Search

As stated earlier on, adding heat and moisture to the inspired gas during invasive mechanical ventilation is mandatory. This can be adequately achieved both by HMEs and heated humidifiers [1].

Genomic prediction models are often calibrated using multi-generation data. Over time, as data accumulates, training data sets become increasingly heterogeneous. Differences in allele frequency and linkage disequilibrium patterns between the training and prediction genotypes may limit prediction accuracy. This leads to the question of whether all available data or a subset of it should be used to calibrate genomic prediction models. Previous research on training set optimization has focused on identifying a subset of the available data that is optimal for a given prediction set. However, this approach does not contemplate the possibility that different training sets may be optimal for different prediction genotypes. To address this problem, we recently introduced a sparse selection index (SSI) that identifies an optimal training set for each individual in a prediction set. Using additive genomic relationships, the SSI can provide increased accuracy relative to genomic-BLUP (GBLUP). Non-parametric genomic models using Gaussian kernels (KBLUP) have, in some cases, yielded higher prediction accuracies than standard additive models. Therefore, here we studied whether combining SSIs and kernel methods could further improve prediction accuracy when training genomic models using multi-generation data. Using four years of doubled haploid maize data from the International Maize and Wheat Improvement Center (CIMMYT), we found that when predicting grain yield the KBLUP outperformed the GBLUP, and that using SSI with additive relationships (GSSI) lead to 5–17% increases in accuracy, relative to the GBLUP. However, differences in prediction accuracy between the KBLUP and the kernel-based SSI were smaller and not always significant.

Most complex traits evolved in the ancestors of all modern humans and have been under negative or balancing selection to maintain the distribution of phenotypes observed today. Yet all large studies mapping genomes to complex traits occur in populations that have experienced the Out-of-Africa bottleneck. Does this bottleneck affect the way we characterise complex traits? We demonstrate using the 1000 Genomes dataset and hypothetical complex traits that genetic drift can strongly affect the joint distribution of effect size and SNP frequency, and that the bias can be positive or negative depending on subtle details. Characterisations that rely on this distribution therefore conflate genetic drift and selection. We provide a model to identify the underlying selection parameter in the presence of drift, and demonstrate that a simple sensitivity analysis may be enough to validate existing characterisations. We conclude that biobanks characterising more worldwide diversity would benefit studies of complex traits.

A new kind of coronavirus, the SARS-Cov2, started the biggest pandemic of the century. It has already killed more than 250,000 people. Due to this fact, it is necessary quick and precise easily available diagnosis tests. The current Covid-19 diagnosis benchmark is RT-PCR with DNA identification, but its results takes too long to be available. Tests based on IgM/IgG antibodies have been used, but their sensitivity and specificity may be very low when viral charge is reduced. Many studies have been demonstrating the Covid-19 impact in hematological parameters. This work proposes an intelligent system to support Covid-19 diagnosis based on blood testing. We employed a dataset provided by Hospital Israelita Albert Einstein, a Brazilian private hospital. The database contains the results of more than one hundred laboratory exams, such as blood count, tests for the presence of viruses such as influenza A, and urine tests, of 5644 patients. Among these patients, 559 of them are infected with SARS-Cov2. We used metaheuristics algorithms to reduce the set of We tested several machine learning methods, and we achieved high classification performance: 95.159% +- 0.693 of overall accuracy, kappa index of 0.903 +- 0.014, sensitivity of 0.968 +- 0.007, precision of 0.938 +- 0.010, and specificity of 0.936 +- 0.011. Experimental results pointed out to Bayes Network as the best configuration. In addition, only 24 blood tests were needed. This points to the possibility of a new low cost rapid test based on common blood exams and intelligent software. The desktop version of the system is fully functional and available for free use.

The presented work shows how a user centered approach might be used to generate and select the optimal design of smart garments for biosignal acquisition. Design is driven by human biosignal analysis, allowing the translation of subjective user’s feelings into technical specification and the definition of customized criteria for concepts evaluation. So, different concepts are generated and, involving users again, the optimal one is chosen using multi criteria decision making based on Fuzzy AHP theory. A case study on a wearable system (i.e., electromyographic shorts) for football performance and risk injury analysis is shown.

The end of Ban Ki-moon’s second term in office led to significant changes in the process to select the next Secretary-General, including a clear invitation to nominate women candidates. Seven women and six men were nominated. This chapter analyses why women have failed to gain the Secretary-Generalship despite the fact that the idea of a woman Secretary-General gained significant support from member states, campaign groups and the media during the 2016 selection process. In this campaign gender equality competed with demands that the selection follow the principles of regional representation as the Eastern Europe regional group demanded their turn, and the most widely shared demand that the selection process should foreground ‘merit’ as the central selection criteria, in order to avoid the selection of a political compromise candidate—as has happened in previous selections. Whilst process innovation indeed depoliticised the selection to the extent that member states, in particular the Permanent Five who were discouraged from deal-making behind closed doors, references to merit facilitated women’s access to the selection process, yet also prevented a woman from being selected for the role of Secretary-General. Indeed, merit and merit discourses have become more recently part of a backlash against gender parity.

This paper considers the problem of creating a model of a convolutional neural network for recognizing tree species from the image of a trunk for ground-based lidar taxation of forest stands. To increase the probability of recognition, it is proposed to use a telegram bot for augmentation of the training set. Training, selection and comparison of convolutional neural network models was performed. A telegram bot has been created that allows you to automate the collection of images of the training sample. The study opens a cycle of works on modeling the carbon balance of forest plantations.

Asynchronous evolutionary algorithms are becoming increasingly popular as a means of making full use of many processors while solving computationally expensive search and optimization problems. These algorithms excel at keeping large clusters fully utilized, but may sometimes inefficiently sample an excess of fast-evaluating solutions at the expense of higher-quality, slow-evaluating ones. We introduce a steady-state parent selection strategy, SWEET (“Selection whilE EvaluaTing”), that sometimes selects individuals that are still being evaluated and allows them to reproduce early. This gives slow-evaluating individuals that have higher fitnesses an increased ability to multiply in the population. We find that SWEET appears effective in simulated take-over time analysis, but that its benefit is confined mostly to early in the run, and our preliminary study on an autonomous vehicle controller problem that involves tuning a spiking neural network proves inconclusive.

In this chapter we describe the origins and mathematics used in the development of the New Investments to Risked Options (NITRO) portfolio selection tool. This tool was used by the Australian Department of Defence in 2019 for a major review of Australia’s military force structure called the Force Structure Plan 2020. This is a strategic decision making process that specifies the requirements for the future force structure and identifies, selects, and schedules projects to satisfy those requirements. In order to satisfy organisational needs, the tool was implemented in Microsoft Excel® using the What’sBest!® optimisation add-in. In this chapter we provide background on the portfolio optimisation problem in Defence. We discuss the challenges of implementing a project portfolio selection and scheduling tool in the Excel® environment along with simple approaches to the visualisation of optimised portfolios. We examine the performance differences between this tool and other commercial solvers. We also analyse the trade-off of using relaxed versus integer decision variables and the use of budget slack on the portfolio selection. We conclude by discussing current portfolio optimisation issues and challenges, along with the viability of the Excel® environment for Defence portfolio selection.

The aim of this study is to discover the supreme and other most important criteria that count in decision making considering vital uncertainties associated with certain parameters, risks, and costs for individuals in order to select the right Covid-19 vaccine based on a set of remarkable criteria. A survey study for assessment according to the given most important criteria based on expert opinion is conducted through the Best-Worst Method (BWM). A form including pairwise comparison vectors was sent to the participants in order to reveal priorities against their subjective decision-making criteria for vaccine selection. The essence of the study addresses that the efficacy criterion has the highest score and it is followed by the other given criteria such as storage requirements, incorporated vaccine technology, and international acceptance criterion. Participants tend to prioritize the origin and price of the vaccine behind all other criteria. Long-sought Covid-19 vaccine and its alternatives with different disclosed criteria of them have led to increasing indecision of people who have an opportunity to choose individually and the government officials who are responsible for country-wide procurement and policymakers; as a result, criteria evaluation is a challenging task. To solve the mentioned multi-criteria decision-making (MCDM) problem, BWM is newly employed in vaccine selection problems and its robust approach reveals the subjective priority of the criteria.

Once the GMP facility has been built and qualified, it must be routinely cleaned and maintained. The qualification procedure should involve the selection of cleaning agents to be used; however, this will also be briefly discussed later in this chapter. Also included will be a guide to cleaning practices and a discussion of facility maintenance.

In this paper, we will describe the selection of variables, model, and determinants of economic performance in Vietnam. The presence of FDI has created competitive pressures on domestic enterprises. This study uses panel data for Vietnamese enterprises in the industry from 2000 to 2018, which quantifies the impact of FDI on the industry leaving domestic enterprises. The results show that in addition to factors such as import and export status, industry concentration, income, age of enterprise, and number labor in enterprise, the emergence of FDI in the same industry increases the ability of domestic firms’ exit.

In the previous chapters, several winding-based discharge strategies have been introduced, which include the traditional LDA-CI method, piecewise NDNQ method, hybrid discharge scheme and indirect current regulation-based methods. However, a crucial problem is that when designing the discharge system for a particular EV, there are no ready-to-use rules that an engineer can follow to pre-evaluate whether or which winding-based discharge technique is available, especially for the high-speed range. To solve this challenge, this chapter proposes general principles for picking out applicable winding-based DC-bus capacitor discharge techniques at the stage of EV design on the basis of parametric analysis. Then, case studies are used to verify the proposed discharge technique selection rules.

This article addresses issues related to the modification of the McEliece cryptosystem. The software development presented in this article is crypto stability, the original McEliece algorithm is post-quantum, unlike its counterparts. The theoretical description of the McEliece cryptosystem was considered. More cryptographically secure combinations are considered for the selection of various parameters, and an estimate of the algorithm's strength is calculated when these parameters are taken into account or not. A mathematical model of the original algorithm was developed. It analyzes the original McEliece algorithm and modifications with leader decoding and decoding over Hamming distance. The result was confirmation that the original algorithm was the most efficient. When analyzing the modifications among themselves, it was concluded that the operating time of the modification in terms of the Hamming distance practically did not differ from the original, but significantly differed from the modification of the leader decoding. The leader decode modification was found to be the most ineffective. The program itself was written in the object-oriented Python 3 language, development environment—IDLE.

At present, machine learning, as an important tool in data mining, is not only the exploration of human cognitive learning process, but also the analysis and processing of data. Facing the challenge of large amounts of data, part of the current research focuses on the improvement and development of machine learning algorithms, and another part of the researchers is devoted to the selection of sample data and the reduction of data sets. These two aspects of research work are parallel. Training sample data selection is a research hotspot in machine learning. Through effective selection of sample data, more informative samples are extracted, redundant samples and noise data are eliminated, so as to improve the quality of training samples and obtain better learning performance. This article aims to study data selection and the application of machine learning algorithms in the context of big data. Based on the analysis of machine learning implementation methods, the construction process of random forests, and random group sampling integration algorithms, the application of random group sampling methods is used to accurately select bases. Compared with the previous algorithms, the RPSE algorithm greatly improves the calculation speed of the data in the classifier and training samples, and ensures that the base classifier performs random calculations on the samples during training. According to the integrated gap spacing, a support vector machine training data can be selected, and the selected data set that needs to be filtered is used as a classifier for the support vector machine for training, so as to obtain the final classification. The experimental results show that compared with the more common traditional data selection algorithms, the RPSE algorithm greatly accelerates the accuracy and speed of data selection, and reduces the accuracy and precision of the support vector computer classification under the necessary conditions.

With the rapid development of artificial intelligence in information processing applications, AI methods have been applied in different fields such as commerce, engineering, management, science, military, and finance. Among them, with the intelligence and modernization of the financial field, machine learning stock selection algorithms are widely used in the prediction of financial time series. The purpose of this article is to study the application of machine learning stock selection algorithms in the financial field. This article first compares and analyzes the three commonly used machine learning stock selection algorithm tools, and summarizes the opportunities brought by the application of machine learning stock selection algorithms to the financial field. This paper proposes the random forest algorithm of particle swarm parameter grid search (PSO-GRID-RF), and applies it to the stock return forecast in the financial field. This article elaborates on the regression prediction evaluation index, and verifies the superiority of the algorithm in this article. The prediction accuracy under the RF, GRID-RF and PSO-GRID-RF algorithms are 0.668%, 0.742%, and 0.870% respectively. It can be seen that this algorithm has higher prediction accuracy in stock prediction.

The purpose is to develop a pattern recognition model that would be able to classify three groups of glaucoma progression (which are: healthy controls, glaucoma suspects, and glaucoma patients) while being interpretable by medical doctors, being non-expert in machine learning. The utilized dataset is a numerical collection of 48 biomarkers acquired from each of 211 patients classified into three groups by an ophthalmologist. Due to the numerical type of the features and the high need for interpretability, it was decided to employ Classification and Regression Trees, and optimize them to obtain the smallest possible number of nodes and thus the highest interpretability while maintaining statistical dependence to the model with the highest quality metric from the review. The 5 \(\times \) 5 cross-validation protocol was used in the designed and conducted experiments. Two criteria were validated to assess the quality of the model selection – balanced accuracy metric and the number of nodes in the tree. The results indicate that this fairly simple approach could preserve a high balanced accuracy score and simultaneously reduce the size of the model – thereby increasing its interpretability. For \(\alpha = 0.2\), this approach can reduce the size of the Classification and Regression Trees to a quarter of its original spread.

Modern sugarcane cultivars are highly polyploid and have giant genomes (10 giga bases (Gb)) derived from interspecific hybridization between the cultivated species S. officinarum L. and the wild species S. spontaneum L. Genetic resources could be useful for developing new varieties, and therefore, plant breeding programs are assembling a germplasm collection to increase the number of possible novel gene combinations. The use of wild relatives in sugarcane breeding started at the beginning of introgression during the nobilization process, and it is still used in breeding programs primarily to search for varieties that are more tolerant to biotic and abiotic stresses. The success of a traditional sugarcane-breeding program relies on several factors, among which the appropriate parental selection must be made to maximize the chance of genetic enhancement. This choice will be determined by the short- and long-term goals, the availability of materials, flowering synchronism, breeding values, and the amount of data available from any parent or combination. In general, the process of developing a new cultivar is long and complex. Genetic resistance to diseases has been successfully achieved through traditional breeding, although this approach is challenging and takes a long time. Several studies have been conducted to unravel and understand the genetic basis of disease resistance and complex traits (e.g., sugar and fiber, among others) through QTL and association mapping. In recent decades, important advances have been made in understanding the sugarcane genome and the gene expression associated with agronomic traits. Furthermore, transgenic sugarcane has been produced in several countries, and there have been numerous initiatives to employ genome editing technology. New breeding technologies and strategies are required to boost genetic improvements significantly in future crop cultivars. Genomic selection has the potential to increase the rate of genetic gain significantly in sugarcane, primarily by (1) reducing the breeding cycle length, (2) increasing the prediction accuracy for clonal performance, and (3) increasing the accuracy of the breeding values for parent selection. This chapter describes the origin, genetic diversity, conservation, and traditional and molecular breeding approaches associated with sugarcane.

Today’s software systems and applications are expanded in almost all the firms and are indulged in various business units that need customer base. The methodology of the multi-release software reliability growth model (SRGM) deals with customer demand and market requirements. There are various multi-release SRGMs given by researchers, but it is challenging to select the optimal model. Traditionally, a multi-criteria decision-making approach has been used to resolve the problem of the ranking of models. In this chapter, the Weighted Distance-based Approach has been proposed to rank the multi-release SRGMs using the Maximum Deviation Method (MDM) and Distance-Based approach (DBA). The models are ranked based on selection criteria having different priority weights and composite distance values. The method MDM is a technique of Multi Criteria Decision Making (MCDM) in which non-linear programming is performed.

I am deeply grateful to everybody who has contributed to the volume, and wish to express my heartfelt thanks to my old friends and colleagues Ivo Duntsch and Ed Mares who have worked so hard to produce a volume in my honour. I’ve done research in a lot of areas in logic, and the selection of authors provides a good cross-section of my preoccupations.

The choice of the most suitable activation functions for artificial neural networks significantly affects training time and task performance. Breast cancer detection is currently based on the use of neural networks and their selection is an element that affects performance. In the present work, reference information on activation functions in neural networks was analyzed. Exploratory research, comprehensive reading, stepwise approach, and deduction were applied as a method. It resulted in phases of comparative evaluation inactivation functions, a quantitative and qualitative comparison of activation functions, and a prototype of neural network algorithm with activation function to detect cancer; It was concluded that the final results put as the best option to use ReLU for early detection of cancer.

Analysis of critical success factors allows software development organizations to focus on the factors to be successful. Selecting and implementing an algorithm for bosom cancer recognition could be hard. In this paper, a framework for modeling and analysis of success factors for the selection of Machine Learning methods used for the recognition of bosom cancer is presented. The objective is to analyze critical success factors in Machine Learning techniques selection for bosom cancer recognition built on Fuzzy Mental Maps. A group of common ML algorithms is presented in conjunction with the success factors. An analysis through measures calculation is presented in a case study. It was concluded that relevant factors for the selection of ML algorithms in the recognition of bosom cancer are: Selection of an ML algorithm according to the results, the study of ML algorithms tested in bosom cancer, obtaining and analyzing algorithm results.

On the current information in the medical area related to cancer analysis, the selection of an optimal Machine Learning algorithm, based on a multicriteria method, for a system that supports clinical decisions is sought. As a methodology, exploratory research and the deductive method were applied to analyze the information from existing articles and ML algorithms' behavior applied in the area of medicine. This research and based on a use case of training and testing of the GLM, SVM, and ANN algorithms for selecting an algorithm. Addition-ally, for clinical decisions, and architecture prototype for medical data collection is presented resulted. Based on AHP and TOPSIS methods Support Vector Machine (SVM) is the best alternative.

The functional variants involved in alcohol metabolism, the A allele of rs1229984:A > G in ADH1B and the A allele of rs671:G > A in ALDH2, are specifically prevalent among East Asian population. They are shown to be under recent positive selection, but the reasons for the selection are unknown. To test whether these positively selected variants have beneficial effects on survival in modern population, we performed the survival analyses using the large-scale Japanese cohort (n = 135,974) with genotype and follow-up survival data. The rs671-A allele was significantly associated with the better survival in the additive model (HR for mortality = 0.960, P = 1.7 × 10−5), and the rs1229984-A had both additive and non-additive effects (HR = 0.962, P = 0.0016 and HR = 0.958, P = 0.0066, respectively), which was consistent with the positive selection. The favorable effects of these alleles on survival were independent of the habit of alcohol consumption itself. The heterogenous combinatory effect between rs1229984 and rs671 genotype was also observed (HRs for AA genotype at rs671 were 1.03, 0.80, and 0.90 for GG, GA, and AA genotype at rs1229984, respectively), supposedly reflecting the synergistic effects on survival.

When linguistic evaluations are used in the decision matrix instead of exact numerical values, fuzzy set theory can capture the vagueness in the linguistic evaluations. Ordinary fuzzy sets have been extended to many new types of fuzzy sets such as intuitionistic fuzzy sets, neutrosophic sets, and picture fuzzy sets. Spherical fuzzy sets is an extension of picture fuzzy sets whose squared sum of their parameters is at most equal to one. This paper develops spherical fuzzy CRiteria Importance Through Intercriteria Correlation (CRITIC) method for prioritizing supplier selection criteria. Supplier selection is one of the most critical aspects of any organization since any mistake in this process may cause poor supplier performance and inefficiencies in the business processes. Supplier selection is a multi-criteria decision making problem involving several conflicting criteria and alternatives. A numerical illustration of the proposed method is also given.

EXtension of the PROMethee (EXPROM) methods were first introduced in 1991. These methods try to find a solution for ranking the alternatives more accurately using the available information. EXPROM-I method performs a partial ranking of alternatives whereas EXPROM-II does a full ranking of the alternatives. Vague and imprecise data of multi-criteria decision making problems can be better captured by spherical fuzzy sets (SFS) than ordinary fuzzy sets. SFS are an extension of picture fuzzy sets, presenting a larger definition volume for the parameters of membership function. In this paper, spherical fuzzy EXPROM method is developed and applied to the solution of a wastewater treatment technology selection problem.

In this study, the new methodology is proposed with the integration of Pythagorean fuzzy set and Bayesian structural method to deal with both objective and subjective uncertainties. The conventional decision-making tools are suffering a couple of fundamental drawbacks, such as (i) the results are depending on subjective terms, (ii) model and data uncertainties are taken into account, (iii) importantly is that confidence level is ignored, and finally (iv) the factor time is not considered into final decisions. In this study, the Pythagorean fuzzy set is overcome with subjective uncertainty, and the Bayesian network is engaged to deal with objective uncertainty. The maintenance strategy selection offshore sectors are studied for the proposed approach to show the effectiveness and efficiency. The results show that the proposed methodology would assist exports in making appropriate decisions.

The REGIME method, initially introduced by Hinloopen et al. [1, 2] is based on paired comparison methods which are easy to understand and uses qualitative data only in a mathematically justifiable way. The computational steps of the method are simple and can be easily apply to various complex problems.

Without a doubt, the location of the warehouse is a momentous decision in the post-Covid era. Considering a contemporary problem, the authors are aimed to reveal changes in the criteria importance determined in the selection of the warehouse location for the medical products. The difference will be unveiled by comparing the actual situation with the results of a previous study that examined pre-Covid phase evaluations of medical sector professionals and reported the criteria’ importance in ware-house location selection. In the earlier study, the Pythagorean fuzzy (PF)-based-DEMATEL was used to find out the criteria importance. In this study, the importance of the criteria in the warehouse location decisions in the medical sector was revealed by making re-evaluations by a decision-making group consisting of industry professionals. In order to create a proper representation of the post-Covid state, the same methodology was applied in the calculation of criteria importance. Thus, compared to pre-Covid phase, the change in the perceived role of proximity to target markets criterion is found on warehouse location decisions in the medical sector.

The performance of an evolutionary algorithm in solving disassembly sequence planning or disassembly line balancing greatly depends on six parts: the evolutionary operator; encoding scheme; solution selection and update strategy; population initialisation; solution maintenance; and terminal condition. This chapter introduces classical single-objective evolutionary algorithms (SOEAs) with typical evolutionary operators, and multi-objective evolutionary algorithms (MOEAs) with typical solution selection and update strategies. The chapter also elaborates on common encoding schemes. Typical settings on algorithm initialisation, solution maintenance and terminal conditions are introduced to help engineers to design efficient evolutionary algorithms for robotic disassembly optimisation problems.

Multi-criteria decision-making methods (MCDM) have been introduced to make effective decisions under conflicting criteria. This study used AHP-based VIKOR, TOPSIS, and MOORA methods to select two researchers among the twenty-six alternative candidates and to compare the findings of the different MCDM methods. The results showed that the AHP-based VIKOR and TOPSIS methods suggested the selection of the same candidates. However, different methods sorted the candidates in a significantly different order. This study reveals that MCDM methods might not always propose the same solution, although they are still useful in effective decision-making and easy to apply.