Browsing by Author "Galvao Wall, David"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    A two-stage classification method for improved positioning using low-cost inertial sensors
    (IEEE, 2024-08-08) Maton, Dariusz; Economou, John; Galvao Wall, David; Khan, Irfan; Cooper, Robert; Ward, David; Trythall, Simon
    The two-stage subtractive clustering Takagi-Sugeno (2SC-TS) method is proposed which completely replaces the established method of inertial navigation with classification models. The classifiers are designed by the subtractive clustering algorithm, an unsupervised learning method. The accuracy of the trajectories is compared against three competitive data-driven methods on three independent experimental datasets. The results show how 2SC-TS generates trajectories with approximately 20% lower positional error compared with the single-stage version (SC-TS), and halves the error produced by competitive deep learning methods. The proposed method may help improve the positioning of people and robots carrying low-cost inertial sensors.
  • No Thumbnail Available
    ItemOpen Access
    Low-cost IMU Sensor Temperature Humidity Zero Bias Data
    (Cranfield University, 2024-05-13 11:08) Maton, Dariusz; Economou, John; Galvao Wall, David; Khan, Irfan; Cooper, Rob
    Dataset containing the responses of three inertial measurement units (IMUs) of the same model (MPU-6050s) under varying temperature and relative humidity conditions in a Sanyo Gallenkamp environmental chamber.
  • No Thumbnail Available
    ItemOpen Access
    Tuning of a Complementary Orientation Filter Using Velocity Data and a Genetic Algorithm
    (Cranfield University, 2024-01-08 14:59) Maton, Dariusz; Economou, John; Khan, Irfan; Galvao Wall, David; Cooper, Rob
    The data uploaded here contains the experimental and simulation data used to demonstrate the utility of the optimisation of a complementary orientation filter using a genetic algorithm (GA). Implementation of the GA in MATLAB is provided as well as supporting functions such as the zero velocity update and weighted-relative velocity error metric (W-RVE). The novelty of the work is the optimal tuning of the complementary filter gain using a GA and velocity data of an object moving in the locally level frame. Optimal filter gains are encoded a Takagi-Sugeno (TS) fuzzy inference system with four Gaussian membership functions. This offers a transparent and traceable encoding.