جستجوی مقالات مرتبط با کلیدواژه « gyroscope » در نشریات گروه « برق »

In this paper, information of gyroscope and star tracker attitude sensors are fused for attitude estimation in the presence multi-rate sensors and the star tracker measurement delay. To this end, the extended Kalman filter (EKF) is modified to reduce the computation burden avoiding computation repetitions after arrival of the delayed multi-rate measurements. The algorithm is modified such that it is truly estimating the attitude in the absence of the star tracker measurements due to low sampling rate frequency and the estimation is optimized after its arrival. Toward this, the idea of predicting the measurement model, firstly proposed in [7], is employed and extended for the EKD based attitude estimation in the presence of multi-rate gyroscope and star tracker sensory information and delay in the star tracker measurement is also involved in the proposed method. The efficiency of the proposed method is finally demonstrated through both simulation and experimental data.

Human physical activity recognition using gyroscope and accelerometer sensors of smartphones has attracted many researches in recent years. In this paper, the performance of principle component analysis feature extraction method and several classifiers including support vector machine, logestic regression, Adaboost and convolutional neural network are evaluated to propose an efficient system for human activity recognition. The proposed system can improve the classification accuracy in comparison with the state of the art researches in this field. The performance of a physical activity recognition system is expected to be robust on different smartphone platforms. The quality of smartphone sensors and their corresponding noises vary considerably between different smartphone models and sometimes within the same model. Therefore, it is beneficial to study the effect of noise on the efficiency of the human activity recognition system. In this paper, the robustness of the investigated classifiers are also studied in various level of sensor noises to find the best robust solution for this purpose. The experimental results, which is provided on a well-known human activity recognition dataset, show that the support vector machine with averaged accuracy of 96.34% perform more robust than the other classifiers on different level of sensor noises.