Congruent Feature Selection Method to Improve the Efficacy of Machine Learning-Based Classification in Medical Image Processing

Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.

Genetic variation and selection of 10-year-old Eucalyptus camaldulensis based on wind damage index and wood properties

Typhoons are becoming frequent and intense with ongoing climate change,threatening ecological security and healthy forest development in coastal areas.Eucalyptus of a predominant introduced species in southern China,faces significant growth challenges because of typhoon.Therefore,it is vital to investigate the variation of related traits and select superior breeding materials for genetic improvement.Variance,genetic parameter,and correlation analyses were carried out on wind damage indices and eight wood proper-ties in 88 families from 11 provenances of 10-year-old Euca-lyptus camaldulensis.The selection index equation was used for evaluating multiple traits and selecting superior prov-enances and family lines as future breeding material.The results show that all traits were highly significantly differ-ent at provenance and family levels,with the wind damage index having the highest coefficient of genetic variation.The heritability of each trait ranged from 0.48 to 0.87,with the wind damage index,lignin and hemicellulose contents,and microfibril angle having the highest heritabilities.The wind damage index had a positive genetic correlation with wood density,a negative correlation with lignin content,a negative phenotypic correlation and a negative genetic correlation with microfibril angle.Wind damage index and genetic progress in the selection of eight wood traits varied from 7.2%to 614.8%.Three provenances and 12 superior families were selected.The genetic gains of the wind damage index were 10.2%and 33.9%for provenances and families,and these may be starting material for genetic modification for wind resistance in eucalyptus and for their dissemination to typhoon-prone coastal areas of southern China.

The genetics of pediatric inflammatory bowel disease:Towards precision medicine

Pediatric inflammatory bowel disease(IBD)is a chronic and heterogeneous disease.IBD is commonly classified into Crohn’s disease and ulcerative colitis.It is linked to serious symptoms and complications.The onset of IBD commonly occurs during adolescence.Despite the significant number of cases globally(~5 million),the causes of pediatric IBD,which constitutes 25%of IBD patients,are not yet fully understood.Apart from environmental factors,genetic factors contribute to a higher risk of developing IBD.The predisposition risk of IBD can be investigated using genetic testing.Genetic mechanisms of pediatric IBD are highly complex which resulted in difficulty in selecting effective treatment or patient management.Genetic variation of IBD would serve as a basis for precision medicine and allow for the discovery of more robust treatment avenues for this condition in pediatric patients.This review aims to discuss the genetics of pediatric IBD,and current development in the screening,diagnosis,and treatment based on genetic profiling of pediatric IBD subjects toward more personalized management of this disease.

Genomic selection for meat quality traits based on VIS/NIR spectral information

The principle of genomic selection(GS) entails estimating breeding values(BVs) by summing all the SNP polygenic effects. The visible/near-infrared spectroscopy(VIS/NIRS) wavelength and abundance values can directly reflect the concentrations of chemical substances, and the measurement of meat traits by VIS/NIRS is similar to the processing of genomic selection data by summing all ‘polygenic effects' associated with spectral feature peaks. Therefore, it is meaningful to investigate the incorporation of VIS/NIRS information into GS models to establish an efficient and low-cost breeding model. In this study, we measured 6 meat quality traits in 359Duroc×Landrace×Yorkshire pigs from Guangxi Zhuang Autonomous Region, China, and genotyped them with high-density SNP chips. According to the completeness of the information for the target population, we proposed 4breeding strategies applied to different scenarios: Ⅰ, only spectral and genotypic data exist for the target population;Ⅱ, only spectral data exist for the target population;Ⅲ, only spectral and genotypic data but with different prediction processes exist for the target population;and Ⅳ, only spectral and phenotypic data exist for the target population.The 4 scenarios were used to evaluate the genomic estimated breeding value(GEBV) accuracy by increasing the VIS/NIR spectral information. In the results of the 5-fold cross-validation, the genetic algorithm showed remarkable potential for preselection of feature wavelengths. The breeding efficiency of Strategies Ⅱ, Ⅲ, and Ⅳ was superior to that of traditional GS for most traits, and the GEBV prediction accuracy was improved by 32.2, 40.8 and 15.5%, respectively on average. Among them, the prediction accuracy of Strategy Ⅱ for fat(%) even improved by 50.7% compared to traditional GS. The GEBV prediction accuracy of Strategy Ⅰ was nearly identical to that of traditional GS, and the fluctuation range was less than 7%. Moreover, the breeding cost of the 4 strategies was lower than that of traditional GS methods, with Strategy Ⅳ being the lowest as it did not require genotyping.Our findings demonstrate that GS methods based on VIS/NIRS data have significant predictive potential and are worthy of further research to provide a valuable reference for the development of effective and affordable breeding strategies.

Early and accurate diagnosis and selection of appropriate treatment plans are crucial for patients with gastrointestinal hemangiomas

Gastrointestinal hemangioma(GIH)is clinically rare,accounting for 7%-10%of benign gastrointestinal tumors and 0.5%of systemic hemangiomas.GIH can occur as either solitary or multiple lesions,with gastrointestinal bleeding as a significant clinical manifestation.Understanding the clinical and endoscopic features of GIH is essential for improving diagnostic accuracy,particularly through endoscopy and selective arteriography,which are highly effective in diagnosing GIH and preventing misdiagnosis and inappropriate treatment.Upon confirmed diagnosis,it is essential to thoroughly evaluate the patient's condition to determine the most suitable treatment modality—whether surgical,endoscopic,or minimally invasive intervention.The minimally invasive interventional partial embolization therapy using polyvinyl alcohol particles,proposed and implemented by Pospisilova et al,has achieved excellent clinical outcomes.This approach reduces surgical trauma and the inherent risks of traditional surgical treatments.

Melon2K array:A versatile 2K liquid SNP chip for melon genetics and breeding

High-throughput genotyping tools can effectively promote molecular breeding in crops.In this study,genotyping by target sequencing(GBTS)system was utilized to develop a genome-wide liquid SNP chip for facilitating genetics and breeding in melon(Cucumis melo L.),a globally cultivated economically important horticultural crop.Based on over eight million SNPs derived from 823 representative melon accessions,16K,8K,4K,2K,1K,500,250 and 125 informative SNPs were screened and evaluated for their polymorphisms,conservation of flanking sequences,and distributions.The set of 2K SNPs was found to be optimal for representing the maximum diversity with the lowest number of SNPs,and it was selected to develop the liquid chip,named“Melon2K”.Using Melon2K,more than 1500 SNPs were detected across 17 samples of five melon cultivars,and the phylogenetic relationships were clearly constructed.Within the same cultivar,genetic differences were also assessed between different samples.We evaluated the performance of Melon2K in genetic background selection during the breeding process,obtaining the introgression lines of interested trait with more than 97%genetic background of elite variety by only two rounds of backcrossing.These results suggest that Melon2K provides a cost-effective,efficient and reliable platform for genetic analysis and molecular breeding in melon.

Parameters selection in gene selection using Gaussian kernel support vector machines by genetic algorithm

In microarray-based cancer classification, gene selection is an important issue owing to the large number of variables and small number of samples as well as its non-linearity. It is difficult to get satisfying results by using conventional linear sta- tistical methods. Recursive feature elimination based on support vector machine (SVM RFE) is an effective algorithm for gene selection and cancer classification, which are integrated into a consistent framework. In this paper, we propose a new method to select parameters of the aforementioned algorithm implemented with Gaussian kernel SVMs as better alternatives to the common practice of selecting the apparently best parameters by using a genetic algorithm to search for a couple of optimal parameter. Fast implementation issues for this method are also discussed for pragmatic reasons. The proposed method was tested on two repre- sentative hereditary breast cancer and acute leukaemia datasets. The experimental results indicate that the proposed method per- forms well in selecting genes and achieves high classification accuracies with these genes.

Genetic variation and selection of introduced provenances of Siberian Pine(Pinus sibirica) in frigid regions of the Greater Xing'an Range,Northeast China

Siberian Pine （Pinus sibirica） is an ecologically and eco-nomically important species in pristine forests throughout northern Rus-sia. Four provenances of P. sibirica were introduced from Mongolia and Russia to the Greater Xing’an Range （the Daxing’anling）, northeast China in 1993. The aim of this research was to study genetic variation and selection of the introduced four Pinus sibirica provenances. Heights （H）, basal diameters （BD）, survival rates （SR） and crown lengths （CL） of different families were measured as primary outcomes in different growth years. Results of data analyses demonstrated high coefficients of phenotypic variation （PCV） and heritability （H2） for H, BD and CL at 18 years after introduction. PCV and H2 increased with age. Correlations of＆amp;nbsp;growth traits between any two growth years were all significantly positive, but the correlation coefficient was smaller when the growth year interval was larger. Correlations between H and the original environment factors decreased gradually, indicating that with long-term subsistence in the new environment, the influence of the source environment declined. Colligation of multiple traits to estimate provenances showed that Novosibirsk, Tomsk, and Altai Mountains had higher survival rates and biomass, and proved more suitable for introduction and plantation in the Greater Xing’an Range in China.

Genetic Diversity of Maize Populations Developed by Two Kinds of Recurrent Selection Methods Investigated with SSR Markers

Two cycles of biparental mass selection （MS） and one cycle of half-sib-S3 family combining selection （HS-S3） for yield were carried out in 2 synthetic maize populations P4C0 and P5C0 synchronously. The genetic diversity of 8 maize populations, including both the basic populations and their developed populations, were evaluated by 30 SSR primers. On the 30 SSR loci, a total of 184 alleles had been detected in these populations. At each locus, the number of alleles varied from 2 to 14, with an average of 6.13. The number and ratio of polymorphic loci in both the basic populations were higher than those of their developed populations, respectively. There was nearly no difference after MS but decreased after HS-S3 in both the basic populations in the mean gene heterozygosity. The mean genetic distance changed slightly after MS but decreased in a bigger degree after HS-S3 in both the basic populations. Analyses on the distribution of genetic distances showed that the ranges of the genetic distance were wider after MS and most of the genetic distances in populations developed by HS-S3 were smaller than those in both the basic populations. The number of genotypes increased after MS but decreased after HS-S3 in both the basic populations. The genetic diversity of intra-population was much more than genetic diversity of inter-population in both the basic populations. All these indexes demonstrated that the genetic diversity of populations after MS was similar to their basic populations, and the genetic diversity was maintained during MS, whereas the genetic diversity of populations decreased after HS-S3. This result indicated that heterogeneity between some of the individuals in the developed populations increased after MS, whereas the populations become more homozygotic after HS-S3.

Multi-Strategy Assisted Multi-Objective Whale Optimization Algorithm for Feature Selection

In classification problems,datasets often contain a large amount of features,but not all of them are relevant for accurate classification.In fact,irrelevant features may even hinder classification accuracy.Feature selection aims to alleviate this issue by minimizing the number of features in the subset while simultaneously minimizing the classification error rate.Single-objective optimization approaches employ an evaluation function designed as an aggregate function with a parameter,but the results obtained depend on the value of the parameter.To eliminate this parameter’s influence,the problem can be reformulated as a multi-objective optimization problem.The Whale Optimization Algorithm(WOA)is widely used in optimization problems because of its simplicity and easy implementation.In this paper,we propose a multi-strategy assisted multi-objective WOA(MSMOWOA)to address feature selection.To enhance the algorithm’s search ability,we integrate multiple strategies such as Levy flight,Grey Wolf Optimizer,and adaptive mutation into it.Additionally,we utilize an external repository to store non-dominant solution sets and grid technology is used to maintain diversity.Results on fourteen University of California Irvine(UCI)datasets demonstrate that our proposed method effectively removes redundant features and improves classification performance.The source code can be accessed from the website:https://github.com/zc0315/MSMOWOA.

ZResponse to selection,heritability and genetic correlations between body weight and body size in Pacific white shrimp,Litopenaeus vannamei

To quantify the response to selection, heritability and genetic correlations between weight and size ofLitopenaeus vannamei, the body weight （BW）, total length （TL）, body length （BL）, first abdominal segment depth （FASD）, third abdominal segment depth （TASD）, first abdominal segment width （FASW）, and partial carapace length （PCL） of 5-month-old parents and of offspring were measured by calculating seven body measurings of offspring produced by a nested mating design. Seventeen half-sib families and 42 full-sib families ofL. vannamei were produced using artificial fertilization from 2-4 dams by each sire, and measured at around five months post-metamorphosis. The results show that heritabilities among various traits were high： 0.515±0.030 for body weight and 0.394±0.030 for total length. After one generation of selection, the selection response was 10.70% for offspring growth. In the 5th month, the realized heritability for weight was 0.296 for the offspring generation. Genetic correlations between body weight and body size were highly variable. The results indicate that external morphological parameters can be applied during breeder selection for enhancing the growth without sacrificing animals for determining the body size and breed ability; and selective breeding can be improved significantly, simultaneously with increased production.

Anti-Byzantine Attacks Enabled Vehicle Selection for Asynchronous Federated Learning in Vehicular Edge Computing

In vehicle edge computing(VEC),asynchronous federated learning(AFL)is used,where the edge receives a local model and updates the global model,effectively reducing the global aggregation latency.Due to different amounts of local data,computing capabilities and locations of the vehicles,renewing the global model with same weight is inappropriate.The above factors will affect the local calculation time and upload time of the local model,and the vehicle may also be affected by Byzantine attacks,leading to the deterioration of the vehicle data.However,based on deep reinforcement learning(DRL),we can consider these factors comprehensively to eliminate vehicles with poor performance as much as possible and exclude vehicles that have suffered Byzantine attacks before AFL.At the same time,when aggregating AFL,we can focus on those vehicles with better performance to improve the accuracy and safety of the system.In this paper,we proposed a vehicle selection scheme based on DRL in VEC.In this scheme,vehicle’s mobility,channel conditions with temporal variations,computational resources with temporal variations,different data amount,transmission channel status of vehicles as well as Byzantine attacks were taken into account.Simulation results show that the proposed scheme effectively improves the safety and accuracy of the global model.

Genetic Feature Selection for Texture Classification

This paper presents a novel approach to feature subset selection using genetic algorithms. This approach has the ability to accommodate multiple criteria such as the accuracy and cost of classification into the process of feature selection and finds the effective feature subset for texture classification. On the basis of the effective feature subset selected, a method is described to extract the objects which are higher than their surroundings, such as trees or forest, in the color aerial images. The methodology presented in this paper is illustrated by its application to the problem of trees extraction from aerial images.

Selection Method of Multi-Objective Problems Using Genetic Algorithm in Motion Plan of AUV

To research the effect of the selection method of multi — objects genetic algorithm problem on optimizing result, this method is analyzed theoretically and discussed by using an autonomous underwater vehicle (AUV) as an object. A changing weight value method is put forward and a selection formula is modified. Some experiments were implemented on an AUV, TwinBurger. The results shows that this method is effective and feasible.

Selection of dialysis methods for end-stage kidney disease patients with diabetes

The increasing prevalence of diabetes has led to a growing population of endstage kidney disease(ESKD)patients with diabetes.Currently,kidney transplantation is the best treatment option for ESKD patients;however,it is limited by the lack of donors.Therefore,dialysis has become the standard treatment for ESKD patients.However,the optimal dialysis method for diabetic ESKD patients remains controversial.ESKD patients with diabetes often present with complex conditions and numerous complications.Furthermore,these patients face a high risk of infection and technical failure,are more susceptible to malnutrition,have difficulty establishing vascular access,and experience more frequent blood sugar fluctuations than the general population.Therefore,this article reviews nine critical aspects:Survival rate,glucose metabolism disorder,infectious complications,cardiovascular events,residual renal function,quality of life,economic benefits,malnutrition,and volume load.This study aims to assist clinicians in selecting individualized treatment methods by comparing the advantages and disadvantages of hemodialysis and peritoneal dialysis,thereby improving patients’quality of life and survival rates.

Comparison of debris flow susceptibility assessment methods:support vector machine,particle swarm optimization,and feature selection techniques

The selection of important factors in machine learning-based susceptibility assessments is crucial to obtain reliable susceptibility results.In this study,metaheuristic optimization and feature selection techniques were applied to identify the most important input parameters for mapping debris flow susceptibility in the southern mountain area of Chengde City in Hebei Province,China,by using machine learning algorithms.In total,133 historical debris flow records and 16 related factors were selected.The support vector machine(SVM)was first used as the base classifier,and then a hybrid model was introduced by a two-step process.First,the particle swarm optimization(PSO)algorithm was employed to select the SVM model hyperparameters.Second,two feature selection algorithms,namely principal component analysis(PCA)and PSO,were integrated into the PSO-based SVM model,which generated the PCA-PSO-SVM and FS-PSO-SVM models,respectively.Three statistical metrics(accuracy,recall,and specificity)and the area under the receiver operating characteristic curve(AUC)were employed to evaluate and validate the performance of the models.The results indicated that the feature selection-based models exhibited the best performance,followed by the PSO-based SVM and SVM models.Moreover,the performance of the FS-PSO-SVM model was better than that of the PCA-PSO-SVM model,showing the highest AUC,accuracy,recall,and specificity values in both the training and testing processes.It was found that the selection of optimal features is crucial to improving the reliability of debris flow susceptibility assessment results.Moreover,the PSO algorithm was found to be not only an effective tool for hyperparameter optimization,but also a useful feature selection algorithm to improve prediction accuracies of debris flow susceptibility by using machine learning algorithms.The high and very high debris flow susceptibility zone appropriately covers 38.01%of the study area,where debris flow may occur under intensive human activities and heavy rainfall events.

Genetic Diversity of Recurrent Selection Populations with Ms2 Gene Assessed by Gliadins in Common Wheat (Triticum aestivum L.)

The male-sterile lines with Ms2 gene were highly evaluated in recurrent selection in wheat （Triticum aestivum L.）. Three populations C6 （population after six cycles of selection）, C7 （population after seven cycles of selection）, and C8 （population after eight cycles of selection） were constructed through recurrent selection with 12 parental materials （P）. Acid polyacrymide gel electrophoresis （A-PAGE） analysis was used to identify gliadin patterns and evaluate the genetic diversity in 12 parents and three populations. A total of 63 bands were identified, of which 17 polymorphic bands and 7 unique bands were present in populations and seven polymorphic bands and four unique bands were present in parents. The number of polymorphic and unique bands decreased gradually from C6 to C8, especially for to- and y-gliadins. The genetic distances in C6, C7, and C8 were calculated. The distributions of genetic distance were different in three recurrent selection populations. From C6 to C8, the genetic distance was 0.2687, 0.2652 and 0.1987, respectively. Statistically significant differences were detected between C7 and C8 with the T value of 37.9718. The result of cluster analysis based on genetic similarity matrix of three populations fitted well to those of principle coordinates analysis （PCoA）. Compared with 12 parents, almost all individuals of three populations are new genotypes. Most of the individuals from C6 and C7 could be divided into two groups, while most individuals of C8 were in one cluster. In conclusion, the results indicated that the genetic diversity was decreased severely according to the information revealed by A-PAGE, although some variations could be created in the recurrent selection. It was necessary to introduce diverse germplasm based on the genetic database of recurrent population to maintain and improve the breeding efficiency in the further program.

Genetic parameters and response to selection for body weight in turbot(Scophthalmus maximus, Linnaeus)

Genetic parameters and response to selection were estimated for harvest body weight in turbot. The data consisted of 10 952 individuals of 508 full-sib families from three generations（G0, G1, and G2）. The heritability estimates for G0, G1, and G2 were 0.11±0.08, 0.18±0.09, and 0.17±0.07, respectively. Over three generations, the heritability estimate was 0.19±0.04. Maternal and common environmental effects were 0.10±0.04, 0.14±0.04, and0.13±0.03 within each generation and 0.12±0.01 across generations. The selection differential in growth was 18.24 g in G0 and 21.19 g in G1 corresponding to an average of 19.72 g per generation. The genetic gains were also calculated, they were 22.06 g in G1 and 11.93 g in G2, corresponding to 6.36% and 3.52% body weight. The total genetic gain after two generations was 10.10% body weight, which indicated that the selective breeding program for the body weight trait in turbot was successful.

Genetic algorithm for pareto optimum-based route selection

A quality of service （QoS） or constraint-based routing selection needs to find a path subject to multiple constraints through a network. The problem of finding such a path is known as the multi-constrained path （MCP） problem, and has been proven to be NP-complete that cannot be exactly solved in a polynomial time. The NPC problem is converted into a multiobjective optimization problem with constraints to be solved with a genetic algorithm. Based on the Pareto optimum, a constrained routing computation method is proposed to generate a set of nondominated optimal routes with the genetic algorithm mechanism. The convergence and time complexity of the novel algorithm is analyzed. Experimental results show that multiobjective evolution is highly responsive and competent for the Pareto optimum-based route selection. When this method is applied to a MPLS and metropolitan-area network, it will be capable of optimizing the transmission performance.

Genetic Variation Assessed with Microsatellites in Mass Selection Lines of the Pacific Oyster (Crassostrea gigas) in China

Abstract Four successive mass selection lines of the Pacific oyster, Crassostrea gigas, selected for faster growth in breeding pro- grams in China were examined at ten polymorphic microsatellite loci to assess the level of allelic diversity and estimate the effective population size. These data were compared with those of their base population. The results showed that the genetic variation of the four generations were maintained at high levels with an average allelic richness of 18.8-20.6, and a mean expected heterozygosity of 0.902-0.921. They were not reduced compared with those of their base population. Estimated effective population sizes based on temporal variances in microsatellite frequencies were smaller to that of sex ratio-corrected broodstock count estimates. Using a rela- tively large number ofbroodstock and keeping an equal sex ratio in the broodstock each generation may have contributed to retaining the original genetic diversity and maintaining relatively large effective population size. The results obtained in this study showed that the genetic variation was not affected greatly by mass selection progress and high genetic variation still existed in the mass selection lines, suggesting that there is still potential for increasing the gains in future generations of C. gigas. The present study provided im- portant information for future genetic improvement by selective breeding, and for the design of suitable management guidelines for genetic breeding of C. gigas.