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.

Selective lithium recovery and regeneration of ternary cathode from spent lithium-ion batteries:Mixed HCl-H_(2)SO_(4) leaching-spray pyrolysis approach

The recycling of spent lithium-ion batteries(LIBs) is crucial for environmental protection and resource sustainability.However,the economic recovery of spent LIBs remains challenging due to low Li recovery efficiency and the need for multiple separation operations.Here,we propose a process involving mixed HCl-H_(2)SO_(4) leaching-spray pyrolysis for recycling spent ternary LIBs,achieving both selective Li recovery and the preparation of a ternary oxide precursor.Specifically,the process transforms spent ternary cathode(LiNi_(x)Co_yMn_(2)O_(2),NCM) powder into Li_(2)SO_(4) solution and ternary oxide,which can be directly used for synthesizing battery-grade Li_(2)CO_(3) and NCM cathode,respectively.Notably,SO_(4)^(2-) selectively precipitates with Li^(+) to form thermostable Li_(2)SO_(4) during the spray pyrolysis,which substantially improves the Li recovery efficiency by inhibiting Li evaporation and intercalation.Besides,SO_(2) emissions are avoided by controlling the molar ratio of Li^(+)/SO_(4)^(2-)(≥2:1),The mechanism of the preferential formation of Li_(2)SO_(4) is interpreted from its reverse solubility variation with temperature.During the recycling of spent NCM811,92% of Li is selectively recovered,and the regenerated NCM811 exhibits excellent cycling stability with a capacity retention of 81.7% after 300 cycles at 1 C.This work offers a simple and robust process for the recycling of spent NCM cathodes.

Changes of community characteristics of a broad-leaved-conifer mixed forest after selection cutting

The modification in structure, composition, and diversity, shrub, as well as herb strata ofPinus koraiensis-Tilia amurensis-Abies nephrolepis forest after 16a of selection cutting in northeastern China was studied. In the selection cutting forest, individuals with small DBH classes characterized size distribution. The virgin forest, on the other hand, was mainly composed of individuals having larger DBH classes. The density of dominant species and the species diversity at tree stratum in the selection-cutting stand was significantly larger than that of in the primeval forest. The shrub layer also showed a similar result. However, the herb layer had comparatively low species diversity. Large growing space and strong light in the artificial gaps must have provided opportunities for the species of shade tolerance or shade intolerance to establish on the stand. The juveniles of non-pioneer species, which were hardly found in highly shaded virgin forest, were also released by the disturbance. Regeneration in the selection-cutting stand was prompted by the disturbance, where the density of saplings occurred nearly 3 times as much as that in the virgin stand. The growth of shrub layer was improved due to the alteration in light condition. The projection volume of the herb layer was less affected. Restoration of a semi-virgin forest to the original status after selection cutting could be possible in several decades. However, for those subjected to clear cutting, it might take several centuries. In order to promote biodiversity, it is reasonable to practice selection cutting in communities for consisting of species with various levels of shade tolerance.

Path Selection of Multimodal Transport Based on Multi-Objective Mixed Integer Programming

Based on “One Belt and One Road”, this paper studies the path selection of multimodal transport by using the method of multi-objective mixed integer programming. Therefore, this paper studies the factors of transportation time, transportation cost and transportation safety performance, and establishes a mathematical model. In addition, the method of multi-objective mixed integer programming is used to comprehensively consider the different emphasis and differences of customers on cargo transportation. Then we use planning tools of Microsoft Excel to solve path selection and to determine whether the chosen path is economical and reliable. Finally, a relatively complex road network is built as an example to verify the accuracy of this planning method.

Marginal Conceptual Predictive Statistic for Mixed Model Selection

We focus on the development of model selection criteria in linear mixed models. In particular, we propose the model selection criteria following the Mallows’ Conceptual Predictive Statistic (Cp) [1] [2] in linear mixed models. When correlation exists between the observations in data, the normal Gauss discrepancy in univariate case is not appropriate to measure the distance between the true model and a candidate model. Instead, we define a marginal Gauss discrepancy which takes the correlation into account in the mixed models. The model selection criterion, marginal Cp, called MCp, serves as an asymptotically unbiased estimator of the expected marginal Gauss discrepancy. An improvement of MCp, called IMCp, is then derived and proved to be a more accurate estimator of the expected marginal Gauss discrepancy than MCp. The performance of the proposed criteria is investigated in a simulation study. The simulation results show that in small samples, the proposed criteria outperform the Akaike Information Criteria (AIC) [3] [4] and Bayesian Information Criterion (BIC) [5] in selecting the correct model;in large samples, their performance is competitive. Further, the proposed criteria perform significantly better for highly correlated response data than for weakly correlated data.

Year-round multi-scale habitat selection by Crested Tit(Lophophanes cristatus)in lowland mixed forests(northern Italy)

Determining how animals respond to resource availability across spatial and temporal extents is crucial to understand ecological processes underpinning habitat selection.Here,we used a multi-scale approach to study the year-round habitat selection of the Crested Tit(Lophophanes cristatus)in a semi-natural lowland woodland of northern Italy,analysing different habitat features at each scale.We performed Crested Tit censuses at three different spatial scales.At the macrohabitat scale,we used geolocalized observations of individuals to compute Manly's habitat selection index,based on a detailed land-use map of the study area.At the microhabitat scale,the trees features were compared between presence and absence locations.At the foraging habitat scale,individual foraging birds and their specific position on trees were recorded using focal animal sampling.Censuses were performed during both the breeding(March to May)and wintering(December to January)seasons.At the macrohabitat scale,the Crested Tits significantly selected pure and mixed pine forests and avoided woods of alien plant species,farmlands and urban areas.At the microhabitat scale,old pine woods with dense cover were selected,with no significant difference in the features of tree selection between the two phenological phases.At the foraging habitat scale,the species was observed spending more time foraging in the canopies than in the understorey,using mostly the portion of Scots Pine(Pinus sylvestris)canopies closer to the trunk in winter,while during the breeding period,the whole canopy was visited.Overall,breeding and wintering habitats largely overlapped in the Crested Tit.Based on our findings,lowland Crested Tits can be well defined as true habitat specialists:they are strictly related to some specific coniferous woodland features.Noteworthily,compared to other tit species,which normally show generalist habits during winter,the Crested Tit behaves as a habitat specialist also out of the breeding season.Our study stressed the importance of considering multi-scale(both spatial and phenological)habitat selection in birds.

Combined Selection in Backcross Population of Papaya(Carica papaya L.)by the Mixed Model Methodology

The selection of superior genotypes based on the simultaneous response to several characteristics of agronomic importance is a key strategy to overcome the scarcity of available varieties of papaya. This study aimed to apply the combined selection by using distinct selection indexes based on both the genetic values obtained by the REML/BLUP methodology and the real measured values to select agronomically superior genotypes of papaya within backcross progenies. The combined selection was carried out based on genetic and phenotypic values, original and standardized, multiplied by the agronomic weights. The results of the analysis of genetic parameters indicate that the evaluated progenies have expressive genetic variability for the considered traits, and that there are real possibilities of genetic progress with the selection. Among the analyzed indexes, the one based on standardized genetic value presented greater consistency in the ranking of genetic material, demonstrating the advantage of data standardization. Five progenies belonging to the BC1 generation, and five to the BC3 generation were selected using this index. A total of 27 plants ag-ronomically superior were selected within the top five progenies and recommended for generation advance, 23 being selected by combined selection and 4 using the direct selection for the four mainly characters in papaya breeding program: production, pulp and fruit firmness and soluble solids. Beyond the selection of superior genotypes for the development of future inbred lines, this study also allowed defining the best strategy to apply the combined selection in papaya using pre-dicted breeding values obtained by BLUP. This strategy may allow higher accuracy in the selection process, thus increasing the chances of success of the breeding programs.

A relay selection scheme based on geometric optimum in cooperative cognitive systems over mixed channels

This paper proposes a relay selection scheme based on geometric optimum principle to maximize the cognitive link＇ s connectivity with limited interference to primary user in cooperative cognitive systems. A dual-hop cognitive relay system is considered, in which the channel impulse response follows independent non-identical distribution （i. n. d. ） each hop, such as Rician, Rayleigh and Nakagami-m distribution. Then, closed-form expressions in terms of outage probability and average bit error rate （ABER） are obtained using amplify-and-forward （AF） relaying protocol over such mixed fading channels. Furthermore, the best range of the relay is derived. Extensive simulation re- suits are conducted to verify the theoretical analysis, which is useful to the network optimal design.

High efficient mixed culture screening and selected microbial community shift for bioleaching process

To screen the high efficient mixed culture and understand the bioleaching behaviors of mixed culture for low-grade copper sulfide ore bioleaching,ten mixed cultures were collected and screened from different acid mine drainages obtained from sulfide mines of China.The leaching rate was set as criterion to screen the mixed culture and the metagenomic approach.Community genome array（CGA） was used for analyzing the mixed culture microbial community shift during the bioleaching process.The results indicate that the mixed culture obtained from Yinshan（YS） lead-zinc mine in Dexing of Jiangxi province in China reaches the maximum copper extraction（68.89%） during the one bioleaching period of 24 d.CGA results show that YS culture contains nine kinds of bacteria which are belong to six divisions,and the microbial community structure is changing during the bioleaching process.This provides a good way to accelerate the bioleaching process and reveals the microbial community shift during the bioleaching process.

Mixed neuroendocrine non-neuroendocrine neoplasms in gastroenteropancreatic tract

Mixed neuroendocrine non-neuroendocrine neoplasms(MiNENs)are a hetero-geneous group of malignant neoplasms that can settle in the gastroenteropan-creatic tract.They are composed of a neuroendocrine(NE)and a non-NE compo-nent in at least 30%of each tumour.The non-NE component can include different histological combinations of glandular,squamous,mucinous and sarcomatoid phenotypes,and one or both of the components can be low-or high grade malignant.Recent changes in the nomenclature of these neoplasms might lead to great deal of confusion,and the lack of specific clinical trials is the main reason why their management is difficult.The review aims to clarify the definition of MiNEN and analyze available evidence about their diagnosis and treatment options according to their location and extension through careful analysis of the available data.It would be important to reach a general consensus on their diagnosis in order to construct a classification that remains stable over time and facilitates the design of clinical trials that,due to their low incidence,will require long recruitment periods.

Mixed neuroendocrine and adenocarcinoma of gastrointestinal tract:A complex diagnosis and therapeutic challenge

In this editorial we comment on the manuscript describing a case of adenocarcinoma mixed with a neuroendocrine carcinoma of the gastroesophageal junction.Mixed neuroendocrine and non-neuroendocrine neoplasms of the gastrointestinal system are rare heterogeneous group of tumors characterized by a high malignant potential,rapid growth,and poor prognosis.Due to the rarity of these cancers,the standard therapy is poorly defined.The diagnosis of these tumors is based on combination of morphological features,immunohistochemical and neuroendocrine and epithelial cell markers.Both endocrine and epithelial cell components can act independently of each other and thus,careful grading of each component separately is required.These cancers are aggressive in nature and the potential of each component has paramount importance in the choice of treatment and response.Regardless of the organ of origin,these tumors portend poor prognosis with increased proportion of neuroendocrine component.Multidisciplinary services and strategies are required for the management of these mixed malignancies to provide the best oncological outcomes.The etiopathogenesis of these mixed tumors remains obscure but poses interesting question.We briefly discuss a few salient points in this editorial.

Mixed neuroendocrine non-neuroendocrine tumors:The quest for evidence

Mixed neuroendocrine non-neuroendocrine neoplasms(MiNENs)are rare mixed tumors containing both neuroendocrine and non-neuroendocrine components that occupy at least 30%of the whole tumor.Biologically,both components appear to derive from an identical cellular precursor undergoing early dual differentiation or late transdifferentiation.While our understanding of MiNENs has improved in recent years,many areas of uncertainty remain.In this context,setting diagnostic criteria capable of capturing the continuum of disease biology while providing clinically meaningful information in terms of prognosis and response to treatments appears vital to advance the field and improve patients’outcomes.Evidence is needed to generate robust classification schemes,and multi-institutional cooperation will likely play a crucial role in building adequately powered cohorts to address some of the most pressing questions discussed in this Editorial.What is the minimum representation for each component needed to define MiNENs?How can the epidemiology of MiNENs change according to different diagnostic definitions?How can we generate the clinical evidence nee-ded to optimize the management of MiNENs?

Dendroclimatological study of Sabina saltuaria and Abies faxoniana in the mixed forests of the Qionglai Mountains,eastern Tibetan Plateau

Tree-ring chronologies were developed for Sabina saltuaria and Abies faxoniana in mixed forests in the Qionglai Mountains of the eastern Tibetan Plateau.Climate-growth relationship analysis indicated that the two co-exist-ing species reponded similarly to climate factors,although S.saltuaria was more sensitive than A.faxoniana.The strong-est correlation was between S.saltuaria chronology and regional mean temperatures from June to November.Based on this relationship,a regional mean temperature from June to November for the period 1605-2016 was constructed.Reconstruction explained 37.3%of the temperature variance during th period 1961-2016.Six major warm periods and five major cold periods were identified.Spectral analysis detected significant interannual and multi-decadal cycles.Reconstruction also revealed the influence of the Atlantic Multi-decadal Oscillation,confirming its importance on climate change on the eastern Tibetan Plateau.

Enhanced selective catalytic reduction of NO with NH3 via porous micro-spherical aggregates of Mn–Ce–Fe–Ti mixed oxide nanoparticles

We rationally designed a high performance denitration(De-NOx) catalyst based on a micrometer-sized spherical Mn–Ce–Fe–Ti(CP-SD)catalyst for selective catalytic reduction(SCR). This was prepared by a co-precipitation and spray drying(CP-SD) method. The catalyst was systematically characterized, and its morphological structure and surface properties were identified. Compare with conventional Mn–Ce–Fe–Ti(CP) catalysts, the Mn–Ce–Fe–Ti(CP-SD) catalyst had superior surface-adsorbed oxygen leading to enhanced 'fast NH3-SCR' reaction. The asobtained Mn–Ce–Fe–Ti(CP-SD) catalyst offered excellent NO conversion and N2 selectivity of 100.0% and 84.8% at 250℃, respectively, with a gas hourly space velocity(GHSV) of 40,000 h-1. The porous micro-spherical structure provides a larger surface area and more active sites to adsorb and activate the reaction gases. In addition, the uniform distribution and strong interaction of manganese, iron, cerium, and titanium oxide species improved H2O and SO2 resistance. The results showed that the Mn–Ce–Fe–Ti(CP-SD) catalyst could be used prospectively as a denitration(De-NOx) catalyst.

Amino-functionalized UiO-66-doped mixed matrix membranes with high permeation performance and fouling resistance

For the reduction of bovine serum proteins from wastewater,a novel mixed matrix membrane was prepared by functionalizing the substrate material polyaryletherketone(PAEK),followed by carboxyl groups(C-SPAEKS),and then adding amino-functionalized UiO-66-NH_(2)(Am-UiO-66-NH_(2)).Aminofunctionalization of UiO-66 was accomplished by melamine,followed by an amidation reaction to immobilize Am-UiO-66-NH_(2),which was immobilized on the surface of the membrane as well as in the pore channels,which enhanced the hydrophilicity of the membrane surface while increasing the negative potential of the membrane surface.This nanoparticle-loaded ultrafiltration membrane has good permeation performance,with a pure water flux of up to 482.3 L·m^(-2)·h^(-1) for C-SPAEKS/AmUiO-66-NH_(2) and a retention rate of up to 98.7%for bovine serum albumin(BSA)-contaminated solutions.Meanwhile,after several hydrophilic modifications,the flux recovery of BSA contaminants by this series of membranes increased from 56.2%to 80.55%of pure membranes.The results of ultra-filtration flux time tests performed at room temperature showed that the series of ultrafiltration membranes remained relatively stable over a test time of 300 min.Thus,the newly developed mixed matrix membrane showed potential for high efficiency and stability in wastewater treatment containing bovine serum proteins.

Separation of mixed salts(Cl-/SO42-) by ED based on monovalent anion selective membranes

The industrial products or wastewater rich in the mixed salts(Cl-/SO4^2-) not only causes the environmental damage, but also induces waste of resource. In this study, an ED stack with monovalent selective AEMs and conventional CEMs was employed to separate the Cl-and SO42-from simulated wastewater. The effect of current density and mass fraction percentage was investigated in order to optimize the experimental conditions during ED process. It was found that at a concentration ratio between NaCl and Na2SO4 of 95/5(wt%/wt%) and a current density of40 m A·cm^-2, a current efficiency of 72%, an energy consumption of 1.6 k W·h·kg^-1 Na Cl and a Cl-/SO4^2-concentration(67.5/3.5 g·L^-1) were obtained. Hence, it is appropriate and effective to separate Cl-and SO42-by ED using the monovalent selective AEMs.

A mixed-coordination electron trapping-enabled high-precision touch-sensitive screen for wearable devices

Touch-sensitive screens are crucial components of wearable devices.Materials such as reduced graphene oxide(rGO),carbon nanotubes(CNTs),and graphene offer promising solutions for flexible touch-sensitive screens.However,when stacked with flexible substrates to form multilayered capacitive touching sensors,these materials often suffer from substrate delamination in response to deformation;this is due to the materials having different Young’s modulus values.Delamination results in failure to offer accurate touch screen recognition.In this work,we demonstrate an induced charge-based mutual capacitive touching sensor capable of high-precision touch sensing.This is enabled by electron trapping and polarization effects related to mixed-coordinated bonding between copper nanoparticles and vertically grown graphene nanosheets.Here,we used an electron cyclotron resonance system to directly fabricate graphene-metal nanofilms(GMNFs)using carbon and copper,which are firmly adhered to flexible substrates.After being subjected to 3000 bending actions,we observed almost no change in touch sensitivity.The screen interaction system,which has a signal-to-noise ratio of 41.16 dB and resolution of 650 dpi,was tested using a handwritten Chinese character recognition trial and achieved an accuracy of 94.82%.Taken together,these results show the promise of touch-sensitive screens that use directly fabricated GMNFs for wearable devices.

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.

Recent progress in ternary mixed matrix membranes for CO_(2) separation

Mixed matrix membranes(MMMs)could combine the advantages of both polymeric membranes and porousfillers,making them an effective alternative to conventional polymer membranes.However,interfacial incompatibility issues,such as the presence of interfacial voids,hardening of polymer chains,and blockage of micropores by polymers between common MMMsfillers and the polymer matrix,currently limit the gas sep-aration performance of MMMs.Ternary phase MMMs(consisting of afiller,an additive,and a matrix)made by adding a third compound,usually functionalized additives,can overcome the structural problems of binary phase MMMs and positively impact membrane separation performance.This review introduces the structure and fabrication processes for ternary MMMs,categorizes various nanofillers and the third component,and summarizes and analyzes in detail the CO_(2) separation performance of newly developed ternary MMMs based on both rubbery and glassy polymers.Based on this separation data,the challenges of ternary MMMs are also discussed.Finally,future directions for ternary MMMs are proposed.

Mixed D-vine copula-based conditional quantile model for stochastic monthly streamflow simulation

Copula functions have been widely used in stochastic simulation and prediction of streamflow.However,existing models are usually limited to single two-dimensional or three-dimensional copulas with the same bivariate block for all months.To address this limitation,this study developed a mixed D-vine copula-based conditional quantile model that can capture temporal correlations.This model can generate streamflow by selecting different historical streamflow variables as the conditions for different months and by exploiting the conditional quantile functions of streamflows in different months with mixed D-vine copulas.The up-to-down sequential method,which couples the maximum weight approach with the Akaike information criteria and the maximum likelihood approach,was used to determine the structures of multivariate Dvine copulas.The developed model was used in a case study to synthesize the monthly streamflow at the Tangnaihai hydrological station,the inflow control station of the Longyangxia Reservoir in the Yellow River Basin.The results showed that the developed model outperformed the commonly used bivariate copula model in terms of the performance in simulating the seasonality and interannual variability of streamflow.This model provides useful information for water-related natural hazard risk assessment and integrated water resources management and utilization.