Elitist Selection Research Articles

Multi-objective Task Scheduling Algorithm Based on Harmony Search for Grid Microservice Optimization

In order to solve the multi-objective task scheduling optimization problem of data platform microservice combination, this paper proposes an improved harmony search algorithm MODRHS, which fuses the multi-objective optimization NSGA-II algorithm, and improve its elite selection strategy by a circular elimination method, and strengthens the uniformity of the non-dominated solutions at first layer and improves the algorithm’s Pareto optimization ability. At the same time, it describes the mathematical expression of the Dockers model and service optimization goals of the data platform microservice scheduling. The improved harmony search algorithm is applied to practical problems. The performance test of MODRHS is carried out through standard test functions and real data sets. Compared with other classic multi-objective optimization algorithms, the convergence and diversity of the MODRHS algorithm have been effectively improved.

Research on new edge computing network architecture and task offloading strategy for Internet of Things

How to effectively utilize edge nodes with limited computing resources to ensure quality of service is a key issue for many end users in Internet of Things. To address this problem, we propose a new cloud-edge computing network architecture, which enables the system to meet the requirements of computing resource and response time. The architecture consists of a powerful cloud computing center, multiple mobile edge computing servers and users in Internet of Things. We jointly optimize the task offloading and resource allocation of end users, thereby constructing a mixed integer nonlinear programming problem in the proposed architecture. To further solve this problem, a joint optimization strategy based on binary custom fireworks algorithm is proposed. This algorithm improves the Gaussian mutation operation in traditional fireworks algorithm by introducing Gaussian mutation probability and elite selection strategy, which makes the mutation directional. Finally, simulation results verify the effectiveness of our proposed joint optimization strategy. Compared with several other newer offloading strategies, the proposed joint optimization strategy can obtain significant performance gains.

Study of commercial cane sugar contributing traits - their variability, association and implications for selection in advanced clonal stages of sugarcane (Saccharum spp.)

Sugarcane is one of the major agro-industrial crops with huge variations in state-wise cane production, productivity and sugar recovery. Twenty-five elite selections of sugarcane clones along with nine commercial checks (early and mid-late maturity group) were evaluated for different cane and sugar yield contributing traits. Analysis of variance revealed significant differences among genotypes along with low ( 20%) genotypic coefficient of variations for all studied traits suggested explicitly the presence of wide variation in genetic material used in the study. All the traits exhibited higher estimates (> 60 %) of heritability (h2b) except sucrose content (26.17 %); while genetic advance (%) of mean was observed low ( 20%) for commercial cane sugar, cane yield, germination, single cane weight, no. of shoots and no. of millable canes. Commercial cane sugar showed significant positive genotypic and phenotypic correlation with germination (%), no. of shoots, no. of millable canes, Stalk length, single cane weight, cane yield and sucrose (%). Cane yield (1.130, 0.995) had highest positive direct effect followed by sucrose (%) (0.308, 0.198). It is suggested that these traits can be considered as main determinant traits. High indirect effects of no. of shoots, no. of millable canes, stalk length, single cane weight through cane yield may be used for indirect selection for improving commercial cane sugar.

A Novel Method for Detecting Future Generations of Targeted and Metamorphic Malware Based on Genetic Algorithm

This paper presents a novel solution for detecting rare and mutating malware programs and provides a strategy to address the scarcity of datasets for modeling these types of malware. To provide sufficient training data for malware behavioral modeling, genetic algorithms are used together with an optimization strategy that selectively creates generations of mutated elite malware samples. In our unique method, a sequence of system API calls is extracted using tracker filter drivers in a sandbox environment. The most obfuscated and metamorphic malware are chosen by an elite selection method. The behavioral chromosomes are formed by mapping extracted APIs to genes using linear regression. Our analysis system includes an Internet simulator and a human emulator to deceive intelligent classes of malware to successfully execute themselves and prevent system halting. The evolution process is performed through crossover and permutation of genes, which are encoded based on the addresses of the kernel-level system functions. An objective function has been defined to optimize the vital indicators of malignancy and tracking rate with a linear time complexity. This guarantees that new generations of malware are more destructive and stealthy than their parents. J48 and deep neural networks were employed in our experiments as they are two popular modeling and classification strategies in the area of behavioral malware detection. Real-world malware samples from valid references were used for the performance evaluation of our approach. Comprehensive scenarios were involved in the experiments to evaluate the performance of our proposed strategy. The results demonstrate significant improvement in detection accuracy - up to 5% considering rare and metamorphic malware. The results also demonstrated a considerable enhancement in true positive rate for the proposed deep-learning algorithm.

Efficient Scheduling of Plantation Company Workers using Genetic Algorithm

Workers at large plantation companies have various activities. These activities include caring for plants, regularly applying fertilizers according to schedule, and crop harvesting activities. The density of worker activities must be balanced with efficient and fair work scheduling. A good schedule will minimize worker dissatisfaction while also maintaining their physical health. This study aims to optimize workers' schedules using a genetic algorithm. An efficient chromosome representation is designed to produce a good schedule in a reasonable amount of time. The mutation method is used in combination with reciprocal mutation and exchange mutation, while the type of crossover used is one cut point, and the selection method is elitism selection. A set of computational experiments is carried out to determine the best parameters’ value of the genetic algorithm. The final result is a better 30 days worker schedule compare to the previous schedule that was produced manually.

Selection of elite ‘‘Maradol’’ papaya plants for the production of quality seeds

The cultivar Red Maradol native of Cuba, has morphological and agronomic features superior to local cultivars and adapted to soils and climates of Venezuela; that is why it is grown in a greater proportion and has been widely accepted by farmers, traders and consumers. However, the lack of availability and high cost of imported seeds limit its expansion in the country. The aim of this work was to select andromonoecious plants from different sources and locations, based on morphological and agronomic characteristics, and produce good quality seeds by self-pollinations. The characteristics for selection were based on those of the cultivar, such as: beginning of flowering between 3 and 4 months after transplant to the field, height of flowering less than or equal to 80 cm, beginning of fruiting before 4 months, height of plants less than 2 m, among others features. Selected plants showed low percentage of sterility, 30 and 64 fruits.plant-1, fruit weights between 1.4 to 1.7 kg, and estimated yields between 42.5 and 98.50 kg.plant-1 yields. Regarding fruit quality, they were elongated and smooth, wide orange-red color pulp. These populations are considered the basis for the production of good quality seeds, to continue the process of selection of more productive pure lines and hybrids.

Improved multi-objective cuckoo search algorithm with novel search strategies for point-to-point part feeding scheduling problems of automotive assembly lines

PurposeThis paper aims to investigate the part feeding scheduling problem with electric vehicles (EVs) for automotive assembly lines. A point-to-point part feeding model has been formulated to minimize the number of EVs and the maximum handling time by specifying the EVs and sequence of all the delivery tasks.Design/methodology/approachFirst, a mathematical programming model of point-to-point part feeding scheduling problem (PTPPFSP) with EVs is presented. Because the PTPPFSP is NP-hard, an improved multi-objective cuckoo search (IMCS) algorithm is developed with novel search strategies, possessing the self-adaptive Levy flights, the Gaussian mutation and elite selection strategy to strengthen the algorithm’s optimization performance. In addition, two local search operators are designed for deep optimization. The effectiveness of the IMCS algorithm is verified by dealing with the PTPPFSP in different problem scales.FindingsNumerical experiments are used to demonstrate how the IMCS algorithm serves as an efficient method to solve the PTPPFSP with EVs. The effectiveness and feasibility of the IMCS algorithm are validated by approximate Pareto fronts obtained from the instances of different problem scales. The computational results show that the IMCS algorithm can achieve better performance than the other high-performing algorithms in terms of solution quality, convergence and diversity.Research limitations/implicationsThis study is applicable without regard to the breakdown of EVs. The current research contributes to the scheduling of in-plant logistics for automotive assembly lines, and it could be modified to cope with similar part feeding scheduling problems characterized by just-in-time (JIT) delivery.Originality/valueBoth limited electricity capacity and no earliness and tardiness constraints are considered, and the scheduling problem is solved satisfactorily and innovatively for an efficient JIT part feeding with EVs applied to in-plant logistics.

A clustering-based differential evolution algorithm for solving multimodal multi-objective optimization problems

Abstract Multimodal Multi-objective Optimization Problems (MMOPs) refer to the problems that have multiple Pareto-optimal solution sets in decision space corresponding to the same or similar Pareto-optimal front in objective space. These problems require the optimization algorithm to locate multiple Pareto Sets (PSs). This paper proposes a differential evolution algorithm based on the clustering technique and an elite selection mechanism to solve MMOPs. In this algorithm, a Clustering-based Special Crowding Distance (CSCD) method is designed to calculate the comprehensive crowding degree in decision and objective spaces. Subsequently, a distance-based elite selection mechanism (DBESM) is introduced to determine the learning exemplars of various individuals. New individuals are generated around the exemplars to obtain a well-distributed population in both decision and objective spaces. To test the performance of the proposed algorithm, extensive experiments on the suit of CEC'2019 benchmark functions have been conducted. The results indicate that the proposed method has superior performance compared with other commonly used algorithms.

Electric distribution network reconfiguration for power loss reduction based on runner root algorithm

This paper proposes a method for solving the distribution network reconfiguration (NR) problem based on runner root algorithm (RRA) for reducing active power loss. The RRA is a recent developed metaheuristic algorithm inspired from runners and roots of plants to search water and minerals. RRA is equipped with four tools for searching the optimal solution. In which, the random jumps and the restart of population are used for exploring and the elite selection and random jumps around the current best solution are used for exploiting. The effectiveness of the RRA is evaluated on the 16 and 69-node system. The obtained results are compared with particle swarm optimization and other methods. The numerical results show that the RRA is the potential method for the NR problem.

Hybrid Harmony Search-Artificial Intelligence Models in Credit Scoring.

Credit scoring is an important tool used by financial institutions to correctly identify defaulters and non-defaulters. Support Vector Machines (SVM) and Random Forest (RF) are the Artificial Intelligence techniques that have been attracting interest due to their flexibility to account for various data patterns. Both are black-box models which are sensitive to hyperparameter settings. Feature selection can be performed on SVM to enable explanation with the reduced features, whereas feature importance computed by RF can be used for model explanation. The benefits of accuracy and interpretation allow for significant improvement in the area of credit risk and credit scoring. This paper proposes the use of Harmony Search (HS), to form a hybrid HS-SVM to perform feature selection and hyperparameter tuning simultaneously, and a hybrid HS-RF to tune the hyperparameters. A Modified HS (MHS) is also proposed with the main objective to achieve comparable results as the standard HS with a shorter computational time. MHS consists of four main modifications in the standard HS: (i) Elitism selection during memory consideration instead of random selection, (ii) dynamic exploration and exploitation operators in place of the original static operators, (iii) a self-adjusted bandwidth operator, and (iv) inclusion of additional termination criteria to reach faster convergence. Along with parallel computing, MHS effectively reduces the computational time of the proposed hybrid models. The proposed hybrid models are compared with standard statistical models across three different datasets commonly used in credit scoring studies. The computational results show that MHS-RF is most robust in terms of model performance, model explainability and computational time.

Elite Niche Particle Swarm Optimization for Energy Clustering in Aeronautical Wireless Sensor Network

Recently, a wide variety of applications of aeronautical wireless sensor networks (AWSNs) make the clustering algorithm a paramount issue and bring profound changes to Internet of Things in AWSN-based applications. In AWSN, an energy-clustering algorithm is very significant to reduce the total energy cost of sensing data and solve the energy balance problem in AWSN. However, it is a challenging issue in AWSNs to have a low lifetime and energy utilization rate. In order to achieve a low energy consumption and further improve the lifetime of AWSNs, in this paper, we propose an elite niche particle swarm optimization (ENPSO), which combine the elite selection and niche sharing mechanism to develop the algorithm’s convergence rate and robustness. In the simulation, we compare the energy cost optimized by ENPSO with that optimized by grey wolf optimization (GWO) and simulated annealing (SA). Simulation results demonstrate that the energy cost optimized by ENPSO is 9.63% and 19.54% smaller than GWO and SA when the number of nodes is 100 with 10% cluster heads. It obviously shows that the performance of proposed ENPSO is better than other two algorithms and have a faster convergent rate and better robustness.

Decomposition and Dominance Relation Based Many-objective Evolutionary Algorithm

In recent year, the Many-objective Optimization Problems (MaOPs) have become an increasingly hot research area in evolutionary computation. However, it is still a difficult problem to achieve a good balance between convergence and diversity on solving various kinds of MaOPs. To alleviate this issue mentioned above, a Decomposition and dominance relation based many-objective Evolutionary Algorithm(DdrEA) is proposed in this paper. Firstly, the population is decomposed into numbers of sub-populations by using a set of uniform weight vectors, in which they are optimized in a cooperative manner. Then, the fitness value of solution in each sub-population is calculated by angle dominance relation and angle. Finally, elite selection strategy is performed according to its corresponding fitness value. That is, in each subspace, the solution with the smallest fitness value is selected as the elite solution to enter the next generation. Comparing with several high-dimensional and multi-objective evolutionary algorithms (NSGA-II/AD, RVEA, MOMBI-II), the experimental results show that the performance of the proposed algorithm DdrEA is better than that of the comparison algorithm, and the convergence and diversity of the population can be effectively balanced.

Combining routing and virtual machine selection algorithm based on multi‐hop cloud wireless access network of mobile edge computing

For the problem that mobile devices that are far away from the base station obtain limited wireless resources, which causes high transmission delays, the study proposes a multi-hop path to assist users who are far away from the base station to use edge computing resources. And it combines cloud radio access network and wireless self-organising network. The modelling aims to minimise the total energy consumption under the constraints of task delay considering the mobility of mobile devices. Meanwhile, it selects the joint optimisation problem of the path for data transmission and the virtual machine for calculation. This study also introduces the krill herd algorithm and analyses its advantages and disadvantages. The author enhances the global search ability of the algorithm by defining perturbation factors in the random diffusion behaviour and introduces a new strategy of elite selection and retention into the iterative process to improve the convergence accuracy. Finally, the improved krill herd algorithm is used to solve the joint optimisation problem and a better allocation result than the separate resource allocation of calculation and communication is obtained. The experiment proves that the selection algorithm combining virtual machine and routing proposed in this study can achieve the expected results.

A multi-objective immune algorithm for intrusion feature selection

Feature selection plays a crucial role in classification problems, which tries to remove redundant or irrelevant features by mapping high-dimensional data to low-dimensional ones. Thus, this approach can improve the classification accuracy and reduce the computational cost to train the classification model. In this paper, we suggest an improved multi-objective immune algorithm (MOIA) for feature selection in intrusion detection. Specifically, the feature subsets for intrusion detection are treated as the individuals for immune optimization, which will select suitable feature subsets in order to reduce the dimensions of the dataset. After that, a neural network is used to train the classification model using the selected suitable feature subsets, and the output of the classification model is regarded as the target fitness value for each individual. As multiple attack types are considered in this paper, a traditional MOIA is modified by using an elite selection strategy based on the reference vectors, which can maintain the individuals with more promising performance when distinguishing more than five attack types in intrusion detection. By this way, the proposed algorithm can accelerate the convergence speed of classification, which also improves the classification accuracy. Experimental results on the NSL-KDD and UNSW-NB15 datasets validate the higher classification accuracy of the proposed algorithm.

Selection of elite Bradyrhizobium strains by biometric techniques for inoculation in cowpea

AbstractPlant breeding programs seek to obtain genotypes with high yield, yield stability, and wide adaptability to environments. Selection of strains (genotypes) for adoption as crop inoculants has a similar aim. However, in both cases, the genotype × environment interaction hinders selection of materials adapted to the most diverse edaphic and climatic conditions. Nevertheless, with adequate biometric techniques, the variation in the response of each strain in the environments can be analyzed, allowing selection of those with the type of response and standard desired. In the present pioneering field study, the Toler and additive main effects and multiplicative interaction analysis models and the Annicchiarico method were used in a complementary manner with strains of nitrogen‐fixing bacteria that are symbionts with cowpea to determine their adaptabilities and phenotypic stabilities. The adaptability and phenotypic stabilities of strains INPA 03‐11B and UFLA 03‐164 were confirmed by these techniques. These strains have the most stable behavior regardless of the environment. The reliability of adopting these strains exceeded 85%. The good response of strain UFLA03‐164, still in the selection phase, is surprising, with results equivalent to application of mineral N, allowing it to be included among the strains approved as inoculants for cowpea.

Elite Adaptive Parallel Evolutionary Algorithm for Sensor Nodes Clustering Optimization in High Density Sensor Network

Minimizing the communication energy consumption has always been a key aspect of the research of High Density Sensor Network (HDSN). HDSN is a group of small devices with restricted battery capacities. Accordingly, the objective of the clustering technique is to design a best set of sensor nodes clustering result for the combination that minimize the communication energy consumption. The ideal clustering problem with discrete variables is a np-hard problem in its accurate formulation. In this study, an improved elite adaptive parallel evolutionary algorithm (EAPEA) is proposed to lower the communication energy consumption in HDSN. The suggested algorithm is tested by a fitness function, and new adaptive operator and elite operator have been designed to speed up the convergence rate. The EAPEA merges the merits of the adaptive adjusting and elite selection. By the mechanism of adaptive adjusting, its overall exploit capacity is fully applied for finding the overall optimal solution. EAPEA simultaneously develop a large number of results to explore the explore area and to avoid local optima. A convergence analysis is carried out, and extensive experiments are carried out that compare EAPEA with two other heuristics. Our experimental simulations denote that the represented EAPEA technique, when used into HDSN, is competent to offer better performance and a low communication energy consumption compared to two other heuristics.

An Improved Artificial Electric Field Algorithm for Multi-Objective Optimization

Real-world problems such as scientific, engineering, mechanical, etc., are multi-objective optimization problems. In order to achieve an optimum solution to such problems, multi-objective optimization algorithms are used. A solution to a multi-objective problem is to explore a set of candidate solutions, each of which satisfies the required objective without any other solution dominating it. In this paper, a population-based metaheuristic algorithm called an artificial electric field algorithm (AEFA) is proposed to deal with multi-objective optimization problems. The proposed algorithm utilizes the concepts of strength Pareto for fitness assignment and the fine-grained elitism selection mechanism to maintain population diversity. Furthermore, the proposed algorithm utilizes the shift-based density estimation approach integrated with strength Pareto for density estimation, and it implements bounded exponential crossover (BEX) and polynomial mutation operator (PMO) to avoid solutions trapping in local optima and enhance convergence. The proposed algorithm is validated using several standard benchmark functions. The proposed algorithm’s performance is compared with existing multi-objective algorithms. The experimental results obtained in this study reveal that the proposed algorithm is highly competitive and maintains the desired balance between exploration and exploitation to speed up convergence towards the Pareto optimal front.

Political Elite Selection in Contemporary Chinese Higher Education

In contemporary China, colleges and universities have become the most important source for the Communist Party of China (CPC) to select political elites. With reference to undergraduates in contemporary Chinese higher education, this article explores the impact of "redness" (family background and ideology) and professional accomplishments (academic achievements) on the selection of Party members. Findings in this study have shown that in Chinese higher education, one's "redness" and "professional" accomplishments remain the main standards to select political elites. First, ideology is the primary criterion for selection of Party members among college/university students. The "redder" one's ideology, the greater is the probability of one being selected for membership. Second, a stronger "red" family background could enhance one's likelihood of selection by the Party, but primarily for those who are in the lower study year in their university/college schooling. This is particularly evident if one's father is a government official, a state-owned enterprise manager or a Party member. Third, the "professional" accomplishment criterion appears to be increasingly important at the higher study years in the university. Specifically, junior and senior students who have higher academic rankings and student awards are associated with a higher probability of selection by the Party.

Optimization algorithm of fireworks explosion based on elevator

The fireworks algorithm proposed in recent years. Compared with other traditional optimization algorithms, the fireworks algorithm has a strong ability to solve optimization problem. This paper improves the fireworks algorithm and proposes an elitism based fireworks explosion optimization algorithm (E-FWA). The E-FWA algorithm improves the explosion radius of fireworks algorithm and adds elite selection strategy to fireworks algorithm. A large number of experiments show that the elitism based fireworks explosion optimization algorithm can reduce the search time, improve the convergence of the algorithm, and avoid falling into the local optimal value.

SOCIAL INEQUITY AS A PRODUCT OF PUBLIC POLICIES IN THE FISCAL FIELD IN POST-COMMUNIST ROMANIA

This analysis is based on the premises that social, economic and fiscal policies can discriminate in a legitim manner certain categories against others only from the perspective of 3 types of reasons: economic criteria; social criteria; meritocratic criteria. From this perspective, any comparative advantage offered to certain groups or individuals, which can not be justified by any of these 3 legitim criteria of discrimination, is actually a privilege, unjustified from the public policies perspective. Even when these advantages follow the logic of differencing based on such legitim criteria, this differencing should be reasonable (to fulfil the condition of social equity as is defined in the theoretic and conceptual frame of this analysis). In Romania, there are significant differences, which do not follow the logic of discrimination according to any of the 3 mentioned criteria, from the perspective of rights, neither from that of obligations. On the other side, even when these are legitim from the above-mentioned perspective, the level of these differences is hard to justify. The differences address categories of people, but are not present on inter-categories level: between the residents connected to centralized heating system (massive subvention regardless the income) and those unconnected (no subvention); the pensions calculated according to different stages of contribution – the entire period, last 5 years, best 5 years, no correlation with the contribution but only with the last month salary. Health insurance is paid only by certain categories, regardless the income, other are excepted also, disregarding the income and some categories pay the contribution to a minimum level, regardless the income. Plus, the level of these differences is unjustified and unjustifiable. The “special” part of the special pensions exceeds in some cases 15 times over the part according to contribution and with the legal possibility unlimited increasing of this non-contributory part for certain categories. The hypothesis I intend to present in this analysis is that this accelerate increasing of the social inequity in the post-communist Romania is the product of establishing and functioning of certain power relations reflected in political decisions that favour one part of the population and disadvantage, correlative, another part of the population. The inequality increased not only based on the meritocratic mechanisms functioning within the economic context of free competition, but mainly based on elite selection mechanisms and social, privileged, un-meritocratic mobility.