www.nature.com/scientificreports/
Figure 1. Dynamic evolution of the quality of water disclosure by paper and paper product companies, 2017–2021.
convergence. It has inherent parallelism and global superiority seeking capability. (3) Accelerated genetic algo- rithms are able to speed up convergence in each generation iteration and improve the efficiency of finding optimal projections by using genetic operations such as crossover and mutation to complete the optimization process in a limited amount of time. In this paper, an accelerated genetic algorithm is used to solve complex nonlinear optimization, improve the algorithm’s performance in finding the best, and solve the high-dimensional global optimum problem. The basic procedure is as follows 31,32 . First, the encoding of model real numbers is constructed, and linear optimization is performed: x ( j ) = a ( j ) + y ( j )( b ( j ) − a ( j )) , ( j = 1,2..., p ) ; Then, the initial parent basic group is produced, and N initial string structure data are randomly generated. { x ∗ ( i , j ) | i = 1,2, · · · , n ; j = 1,2, · · · , p } , A further population of N individuals is generated for evolutionary sorting { f ( i ) | i = 1,2, · · · , n ;}{ y ( i , j ) | i = 1,2, · · · , n ; j = 1,2, · · · , p } ; Assessment of the degree of adaptation. The merits and demerits of the individual or solution. F ( i ) = 1 /( f 2 ( i ) + 0.001 ) ; and select the next generation of individuals. After selecting good individuals from each chromosome, the cycle was repeated—forming a new individual P S ( i ) = F ( i )/ n i = 1 F ( i ) . By cross-operation, Y 2 ( i , j ) = u 1 y ( i 1 , j ) + ( 1 − u 1 ) y ( i 2 , j )< 0.5
Y 2 ( i , j ) = u 2 y ( i 1 , j ) + ( 1 − u 2 ) y ( i 2 , j ) , u 3 ≥ 0.5.
Mutation operation Y 3 ( i , j ) = u ( j ) , u m < p m ( i ) ; Y 3 ( i , j ) = u ( j ) , u m ≥ p m ( i ) ; Finally iterate. The cycle is repeated until the best individual in the group of N individuals is found and the operation is finished. Results and discussions Vertical changes in water disclosure for paper and paper product companies. Using 2017–2021 (excluding ST, ST*, and current year listed companies) as sample data, a projection tracing model with an accel- erated genetic algorithm was used to analyze the change in the trend of information disclosure about water resources in listed companies of paper and paper products. MATLAB 2022 was used to program the data, and the parents’ initial population size was 200, the crossover probability was 0. 8, the variation probability was 0.1, the number of outstanding individuals was selected as 20, and the number of accelerations was 20. Obtain the best projection direction of the indicator a ∗ = (0.1157, 0.2559, 0.1702, 0.1985, 0.2042, 0.3147, 0.2496, 0.3384, 0.1782, 0.2317, 0.1436, 0.1964, 0.1240, 0.2079, 0.1993, 0.2215, 0.2676, 0.2359, 0.2617, 0.2178), and to obtain the value of the investment evaluation of each sample corresponding to the disclosure of water resources informa- tion (Fig. 1). Changes in the vertical projection value of water information disclosure of paper and paper product companies. From the characteristics of the projection value change trend of water information disclosure of paper and paper product enterprises over the years, the projection value of each subsystem shows a staggered state of increase and decrease. Among them, the change trend of the disclosure carrier projection value shows a gradual decrease, as shown in Fig. 1. Water environment regulation, water environment assets, water environment management projection value in 2017 to 2019 overall steadily increasing, especially the water environment assets projection value from 0.4802 to 0.6778, 2019–2021, except for the disclosure carrier and water environment management projection value, showing a slow decline after a continuous increase, mainly
Scientific Reports |
https://doi.org/10.1038/s41598-023-39307-y
7 Vol.:(0123456789)
(2023) 13:12225 |
Made with FlippingBook Online newsletter maker