An increased electricity demand and dynamic load changes are creating a huge burden on the modern utility grid, thereby affecting supply reliability and quality. It is thus crucial for modern power system researchers to focus on these aspects to reduce grid outages. High-quality power is always desired to run various businesses smoothly, but power-electronic-converter-based renewable energy integrated into the utility grid is the major source of power quality issues. Many solutions are constantly being invented, yet a continuous effort and new optimized solutions are encouraged to address these issues by adhering to various global standards (IEC, IEEE, EN, etc.). This paper therefore proposes a concept of establishing a renewable-energy-based microgrid cluster by integrating various buildings located in an urban community. This enhances power supply reliability by managing the available energy in the cluster without depending on the utility grid. Further, a “fuzzy space vector pulse width modulation” (FSV-PWM) technique is proposed to control the inverter, which improves the power supply quality. This work uniquely optimized the dq reference currents using fuzzy logic theory, which were used to plot the space vectors with effective sector selection to generate accurate PWM signals for inverter control. The modeling/simulation of the microgrid cluster involving the FSV-PWM-based inverter was carried out using MATLAB/Simulink®. The efficacy of the proposed FSV-PWM over the conventional ST-PWM was verified by plotting voltage, frequency, real/reactive power, and harmonic distortion characteristics. Various power quality indices were calculated under different disturbance conditions. The results showed that the use of the proposed FSV-PWM-based inverter adhered to all the key standard requirements, while the conventional system failed in most of the indices.
Voice-controlled devices are in demand due to their hands-free controls. However, using voice-controlled devices in sensitive scenarios like smartphone applications and financial transactions requires protection against fraudulent attacks referred to as “speech spoofing”. The algorithms used in spoof attacks are practically unknown; hence, further analysis and development of spoof-detection models for improving spoof classification are required. A study of the spoofed-speech spectrum suggests that high-frequency features are able to discriminate genuine speech from spoofed speech well. Typically, linear or triangular filter banks are used to obtain high-frequency features. However, a Gaussian filter can extract more global information than a triangular filter. In addition, MFCC features are preferable among other speech features because of their lower covariance. Therefore, in this study, the use of a Gaussian filter is proposed for the extraction of inverted MFCC (iMFCC) features, providing high-frequency features. Complementary features are integrated with iMFCC to strengthen the features that aid in the discrimination of spoof speech. Deep learning has been proven to be efficient in classification applications, but the selection of its hyper-parameters and architecture is crucial and directly affects performance. Therefore, a Bayesian algorithm is used to optimize the BiLSTM network. Thus, in this study, we build a high-frequency-based optimized BiLSTM network to classify the spoofed-speech signal, and we present an extensive investigation using the ASVSpoof 2017 dataset. The optimized BiLSTM model is successfully trained with the least epoch and achieved a 99.58% validation accuracy. The proposed algorithm achieved a 6.58% EER on the evaluation dataset, with a relative improvement of 78% on a baseline spoof-identification system.
1 August 2021 in Journal of Electrical Engineering
This work proposes a novel frequency domain despeckling technique pertaining to the enhancement of the quality of medical ultrasound images. The results of the proposed method have been validated in comparison to both the time-domain and the frequency-domain projections of the schur decomposition as well as with several other benchmark schemes such as frost, lee, probabilistic non-local means (PNLM) and total variation filtering (TVF). The proposed algorithm has shown significant improvements in edge detection and signal to noise ratio (SNR) levels when compared with the performance of the other techniques. Both real and simulated medical ultrasound images have been used to evaluate the numerical and visual effects of each algorithm used in this work.
Almost all despeckling schemes have worked on removing speckle noise from the medical ultrasound image after reconstruction; in the final stage when the image is displayed on the screen. In this paper we use the principle component analysis approach (PCA) and Improved PCA (IPCA) by using a nonlinear soft thresholding technique to remove speckle noise from the medical ultrasound image before reconstruction. Wiener filter and NLmeans filter are used as benchmark for performance comparison with PCA and IPCA. Performance comparison is done between despeckling the image before decimation and after decimation. Despeckling the image before decimation has removed the speckle noise more efficiently than despeckling it after decimation and maintained the texture of the original image. Wiener filter and NLmeans were found less efficient than PCA or IPCA in removing speckle noise. IPCA has provided better visual and numerical results than PCA and that is mainly in terms of edge detection and peak signal to noise ratio.