Education, Science, Technology, Innovation and Life
Open Access
Sign In

Optimisation of efficient soil sampling scheme based on machine learning and approximation algorithm

Download as PDF

DOI: 10.23977/jeis.2025.100105 | Downloads: 29 | Views: 661

Author(s)

Xuecheng Luo 1, Shouyin Xiao 1, Mingyu Wang 1, Zhicheng Xu 1, Sijia Wang 1, Hongfan Chai 1

Affiliation(s)

1 School of Management, Shanxi medical University, Jinzhong, China

Corresponding Author

Xuecheng Luo

ABSTRACT

The aim of this study is to optimise the soil sampling scheme through machine learning and approximation algorithms to improve the efficiency of soil sampling work. The research methodology included calculating straight-line distances between sampling points using Haversine's formula and applying a clustering model and path-planning algorithm to determine the most efficient sampling routes. The main results show that the use of Haversine's formula, K-means clustering algorithm and Christofides' algorithm can significantly reduce the time required for soil sampling and increase the efficiency of the work. In addition, the paths were optimised for equalisation by the greedy algorithm to ensure that the daily working time was more balanced and within the allowed time frame. The study concludes that the proposed method not only optimises the soil sampling schedule but also ensures that the working hours are balanced and within the stipulated time limits.

KEYWORDS

Soil Sampling, Machine Learning, Approximation Algorithms, Path Optimisation, Efficiency, Workload Balancing

CITE THIS PAPER

Xuecheng Luo, Shouyin Xiao, Mingyu Wang, Zhicheng Xu, Sijia Wang, Hongfan Chai, Optimisation of efficient soil sampling scheme based on machine learning and approximation algorithm. Journal of Electronics and Information Science (2025) Vol. 10: 39-46. DOI: http://dx.doi.org/10.23977/10.23977/jeis.2025.100105.

REFERENCES

[1] Diveev A, Konstantinov S, Shmalko E, et al. Machine learning control based on approximation of optimal trajectories[J]. Mathematics, 2021, 9(3): 265.
[2] Maoudj A, Hentout A. Optimal path planning approach based on Q-learning algorithm for mobile robots[J]. Applied Soft Computing, 2020, 97: 106796.
[3] Narvaez P, Siu K Y, Tzeng H Y. New dynamic SPT algorithm based on a ball-and-string model[J]. IEEE/ACM transactions on networking, 2001, 9(6): 706-718.
[4] Yan C, Xiang X, Wang C. Towards real-time path planning through deep reinforcement learning for a UAV in dynamic environments[J]. Journal of Intelligent & Robotic Systems, 2020, 98: 297-309.
[5] Pritzkoleit M, Knoll C, Röbenack K. Reinforcement Learning and Trajectory Planning based on Model Approximation with Neural Networks applied to Transition Problems[J]. IFAC-PapersOnLine, 2020, 53(2): 1581-1587.
[6] Wang Q, Tang C. Deep reinforcement learning for transportation network combinatorial optimisation: a survey[J]. Knowledge-Based Systems, 2021, 233: 107526. 
[7] Hu J, Wang M, Zhang C, et al. Path Planning for Unmanned Vehicles Based on Value Function Approximation Algorithm[C]//2019 IEEE 15th International Conference on Control and Automation (ICCA). IEEE, 2019: 272-277.
[8] Mordatch I, Todorov E. Combining the benefits of function approximation and trajectory optimization[C]//Robotics: Science and Systems. 2014, 4: 23.

Downloads: 12710
Visits: 493276

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.