Search

These investigations are to find the numerical solutions of the nonlinear smoke model to exploit a stochastic framework called gudermannian neural works (GNNs) along with the optimization procedures of global/local search terminologies based genetic algorithm (GA) and interior-point algorithm (IPA), i.e., GNNs-GA-IPA. The nonlinear smoke system depends upon four groups, temporary smokers, potential smokers, permanent smokers and smokers. In order to solve the model, the design of fitness function is presented based on the differential system and the initial conditions of the nonlinear smoke system. To check the correctness of the GNNs-GA-IPA, the obtained results are compared with the Runge-Kutta method. The plots of the weight vectors, absolute error and comparison of the results are provided for each group of the nonlinear smoke model. Furthermore, statistical performances are provided using the single and multiple trial to authenticate the stability and reliability of the GNNs-GA-IPA for solving the nonlinear smoke system.

The harm of agricultural pests presents a remarkable effect on the quality and safety of edible farm products and the monitoring and identification of agricultural pests based on the Internet of Things (IoT) produce a large amount of data to be transmitted. To achieve efficient and real-time transmission of the sensors’ data for pest monitoring, this paper selects 235 geographic coordinates of agricultural pest monitoring points and uses genetic algorithm (GA), particle swarm optimization (PSO), and simulated annealing (SA) to optimize the data transmission paths of sensors. The three intelligent algorithms are simulated by MATLAB software. The results show that the optimized path based on PSO can make the shortest time used for transmitting data, and its corresponding minimum time is 4.868012 s. This study can provide a reference for improving the transmission efficiency of agricultural pest monitoring data, provide a guarantee for developing real-time and effective pest control strategies, and further reduce the threat of pest damage to the safety of farm products.

Glaucoma is a major cause of blindness. Most patients start to observe that late after the disease causes a high level of damage in the optic nerve head and the high percentage of vision loss. Early diagnosis and treatment are essential and must be taken. Image processing mass-screening and machine learning classification can support early and automatic diagnosis of Glaucoma symptoms so as to take protective measures and to extend symptom-free life of patients. This paper proposes improved techniques to extract disease-related and image-based features. Support Vector Machines and Genetically-Optimized Artificial Neural Networks, pronounced machine learning algorithms, are fine-tuned to combine the two set of features in one automated image classification system. The proposed methodology was applied to a dataset of 106 retina images obtained from three hospitals. The proposed system automatically detected Glaucoma using Support Vector Machines technique with 100% specificity and 87% accuracy. Artificial Neural Network classified the images with 98% accuracy.

Class imbalance is one of the most basic and important problems of web data. The key to overcoming the class imbalance problems is to increase the effective instances of the minority, that is, data augmentation. Generative Adversarial Networks (GANs), which have recently been successfully applied in the field of image generation, can be used for data augmentation because they can learn the data distribution given ample training data instances and generate more data. However, learning the distributions from the imbalanced data can make GANs easily get stuck in a local optimum. In this work, we propose a new training strategy called Annealing Genetic GAN (AGGAN), which incorporates simulated annealing genetic algorithm into the training process of GANs. And this can help GANs avoid the local optimum trapping problem, which easily occurs when the training set is imbalanced. Unlike existing GANs, which use a fixed adversarial learning objective alternately training a generator, we use multiple adversarial learning objectives to train a set of generators and use the Metropolis criterion in simulated annealing to decide whether the generator should update. More specifically, the Metropolis criterion accepts worse solutions with a certain probability, so it can make our AGGAN escape from the local optimum and find a better solution. Theory and mathematical analysis provide strong theoretical support for the proposed training strategy. And experiments on several datasets demonstrate that AGGAN achieves convincing ability to solve the class imbalanced problem and reduces the training problems inherent in existing GANs.

Cascaded Short Term Hydro-Thermal Scheduling problem (CSTHTS) is a single objective, non-linear multi-modal or convex (depending upon the cost function of thermal generation) type of Short Term Hydro-Thermal Scheduling (STHTS), having complex hydel constraints. It has been solved by many metaheuristic optimization algorithms, as found in the literature. Recently, the authors have published the best-achieved results of the CSTHTS problem having quadratic fuel cost function of thermal generation using an improved variant of the Accelerated PSO (APSO) algorithm, as compared to the other previously implemented algorithms. This article discusses and presents further improvement in the results obtained by both improved variants of APSO and PSO algorithms, implemented on the CSTHTS problem.

The use of multidimensional forced-choice questionnaires has been proposed as a means of improving validity in the assessment of non-cognitive attributes in high-stakes scenarios. However, the reduced precision of trait estimates in this questionnaire format is an important drawback. Accordingly, this article presents an optimization procedure for assembling pairwise forced-choice questionnaires while maximizing posterior marginal reliabilities. This procedure is performed through the adaptation of a known genetic algorithm (GA) for combinatorial problems. In a simulation study, the efficiency of the proposed procedure was compared with a quasi-brute-force (BF) search. For this purpose, five-dimensional item pools were simulated to emulate the real problem of generating a forced-choice personality questionnaire under the five-factor model. Three factors were manipulated: (1) the length of the questionnaire, (2) the relative item pool size with respect to the questionnaire’s length, and (3) the true correlations between traits. The recovery of the person parameters for each assembled questionnaire was evaluated through the squared correlation between estimated and true parameters, the root mean square error between the estimated and true parameters, the average difference between the estimated and true inter-trait correlations, and the average standard error for each trait level. The proposed GA offered more accurate trait estimates than the BF search within a reasonable computation time in every simulation condition. Such improvements were especially important when measuring correlated traits and when the relative item pool sizes were higher. A user-friendly online implementation of the algorithm was made available to the users.

Retinal direction-selectivity originates in starburst amacrine cells (SACs), which display a centrifugal preference, responding with greater depolarization to a stimulus expanding from soma to dendrites than to a collapsing stimulus. Various mechanisms were hypothesized to underlie SAC centrifugal preference, but dissociating them is experimentally challenging and the mechanisms remain debatable. To address this issue, we developed the Retinal Stimulation Modeling Environment (RSME), a multifaceted data-driven retinal model that encompasses detailed neuronal morphology and biophysical properties, retina-tailored connectivity scheme and visual input. Using a genetic algorithm, we demonstrated that spatiotemporally diverse excitatory inputs–sustained in the proximal and transient in the distal processes–are sufficient to generate experimentally validated centrifugal preference in a single SAC. Reversing these input kinetics did not produce any centrifugal-preferring SAC. We then explored the contribution of SAC-SAC inhibitory connections in establishing the centrifugal preference. SAC inhibitory network enhanced the centrifugal preference, but failed to generate it in its absence. Embedding a direction selective ganglion cell (DSGC) in a SAC network showed that the known SAC-DSGC asymmetric connectivity by itself produces direction selectivity. Still, this selectivity is sharpened in a centrifugal-preferring SAC network. Finally, we use RSME to demonstrate the contribution of SAC-SAC inhibitory connections in mediating direction selectivity and recapitulate recent experimental findings. Thus, using RSME, we obtained a mechanistic understanding of SACs’ centrifugal preference and its contribution to direction selectivity., Author summary Retinal direction selectivity is a canonical example for a computation undertaken by the retina. Starburst amacrine cells (SACs), interneurons in the retina, mediate direction selectivity via two mechanisms: they form asymmetric inhibitory connections with direction selective ganglion cells (DSGCs); and their processes are themselves direction selective, displaying a centrifugal preference. Various hypotheses were raised to account for this centrifugal preference, including the arrangement of SAC excitatory inputs, their kinetics, as well as reciprocal inhibition between SACs. To address this, we developed the Retinal Stimulation Modeling Environment (RSME)–a modeling environment for highly detailed, biologically plausible simulations, tailored to the exploration of neuronal dynamic and visual processing in retinal circuits. We started with exploring the excitation to a single SAC, and found that a precise organization of the input kinetics along SAC processes can generate a centrifugal preference that matched our experimental recordings. We then generated a network of SACs and found that reciprocal inhibition between SACs further enhances the centrifugal preference. Finally, we embedded a DSGC in the network, and dissected the contribution of SAC-DSGC asymmetric connections and SAC centrifugal preference to direction selectivity in DSGC.

A novel way of integrating the genetic algorithm (GA) and the analytic network process (ANP) is presented in this paper in order to develop a new warehouse assessment scheme, which is developed through various stages. First, we define the main criteria that influence a warehouse performance. The proposed algorithm that integrates the GA with the ANP is then utilized to determine the relative importance values of the defined criteria and sub-criteria by considering the interrelationships among them, and assign strength values for such interrelationships. Such an algorithm is also employed to linguistically present the relative importance and the strength of the interrelationships in a way that can circumvent the use of pairwise comparisons. Finally, the audit checklist that consists of questions related to the criteria is integrated with the proposed algorithm for the development of the warehouse assessment scheme. Validated on 45 warehouses, the proposed scheme has been shown to be able to identify the warehouse competitive advantages and the areas where more improvements can be achieved.

Here, a data mining–driven scheme based on discrete wavelet transform (DWT) is proposed for high impedance fault (HIF) detection in active distribution networks. Correlation between the phase current signal and the related details of the current wavelet transform is presented as a new index for HIF detection. The proposed HIF detection method is implemented in two subsequent stages. In the first stage, the most important features for HIF detection are extracted using support vector machine (SVM) and decision tree (DT). The parameters of SVM are optimised using the genetic algorithm (GA) over the input scenarios. In second stage, SVM is utilised to classify the input data. The efficiency of the utilised SVM-based classifier is compared with a probabilistic neural network (PNN). A comprehensive list of scenarios including load switching, inrush current, solid short-circuit faults, HIF faults in the presence of harmonic loads is generated. The performance of the proposed algorithm is investigated for two active distribution networks including IEEE 13-Bus and IEEE 34-Bus systems.

This paper presents a novel algorithm for solving a Student-Project Allocation problem, a variation of a two-sided matching algorithm, where a large number of students are allocated to numerous projects with limited available allocation places. Several new or improved algorithms are proposed, inspired by recommender systems and combined into a genetic algorithm. The main two algorithms are (i) variating the master list of student average grade ranking inspired by a fuzzy approach and (ii) extending the incomplete project preference lists by exploring the similarities of student choices, thus minimizing the number of randomly allocated students. The algorithm was implemented for allocating more than 500 students to more than 200 projects, in a course at the University of Zagreb, Faculty of Electrical Engineering and Computing. We compared our algorithm with the Deferred Acceptance (DA) Algorithm to check its validity. Using the fuzzy approach, the number of unallocated students decreased by 10%, with almost no effect to the top-ranked students. The combined usage of all proposed algorithms increased the number of successfully allocated students by more than 25%.

Improving genetic yield potential in major food grade crops such as soybean (Glycine max L.) is the most sustainable way to address the growing global food demand and its security concerns. Yield is a complex trait and reliant on various related variables called yield components. In this study, the five most important yield component traits in soybean were measured using a panel of 250 genotypes grown in four environments. These traits were the number of nodes per plant (NP), number of non-reproductive nodes per plant (NRNP), number of reproductive nodes per plant (RNP), number of pods per plant (PP), and the ratio of number of pods to number of nodes per plant (P/N). These data were used for predicting the total soybean seed yield using the Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Random Forest (RF), machine learning (ML) algorithms, individually and collectively through an ensemble method based on bagging strategy (E-B). The RBF algorithm with highest Coefficient of Determination (R2) value of 0.81 and the lowest Mean Absolute Errors (MAE) and Root Mean Square Error (RMSE) values of 148.61 kg.ha-1, and 185.31 kg.ha-1, respectively, was the most accurate algorithm and, therefore, selected as the metaClassifier for the E-B algorithm. Using the E-B algorithm, we were able to increase the prediction accuracy by improving the values of R2, MAE, and RMSE by 0.1, 0.24 kg.ha-1, and 0.96 kg.ha-1, respectively. Furthermore, for the first time in this study, we allied the E-B with the genetic algorithm (GA) to model the optimum values of yield components in an ideotype genotype in which the yield is maximized. The results revealed a better understanding of the relationships between soybean yield and its components, which can be used for selecting parental lines and designing promising crosses for developing cultivars with improved genetic yield potential.

Funder: Science and Technology Facilities Council; funder-id: http://dx.doi.org/10.13039/501100000271, Funder: Winton Programme for the Physics of Sustainability, Funder: German Academic Scholarship Foundation, Rationally and efficiently modifying the amino-acid sequence of proteins to control their ability to undergo liquid–liquid phase separation (LLPS) on demand is not only highly desirable, but can also help to elucidate which protein features are important for LLPS. Here, we propose a computational method that couples a genetic algorithm to a sequence-dependent coarse-grained protein model to evolve the amino-acid sequences of phase-separating intrinsically disordered protein regions (IDRs), and purposely enhance or inhibit their capacity to phase-separate. We validate the predicted critical solution temperatures of the mutated sequences with ABSINTH, a more accurate all-atom model. We apply the algorithm to the phase-separating IDRs of three naturally occurring proteins, namely FUS, hnRNPA1 and LAF1, as prototypes of regions that exist in cells and undergo homotypic LLPS driven by different types of intermolecular interaction, and we find that the evolution of amino-acid sequences towards enhanced LLPS is driven in these three cases, among other factors, by an increase in the average size of the amino acids. However, the direction of change in the molecular driving forces that enhance LLPS (such as hydrophobicity, aromaticity and charge) depends on the initial amino-acid sequence. Finally, we show that the evolution of amino-acid sequences to modulate LLPS is strongly coupled to the make-up of the medium (e.g. the presence or absence of RNA), which may have significant implications for our understanding of phase separation within the many-component mixtures of biological systems.

Genome-wide association studies (GWAS) are observational studies of a large set of genetic variants in an individual's sample in order to find if any of these variants are linked to a particular trait. In the last two decades, GWAS have contributed to several new discoveries in the field of genetics. This research presents a novel methodology to which GWAS can be applied to. It is mainly based on two machine learning methodologies, genetic algorithms and support vector machines. The database employed for the study consisted of information about 370,750 single-nucleotide polymorphisms belonging to 1076 cases of colorectal cancer and 973 controls. Ten pathways with different degrees of relationship with the trait under study were tested. The results obtained showed how the proposed methodology is able to detect relevant pathways for a certain trait: in this case, colorectal cancer. Keywords: machine learning; support vector machines; genetic algorithms; genome-wide association studies; single nucleotide polymorphism; pathways analysis

BackgroundAnticipating an initial shortage of vaccines for COVID-19, the Centers for Disease Control (CDC) in the United States developed priority vaccine allocations for specific demographic groups in the population. This study evaluates the performance of the CDC vaccine allocation strategy with respect to multiple potentially competing vaccination goals (minimizing mortality, cases, infections, and years of life lost (YLL)), under the same framework as the CDC allocation: four priority vaccination groups and population demographics stratified by age, comorbidities, occupation and living condition (congested or non-congested).MethodsWe developed a compartmental disease model that incorporates key elements of the current pandemic including age-varying susceptibility to infection, age-varying clinical fraction, an active case-count dependent social distancing level, and time-varying infectivity (accounting for the emergence of more infectious virus strains). Under this model, the CDC allocation strategy is compared to all other possibly optimal allocations that stagger vaccine roll-out in up to four phases (17.5 million strategies).ResultsThe CDC allocation strategy performed well in all vaccination goals but never optimally. Under the developed model, the CDC allocation deviated from the optimal allocations by small amounts, with 0.19% more deaths, 4.0% more cases, 4.07% more infections, and 0.97% higher YLL, than the respective optimal strategies. The CDC decision to not prioritize the vaccination of individuals under the age of 16 was optimal, as was the prioritization of health-care workers and other essential workers over non-essential workers. Finally, a higher prioritization of individuals with comorbidities in all age groups improved outcomes compared to the CDC allocation.InterpretationThe developed approach can be used to inform the design of future vaccine allocation strategies in the United States, or adapted for use by other countries seeking to optimize the effectiveness of their vaccine allocation strategies.FundingThe authors received no funding for this work.Research in contextEvidence before this studyThe Centers for Disease Control and Prevention (CDC) prioritized population groups for vaccination based on available scientific evidence, the feasibility of different implementation strategies, and ethical considerations. We searched PubMed using the query “(((COVID) AND (vaccin*)) AND (model)) AND ((priorit*) OR alloc*)” up to June 15, 2021, with no date or language restrictions. The search identified 190 articles, of which 15 used predictive models to evaluate the efficacy of vaccine allocation strategies in achieving vaccination campaign goals such as reducing mortality or incidence. All studies compared only a small number of specific, expertise-based allocations. Most studies stratified the population by age, while some considered additional characteristics such as occupation or comorbidity status, but none took into account all characteristics included in the CDC vaccine prioritizations.Added value of this studyWe developed a compartmental disease model that takes into account several important components of the COVID-19 pandemic, and stratifies the U.S. population by all characteristics included in the CDC vaccine prioritization recommendations. In a novel global optimization approach, we compared the CDC recommendations to all potentially optimal strategies (17.5 million strategies) that also stagger the vaccine roll-out in four phases. The CDC allocation strategy performed well in all considered outcome measures, but never optimally; a higher prioritization of individuals with comorbidities in all age groups improved outcomes. The CDC decision to initially not vaccinate children, as well as the prioritization of health-care workers and other essential workers over non-essential workers proved optimal under all outcome measures.Implications of all the available evidenceOur study identifies and compares the optimal vaccine allocation strategies for several competing vaccination goals. The developed global optimization approach can be used to inform the design of future vaccine allocation strategies in the United States and elsewhere.

In genome-wide association studies, detecting high-order epistasis is important for analyzing the occurrence of complex human diseases and explaining missing heritability. However, there are various challenges in the actual high-order epistasis detection process due to the large amount of data, &ldquo, small sample size problem&rdquo, diversity of disease models, etc. This paper proposes a multi-objective genetic algorithm (EpiMOGA) for single nucleotide polymorphism (SNP) epistasis detection. The K2 score based on the Bayesian network criterion and the Gini index of the diversity of the binary classification problem were used to guide the search process of the genetic algorithm. Experiments were performed on 26 simulated datasets of different models and a real Alzheimer&rsquo, s disease dataset. The results indicated that EpiMOGA was obviously superior to other related and competitive methods in both detection efficiency and accuracy, especially for small-sample-size datasets, and the performance of EpiMOGA remained stable across datasets of different disease models. At the same time, a number of SNP loci and 2-order epistasis associated with Alzheimer&rsquo, s disease were identified by the EpiMOGA method, indicating that this method is capable of identifying high-order epistasis from genome-wide data and can be applied in the study of complex diseases.

Evolutionary biologists frequently wish to measure the fitness of alternative phenotypes using behavioural experiments. However, many phenotypes are complex. One example is coloration: camouflage aims to make detection harder, while conspicuous signals (e.g. for warning or mate attraction) require the opposite. Identifying the hardest and easiest to find patterns is essential for understanding the evolutionary forces that shape protective coloration, but the parameter space of potential patterns (coloured visual textures) is vast, limiting previous empirical studies to a narrow range of phenotypes. Here we demonstrate how deep learning combined with genetic algorithms can be used to augment behavioural experiments, identifying both the best camouflage and the most conspicuous signal(s) from an arbitrarily vast array of patterns. To show the generality of our approach, we do so for both trichromatic (e.g. human) and dichromatic (e.g. typical mammalian) visual systems, in two different habitats. The patterns identified were validated using human participants; those identified as the best for camouflage were significantly harder to find than a tried-and-tested military design, while those identified as most conspicuous were significantly easier to find than other patterns. More generally, our method, dubbed the 'Camouflage Machine', will be a useful tool for identifying the optimal phenotype in high dimensional state-spaces. This article is protected by copyright. All rights reserved.

The coordination of different container-handling equipment is an important method for improving the overall efficiency of automated container terminals. In the real terminal, we should consider many real-life issues, such as the equipment capacity, the equipment collision, changing lanes in the multi-lane road, and choosing one of container-handling lanes for each container. This paper proposes the integrated scheduling problem of three container-handling equipment with the capacity constraint and the dual-cycle strategy, for simultaneously solving the equipment scheduling problem, the assignment problem of the container-handling lane and the conflict-free route planning problem of automated guided vehicles (AGVs). With the objective of minimizing the ship’s berth time, we propose a mixed-integer programming model based on the space-time network representation method and two bilevel optimization algorithms based on conflict resolution rules. Finally, numerical experiments are conducted to verify the effectiveness of the proposed model and two bilevel optimization algorithms.

The problem of delivering and fetching wagons at a railway station with mixed-shaped goods operation sites is considered, with a view to minimizing the running time between goods operation sites and waiting time of the locomotive in the planning period as the optimization objective. A general mathematical model for delivering and fetching wagons at a railway station with mixed-shaped goods operation sites has been formulated. The methods of judging and processing reverse of delivering and fetching wagons, dividing batches, and judging number of wagons for batch operation are provided to determine the feasibility of the solution, and an improved simulated annealing algorithm is introduced as our algorithm to the model. Finally, an experimental station is taken as an example to verify the model and algorithm. The results show that simulated annealing algorithm is relatively superior in computational efficiency and result compared with genetic algorithm and tabu search algorithm, the computing time of the algorithm provided can meet the requirements of planning shunting operations in railway station, and the model proposed is universal for other layout forms of GOSs and different operation forms.

The reformations of the electrical power sector have resulted in very dynamic and competitive market that has changed many elements of the power industry. Excessive demand of energy, depleting the fossil fuel reserves of planet and releasing the toxic air pollutant, has been causing harm to earth habitats. In this new situation, insufficiency of energy supplies, rising power generating costs, high capital cost of renewable energy equipment, environmental concerns of wind power turbines, and ever-increasing demand for electrical energy need efficient economic dispatch. The objective function in practical economic dispatch (ED) problem is nonlinear and non-convex, with restricted equality and inequality constraints, and traditional optimization methods are incapable of resolving such non-convex problems. Over the recent decade, meta-heuristic optimization approaches have acquired enormous reputation for obtaining a solution strategy for such types of ED issues. In this paper, a novel soft computing optimization technique is proposed for solving the dynamic economic dispatch problem (DEDP) of complex non-convex machines with several constraints. Our premeditated framework employs the genetic algorithm (GA) as an initial optimizer and sequential quadratic programming (SQP) for the fine tuning of the pre-optimized run of GA. The simulation analysis of GA-SQP performs well by acquiring less computational cost and finite time of execution, while providing optimal generation of powers according to the targeted power demand and load, whereas subject to valve point loading effect (VPLE) and multiple fueling option (MFO) constraints. The adequacy of the presented strategy concerning accuracy, convergence as well as reliability is verified by employing it on ten benchmark case studies, including non-convex IEEE bus system at the same time also considering VPLE of thermal power plants. The potency of designed optimization seems more robust with fast convergence rate while evaluating the hard bounded DEDP. Our suggested hybrid method GA-SQP converges to achieve the best optimal solution in a confined environment in a limited number of simulations. The simulation results demonstrate applicability and adequacy of the given hybrid schemes over conventional methods.

Background Feature selection is a crucial step in machine learning analysis. Currently, many feature selection approaches do not ensure satisfying results, in terms of accuracy and computational time, when the amount of data is huge, such as in ‘Omics’ datasets. Results Here, we propose an innovative implementation of a genetic algorithm, called GARS, for fast and accurate identification of informative features in multi-class and high-dimensional datasets. In all simulations, GARS outperformed two standard filter-based and two ‘wrapper’ and one embedded’ selection methods, showing high classification accuracies in a reasonable computational time. Conclusions GARS proved to be a suitable tool for performing feature selection on high-dimensional data. Therefore, GARS could be adopted when standard feature selection approaches do not provide satisfactory results or when there is a huge amount of data to be analyzed.

On-demand cloud computing is one of the rapidly evolving technologies that is being widely used in the industries now. With the increase in IoT devices and real-time business analytics requirements, enterprises that ought to scale up and scale down their services have started coming towards on-demand cloud computing service providers. In a cloud data center, a high volume of continuous incoming task requests to physical hosts makes an imbalance in the cloud data center load. Most existing works balance the load by optimizing the algorithm in selecting the optimal host and achieves instantaneous load balancing but with execution inefficiency for tasks when carried out in the long run. Considering the long-term perspective of load balancing, the research paper proposes Stackelberg (leader-follower) game-theoretical model reinforced with the satisfaction factor for selecting the optimal physical host for deploying the tasks arriving at the data center in a balanced way. Stackelberg Game Theoretical Model for Load Balancing (SGMLB) algorithm deploys the tasks on the host in the data center by considering the utilization factor of every individual host, which helps in achieving high resource utilization on an average of 60%. Experimental results show that the Stackelberg equilibrium incorporated with a satisfaction index has been very useful in balancing the loading across the cluster by choosing the optimal hosts. The results show better execution efficiency in terms of the reduced number of task failures by 47%, decreased 'makespan' value by 17%, increased throughput by 6%, and a decreased front-end error rate as compared to the traditional random allocation algorithms and flow-shop scheduling algorithm.

Recent advances in single-molecule fluorescent imaging have enabled quantitative measurements of transcription at a single gene copy, yet an accurate understanding of transcriptional kinetics is still lacking due to the difficulty of solving detailed biophysical models. Here we introduce a stochastic simulation and statistical inference platform for modeling detailed transcriptional kinetics in prokaryotic systems, which has not been solved analytically. The model includes stochastic two-state gene activation, mRNA synthesis initiation and stepwise elongation, release to the cytoplasm, and stepwise co-transcriptional degradation. Using the Gillespie algorithm, the platform simulates nascent and mature mRNA kinetics of a single gene copy and predicts fluorescent signals measurable by time-lapse single-cell mRNA imaging, for different experimental conditions. To approach the inverse problem of estimating the kinetic parameters of the model from experimental data, we develop a heuristic optimization method based on the genetic algorithm and the empirical distribution of mRNA generated by simulation. As a demonstration, we show that the optimization algorithm can successfully recover the transcriptional kinetics of simulated and experimental gene expression data. The platform is available as a MATLAB software package at https://data.caltech.edu/records/1287.

In this work, we propose the use of a genetic-algorithm-based attack against machine learning classifiers with the aim of ‘stealing’ users’ biometric actigraphy profiles from health related sensor data. The target classification model uses daily actigraphy patterns for user identification. The biometric profiles are modeled as what we call impersonator examples which are generated based solely on the predictions’ confidence score by repeatedly querying the target classifier. We conducted experiments in a black-box setting on a public dataset that contains actigraphy profiles from 55 individuals. The data consists of daily motion patterns recorded with an actigraphy device. These patterns can be used as biometric profiles to identify each individual. Our attack was able to generate examples capable of impersonating a target user with a success rate of 94.5%. Furthermore, we found that the impersonator examples have high transferability to other classifiers trained with the same training set. We also show that the generated biometric profiles have a close resemblance to the ground truth profiles which can lead to sensitive data exposure, like revealing the time of the day an individual wakes-up and goes to bed.

The Ironless Inductive Position Sensor (I2PS) is a state-of-the-art high precision linear position sensor, which is designed to be radiation hard and immune to magnetic fields. This sensor is built for the Large Hadron Collider collimation system at the European Organization for Nuclear Research. It is continuously monitored to assess the precision, accuracy and drifts during the machine’s operation. The ironless inductive position sensor was previously designed and optimised manually on a programmed electromagnetic model and simulated using a finite element model simulator. This sensor has the potential to be used extensively in industry, especially in areas with high radiation and high electro-magnetic interference. To industrialise it, an automated design procedure is required that offers the possibility to a user with minimal knowledge to design and optimise the sensor. This paper identifies the optimisation parameters and constants required in the manual design. It hence presents an automated design procedure which uses a multi-objective optimisation algorithm to automatically produce ironless inductive position sensors tailor-made to the user’s specifications., peer-reviewed

To solve the problem of one-sided pursuit of the shortest distance but ignoring the tourist experience in the process of tourism route planning, an improved ant colony optimization algorithm is proposed for tourism route planning. Contextual information of scenic spots significantly effect people’s choice of tourism destination, so the pheromone update strategy is combined with the contextual information such as weather and comfort degree of the scenic spot in the process of searching the global optimal route, so that the pheromone update tends to the path suitable for tourists. At the same time, in order to avoid falling into local optimization, the sub-path support degree is introduced. The experimental results show that the optimized tourism route has greatly improved the tourist experience, the route distance is shortened by 20.5% and the convergence speed is increased by 21.2% compared with the basic algorithm, which proves that the improved algorithm is notably effective.

Rational protein design aims at the targeted modification of existing proteins. To reach this goal, software suites like Rosetta propose sequences to introduce the desired properties. Challenging design problems necessitate the representation of a protein by means of a structural ensemble. Thus, Rosetta multi-state design (MSD) protocols have been developed wherein each state represents one protein conformation. Computational demands of MSD protocols are high, because for each of the candidate sequences a costly three-dimensional (3D) model has to be created and assessed for all states. Each of these scores contributes one data point to a complex, design-specific energy landscape. As neural networks (NN) proved well-suited to learn such solution spaces, we integrated one into the frameworkRosetta:MSFinstead of the so far used genetic algorithm with the aim to reduce computational costs. As its predecessor,Rosetta:MSF:NNadministers a set of candidate sequences and their scores and scans sequence space iteratively. During each iteration, the union of all candidate sequences and their Rosetta scores are used to re-train NNs that possess a design-specific architecture. The enormous speed of the NNs allows an extensive assessment of alternative sequences, which are ranked on the scores predicted by the NN. Costly 3D models are computed only for a small fraction of best-scoring sequences; these and the corresponding 3D-based scores replace half of the candidate sequences during each iteration. The analysis of two sets of candidate sequences generated for a specific design problem by means of a genetic algorithm confirmed that the NN predicted 3D-based scores quite well; the Pearson correlation coefficient was at least 0.95. ApplyingRosetta:MSF:NN:enzdesto a benchmark consisting of 16 ligand-binding problems showed that this protocol converges ten-times faster than the genetic algorithm and finds sequences with comparable scores.

As the amounts of data and use of distributed systems for data storage and processing have increased, reducing the number of replications has turned into a crucial requirement in these systems, which has been addressed by plenty of research. In this paper, an algorithm has been proposed to reduce the number of replications in big data transfer and, eventually to lower the traffic load over the grid by classifying data efficiently and optimally based on the sent data types and using VIKOR as a method of multivariate decision-making for ranking replication sites. Considering different variables, the VIKOR method makes it possible to take all the parameters effective in the assessment of site ranks into account. According to the results and evaluations, the proposed method has exhibited an improvement by about thirty percent in average over the LRU, LFU, BHR, and Without Rep. algorithms. Furthermore, it has improved the existing multivariate methods through different approaches to replication by thirty percent, as it considers effective parameters such as time, the number of replications, and replication site, causing replication to occur when it can make an improvement in terms of access.

The utilization of a storage space can be considerably improved by using dense mobile racks. However, it is necessary to perform an optimisation study on the order picking to reduce the time cost as much as possible. According to the channel location information that needs to be sorted, the multiple orders are divided into different batches by using hierarchical clustering. On this basis, a mathematical model for the virtual order clusters formed in the batches is established to optimize the order cluster picking and rack position movement, with the minimum picking time as the objective. For this model, a hybrid genetic algorithm is designed, and the characteristics of the different examples and solution algorithms are further analysed to provide a reference for the solution of the order picking optimisation problem in a dense mobile rack warehouse.

This paper deals with the use of proportional-integral-derivative controllers for the closed-loop control of the depth of hypnosis in anesthesia by using propofol administration and the bispectral index as a controlled variable.The controller parameters are optimized by using genetic algorithms and it is shown that a gain scheduling strategy should be employed to address the induction and maintenance phases separately.The selection of the filter on the controller output is also considered and the trade-off between the performance and the noise effect in the control variable is analyzed. Background and Objective: This paper addresses the use of proportional-integral-derivative controllers for regulating the depth of hypnosis in anesthesia by using propofol administration and the bispectral index as a controlled variable. In fact, introducing an automatic control system might provide significant benefits for the patient in reducing the risk for under- and over-dosing.Methods: In this study, the controller parameters are obtained through genetic algorithms by solving a min-max optimization problem. A set of 12 patient models representative of a large population variance is used to test controller robustness. The worst-case performance in the considered population is minimized considering two different scenarios: the induction case and the maintenance case.Results: Our results indicate that including a gain scheduling strategy enables optimal performance for induction and maintenance phases, separately. Using a single tuning to address both tasks may results in a loss of performance up to 102% in the induction phase and up to 31% in the maintenance phase. Further on, it is shown that a suitably designed low-pass filter on the controller output can handle the trade-off between the performance and the noise effect in the control variable.Conclusions: Optimally tuned PID controllers provide a fast induction time with an acceptable overshoot and a satisfactory disturbance rejection performance during maintenance. These features make them a very good tool for comparison when other control algorithms are developed.

In this paper, we focused on a real-life, large-scale problem of loom scheduling, which has 1100 independent jobs and 133 unrelated parallel machines with machine eligibility constraint. The authors focused on the scheduling problems that includes sequence-dependent setup times and the job splitting property to minimize the makespan. An adapted version of hybrid genetic algorithm in this study, incorporated a machine eligibility constraint. Adding this constraint complicated the problem, but doing so is compulsory to solve a real-life problem. To simplify the problem, we used the typesetting structure of the weaving industry. Utilizing random key numbers provided feasible chromosomes for each generation. Flexible chromosome structures and local search adaptation into the genetic algorithm were some of the other factors that allowed us to improve the makespan by up to 14% in this application.

One of the major consequences of the digital revolution has been the increase in the use of electronic devices in health services. Despite their remarkable advantages, though, the use of computers and other visual display terminals for a prolonged time may have negative effects on vision, leading to a greater risk of Computer Vision Syndrome (CVS) among their users. In this study, the importance of ocular and visual symptoms related to CVS was evaluated, and the factors associated with CVS were studied, with the help of an algorithm based on regression trees and genetic algorithms. The performance of this proposed model was also tested to check its ability to predict how prone a worker is to suffering from CVS. The findings of the present research confirm a high prevalence of CVS in healthcare workers, and associate CVS with a longer duration of occupation and higher daily computer usage.

The number of people who use computers for business and personal purposes increases as technology grows. The application of ergonomic practices on computer workstations reduces the musculoskeletal discomfort experienced and increases the overall satisfaction of the users. Keyboards are available in various systems, from computers to mobile devices, and have difference shapes and sizes. The keyboard size and shape is known to influence the user’s upper extremities. Alternative keyboard designs help diminish the pain in the arms that occurs due to awkward arm postures. Most previous studies tried to optimize the keyboard layout based on ergonomic typing and the frequency of letters’ co-occurrence. This research considers the frequency of the appearance of the most used 3,000 words in the English language. First, the frequency of each letter pair is calculated by the Text Analyzer. Then, a genetic algorithm is applied to design an ergonomically optimized keyboard to minimize the total distance of finger travel among the selected alphanumeric characters. The results showed that the distance travelled obtained by the proposed keyboard layout is less than that for the QWERTY keyboard in all different types of texts, in which an average of 6.04% improvement was achieved. Therefore, the proposed design can be used for keyboards to reduce time and fatigue.

We generalize the notion of lambda-superstrings, presented in a previous paper, to the notion of weighted lambda-superstrings. This generalization entails an important improvement in the applications to vaccine designs, as it allows epitopes to be weighted by their immunogenicities. Motivated by these potential applications of constructing short weighted lambda-superstrings to vaccine design, we approach this problem in two ways. First, we formalize the problem as a combinatorial optimization problem (in fact, as two polynomially equivalent problems) and develop an integer programming (IP) formulation for solving it optimally. Second, we describe a model that also takes into account good pairwise alignments of the obtained superstring with the input strings, and present a genetic algorithm that solves the problem approximately. We apply both algorithms to a set of 169 strings corresponding to the Nef protein taken from patiens infected with HIV-1. In the IP-based algorithm, we take the epitopes and the estimation of the immunogenicities from databases of experimental epitopes. In the genetic algorithm we take as candidate epitopes all 9-mers present in the 169 strings and estimate their immunogenicities using a public bioinformatics tool. Finally, we used several bioinformatic tools to evaluate the properties of the candidates generated by our method, which indicated that we can score high immunogenic lambda-superstrings that at the same time present similar conformations to the Nef virus proteins. This research was supported in part by the Basque Government, grants IT753-13 and IT974-16 and by the UPV/EHU and Basque Center of Applied Mathematics, grant US18/21. This research was also in part by the Slovenian Research Agency (I0-0035, research program P1-0285, and research projects N1-0032, J1-7051, and J1-9110). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

We studied previously optimal shape of external shading of windows in a cellular office with an outer edge modeled by a non-uniform rational basis spline (NURBS) curve whose control points were placed uniformly around western fin, overhang and eastern fin of the window, and whose depths were allowed to vary independently. We observed there that for each climate considered in the study there exists a shading shape close to the optimal one, but with a substantially simpler structure of control points for the NURBS curve. This simpler structure was reflected in partitioning control points into six groups such that all control points in the same group have equal depths, with groups corresponding to lower part of the western fin, upper part of the western fin, joint of the western fin and the overhang, internal part of the overhang, joint of the overhang and the eastern fin and the remaining part of the eastern fin. Here we confirm that shadings with control point structure restricted in such way can perform as well as shadings with unrestricted control points by optimising shape of external shading of windows in an apartment room for both restricted and unrestricted control point structure for the same range of climates, and showing that differences in heating and cooling demands between Pareto optimal shadings in both cases are negligibly small. This grouping of control points thus gives a simple and natural division of shading into a small number of basic constituents that have most impact on its heating and cooling demands. We further consider the convex hull of the Pareto front for shadings with restricted control points, as it contains shadings that minimise equivalent source energy in terms of the ratio of efficiencies and source energy conversion factors for district heating and cooling. We show that, in cases when depths of control point groups in convex hull shadings do not experience sudden changes between their extremal values, these depths can be fitted reasonably well by a sigmoid function that results in functional shadings that satisfactorily approximate heating and cooling demands of shadings in the Pareto front.

A population’s spatial structure affects the rate of genetic change and the outcome of natural selection. These effects can be modeled mathematically using the Birth-death process on graphs. Individuals occupy the vertices of a weighted graph, and reproduce into neighboring vertices based on fitness. A key quantity is the probability that a mutant type will sweep to fixation, as a function of the mutant’s fitness. Graphs that increase the fixation probability of beneficial mutations, and decrease that of deleterious mutations, are said to amplify selection. However, fixation probabilities are difficult to compute for an arbitrary graph. Here we derive an expression for the fixation probability, of a weakly-selected mutation, in terms of the time for two lineages to coalesce. This expression enables weak-selection fixation probabilities to be computed, for an arbitrary weighted graph, in polynomial time. Applying this method, we explore the range of possible effects of graph structure on natural selection, genetic drift, and the balance between the two. Using exhaustive analysis of small graphs and a genetic search algorithm, we identify families of graphs with striking effects on fixation probability, and we analyze these families mathematically. Our work reveals the nuanced effects of graph structure on natural selection and neutral drift. In particular, we show how these notions depend critically on the process by which mutations arise., Author summary When a new mutation appears in a population, it may ultimately spread to all individuals, or it may go extinct. Which outcome occurs depends on how the mutation affects the organism’s fitness (i.e., natural selection), but also on random chance. The spatial arrangement of organisms in the population can alter the balance between selection and random chance: amplifying one, suppressing the other. However, these effects can be difficult to predict or compute, even in simple, idealized mathematical models. We develop a method to efficiently calculate the effects of spatial structure on natural selection, in the case that mutations have only a weak effect on fitness. We use this method to comb through millions of distinct spatial structures, identifying those with the most extreme effects on natural selection. The question we study has applications to cancer research, with an individual’s cells considered as a population, of which cancer cells are an invading mutant type.

In the process of software development, regression testing is one of the major activities that is done after making modifications in the current system or whenever a software system evolves. But, the test suite size increases with the addition of new test cases and it becomes in-efficient because of the occurrence of redundant, broken, and obsolete test cases. For that reason, it results in additional time and budget to run all these test cases. Many researchers have proposed computational intelligence and conventional approaches for dealing with this problem and they have achieved an optimized test suite by selecting, minimizing or reducing, and prioritizing test cases. Currently, most of these optimization approaches are single objective and static in nature. But, it is mandatory to use multi-objective dynamic approaches for optimization due to the advancements in information technology and associated market challenges. Therefore, we have proposed three variants of self-tunable Adaptive Neuro-fuzzy Inference System i.e. TLBO-ANFIS, FA-ANFIS, and HS-ANFIS, for multi-objective regression test suites optimization. Two benchmark test suites are used for evaluating the proposed ANFIS variants. The performance of proposed ANFIS variants is measured using Standard Deviation and Root Mean Square Error. A comparison of experimental results is also done with six existing methods i.e. GA-ANFIS, PSO-ANFIS, MOGA, NSGA-II, MOPSO, and TOPSIS and it is concluded that the proposed method effectively reduces the size of regression test suite without a reduction in the fault detection rate.

Collaboration among logistics facilities in a multicenter logistics delivery network can significantly improve the utilization of logistics resources through resource sharing including logistics facilities, vehicles, and customer services. This study proposes and tests different resource sharing schemes to solve the optimization problem of a collaborative multicenter logistics delivery network based on resource sharing (CMCLDN-RS). The CMCLDN-RS problem aims to establish a collaborative mechanism of allocating logistics resources in a manner that improves the operational efficiency of a logistics network. A bi-objective optimization model is proposed with consideration of various resource sharing schemes in multiple service periods to minimize the total cost and number of vehicles. An adaptive grid particle swarm optimization (AGPSO) algorithm based on customer clustering is devised to solve the CMCLDN-RS problem and find Pareto optimal solutions. An effective elite iteration and selective endowment mechanism is designed for the algorithm to combine global and local search to improve search capabilities. The solution of CMCLDN-RS guarantees that cost savings are fairly allocated to the collaborative participants through a suitable profit allocation model. Compared with the computation performance of the existing nondominated sorting genetic algorithm-II and multi-objective evolutionary algorithm, AGPSO is more computationally efficient. An empirical case study in Chengdu, China suggests that the proposed collaborative mechanism with resource sharing can effectively reduce total operational costs and number of vehicles, thereby enhancing the operational efficiency of the logistics network.

A ventilation network feature graph can directly and quantitatively represent the features of a ventilation network. To ensure the stability of airflow in a mine and improve ventilation system analysis, we propose a new algorithm to draw ventilation network feature graphs. The independent path method serves as the algorithm’s main frame, and an improved adaptive genetic algorithm is embedded so that the graph may be drawn better. A mathematical model based on the node adjacency matrix method for unidirectional circuit discrimination is constructed as the drawing algorithm may not be valid in such cases. By modifying the edge-seeking strategy, the improved depth-first search algorithm can be used to determine all of the paths in the ventilation network with unidirectional circuits, and the equivalent transformation method of network topology relations is used to draw the ventilation network feature graph. Through the analysis of the topological relation of a ventilation network, a simplified mathematical model is constructed, and network simplification technology makes the drawing concise and hierarchical. The rapid and intuitive drawing of the ventilation network feature graphs is significant for optimization of the ventilation system and day-to-day management.

Agents’ perceptions on the state of the economy can be affected during economic crises. Tendency surveys are the main source of agents’ expectations. The main objective of this study is to assess the impact of the 2008 financial crisis on agents’ expectations. With this aim, we evaluate the capacity of survey-based expectations to anticipate economic growth in the United States, Japan, Germany and the United Kingdom. We propose a symbolic regression (SR) via genetic programming approach to derive mathematical functional forms that link survey-based expectations to GDP growth. By combining the main SR-generated indicators, we generate estimates of the evolution of GDP. Finally, we analyse the effect of the crisis on the formation of expectations, and we find an improvement in the capacity of agents’ expectations to anticipate economic growth after the crisis in all countries except Germany.

Sensor node placement optimization has a significant role in wireless sensor networks, especially in structural health monitoring. Since sensor node placement affects the routing, optimization should be Jointly done for the node placement and routing. The existing work separately optimizes the node placement and routing (by performing routing after carrying out the node placement). However, this approach does not guarantee the optimality of the overall solution. In this paper, joint optimization of sensor placement, routing, and flow assignment is introduced and solved using mixed integer programming modeling. Finding an optimal solution for this joint problem is too complex. Hence, a near-optimal solution is obtained using genetic algorithms with reduced complexity. In addition, a heuristic algorithm for joint routing and flow assignment with placement is proposed using the effective independence model, which optimizes the information quality and energy consumption for efficient communication. Lastly, results are presented in a nine-floor building to compare the three proposed algorithms with the heuristic algorithm by Li et al. The numerical results show the efficiency of the proposed algorithms and the tradeoff between the efficiency and the complexity. 2001-2012 IEEE. Scopus

Tendency surveys are the main source of agents' expectations. This study has a twofold aim. First, it proposes a new method to quantify survey-based expectations by means of symbolic regression (SR) via genetic programming. Second, it combines the main SR-generated indicators to estimate the evolution of GDP, obtaining the best results for the Czech Republic and Hungary. Finally, it assesses the impact of the 2008 financial crisis, finding that the capacity of agents' expectations to anticipate economic growth in most Central and Eastern European economies improved after the crisis.

An active aerodynamic feeding system developed at the IFA offers a large potential regarding output rate, reliability and neutrality towards part geometries. In this paper, the procedure of a genetic algorithm's into the feeding system's control is shown. The genetic algorithm automatically identifies optimal values for the feeding system's parameters which need to be adjusted when setting up for new workpieces. The general functioning of the automatic parameter identification is confirmed during tests on the convergence behaviour of the genetic algorithm. Thereby, a trade-off between the adjustment time of the feeding system and the solution quality is revealed. © 2016 The Authors. DFG/NY 4/51-1

A review of evolutionary algorithms (EAs) with applications to antenna and propagation problems is presented. EAs have emerged as viable candidates for global optimization problems and have been attracting the attention of the research community interested in solving real-world engineering problems, as evidenced by the fact that very large number of antenna design problems have been addressed in the literature in recent years by using EAs. In this paper, our primary focus is on Genetic Algorithms (GAs), Particle Swarm Optimization (PSO), and Differential Evolution (DE), though we also briefly review other recently introduced nature-inspired algorithms. An overview of case examples optimized by each family of algorithms is included in the paper.

Purpose Allogeneic hematopoietic stem-cell transplantation (HSCT) is potentially curative for acute leukemia (AL), but carries considerable risk. Machine learning algorithms, which are part of the data mining (DM) approach, may serve for transplantation-related mortality risk prediction. Patients and Methods This work is a retrospective DM study on a cohort of 28,236 adult HSCT recipients from the AL registry of the European Group for Blood and Marrow Transplantation. The primary objective was prediction of overall mortality (OM) at 100 days after HSCT. Secondary objectives were estimation of nonrelapse mortality, leukemia-free survival, and overall survival at 2 years. Donor, recipient, and procedural characteristics were analyzed. The alternating decision tree machine learning algorithm was applied for model development on 70% of the data set and validated on the remaining data. Results OM prevalence at day 100 was 13.9% (n = 3,936). Of the 20 variables considered, 10 were selected by the model for OM prediction, and several interactions were discovered. By using a logistic transformation function, the crude score was transformed into individual probabilities for 100-day OM (range, 3% to 68%). The model's discrimination for the primary objective performed better than the European Group for Blood and Marrow Transplantation score (area under the receiver operating characteristics curve, 0.701 v 0.646; P < .001). Calibration was excellent. Scores assigned were also predictive of secondary objectives. Conclusion The alternating decision tree model provides a robust tool for risk evaluation of patients with AL before HSCT, and is available online ( http://bioinfo.lnx.biu.ac.il/∼bondi/web1.html ). It is presented as a continuous probabilistic score for the prediction of day 100 OM, extending prediction to 2 years. The DM method has proved useful for clinical prediction in HSCT.

A longstanding question in sensory neuroscience is what types of stimuli drive neurons to fire. The characterization of effective stimuli has traditionally been based on a combination of intuition, insights from previous studies, and luck. A new method termed XDream (EXtending DeepDream with real-time evolution for activation maximization) combined a generative neural network and a genetic algorithm in a closed loop to create strong stimuli for neurons in the macaque visual cortex. Here we extensively and systematically evaluate the performance of XDream. We use ConvNet units as in silico models of neurons, enabling experiments that would be prohibitive with biological neurons. We evaluated how the method compares to brute-force search, and how well the method generalizes to different neurons and processing stages. We also explored design and parameter choices. XDream can efficiently find preferred features for visual units without any prior knowledge about them. XDream extrapolates to different layers, architectures, and developmental regimes, performing better than brute-force search, and often better than exhaustive sampling of >1 million images. Furthermore, XDream is robust to choices of multiple image generators, optimization algorithms, and hyperparameters, suggesting that its performance is locally near-optimal. Lastly, we found no significant advantage to problem-specific parameter tuning. These results establish expectations and provide practical recommendations for using XDream to investigate neural coding in biological preparations. Overall, XDream is an efficient, general, and robust algorithm for uncovering neuronal tuning preferences using a vast and diverse stimulus space. XDream is implemented in Python, released under the MIT License, and works on Linux, Windows, and MacOS.

The text clustering is considered as one of the most effective text document analysis methods, which is applied to cluster documents as a consequence of the expanded big data and online information. Based on the review of the related work of the text clustering algorithms, these algorithms achieved reasonable clustering results for some datasets, while they failed on a wide variety of benchmark datasets. Furthermore, the performance of these algorithms was not robust due to the inefficient balance between the exploitation and exploration capabilities of the clustering algorithm. Accordingly, this research proposes a Memetic Differential Evolution algorithm (MDETC) to solve the text clustering problem, which aims to address the effect of the hybridization between the differential evolution (DE) mutation strategy with the memetic algorithm (MA). This hybridization intends to enhance the quality of text clustering and improve the exploitation and exploration capabilities of the algorithm. Our experimental results based on six standard text clustering benchmark datasets (i.e. the Laboratory of Computational Intelligence (LABIC)) have shown that the MDETC algorithm outperformed other compared clustering algorithms based on AUC metric, F-measure, and the statistical analysis. Furthermore, the MDETC is compared with the state of art text clustering algorithms and obtained almost the best results for the standard benchmark datasets.

The turning points of housing prices play a significant role in the real estate market and economy. However, because multiple factors impact the market, the prediction of the turning points of housing prices faces significant challenges. To solve this problem, in this study, a historical data-based model that incorporates a multi-population genetic algorithm with elitism into the log-periodic power law model is proposed. This model overcomes the weaknesses of multivariate and univariate methods that it does not require any external factors while achieving excellent interpretations. We applied the model to the case study collected from housing prices in Wuhan, China, from December 2016 to October 2018. To verify its reliability, we compared the results of the proposed model to those of the log-periodic power law model optimized by the standard genetic algorithm and simulated annealing, the results of which indicate that the proposed model performs best in terms of prediction. Efficiently predicting and analyzing the housing prices will help the government promulgate effective policies for regulating the real estate market and protect home buyers.

Late-onset Alzheimer's Disease (LOAD) is the most common form of dementia in the elderly. Genome-wide association studies (GWAS) for LOAD have open new avenues to identify genetic causes and to provide diagnostic tools for early detection. Although several predictive models have been proposed using the few detected GWAS markers, there is still a need for improvement and identification of potential markers. Commonly, polygenic risk scores are being used for prediction. Nevertheless, other methods to generate predictive models have been suggested. In this research, we compared three machine learning methods that have been proved to construct powerful predictive models (genetic algorithms, LASSO, and step-wise) and propose the inclusion of markers from misclassified samples to improve overall prediction accuracy. Our results show that the addition of markers from an initial model plus the markers of the model fitted to misclassified samples improves the area under the receiving operative curve by around 5%, reaching ~0.84, which is highly competitive using only genetic information. The computational strategy used here can help to devise better methods to improve classification models for AD. Our results could have a positive impact on the early diagnosis of Alzheimer's disease.

China Railway Corporation (CRC) has been paid more attention to passenger transportation revenue, with its increase proportion in transportation revenue. Due to the price regulation, the only way CRC can improve ticket sale profit is to find a best seat allocation scheme. This study focuses on the optimization of railway revenue management problem in China with consideration of i) customer behaviors including their arrival and purchase preferences, ii) a specific ticket booking mechanism called “seat-based control”. To evaluate the performance of seat-based control, we build a Discrete-Time Markov Chain model to describe the ticket reservation process and then design a genetic algorithm to find approximate solutions. The performance of proposed method is tested in two experiments with two other benchmarks. Finally, we apply it to practical data of the Nanning-Guangzhou high-speed railway line.

Bees play a key role in the functioning of human-modified and natural ecosystems by pollinating agricultural crops and wild plant communities. Global pollinator conservation efforts need large-scale and long-term monitoring to detect changes in species’ demographic patterns and shifts in bee community structure. The objective of this project was to test a molecular sequencing pipeline that would utilize a commonly used locus, produce accurate and precise identifications consistent with morphological identifications, and generate data that are both qualitative and quantitative. We applied this amplicon sequencing pipeline to native bee communities sampled across Conservation Reserve Program (CRP) lands and native grasslands in eastern North Dakota. We found the 28S LSU locus to be more capable of discriminating between species than the 18S SSU rRNA locus, and in some cases even resolved instances of cryptic species or morphologically ambiguous species complexes. Overall, we found the amplicon sequencing method to be a qualitatively accurate representation of the sampled bee community richness and species identity, especially when a well-curated database of known 28S LSU sequences is available. Both morphological identification and molecular sequencing revealed similar patterns in native bee community structure across CRP lands and native prairie. Additionally, a genetic algorithm approach to compute taxon-specific correction factors using a small subset of the most concordant samples demonstrated that a high level of quantitative accuracy could be possible if the specimens are fresh and processed soon after collection. Here we provide a first step to a molecular pipeline for identifying insect pollinator communities. This tool should prove useful for future national monitoring efforts as use of molecular tools becomes more affordable and as numbers of 28S LSU sequences for pollinator species increase in publicly-available databases.