This paper presents design and implementation of an attitude and heading reference system (AHRS) based on low-cost MEMS sensors and complementary filtering (CF). Different from traditional solutions, information fusion is performed with Euler angles directly, which is more straightforward for understanding; however it proposes many challenges for reaching a stable and accurate estimation as when these angles approach or traverse their range boundaries, estimation may get discontinuous. Thus an effective discontinuity avoiding strategy is suggested in this paper to refine the estimation. Besides, instead of extended Kalman filtering (EKF), CF is utilized for state estimation of AHRS as it features fusion of high-frequency and low-frequency signals. In order to make up for shortcomings of MEMS sensors such as multiple errors, drifts, and bad accuracy, some effective calibration and filtering algorithms are proposed to guarantee agreeable AHRS performance. Also, architecture of the MEMS IMU (inertial measurement unit) and mathematical principles for AHRS solution are explained and implemented in this paper. Meanwhile, experimental comparisons have proved feasibility and acceptable performance of this AHRS design.
How to handle time features shall be the core question of any time series forecasting model. Ironically, it is often ignored or misunderstood by deep-learning based models, even those baselines which are state-of-the-art. This behavior makes their inefficient, untenable and unstable. In this paper, we rigorously analyze three prevalent but deficient/unfounded deep time series forecasting mechanisms or methods from the view of time series properties, including normalization methods, multivariate forecasting and input sequence length. Corresponding corollaries and solutions are given on both empirical and theoretical basis. We thereby propose a novel time series forecasting network, i.e. RTNet, on the basis of aforementioned analysis. It is general enough to be combined with both supervised and self-supervised forecasting format. Thanks to the core idea of respecting time series properties, no matter in which forecasting format, RTNet shows obviously superior forecasting performances compared with dozens of other SOTA time series forecasting baselines in three real-world benchmark datasets. By and large, it even occupies less time complexity and memory usage while acquiring better forecasting accuracy. The source code is available at https://github.com/OrigamiSL/RTNet.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.