Research on innovation of public service supply mechanism from the perspective of social cooperative governance based on improved genetic algorithms using fuzzy TOPSIS

Abstract

With the deepening of reform and opening up, the social management function of county government is becoming more and more important. As one of the symbols of the maturity of modern country, public service function is not only a test of the comprehensive ability of the country, but also a profound practice of serving the people. Aiming at the problem that traditional genetic algorithm is easy to fall into local optimal solution and its performance is unstable, an adaptive genetic algorithm (CEAGA) based on co-evolution is proposed. And then combined with some of the constraints inherent in the battlefield situation, a comprehensive evaluation model was established. The analysis on social cooperative governance is carried based on the fuzzy TOPSIS which is utilised for making multi criteria decision making situations. Research shows that the innovation of the public service supply mechanism must respect the reality of China’s political ecology, ensure the government’s dominant position in the governance of public affairs, and at the same time correctly respond to the development of social forces. The theory of collaborative governance also provides a new research perspective for the innovation and development of public service mechanisms.

Keywords

Improved genetic algorithm social collaborative governance public service supply mechanism innovation fuzzy TOPSIS

1 Introduction

Since the 1980s, Western countries have faced a common contradiction: on the one hand, the governments financial pressure, the government’s inefficiency and monopoly of providing services, and on the other hand, the public does not allow the government to give up excessive public services [1]. The Chinese government has also evolved from the guidance of only paying attention to its role to the top-level design level, and has built it into an effective framework for cooperation among various entities. Since the founding of New China, with the transition from the planned economic system to the socialist market economic system, China’s social management has experienced a transformation from the “unit system” to the “post-unit system” [2]. The key content of building a service-oriented government and realizing the transformation of government functions lies in perfecting the supply mechanism of public services so as to promote the comprehensive, coordinated and sustainable development of social economy. But in practical application, the convergence speed of the basic genetic algorithm (SGA) is slow, its stability is poor and it is prone to premature convergence [3]. Electronic jamming technology is one of the important branches in the field of electronic countermeasure, which kills the enemy’s electronic equipment and communication system by using some electronic disturbance measures [4]. Therefore, paying attention to and studying the performance of government public service functions has become the key to conform to social development, improve people’s livelihood and build a service government [5].

From the perspective of governance modernization, our government, on the basis of emphasizing the construction and improvement of socialist system with Chinese characteristics, has made other social subjects have more governance power and space of action by transferring power [6]. County-level government is located in the combination of urban and rural areas, industry and agriculture, macro-management and micro-management. It is the most important level of grass-roots government in China [7]. Collaborative governance can effectively solve the supply situation of public service fragmentation, decentralization and inefficiency caused by the lack of coordination and poor communication among different suppliers. It can not only give full play to the overall effect of the multi-supply subject, but also reflect the unique advantages of a single supply subject, and continuously improve the ability and level of government public services [8]. In response to the above problems, the researchers proposed many improved methods to adjust the selection pressure and avoid the occurrence of precocity by modifying the genetic operator and the scale transformation of the fitness function [9]. The use of electronic interference technology can interfere with the accuracy of enemy electronic equipment, reduce its performance; affect the communication system between the enemy combat units, reduce the enemy’s fire suppression and guidance capabilities, so that it can not accurately conduct battlefield situation reconnaissance and analysis. In this context, the theory of collaborative governance has become a discourse system for solving the dilemma of government public service functions [10].

With the continuous development of science and technology, modern warfare has developed from a traditional large-scale war to a local small-scale war. The attack method has also been gradually transformed from the original centralized control of firepower to electronic reconnaissance, and the electronic countermeasure technology and fire control are mutually Combined combat mode, this increases the complexity of the battlefield situation. China in the process of globalization is no exception [11]. First, the social governance dominance, from the government’s unilateral governance to the government and social various subjects governance [12]. The second is the status of the pluralistic subject of society, from passive acceptance of the dynamics of government management to active participation in the government’s main governance. Third, the way of management, from vertical leadership to network [13]. British scholar Hood pointed out: “It is very important to understand the relationship between government tools and environment. Public administration should study the performance of specific tools in what situations. After years of efforts to strengthen and innovate social management, many urban areas have made remarkable achievements in promoting public service reform, but they are still facing challenges brought by imbalances in the structure of public services, inadequate supply of services, inefficiency and other issues [14]. However, the improvement on the basis of single population is based on individual fitness to control individual evolution, and it is difficult to achieve the desired effect, so using multiple population evolution is a good solution [15].

In this paper, we propose a model based on improved genetic algorithm, which is a new model of innovation of public service supply mechanism in the perspective of social cooperative governance.

In summary, our contributions are as follows:

This paper presents a new model for improved genetic algorithm.

The model is widely applicable in the environment of improved genetic algorithm, and it has high applicability for the innovation of public service supply mechanism in the perspective of most social cooperative governance.

The new model proposed in this paper has better visualization effect, higher accuracy and wider applicability.

2 Related work

With the development of the concept of social management by the government, scholars from all walks of life at home and abroad have paid extensive attention to and studied the concept of social cooperative governance under the requirements of the modernization of national governance. We can learn from the excellent social management experience of foreign countries, but at present there are few studies on the social management of foreign local governments in academic circles. Merei G and others mentioned in the modern public goods theory that “products that must be consumed equally by collective members” are public goods, and pointed out that such products are non-competitive and non-exclusive [16]. In recent years, many monographs have been published on the issue of social management innovation. Norman BA profoundly explained the practical significance of the Chinese-style governance mechanism to modern China from the perspectives of the theoretical basis of governance and good governance, social autonomy and governance order, and considered this to be a major understanding and innovation of our party and the national government [17]. Tonella et al. also explored how to strengthen and innovate social management from the perspective of rural social management in the “Spots of Rural Social Management Innovation at County Level Governments” [18]. He also pointed out that the focus of strengthening and innovating social management at the county level is mainly to maintain social stability and harmonious development at the grassroots level, and to more effectively consolidate the party’s ruling foundation at the grassroots level.

Relevant literature search provides a general background for the social management research field of county-level governments. Through the investigation of monographs, it is helpful to understand more comprehensively the research status of county-level government social management. Scholars such as Qu H deeply analyzed the inevitability and development trend of social sector reform and development under the goal of realizing social governance modernization in China [19]. At the same time, it is pointed out that in order to ensure the smooth progress of governance, the organization should set up a dialogue platform between the public and the government and play a key role. The social management functions of county-level governments in rural areas should focus on building a joint urban-rural network to maintain rural social stability. Implementing the system of letters and visits with special features, and resolving social contradictions in a timely and effective manner. We should promote democracy at the grass-roots level, expand the quality of rural cadres and promote social harmony in rural areas. Rauwolf G.A. and others discuss that if a country’s social state is in a mature stage, then the social organization of the country presents a positive development trend [20]. While strengthening the leadership of the Party to social organizations, we should also strengthen the improvement of the Party’s self-governance ability. The author systematically analyses the institutional obstacles to the development of civil society organizations in China, and proposes institutional amendments to these obstacles. The results show that there are many vacancies in the research fields such as the way and role of the state government in guiding the development of social organizations, and there are still many deficiencies in the theoretical and Path Research of social organizations participating in cooperative governance in the perspective of cooperative governance in our country, which need to be further improved and supplemented.

3 Methodology

Electronic Warfare (EW) is the main core technology in this strategy. The so-called electronic warfare is to use various electronic measures and actions to weaken or destroy the performance and accuracy of enemy electronic equipment, reduce its operational efficiency, and make the enemy into chaos, so as to win the initiative of the operation for the enemy. At present, our country has entered a new stage of building a well-off society in an all-round way. In the new stage of development, the focus of the transformation of government functions is to strengthen public service functions in order to promote the coordinated development of economy and society in an all-round way. From the perspective of collaborative governance, there are still some problems in the development of social organizations, such as narrow sources of funds, insufficient brand awareness of public welfare projects and insufficient follow-up force, which hinder the development of organizations themselves and the realization of collaborative governance. In the process of collaborative governance, the inevitability and effectiveness of social organization participation and its own lack of capacity form a contradiction. On the one hand, the scope and effect of social organizations are increasingly prominent; on the other hand, the lack of their own capabilities limits the sustainability of their role, resulting in poor final results. Social management research is mainly about the government’s model of providing services and the relationship between government and citizens. It is part of the public administration theory, which is analyzed and summarized from the government’s practical activities, and is continuously refined and sublimated in practice.

For a community of n different populations, the collaborative model based on ecological population density is the rewritten Lotka-Volterra competition equation: $f = \frac{α P}{π d^{2}} \frac{ch (α \cdot \frac{L_{a} - x}{d})}{sh (α \cdot \frac{L_{a}}{d})} - \frac{4 R_{f}}{π d} \cdot x$ (1) The variation is limited to the individual’s Δ neighborhood, with the goal of speeding up the convergence of local populations. Among them, the adaptive mutation rate is defined as: $S = S_{as} = \frac{4 P}{π {dE}_{a} α} ch (α \cdot \frac{L_{a}}{d})$ (2)

The crossover and mutation probabilities in the basic genetic algorithm are fixed, which usually causes the genetic algorithm to be unstable. Therefore, the adaptive genetic operation is used in this paper. The crossover probability f and the mutation probability x can be automatically changed with the fitness. In the adaptive genetic algorithm, the crossover probability f and the mutation probability b are adaptively adjusted according to the following formula: $f^{'} = af + b$ (3) $f (x) = \frac{1}{g (x)}$ (4)

The global convergence performance and stability of the CEAGA algorithm are proved by many experiments. The function f1 is a nonlinear multidimensional multimodal function. When n is large, it is difficult to obtain a global optimal solution. The functions f2 and f3 are typical multi-dimensional multi-peak functions, which are easy to fall into the local optimal solution when solving. When n=30, the verification is performed. Figures 1, 2 and 3 are the one-time iterative optimization processes of the three functions.

Fig. 1

Function f1 iteration process.

Fig. 2

Function f2 iterative process.

Fig. 3

Function f3 iteration process.

Assuming that the enemy has four targets and we have four jamming equipment, we need to find out how to allocate jamming resources to maximize the jamming revenue. The jamming effectiveness matrix of the jamming equipment is shown in Equation (5). According to the definition of enumeration method, the following mathematical models can be established as shown in equation (6): $\frac{P}{S} = \frac{π {dE}_{a} α}{4 th (α \cdot \frac{L_{a}}{d})}$ (5) $f_{0} = \frac{α P}{π d^{2}} \frac{ch (α \cdot \frac{L_{a}}{d})}{sh (α \cdot \frac{L_{a}}{d})}$ (6)

As shown in Table 1, the design of probability table depends on the specific situation. Since this selection method is only related to the order of individual fitness, it does not require that individual fitness must be positive.

Table 1

Probability design table

Individual ordination ordination in population	Individual fitness	Probability assignment
1	80	0.28
2	75	0.23
3	60	0.19

Each decision should not only consider their own needs, but should proceed from the overall situation and constantly adjust the program to achieve the overall planning. According to the above description, the general mathematical models of dynamic programming can be established as shown in formulas (7) and (8): $f^{'} = f - (\bar{f} - c σ)$ (7) $f_{max}^{'} = C_{mult} \cdot f_{avg}$ (8)

In order to improve the efficiency of the algorithm, this paper proposes an individual intelligent repair method for the coordinated scheduling problem of cooperative interference resources. Suppose the enemy has 4 targets, and the corresponding threat level is shown in Table 2. Suppose we have 4 interference devices, and their interference performance against enemy targets is shown in Table 3.

Table 2

Enemy Target Threat Level

C1	C2	C3	C4
0.75	0.6	0.8	0.2

Table 3

Interference Effectiveness Values of Jamming Equipment

Target	C1	C2	C3	C4
A1	0.8	0.7	0.55	0.7
A2	0.6	0.5	0.43	0.5
A3	0.5	0.4	0.25	0.4
A4	0.2	0.6	0.68	0.6

Because only three basic operators, selection, crossover and replication, are used, it is not only simple to operate and easy to understand, but also provides a basic model for all subsequent algorithm improvements, which has a certain significance. The basic flow chart of SGA is shown in Fig.4.

With the increasing diversification of social development, how to realize the development of various subsystems in the social system from chaotic disorder to regular cooperation has become an important theoretical and practical issue that we must face and think about. Although there are few literatures on social management of county-level government at home and abroad, these studies have laid a macro foundation for Exploring Innovation of social management of county-level government and broadened research ideas. From the perspective of population, population evolution in a certain ecological environment is not only affected by its own fitness. It is also affected by competition and synergy between the environment and other populations. The latter two factors can be reflected by population density at the population level. In the process of achieving coordinated governance, the government must properly decentralize and give up enough space. At the same time, social organizations have sufficient autonomy to participate in this part of the space to form synergy. To make this reform goal a reality, we must innovate public service delivery mechanisms and continuously improve the capacity and level of government public services. Not only that, but through electronic interference, we can also cover our important goals and maximize our initiative for the battlefield. Therefore, in the modern war of the future, electronic countermeasures technology will play a pivotal role.

In the particle swarm algorithm, each particle represents a solution to the problem sought, and its value is calculated by the fitness evaluation function. Each particle passes its optimal particle and global optimal particle, and its position and velocity are reset by Equations (9), (10), and (11).

$Dr (p) = \frac{D (p)}{min (P_{A}, P_{B})}$ (9) $R_{A} (p) = \frac{min (A_{A}, A_{B})}{max (A_{A}, A_{B})}$ (10) $Cost (P_{i}) = \sum_{e \in P_{i}} C (e)$ (11)

There are few studies on collaborative governance in the scope of government governance. From the definition of synergy and governance, we can get the general connotation of collaborative governance. As the core theme in public management research, public service has always remained unchanged as an important function reflecting the essential attributes of government services in the long history of theoretical evolution. What needs to change or keep pace with the times is that the public service supply model continues to innovate as the theoretical paradigm changes. But what is collaborative governance? So far, there has not been a clear documentary record at home and abroad. To correctly understand this concept, we should start from synergy and governance. “Social governance” is concretely summarized as “realizing and safeguarding the rights of the masses as the core, giving play to the role of multiple governance subjects. In view of the social problems in state governance, we should improve social welfare, guarantee and improve people’s livelihood, resolve social contradictions, promote social equity and promote the orderly and harmonious development of society. Some scholars have introduced the idea of co-evolution into multi-population genetic evolutionary algorithm. The global convergence of genetic algorithm is improved and immature convergence is controlled by cooperative competition among different populations. However, the algorithm is prone to weaken and degenerate synergy in the process of evolution.

Pheromone Local Adjustment: When an ant runs for a period of time, it needs to adjust the local pheromone concentration between a and L, as shown in Equation (12). $K_{i} = \frac{t * sqrt (Ne) + α}{L + β}$ (12)

4 Result analysis and discussion

Collaborative jamming resource allocation problem is a combinatorial optimization problem. It refers to how to allocate our available resources reasonably to jam the enemy in order to obtain maximum benefits. It belongs to an important branch of military operational research. Coevolution individuals are influenced by three main factors in their own evolution process: individual fitness, living environment and competition with other individuals. Synergetics originates from Greek and means the study of coordination and cooperation. Some scholars believe that the whole world is a cooperative system. Synergetics studies the interaction between cooperative systems and subsystems driven by external parameters. The conditions, characteristics and evolutionary rules of forming orderly structure of space, time or function on macro scale by self-organization are emerging comprehensive disciplines. It can be seen that this is based on the political and administrative dichotomy. It is believed that the services of the administrative department should cover all aspects and assume the monopoly of service responsibility. According to modern synergy theory, synergy contributes to the stability and order of the whole system. It can amplify the system’s efficacy from both quality and quantity, create new functions that are not available locally, and realize value-added power. In short, collaborative governance is the multi-agent in society to manage social affairs through a coordinated system to maintain social stability and maximize the public interest.

In this paper, three more complex complex functions are selected to investigate the performance of the improved algorithm in maintaining population diversity, which are represented by f1, f2, and f3, respectively, and experiments are carried out separately. The experimental results are shown in Figs. 5, 6, and 7) shown.

Fig. 4

Basic flow chart of SGA.

Fig. 5

Function f1.

Fig. 6

Function f2.

Fig. 7

Function f3.

The Global Governance Council introduced a definition of collaborative governance in 1995 that collaborative governance covers all actions of individuals and public and private institutions to manage their common affairs. “Administrative authorities infiltrate public power into every corner to complete the policy. This requires us to have a well-trained, well-behaved officer, which is clearly an integral part of the job.” According to modern synergy theory, synergy contributes to the stability and order of the whole system. It can amplify the system’s efficacy from both quality and quantity, create new functions that are not available locally, and realize value-added power. “Synergetics is a science that studies the orderly, self-organizing collective behavior under the control of universal law. In a word, Synergetics refers to a new comprehensive discipline which studies the interaction, coordination and cooperation among various elements or subsystems in the system and forms the organic whole changing law. Among the N sub-populations of the global population, the better individuals concentrate on the local population through lifting operations. In order to make the local population converge to the optimal solution quickly, the local adaptive evolutionary algorithm based on neighborhood is adopted. But this kind of heuristic rule has no generality, so different heuristic rules need to be designed for different problems. The commonly used algorithms include first come first served, the highest ranking position weight and so on.

The average evolutionary algebra and the success rate of the algorithm are shown in Table 4 after 20 operations of the above three composite functions under the same experimental conditions.

Table 4

Average Evolutionary Algebra and Success Rate of Individual Functions

Algorithm	F1		F2		F3
	Average Evolutionary Algebra	Success rate	Average Evolutionary Algebra	Success Evolutionary rate	Average rate Algebra	Success
Basic genetic algorithm	5.6	2.7	6.3	87.6	215.7	36.7
Improved genetic algorithm	354.0	100	2.7	100	138.4	100

Social cooperative governance is an organic combination of synergetics and social governance theory. “It can be seen as a process of finding an effective governance structure in an open system”. Therefore, the theory of social cooperative governance is to reinterpret the new research paradigm formed by the theory of social governance with the basic ideas and methods of synergetics. It is a kind of productivity that has made a qualitative leap and expanded. The theory of bureaucracy is a kind of management structure with clear division of labor, orderly high and low levels and restraint at different levels. According to this theory, the western public service supply began to aim at improving efficiency and increasing output, and through the formulation of relevant policies and regulations, clear service standards, such as the quantity, time, quality and personnel of services, have detailed provisions. Then the specific application to the public service field, the public service collaborative supply is the inevitable result of the integration of the public service supply mechanism and the theory of collaborative governance. Since the problem of combinatorial optimization has a great influence on the development of the battlefield situation, many countries have paid more and more attention to this issue in order to obtain the initiative of the battlefield, and more and more scholars have studied it. The improved co-evolution algorithm has a good global search capability. It combines with the local adaptive evolution algorithm based on neighborhood, aiming to improve the genetic algorithm from both global and local aspects, so that CEAGA algorithm has both strong global search ability and good convergence speed.

The basic genetic algorithm and the improved genetic algorithm are used to solve the problem as shown in Table 5. From the experimental data comparison, it can be found that the improved algorithm has better performance for the handling of the knapsack problem.

Table 5

Comparison of traditional genetic algorithm and improved algorithm in the application of knapsack problem

Algorithm	Total quality	Total value obtained	Number of the stuffs	Number of backpacks
Basic genetic algorithm	847	2485	60	500
Improved genetic algorithm	1169	2654
Basic genetic algorithm	1347	5478	120	1000
Improved genetic algorithm	1458	5698

5 Fuzzy TOPSIS

This model is on the basis of ranking scenario of considering the closeness related to the estimation objects to an aim which is idealized, in case to achieve to calculate the advantages which are related present choices. While proceeding for decision making procedures, it could not handle the bias occurred due to uncertainty and vagueness. Theory of fuzzy set is utilised for solving the issues such as uncertainty and ambiguity in process of decision making. Moreover, the association of fuzzy group and suitability during the process of tendencies for providing issues related to decision making scenario. This method are broadly utilised by various researchers and mentioned for various fields like predicting the vulnerability. Various researchers utilize fuzzy TOPSIS in finding the selection procedure of information management.

As discussed before, the fuzzy TOPSIS models that associates the theory of fuzzy set with TOPSIS which is traditional method. In model of basis estimation of optimal explanation is that the distance geometric amongst the explanation and positive ideal explanation (PIS) is lowest number of benefit level, and solution amongst the geometric distance and negative ideal explanation (NIE) is the longest under standard of cost.

The initial steps of TOPSIS fuzzy model are as below:

Step 1: Concept of matrix of fuzzy decision

There exist n makers of decision evaluating n choices with t criteria. It can be mentioned in matrix as: $Q = [\begin{matrix} q_{11} & q_{12} & \dots & \dots & q_{1 t} \\ q_{21} & q_{22} & \dots & \dots & q_{2 t} \\ ⋮ \\ ⋮ \\ q_{t 1} & q_{t 2} & q_{tt} \end{matrix}], u = 1, 2, 3, \dots, v = 1, 2, 3 \dots . .$ (13)

Step 2: matrix which is normalized by fuzzy decision

The matrix which is of normalized form: $Q = [q_{uv}]_{nt}$ (14)

The values which are normalized for cost and benefits scenario are estimated as given below:

Benefit scenario: $q_{uv} = (\frac{b_{uv}}{d_{v}^{*}}, \frac{a_{uv}}{d_{v}^{*}}, \frac{c_{uv}}{d_{v}^{*}}), u = 1, 2, 3 \dots \dots, v = 1, 2, 3 \dots \dots$ (15)

Cost scenario: $q_{uv} = (\frac{b_{v}^{-}}{d_{v}^{*}}, \frac{b_{v}^{-}}{d_{v}^{*}}, \frac{b_{v}^{-}}{d_{v}^{*}}), u = 1, 2, 3 \dots \dots, v = 1, 2, 3 \dots \dots$ (16)

6 Conclusions

The challenge that spheroidization brings to the government is all-encompassing. The government and the society must respond to the challenge by “common governance”. To achieve co-governance, we must first establish a benign interaction system between the government and the society, that is, establish an institutionalized communication, service and interaction mechanism between the government and the society to form a benign communication and interaction. The deployment of the Party Central Committee and the State Council has clarified the guiding ideology, fundamental purpose, and methods for local governments to strengthen and innovate social management. In summarizing the relevant literature, it can be clearly found that it is important to build a sound organizational platform and introduce advanced service technologies. However, in the face of social forces that cannot be ignored, it seems that the development and improvement of public service system construction from the perspective of multi-subject participation is more in line with the current needs, and can also respond to the changes in the relationship between the state and society. In global search, an improved co-evolutionary algorithm is adopted to avoid pure genetic evolution based on individual fitness and improve population diversity. This paper mainly studies the genetic algorithm in artificial intelligence technology, and uses it to solve the problem of optimal resource allocation for different platforms. However, the traditional genetic algorithm has some shortcomings, which are manifested in that it is easy to fall into the local optimal problem, which makes the algorithm unable to achieve global optimal convergence.

References

Arabali

, Ghofrani

, Etezadi-Amoli

, et al., Genetic-Algorithm-Based Optimization Approach for Energy Management [J], IEEE Transactions on Power Delivery 28(1) (2013), 162–170.

Dasgupta

, Mandal

, Dutta

, et al., A Genetic Algorithm (GA) based Load Balancing Strategy for Cloud Computing[J], Procedia Technology 10(2) (2013), 340–347.

Ghamisi

and Benediktsson

J.A.

, Feature Selection Based on Hybridization of Genetic Algorithm and Particle Swarm Optimization[J], IEEE Geoscience and Remote Sensing Letters 12(2) (2014), 309–313.

Hartmann

, A Competitive Genetic Algorithm for Resource-Constrained Project Scheduling[J], Naval Research Logistics 45(7) (2015), 733–750.

Ismail

M.S.

, Moghavvemi

and Mahlia

, Characterization of PV panel and Global Optimization of Its Model Parameters using Genetic Algorithm[J], Energy Conversion and Management 73(9) (2013), 10–25.

Merei

, Berger

and Sauer

D.U.

, Optimization of an off-grid hybrid PV–Wind–Diesel system with different battery technologies using genetic algorithm[J], Solar Energy 97 (2013), 460–473.

Morris

G.M.

, Goodsell

D.S.

, Halliday

R.S.

, et al., Automated docking using a Lamarckian genetic algorithm and an empirical binding free energy function[J], Journal of Computational Chemistry 19(14) (1998), 1639–1662.

Neath

M.J.

, Swain

A.K.

, Madawala

U.K.

, et al., An Optimal PID Controller for a Bidirectional Inductive Power Transfer System Using Multiobjective Genetic Algorithm [J], IEEE Transactions on Power Electronics 29(3) (2013), 1523–1531.

Niesse

J.A.

and Mayne

H.R.

, Global optimization of atomic and molecular clusters using the space-fixed modified genetic algorithm method [J], Journal of Computational Chemistry 18(9) (1997), 1233–1244.

10.

Norman

B.A.

, A genetic algorithm methodology for complex scheduling problems [J], Naval Research Logistics 46(2) (2015), 199–211.

11.

Oreski

and Oreski

, Genetic algorithm-based heuristic for feature selection in credit risk assessment[J], Expert Systems with Applications 41(4) (2014), 2052–2064.

12.

Qiu

, Zhong

, Li

, et al., Phase-Change Memory Optimization for Green Cloud with Genetic Algorithm [J], IEEE Transactions on Computers 64(12) (2015), 1–1.

13.

, Xing

and Alexander

, An improved genetic algorithm with co-evolutionary strategy for global path planning of multiple mobile robots [J], Neurocomputing 120(10) (2013), 509–517.

14.

Rauwolf

G.A.

and Coverstone-Carroll

V.L.

, Near-optimal low-thrust orbit transfers generated by a genetic algorithm [J], Journal of Spacecraft and Rockets 33(6) (1996), 859–862.

15.

Roberge

, Tarbouchi

and Labonte

, Comparison of Parallel Genetic Algorithm and Particle Swarm Optimization for Real-Time UAV Path Planning [J], IEEE Transactions on Industrial Informatics 9(1) (2013), 132–141.

16.

Simpson

T.W.

and D’Souza

B.S.

, Assessing Variable Levels of Platform Commonality Within a Product Family Using a Multiobjective Genetic Algorithm [J], Concurrent Engineering 12(2) (2013), 119–129.

17.

Tavakkolimoghaddam

, Safari

and Sassani

, Reliability optimization of series-parallel systems with a choice of redundancy strategies using a genetic algorithm [J], Reliability Engineering & System Safety 93(4) (2017), 550–556.

18.

Tonella , Paolo , Susi , et al., Interactive requirements prioritization using a genetic algorithm [J], Information & Software Technology 55(1) (2013), 173–187.

19.

, Li

, Hu

, et al., A genetic algorithm for task scheduling on heterogeneous computing systems using multiple priority queues [J], Information Sciences 270 (2014), 255–287.

20.

and Xu

, A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network [J], Applied Energy 134 (2014), 102–113.