLAY A ROLE IN HYPERTENSION

Objectives: A subset of T cells, γδ T cells, participate in the pathogenesis of hypertension. It has been shown that memory T cells develop after a hypertensive insult and sensitize mice to develop hypertension to subsequent mild hypertensive stimuli. However, whether memory γδ T cells develop and play a role in hypertension is unknown. We hypothesize that memory γδ T cells form after a hypertensive challenge, and that they sensitize mice to develop hypertension to mild hypertensive stimuli. Methods: Ten-12-week-old C57BL/6J mice were exposed or not to a pressor dose of angiotensin II (490 ng/kg/min, SC) for two weeks, followed by a two-week washout period, and then infused with a subpressor dose of angiotensin II (140 ng/kg/min, SC) for two weeks. Blood pressure (BP) was measured by telemetry and memory γδ T cells profiled by flow cytometry. A subset of mice was injected IP with 400 μg of anti-T cell receptor γδ-depleting or isotype control antibodies 1 day before and 6 days after the initiation of second hypertensive challenge. A final subset was injected IV with 2.5x105 γδ T cells isolated from hypertensive or normotensive mice, and then exposed to a subpressor dose of angiotensin II as above. Results: Repeated hypertensive challenges yielded a higher systolic BP than one mild hypertensive stimulus (154 ± 4 vs 120 ± 3 mm Hg, P < 0.01). Two-week pressor dose angiotensin II increased effector memory γδ T cells in mesenteric artery perivascular adipose tissue (1.25 ± 0.37% vs. 0.24 ± 0.12%, P < 0.05) and mesenteric lymph nodes (1.49 ± 0.03% vs 0.82 ± 0.15%, P < 0.05). γδ T cell depletion reduced systolic BP elevation from day 8 (135 ± 5 vs 150 ± 5 mm Hg, P < 0.05) to day 13 of the second hypertensive challenge (150 ± 5 vs 163 ± 2 mm Hg, P < 0.05). Adoptive transfer of γδ T cells isolated from hypertensive compared to normotensive mice caused a greater systolic BP elevation in response to a subpressor dose of angiotensin II (159 ± 3 vs 142 ± 6 mm Hg, P < 0.01). Conclusion: Memory γδ T cells develop after a hypertensive challenge and sensitize mice to mild hypertensive stimuli. Memory γδ T cells may represent a novel therapeutic target to treat hypertensive humans.

An Intelligent Hybrid Ensemble Gene Selection Model for Autism Using DNN

Autism Spectrum Disorder (ASD) is a complicated neurodevelopmental disorder that is often identified in toddlers. The microarray data is used as a diagnostic tool to identify the genetics of the disorder. However, microarray data is large and has a high volume. Consequently, it suffers from the problem of dimensionality. In microarray data, the sample size and variance of the gene expression will lead to overfitting and misclassification. Identifying the autism gene (feature) subset from microarray data is an important and challenging research area. It has to be efficiently addressed to improve gene feature selection and classification. To overcome the challenges, a novel Intelligent Hybrid Ensemble Gene Selection (IHEGS) model is proposed in this paper. The proposed model integrates the intelligence of different feature selection techniques over the data partitions. In this model, the initial gene selection is carried out by data perturbation, and the final autism gene subset is obtained by functional perturbation, which reduces the problem of dimensionality in microarray data. The functional perturbation module employs three meta-heuristic swarm intelligence-based techniques for gene selection. The obtained gene subset is validated by the Deep Neural Network (DNN) model. The proposed model is implemented using python with six National Center for Biotechnology Information (NCBI) gene expression datasets. From the comparative study with other existing state-of-the-art systems, the proposed model provides stable results in terms of feature selection and classification accuracy.

Fundamental Frequency Contour (Melody) of Infant Vocalizations across the First Year

Introduction: The fundamental frequency contour (melody) of cry and non-cry utterances becomes more complex with age. However, there is a lack of longitudinal analyses of melody development during the first year of life. Objective: The aim of the study was to longitudinally analyze melody development in typical vocalization types across the first 12 months of life. The aim was twofold: (1) to answer the question whether melody becomes more complex in all vocalization types with age and (2) to characterize complex patterns in more detail. Methods: Repeatedly recorded vocalizations (n = 10,988) of 10 healthy infants (6 female) over their first year of life were analyzed using frequency spectrograms and fundamental frequency (f0) analyses (PRAAT). Melody complexity analysis was performed using specific in-lab software (CDAP, pw-project) in a final subset of 9,237 utterances that contained noise-free, undisturbed contours. Generalized mixed linear models were used to analyze age and vocalization type effects on melody complexity. Results: The vocalization repertoire showed a higher proportion of complex melodies from the second month onward. The age effect was significant, but no difference was found in melody complexity between cry and non-cry vocalizations across the first 6 months. From month 7–12, there was a further significant increase in complex structures only in canonical babbling not in marginal babbling. Melody segmentations by laryngeal constrictions prevailed among complex shapes. Conclusion: The study demonstrated the regularity of melody development in different vocalization types throughout the first year of life. In terms of prosodic features of infant sounds, melody contour is of primary importance, and further studies are required that also include infants at risk for language development.

Comparing and integrating artificial intelligence and similarity search detection techniques: application to seismic sequences in Southern Italy

SUMMARYUnderstanding mechanical processes occurring on faults requires detailed information on the microseismicity that can be enhanced today by advanced techniques for earthquake detection. This problem is challenging when the seismicity rate is low and most of the earthquakes occur at depth. In this study, we compare three detection techniques, the autocorrelation FAST, the machine learning EQTransformer, and the template matching EQCorrScan, to assess their ability to improve catalogues associated with seismic sequences in the normal fault system of Southern Apennines (Italy) using data from the Irpinia Near Fault Observatory (INFO). We found that the integration of the machine learning and template matching detectors, the former providing templates for the cross-correlation, largely outperforms techniques based on autocorrelation and machine learning alone, featuring an enrichment of the automatic and manual catalogues of factors 21 and 7, respectively. Since output catalogues can be polluted by many false positives, we applied refined event selection based on the cumulative distribution of their similarity level. We can thus clean up the detection lists and analyse final subsets dominated by real events. The magnitude of completeness decreases by more than one unit compared to the reference value for the network. We report b-values associated with sequences smaller than the average, likely corresponding to larger differential stresses than for the background seismicity of the area. For all the analysed sequences, we found that main events are anticipated by foreshocks, indicating a possible preparation process for main shocks at subkilometric scales.

PSO-Driven Feature Selection and Hybrid Ensemble for Network Anomaly Detection

As a system capable of monitoring and evaluating illegitimate network access, an intrusion detection system (IDS) profoundly impacts information security research. Since machine learning techniques constitute the backbone of IDS, it has been challenging to develop an accurate detection mechanism. This study aims to enhance the detection performance of IDS by using a particle swarm optimization (PSO)-driven feature selection approach and hybrid ensemble. Specifically, the final feature subsets derived from different IDS datasets, i.e., NSL-KDD, UNSW-NB15, and CICIDS-2017, are trained using a hybrid ensemble, comprising two well-known ensemble learners, i.e., gradient boosting machine (GBM) and bootstrap aggregation (bagging). Instead of training GBM with individual ensemble learning, we train GBM on a subsample of each intrusion dataset and combine the final class prediction using majority voting. Our proposed scheme led to pivotal refinements over existing baselines, such as TSE-IDS, voting ensembles, weighted majority voting, and other individual ensemble-based IDS such as LightGBM.

A graph based preordonnances theoretic supervised feature selection in high dimensional data

Generally, for high-dimensional datasets, only some features are relevant, while others are irrelevant or redundant. In the machine learning field, the use of a strategy for eliminating insignificant features from a dataset is very important for the classification task. Feature selection is the process of identifying the most informative features that help in predicting sample classes efficiently in order to achieve better classification performance. In this research paper, a new hybrid feature selection strategy for high-dimensional datasets is proposed to find the most discriminative subset of features for the dataset with the irrelevant and redundant features discarded. The proposed algorithm is called Maximal Clique based on the coefficients Ψ (MaCΨ algorithm). The MaCΨ method has the capability to handle categorical, numerical, and hybrid datasets. Furthermore, it can be applied either to binary or multi-class classification problems. The global structure of the MaCΨ algorithm can be described by three steps. In the first step, a weight is proposed to evaluate the importance of each feature in the dataset by balancing the trade-off between two novel measures of relevance and redundancy, and then the K most important features are selected to form the candidate subset, where K is taken as user input. In the second phase, a wrapper method based on graph theory is applied to the subset retained from the first step to extract the optimal subset of features. In the last stage, the final subset of features with the highest classification performance and the lowest number of features is obtained by applying the backward elimination algorithm to the optimal subset. The performance of the MaCΨ methodology is investigated on artificial as well as real-world datasets with different dimensionalities. The statistical analysis of the experimental results clearly indicates that the MaCΨ approach achieves competitive results in terms of the classification accuracy and the number of selected features compared with some state-of-the-art approaches.

Abstract P239: Angiotensin II-Induced Memory Gamma Delta T Cells Sensitize Mice To A Mild Hypertensive Stimulus

Hypothesis: We hypothesize that memory γδ T cells form after a hypertensive challenge, and that they sensitize mice to develop hypertension to mild hypertensive stimuli. Methods: Ten-12-week-old C57BL/6J mice were exposed or not to a pressor dose of angiotensin II (490 ng/kg/min, SC) for two weeks, followed by a two-week washout period, and then infused with a subpressor dose of angiotensin II (140 ng/kg/min, SC) for two weeks. Blood pressure (BP) was measured by telemetry and memory γδ T cells profiled by flow cytometry. A subset of mice was injected IP with 400 μg of anti-T cell receptor γδ-depleting or isotype control antibodies 1 day before and 6 days after the initiation of second hypertensive challenge. A final subset was injected IV with 2.5x10 5 γδ T cells isolated from hypertensive or normotensive mice, and then exposed to a subpressor dose of angiotensin II as above. Results: Repeated hypertensive challenges yielded a higher systolic BP than one mild hypertensive stimulus (154±4 vs 120±3 mm Hg, P <0.01). Two-week pressor dose angiotensin II increased effector memory γδ T cells in mesenteric artery perivascular adipose tissue (1.25±0.37% vs. 0.24±0.12%, P<0.05) and mesenteric lymph nodes (1.49±0.03% vs 0.82±0.15%, P<0.05). γδ T cell depletion reduced systolic BP elevation from day 8 (135±5 vs 150±5 mm Hg, P <0.05) to day 13 of the second hypertensive challenge (150±5 vs 163±2 mm Hg, P <0.05). Adoptive transfer of γδ T cells isolated from hypertensive compared to normotensive mice caused a greater systolic BP elevation in response to a subpressor dose of angiotensin II (159±3 vs 142±6 mm Hg, P <0.01). Conclusion: Memory γδ T cells develop after a hypertensive challenge and sensitize mice to mild hypertensive stimuli. Memory γδ T cells may represent a novel therapeutic target to treat hypertensive humans.

A new improved maximal relevance and minimal redundancy method based on feature subset

Feature selection plays a very significant role for the success of pattern recognition and data mining. Based on the maximal relevance and minimal redundancy (mRMR) method, combined with feature subset, this paper proposes an improved maximal relevance and minimal redundancy (ImRMR) feature selection method based on feature subset. In ImRMR, the Pearson correlation coefficient and mutual information are first used to measure the relevance of a single feature to the sample category, and a factor is introduced to adjust the weights of the two measurement criteria. And an equal grouping method is exploited to generate candidate feature subsets according to the ranking features. Then, the relevance and redundancy of candidate feature subsets are calculated and the ordered sequence of these feature subsets is gained by incremental search method. Finally, the final optimal feature subset is obtained from these feature subsets by combining the sequence forward search method and the classification learning algorithm. Experiments are conducted on seven datasets. The results show that ImRMR can effectively remove irrelevant and redundant features, which can not only reduce the dimension of sample features and time of model training and prediction, but also improve the classification performance.

Examining virtual driving test performance and its relationship to individuals with HIV-associated neurocognitive disorders.

SignificanceExisting screening tools for HIV-associated neurocognitive disorders (HAND) are often clinically impractical for detecting milder forms of impairment. The formal diagnosis of HAND requires an assessment of both cognition and impairment in activities of daily living (ADL). To address the critical need for identifying patients who may have disability associated with HAND, we implemented a low-cost screening tool, the Virtual Driving Test (VDT) platform, in a vulnerable cohort of people with HIV (PWH). The VDT presents an opportunity to cost-effectively screen for milder forms of impairment while providing practical guidance for a cognitively demanding ADL.ObjectivesWe aimed to: (1) evaluate whether VDT performance variables were associated with a HAND diagnosis and if so; (2) systematically identify a manageable subset of variables for use in a future screening model for HAND. As a secondary objective, we examined the relative associations of identified variables with impairment within the individual domains used to diagnose HAND.MethodsIn a cross-sectional design, 62 PWH were recruited from an established HIV cohort and completed a comprehensive neuropsychological assessment (CNPA), followed by a self-directed VDT. Dichotomized diagnoses of HAND-specific impairment and impairment within each of the seven CNPA domains were ascertained. A systematic variable selection process was used to reduce the large amount of VDT data generated, to a smaller subset of VDT variables, estimated to be associated with HAND. In addition, we examined associations between the identified variables and impairment within each of the CNPA domains.ResultsMore than half of the participants (N = 35) had a confirmed presence of HAND. A subset of twenty VDT performance variables was isolated and then ranked by the strength of its estimated associations with HAND. In addition, several variables within the final subset had statistically significant associations with impairment in motor function, executive function, and attention and working memory, consistent with previous research.ConclusionWe identified a subset of VDT performance variables that are associated with HAND and assess relevant functional abilities among individuals with HAND. Additional research is required to develop and validate a predictive HAND screening model incorporating this subset.

Strongyloides stercoralis prevalence in solid-organ and haematopoietic stem cell transplant candidates and recipients: a systematic review and meta-analysis protocol

IntroductionStrongyloides stercoralis is an intestinal helminth ubiquitous in tropical and subtropical regions worldwide. It persists in the human host for a lifetime as a result of autoinfection and if undetected...

Sleep Apnea Detection Using Multi-Error-Reduction Classification System with Multiple Bio-Signals.

Introduction: Obstructive sleep apnea (OSA) can cause serious health problems such as hypertension or cardiovascular disease. The manual detection of apnea is a time-consuming task, and automatic diagnosis is much more desirable. The contribution of this work is to detect OSA using a multi-error-reduction (MER) classification system with multi-domain features from bio-signals. Methods: Time-domain, frequency-domain, and non-linear analysis features are extracted from oxygen saturation (SaO), ECG, airflow, thoracic, and abdominal signals. To analyse the significance of each feature, we design a two-stage feature selection. Stage 1 is the statistical analysis stage, and Stage 2 is the final feature subset selection stage using machine learning methods. In Stage 1, two statistical analyses (the one-way analysis of variance (ANOVA) and the rank-sum test) provide a list of the significance level of each kind of feature. Then, in Stage 2, the support vector machine (SVM) algorithm is used to select a final feature subset based on the significance list. Next, an MER classification system is constructed, which applies a stacking with a structure that consists of base learners and an artificial neural network (ANN) meta-learner. Results: The Sleep Heart Health Study (SHHS) database is used to provide bio-signals. A total of 66 features are extracted. In the experiment that involves a duration parameter, 19 features are selected as the final feature subset because they provide a better and more stable performance. The SVM model shows good performance (accuracy = 81.68%, sensitivity = 97.05%, and specificity = 66.54%). It is also found that classifiers have poor performance when they predict normal events in less than 60 s. In the next experiment stage, the time-window segmentation method with a length of 60 s is used. After the above two-stage feature selection procedure, 48 features are selected as the final feature subset that give good performance (accuracy = 90.80%, sensitivity = 93.95%, and specificity = 83.82%). To conduct the classification, Gradient Boosting, CatBoost, Light GBM, and XGBoost are used as base learners, and the ANN is used as the meta-learner. The performance of this MER classification system has the accuracy of 94.66%, the sensitivity of 96.37%, and the specificity of 90.83%.

Effective memetic algorithm for multilabel feature selection using hybridization-based communication

Multilabel feature selection, which is used to select features relevant to multiple labels, has demonstrated its effectiveness in prediction time and learning accuracy. A memetic algorithm that uses a feature subset refining process has been verified to outperform existing genetic algorithms in identifying an optimal feature subset. However, as the refinement process is consistently applied to all solutions of feature subsets, similar feature subsets can be over-produced, thereby limiting the synergy of hybridization. Here, we propose an evolutionary multilabel feature selection algorithm that searches the final feature subset using multiple populations to prevent limiting the synergy of hybridization. A new hybridization-based communication process refines solutions originated from each best solution of multiple populations, then, randomly distributes the produced solutions. With this approach, the proposed method circumvents the degradation of search capability and keeps the synergy of hybridization. Our experimental results indicate that the proposed method could identify better feature subsets than conventional methods.

Efficient subset simulation with active learning Kriging model for low failure probability prediction

For low failure probability prediction, subset simulation can reduce the number of simulations significantly compared to the traditional MCS method for a target prediction error limit. To further reduce the computational effort for cases where the performance function evaluation is tedious and time-consuming, the performance function is approximated by a sequentially updated (instead of a global) Kriging model. For this purpose, an active learning technique with a new learning and stopping criterion is employed to efficiently select points to train the computationally cheaper Kriging model at each simulation level, which is used to estimate the intermediate threshold and generate a new simulation sample. The updated Kriging model at the final subset simulation level is used to compute the conditional failure probability. The failure probability is estimated based on an initial simulation sample size N, and an updated N is computed and employed to obtain the final failure probability within a desired bound on the variability. The efficiency (in terms of the number of expensive evaluations using the actual performance function) and prediction error (represented by the mean square error (MSE)) of the proposed method are benchmarked using several examples. The method is shown to be more efficient (using lesser expensive evaluations) with smaller MSE for problems having low failure probabilities compared with selected existing methods.

An effective feature subset selection approach based on Jeffries-Matusita distance for multiclass problems

Jeffries-Matusita (JM) distance, a transformation of the Bhattacharyya distance, is a widely used measure of the spectral separability distance between the two class density functions and is generally used as a class separability measure. It can be considered to have good potential to be used for evaluation of the effectiveness of a feature in discriminating two classes. The capability of JM distance as a ranking based feature selection technique for binary classification problems has been verified in some research works as well as in our earlier work. It was found by our simulation experiments with benchmark data sets that JM distance works equally well compared to other popular feature ranking methods based on mutual information, information gain or Relief. Extension of JM distance measure for feature ranking in multiclass problems has also been reported in the literature. But all of them are basically rank based approaches which deliver the ranking of the features and do not automatically produce the final optimal feature subset. In this work, a novel heuristic approach for finding out the optimum feature subset from JM distance based ranked feature lists for multiclass problems have been developed without explicitly using any specific search technique. The proposed approach integrates the extension of JM measure for multiclass problems and the selection of the final optimal feature subset in a unified process. The performance of the proposed algorithm has been evaluated by simulation experiments with benchmark data sets in comparison with two other previously developed multiclass JM distance measures (weighted average JM distance and another multiclass extension equivalent to Bhattacharyya bound) and some other popular filter based feature ranking algorithms. It is found that the proposed algorithm performs better in terms of classification accuracy, F-measure, AUC with a reduced set of features and computational cost.

Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods

Introduction: This study aims to assess the utility of Boosting ensemble classification methods for increasing the diagnostic performance of multiparametric Magnetic Resonance Imaging (mpMRI) radiomic models, in differentiating benign and malignant breast lesions. Methods: The dataset includes mpMR images of 140 female patients with mass-like breast lesions (70 benign and 70 malignant), consisting of Dynamic Contrast Enhanced (DCE) and T2-weighted sequences, and the Apparent Diffusion Coefficient (ADC) calculated from the Diffusion Weighted Imaging (DWI) sequence. Tumor masks were manually defined in all consecutive slices of the respective MRI volumes and 3D radiomic features were extracted with the Pyradiomics package. Feature dimensionality reduction was based on statistical tests and the Boruta wrapper. Hierarchical Clustering on Spearman's rank correlation coefficients between features and Random Forest classification for obtaining feature importance, were implemented for selecting the final feature subset. Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) classifiers, were trained and tested with bootstrap validation in differentiating breast lesions. A Support Vector Machine (SVM) classifier was also exploited for comparison. The Receiver Operator Characteristic (ROC) curves and DeLong's test were utilized to evaluate the classification performances. Results: The final feature subset consisted of 5 features derived from the lesion shape and the first order histogram of DCE and ADC images volumes. XGboost and LGBM achieved statistically significantly higher average classification performances [AUC = 0.95 and 0.94 respectively], followed by Adaboost [AUC = 0.90], GB [AUC = 0.89] and SVM [AUC = 0.88]. Conclusion: Overall, the integration of Ensemble Learning methods within mpMRI radiomic analysis can improve the performance of computer-assisted diagnosis of breast cancer lesions.

Research on Gene Expression Data Based on Jonckheere-Terpstra Test

Non-parametric tests are often used in feature selection of gene expression data. In order to achieve feature selection and redundancy removal of gene expression data and obtain feature subsets with higher classification accuracy, this paper proposes a feature selection algorithm based on Jonckheere-Terpstra test for the characteristics of high noise and high redundancy in gene expression data, and applies the algorithm to both binary and multiclassified gene expression datasets. The algorithm first uses Jonckheere-Terpstra test to perform feature selection on the datasets to initially reduce the data dimension, and then uses Pearson correlation test to remove the redundancy of the selected data sets to obtain the final feature subset. In order to test its classification performance, support vector machine and k-nearest neighbor were used for classification experiments respectively. The experimental results show that the algorithm has high classification accuracy for both feature selection and redundancy removal of binary and multiclassified datasets.

A Two-Stage Feature Selection Approach for Fruit Recognition Using Camera Images With Various Machine Learning Classifiers

Fruit and vegetable identification and classification system is always necessary and advantageous for the agriculture business, the food processing sector, as well as the convenience shops and hypermarkets where these products are sold. Therefore, it is necessary to build an effective automated tool to meet the needs of the market by boosting the outcome, in order to improve economic efficiency. In this paper, a two-stage model is proposed to recognize fruits using camera images. We employed a Densnet121 to get the features from the fruits dataset in the first module. In the second stage, we utilize a feature subset selection method to choose the most significant features for recognizing fruits from the images of the fruits. In this study, Adaptive particle - Grey Wolf Optimization (APGWO) has been applied for choosing the most pertinent features. The final subset feature has been used for recognizing fruits using several machine learning classifiers, namely K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Multilayer Perceptron (MLP). The proposed research’s experimental results are highly effective; the training time of proposed models is reduced to over 50%, and the classification accuracy reaches 99%.