Qin Le
ABSTRACT
The traditional seismic data anomaly identification method usually adopts a simple threshold method to determine the data collected by the device outside the set normal monitoring threshold as abnormal data, and the abnormal data cannot be accurately identified. This paper adopts a method to improve the traditional anomaly recognition L-IAZPSO-SVM method to improve the accuracy of abnormal data recognition.In this paper, the earthquake precursor data [1] provided by China Seismic Network is used as the input index, and the improved PSO (Particle Swarm Optimization) [2] is used to optimize the SVM(support vector machine) [3] training to realize the identification and prediction of abnormal data. First Using Cluster analysis and PCA(Principal Component Analysis) [4] make the data preprocessed, and then Itô Lemma [5] is used to optimize the PSO initialization process to improve the particle variability and make the initial particles diverse. The adaptive speed update method is used to improve the problem that the algorithm is easy to fall into the local optimal solution in the later stage of the algorithm. The Ziggurat algorithm [6] is used to increase the number of particles and solve the problem of imbalance between the global search capability and the local search capability of the system. The improved algorithm solves the problem that the traditional SVM method cannot determine the number of support vectors, the system fitting fuzzy problem and improves the algorithm's abnormal recognition rate and prediction rate. Compared with the traditional PSO-SVM method, other improved PSO-SVM methods, and other anomaly data detection algorithms, the system's running speed, global search capability, operational stability, and abnormal data recognition rate prediction rate are improved.
- Wang Keying, Zou Lizhen, Liang Jianhong, Ren Kexin, Qiu Haijiang, Ding Qiuqin, Liu Jingguang. Seismic catalog database and seismic phase database of China Seismological Network and Global Seismic Network. Seismological and Geomagnetic Observation and Research, 2003, (03): 37--43.Google Scholar
- Sierra M R, Carlos A. Coello Coello. Improving PSO-Based Multi-objective Optimization Using Crowding, Mutation and &epsis;-Dominance. Lecture Notes in Computer Science, 2005, 3410: 505--519.Google ScholarDigital Library
- Drosou K, Koukouvinos C. A new variable selection method based on SVM for analyzing supersaturated designs. 2019, 51(1): 21--36.Google Scholar
- Liu C. Gabor-based kernel PCA with fractional power polynomial models for face recognition. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2004, 26(5): 572--81.Google ScholarDigital Library
- Rathnayaka R M K T, Jianguo W, Seneviratna D M K N. Geometric Brownian Motion with Ito's lemma approach to evaluate market fluctuations: A case study on Colombo Stock Exchange// International Conference on Behavior. IEEE, 2015.Google Scholar
- Mcfarland C D. A modified ziggurat algorithm for generating exponentially- and normally-distributed pseudorandom numbers. Journal of Statistical Computation & Simulation, 2016, 86(7): 1281--1294.Google ScholarCross Ref
- Rotondi R, Varini E. Failure models driven by a self-correcting point process in earthquake occurrence modeling. Stochastic Environmental Research and Risk Assessment, 2019, 33(1--4): 709--724.Google ScholarCross Ref
- Mao L F, Yao J G, Jin Y S, et al. Abnormal Data Identification and Missing Data Filling in Medium-and Long-Term Load Forecasting. Power System Technology, 2010, 34(7): 148--153.Google Scholar
- Guan Ziqi, Zhu Yulong, Liu Xiaoguang, Liu Dan, Chang Yunlong. Modeling of weld pool illuminance based on GA optimized BP neural network. Thermal Processing Technology, 2019, (07): 216--220.Google Scholar
- Zhang Y, Wu L. Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network. Expert Systems with Applications, 2009, 36(5): 8849--8854.Google ScholarDigital Library
- Xiong Yi, Liang Yiwen, Tan Chengyu, Zhou Wen. Anomaly Detection of Earthquake Precursor Observation Data Based on Reverse Selection. Computer Engineering and Applications, 1--7.Google Scholar
- Qian Xiaoyu, Ge Hongwei, Cai Ming. Multi-objective particle swarm optimization algorithm based on target space decomposition and continuous mutation. Journal of Intelligent Systems, 2019, (03): 1--7.Google Scholar
- Zhang Xiaoli, Wang Qinfei, Yan Wenli. An Improved Particle Swarm Optimization Algorithm with Adaptive Inertia Weight. Microelectronics & Computer, 2019, 36(03): 66--70.Google Scholar
- Bezdek J C, Ehrlich R, Full W. FCM: The fuzzy c-means clustering algorithm. Computers & Geosciences, 1984, 10(2): 191--203.Google ScholarCross Ref
- Agbehadji I E, Fong S, Millham R. Wolf search algorithm for numeric association rule mining// IEEE International Conference on Cloud Computing & Big Data Analysis. 2016.Google Scholar
- Duan H, Yu Y, Zhang X, et al. Three-dimension path planning for UCAV using hybrid meta-heuristic ACO-DE algorithm. Simulation Modelling Practice & Theory, 2010, 18(8): 1104--1115.Google ScholarCross Ref
- Tang X, Yang Q, Sun Y. Gas flow-rate measurement using a transit-time multi-path ultrasonic flow meter based on PSO-SVM// Instrumentation & Measurement Technology Conference. 2017.Google Scholar
- Run-Xiu W U, Sun H, Zhu D G, et al. Particle Swarm Optimization Algorithm Based on Optimal Particle Guidance and Gauss Perturbance. Journal of Chinese Computer Systems, 2016.Google Scholar
Index Terms
- Study on Precursor Anomaly Data Recognition and Prediction of L-IAZPSO-SVM Algorithm
Recommendations
On performance analysis of hybrid algorithm (improved PSO with simulated annealing) with GA, PSO for multiprocessor job scheduling
Particle Swarm Optimization is currently employed in several optimization and search problems due its ease and ability to find solutions successfully. A variant of PSO, called as Improved PSO has been developed in this paper and is hybridized with the ...
The PSO optimisation SVM prediction model for the asphalt pavement environment and service fatigue life
In order to improve the accuracy of prediction by support vector machine (SVM), parameter optimisation of SVM is an important part of asphalt pavement life prediction. In this paper, a particle swarm optimisation support vector machine (PSO_SVM) method ...
Car Sales Volume Prediction Based on Particle Swarm Optimization Algorithm and Support Vector Regression
ICICTA '11: Proceedings of the 2011 Fourth International Conference on Intelligent Computation Technology and Automation - Volume 01In this paper, the car sales prediction model is established by using Support Vector Regression(SVR) combined with Particles Swarm Optimization algorithm (PSO-SVR). In this model, PSO Algorithm is used to optimize the 3 parameter used in Support Vector ...
Comments