M. Nezhadshahbodaghi, K. Bahmani, M. R. Mosavi, D. MartÃn,
Volume 19, Issue 2 (June 2023)
Abstract
Today, it can be said that in every field in which timely information is needed, we can use the applications of time-series prediction. In this paper, among so many chaotic systems, the Mackey-Glass and Loranz are chosen. To predict them, Multi-Layer Perceptron Neural Network (MLP NN) trained by a variety of heuristic methods are utilized such as genetic, particle swarm, ant colony, evolutionary strategy algorithms, and population-based incremental learning. Also, in addition to expressed methods, we propose two algorithms of Bio-geography-Based Optimization (BBO) and fuzzy system to predict these chaotic systems. Simulation results show that if the MLP NN is trained based on the proposed meta-heuristic algorithm of BBO, training and testing accuracy will be improved by 28.5% and 51%, respectively. Also, if the presented fuzzy system is utilized to predict the chaotic systems, it outperforms approximately by 98.5% and 91.3% in training and testing accuracy, respectively.
Nerjes Rahemi, Kurosh Zarrinnegar, Mohammad Reza Mosavi,
Volume 21, Issue 3 (September 2025)
Abstract
In determining position using GPS, due to local effects, pseudo-range errors cannot be mitigated by methods such as the use of reference stations or mathematical models; however, by using precise carrier phase observations and deploying a statistically optimal filter such as Phase-Adjusted Pseudo-range (PAPR) algorithm, the error can be significantly reduced. Additionally, the correlation between observations is a factor affecting positioning accuracy. In this paper, by using both pseudo-range and carrier phase observations and taking into account the effect of spatial correlation between observations to determine the variance-covariance matrix, the accuracy of position determination using the recursive Least Squares method is increased. For this purpose, the PAPR algorithm was implemented to reduce error. Next, a non-diagonal variance-covariance matrix was introduced to estimate the variance of the observations based on their spatial correlations. Experimental results on real data show that the proposed method improves positioning accuracy by at least 10% compared to previous methods. To evaluate the complexity of the proposed models, we employed an ARM STM32H743 processor. The findings indicate a modest increase in the proposed model complexity compared to earlier models, along with a substantial improvement in positioning accuracy.
