Journal: Sensors (Basel, Switzerland)

Article Title: Classification of HEp-2 Staining Pattern Images Using Adapted Multilayer Perceptron Neural Network-Based Intra-Class Variation of Cell Shape

doi: 10.3390/s23042195

Figure Lengend Snippet: An adapted MLP classifier using Softmax based gradient descent classification features using no data augmentation (first row) and data augmentation (second row), where x-axis is training vectors, containing the number of samples and the number of features, and y-axis is the number of samples to plot decision borders.

Article Snippet: The output layer is a vector of six class. shows an adapted MLP classifier using Softmax based gradient descent classification features using data augmentation and no data augmentation. shows an adapted MLP classifier using Softmax based gradient descent calculation cost and iteration and the best result is on i t e r a t i o n = 500 .

Techniques:

Journal: Sensors (Basel, Switzerland)

Article Title: Classification of HEp-2 Staining Pattern Images Using Adapted Multilayer Perceptron Neural Network-Based Intra-Class Variation of Cell Shape

doi: 10.3390/s23042195

Figure Lengend Snippet: A adapted MLP classifier using Softmax based gradient descent calculation cost and iteration.

Article Snippet: The output layer is a vector of six class. shows an adapted MLP classifier using Softmax based gradient descent classification features using data augmentation and no data augmentation. shows an adapted MLP classifier using Softmax based gradient descent calculation cost and iteration and the best result is on i t e r a t i o n = 500 .

Techniques:

Journal: Sensors (Basel, Switzerland)

Article Title: Validation of 3-Space Wireless Inertial Measurement Units Using an Industrial Robot

doi: 10.3390/s21206858

Figure Lengend Snippet: Accelerometer trust values.

Article Snippet: IMU orientation was calculated from raw accelerometer, gyroscope, and magnetometer values using one of the sensor fusion methods available through the 3-Space Mocap Studio program: the gradient descent filter (QGrad), the complementary filter (QComp), or the Kalman filter.

Techniques:

Journal: Sensors (Basel, Switzerland)

Article Title: Validation of 3-Space Wireless Inertial Measurement Units Using an Industrial Robot

doi: 10.3390/s21206858

Figure Lengend Snippet: RMSE of the angular difference between measured and reference values for each IMU data fusion method during rotation, translation, and stationary sequences. Axis refers to the IMU axis of rotation for the rotation sequence and the IMU axis aligned with gravity for the stationary trial.

Article Snippet: IMU orientation was calculated from raw accelerometer, gyroscope, and magnetometer values using one of the sensor fusion methods available through the 3-Space Mocap Studio program: the gradient descent filter (QGrad), the complementary filter (QComp), or the Kalman filter.

Techniques: Sequencing

Journal: Sensors (Basel, Switzerland)

Article Title: Validation of 3-Space Wireless Inertial Measurement Units Using an Industrial Robot

doi: 10.3390/s21206858

Figure Lengend Snippet: Results of ANOVA and multiple comparison tests for the difference in mean error for QComp, QGrad, and Kalman filters. Axis refers to the IMU axis of rotation for the rotation sequence and the IMU axis aligned with gravity for the stationary trial. Significant differences ( p < 0.05) indicated with an asterisk (*). Multiple comparison test results are not included for the Kalman filter with the magnetometer enabled because it is the instances of comparable performance that are of interest in this case.

Article Snippet: IMU orientation was calculated from raw accelerometer, gyroscope, and magnetometer values using one of the sensor fusion methods available through the 3-Space Mocap Studio program: the gradient descent filter (QGrad), the complementary filter (QComp), or the Kalman filter.

Techniques: Comparison, Sequencing

Journal: Sensors (Basel, Switzerland)

Article Title: Validation of 3-Space Wireless Inertial Measurement Units Using an Industrial Robot

doi: 10.3390/s21206858

Figure Lengend Snippet: Results of ANOVA and multiple comparison tests for the difference in mean error about X, Y, and Z axes at 45°/s for each filter without the magnetometer. Significant differences ( p < 0.05) indicated with an asterisk (*).

Article Snippet: IMU orientation was calculated from raw accelerometer, gyroscope, and magnetometer values using one of the sensor fusion methods available through the 3-Space Mocap Studio program: the gradient descent filter (QGrad), the complementary filter (QComp), or the Kalman filter.

Techniques: Comparison

Journal: Sensors (Basel, Switzerland)

Article Title: Validation of 3-Space Wireless Inertial Measurement Units Using an Industrial Robot

doi: 10.3390/s21206858

Figure Lengend Snippet: Results of ANOVA and multiple comparison tests for the difference in mean error during rotations executed at 45°/s, 90°/s, and 360°/s. Significant differences ( p < 0.05) indicated with an asterisk (*).

Article Snippet: IMU orientation was calculated from raw accelerometer, gyroscope, and magnetometer values using one of the sensor fusion methods available through the 3-Space Mocap Studio program: the gradient descent filter (QGrad), the complementary filter (QComp), or the Kalman filter.

Techniques: Comparison