O
Odongo Steven Eyobu
Researcher at Kyungpook National University
Publications - 25
Citations - 469
Odongo Steven Eyobu is an academic researcher from Kyungpook National University. The author has contributed to research in topics: Computer science & Vehicular ad hoc network. The author has an hindex of 7, co-authored 20 publications receiving 216 citations. Previous affiliations of Odongo Steven Eyobu include Makerere University.
Papers
More filters
Journal ArticleDOI
Feature Representation and Data Augmentation for Human Activity Classification Based on Wearable IMU Sensor Data Using a Deep LSTM Neural Network.
TL;DR: A spectrogram-based feature extraction approach combined with an ensemble of data augmentations in feature space is proposed to take care of the data scarcity problem and produces state-of-the-art accuracy results in HAR.
Journal ArticleDOI
An Indoor Position-Estimation Algorithm Using Smartphone IMU Sensor Data
TL;DR: A position-estimation algorithm that uses the combined features of the accelerometer, magnetometer, and gyroscope data from an IMU sensor for position estimation and achieves a high position accuracy that significantly outperforms that of conventional estimation methods used for validation.
Journal ArticleDOI
A Comparative Review of Hand-Eye Calibration Techniques for Vision Guided Robots
Ikenna Enebuse,Mathias Foo,Babul Salam Ksm Kader Ibrahim,Hafiz Ahmed,Fhon Supmak,Odongo Steven Eyobu +5 more
TL;DR: A review of hand-eye calibration can be found in this paper, where a general overview of the strengths and weaknesses of different handeye calibration algorithms available to academics and industrial practitioners is presented.
Proceedings ArticleDOI
Localization Error Analysis of Indoor Positioning System Based on UWB Measurements
TL;DR: The experimental results show that the linearized least square algorithm has poor performance for UWB indoor localization, and the fingerprint estimation algorithm shows better performance compared to linearization least square estimation and weighted centroid estimation algorithms.
Journal ArticleDOI
Augmented CWT Features for Deep Learning-Based Indoor Localization Using WiFi RSSI Data
TL;DR: Two novel feature set extractions based on the continuous wavelet transforms (CWT) of the received signal strength indicators’ (RSSI) data are introduced and it is shown that the proposed augmented CWT-image feature set outperformed the augmentedCWT-PSD numerical feature set.