Search

Deep learning (DL) technology has shown to be the most effective method of completing class assignments in the last several years. Specifically, these approaches were used for segmentation, classification, and prediction of retinal blood vessels, which was previously unattainable. U-Net deep learning technology has been hailed as one of the most significant technological advances in recent history. In the proposed work, improved segmentation of retinal images using U-Net, bidirectional ConvLSTM U-Net (BiDCU-Net), and fully connected convolutional layers, such as absolute U-Net, BiConvLSTM preferences, and also the fully connected convolutional layer method are proposed. Three well-known datasets were subjected to the suggested technique’s evaluation: the DRIVE, STARE, and CHASE DB1 databases. This suggested technique was tested using the required precise measures in percentage of accuracy, F1 score, sensitivity, and specificity in DRIVE, 97.32, 83.85, 82.56, and 98.68 in CHASE, 97.44, 81.94, 83.92, and 98.45 in STARE, 97.33, 82.3, 82.12, and 98.57 in STARE, respectively. Furthermore, we assert that the strategy outperforms three other similar strategies in terms of effectiveness.

Noise reduction at the specific frequency of the line voltage of two level three phase voltage source inverter (VSI) fed induction motor (IM) is dealt in this paper, and the paper aims to develop a new PWM called random space vector pulse width modulation technique (RSVPWM) for reducing noise on line voltage and as well is applied for modeling in cloudsystems. The developed Random SVPWM combines RPWM and Space vector modulation (SVPWM) technique, the paper also investigates the three-phase VSI fed IM and its noise behavior along with noise reduction for cloud system. The proposed method includes a gap in the spectrum of line voltage at selective frequency in human hearing range and as well employed in cloud systems. Therefore, unlike conventional RPWM techniques, switching periods are determined based on the position of rotary reference vector. This work on comparison with other PWM techniques such as sine PWM, RPWM and SVPWM, performs in a better manner. Among all PWM method the proposed RSVPWM generate higher voltages with low total harmonic distortion for VSI fed IM and as well for the considered cloud system models. The proposed RSVPWM achieves less line voltage noise (10.4 dB at lower modulation range and 9 dB at higher modulation range), which proves its effectiveness. The simulation and experimentation is carried out for the full range of switching frequency of 1–20 kHz. The modulation method can be used in both open- and closed-loop IM drive such as V/F and vector control. The above method is applied for both IM and considered cloud system problems.