Treffer: Performance Analysis of 1D Linear Kalman Filter in Modern Scientific Computing Environments.

We present a comprehensive performance analysis of 1D linear Kalman filter implementations across three modern scientific computing environments: Python, Julia, and R. Using a position tracking problem with hypothetical noisy sonar measurements, we evaluated both numerical accuracy and computational efficiency. All implementations produced numerically identical results within machine precision (maximum differences of 1.2 = 10-14 m for position estimates), demonstrating the filter's ability to reduce measurement noise by 73.1% while accurately estimating unmeasured velocity states. Performance benchmarking revealed significant efficiency differences, with Python achieving a median execution time of 1.87 seconds, compared to 4.38 seconds for R and 34.82 seconds for Julia. Statistical analysis confirmed these differences were highly significant (Kruskal-Wallis H = 1332.445, p = 0.001) with extremely large effect sizes (Cohen's d > 13 for all comparisons). Memory profiling revealed significant differences in resource utilization, with Python maintaining the most efficient footprint (97.67 MB), followed by Julia (132.45 MB) and R (168.21 MB), all with minimal variation. The unexpected underperformance of Julia relative to Python contradicts theoretical expectations and highlights the importance of empirical benchmarking for scientific computing applications. Our results provide practical guidance for implementing Kalman filters in time-critical or resource-constrained applications. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Data Science (IJoDS) is the property of INSIGHT - Indonesian Society for Knowledge & Human Development and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)