基于差分进化算法的低参数依赖无线非接触式感知方法

Low Parameter-Dependent Device-Free Sensing Method Based on Differential Evolution Algorithm

摘要

针对无线非接触式感知技术在实际应用中存在的参数依赖性较高,且现有基于优化算法的低参数依赖解决方案易陷入局部极小值的问题,提出一种基于差分进化算法的低参数依赖无线非接触式感知方法.该方法通过差分进化算法优化感知系统参数配置,结合迭代搜索和多参数组合性能评估的方式逼近全局最优解,并引入多分类器验证方法的有效性.实验结果表明,该方法可有效克服参数依赖性问题,提升数据采集准确性和目标检测精度,在人体行为识别数据集上分类准确率达97.06%,在脑神经数据集上分类准确率达94.02%,具有良好的实用性和鲁棒性,并有效解决了传统感知方法的参数依赖与局部最优解缺陷,为无线非接触式感知技术的工程化应用提供了新的参数优化思路.

Abstract

Aiming at the problems that device-free sensing technology had high parameter dependence in practical applications and existing low-parameter-dependent solutions based on optimization algorithms tended to fall into local minima, we proposed a low-parameter-dependent device-free sensing method based on the differential evolution algorithm. The proposed method optimized the parameter configuration of the sensing system through the differential evolution algorithm, combined iterative search and performance evaluation of multi-parameter combinations to gradually approach the global optimal solution, and introduced multiple classifiers to verify the effectiveness of the method. The experimental results show that this method can effectively overcome the problem of parameter dependence, improve the accuracy of data collection and target detection, with a classification accuracy of 97.06% on the human behavior recognition dataset and 94.02% on the brain nerve dataset. It has good practicability and robustness, and effectively solves the defects of parameter dependence and local optimal solutions of traditional sensing methods, providing a new parameter optimization idea for the engineering application of device-free sensing technology.

关键词

无线非接触式感知 / 差分进化算法 / 低参数依赖 / 优化算法

Key words

device-free sensing / differential evolution algorithm / low parameter-dependent / optimization algorithm

参考文献

[1] SHI F Z, LI W D, TANG C, et al. Decimeter-Level Indoor Localization Using WiFi Round-Trip Phase and Factor Graph Optimization[J]. IEEE Journal on Selected Areas in Communications, 2024, 42(1): 177-191.

[2] 张志强, 王健, 刘畅. 基于改进差分进化的无线传感器网络覆盖优化[J]. 东北师大学报(自然科学版), 2025, 57(2):68-75.

[3] (ZHANG Z Q, WANG J, LIU C. Coverage Optimization of Wireless Sensor Networks Based on Improved Differential Evolution[J]. Journal of Northeast Normal University (Natural Science), 2025, 57(2): 68-75.)

[4] QIN A K, HUANG V L, SUGANTHAN P N. Differential Evolution Algorithm with Strategy Adaptation for Global Numerical Optimization[J]. IEEE Transactions on Evolutionary Computation, 2009, 13(2): 398-417.

[5] DAS S, SUGANTHAN P N. Differential Evolution: A Survey of the State-of-the-Art[J]. IEEE Transactions on Evolutionary Computation, 2011, 15(1): 4-31.

[6] ZAHARIE D. A Comparative Analysis of Crossover Variants in Differential Evolution[C]// Proceedings of the International Multiconference on Computer Science and Information Technology. Wisla: Polskie Towarzystwo Informatyczne, 2007: 171-181.

[7] STORN R, PRICE K. Differential Evolution—A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359.

[8] 黄伟, 张磊, 吴昊. 地质环境监测中无线传感网络优化部署方法[J]. 吉林大学学报(地球科学版), 2025, 45(4):1123-1131. |

[9] (HUANG W, ZHANG L, WU H. Optimal Deployment Method of Wireless Sensor Networks in Geological Environment Monitoring[J]. Journal of Jilin University (Earth Science Edition), 2025, 45(4): 1123-1131.)

[10] 林浩, 马晓东. 基于差分进化与特征融合的WiFi非接触行为识别[J]. 计算机工程, 2026, 52(1):156-163.

[11] (LIN H, MA X D. WiFi Contactless Behavior Recognition Based on Differential Evolution and Feature Fusion[J]. Computer Engineering, 2026, 52(1): 156-163.)

[12] YOO S, KIM H, LEE J. Combining Reinforcement Learning with Genetic Algorithm for Many-to-Many Route Optimization of Autonomous Vehicles[J]. IEEE Access, 2024, 12: 26931-26942.

[13] ZHAO Y, ZHU Y C, WANG S W. User Scheduling in Wireless Networks for Deterministic Service: An Efficient Genetic Algorithm Method[J]. IEEE Networking Letters, 2024, 6(1): 1-5.

[14] KWON M S, LIM D K. A Study on the Optimal Design of PMa-SynRM for Electric Vehicles Combining Random Forest and Genetic Algorithm[J]. IEEE Access, 2023, 11: 52357-52369.

[15] LI J X, ZHU X Y, WANG J Y. AdaBoost.C2: Boosting Classifiers Chains for Multi-label Classification[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2023: 8580-8587.

[16] KIM S J, KIM J. A Combined Learning Based Classifier Using Decision Tree and Logistic Regression[C]// 2023 9th International Conference on Control, Decision and Information Technologies. Piscataway, NJ: IEEE, 2023: 1-4.

[17] 陈勇, 李海涛, 王鹏. 面向无线感知的自适应差分进化参数优化方法[J]. 江苏大学学报(自然科学版), 2024, 45(3):321-327.

[18] (CHEN Y, LI H T, WANG P. Adaptive Differential Evolution Parameter Optimization Method for Wireless Sensing[J]. Journal of Jiangsu University (Natural Science Edition), 2024, 45(3): 321-327.)

[19] LI D W, CHENG L, MA J S. Incident Duration Prediction Based on Latent Gaussian Naive Bayesian Classifier[J]. International Journal of Computational Intelligence Systems, 2011, 4(3): 345-352.

[20] ACLIKKAR M, TOKGǑZ S. An Improved KNN Classifier Based on a Novel Weighted Voting Function and Adaptive K-Value Selection[J]. Neural Computing and Applications, 2024, 36: 4027-4045.

[21] WANG Q, TAN W Y, LI P W, et al. Novel Multiwavelet-Based LPC Random Forest Classifier for Bluetooth RF-Fingerprint Identification[C]// 2022 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB). Piscataway, NJ: IEEE, 2022: 1-6.

[22] ASRITHA K R, SOUNDARIA G. Animal Collision Detection in Real Time to Prevent Accident Using KNN Classifier in Comparison with Stochastic Gradient Descent[C]// 2023 6th International Conference on Contemporary Computing and Informatics. Piscataway, NJ: IEEE, 2023: 1478-1482.

[23] WANG H J, SHAO Y H. Sparse and Robust SVM Classifier for Large Scale Classification[J]. Applied Intelligence, 2023, 53: 19647-19671.

[24] DOS SANTOS E M, SAN-MARTIN R, FRAGA F J. Comparison of Subject-Independent and Subject-Specific EEG-Based BCI Using LDA and SVM Classifiers[J]. Medical and Biological Engineering and Computing, 2023, 61: 835-845.

基金资助

吉林省科技厅科技发展计划项目(20220508038RC)