Narrow Results

Fault isolation in electronic circuits is a trending area of interest as analog circuits find valuable application in industry. The failures in circuit systems cause severe issues in the normal functioning of the system that insists on the need for an automatic method of fault isolation in analog circuits. Literature conveys the issues associated with the fault isolation and hence, to address the severity of the faults, a novel model is proposed to isolate the fault causing component in the circuit. The proposed Multi-Rider Optimization-based Neural Network (M-RideNN) isolates the faulty part of the circuit from the fault-free areas such that the fault diagnosis is structured in an effective way. The fault isolation is progressed as four major steps such as establishing the fault dictionary, signal normalization using Linear Predictive Coding (LPC), effective dimensional reduction methodology using Probabilistic Principal Component Analysis (PPCA), and fault isolation using the proposed M-RideNN classifier. Finally, the experimentation using three circuits, namely Triangular Wave Generator (TWG), Bipolar Transistor Amplifier (BTA), differentiator (DIF), and an application circuit, Solar Power Converter (SPC), proves that the proposed M-RideNN classifier offers better classification accuracy of 93.18% with a minimum Mean Square Error (MSE) of 0.0682.

Automatic speech emotion recognition (ASER) from source speech signals is quite a challenging task since the recognition accuracy is highly dependent on extracted features of speech that are utilized for the classification of speech emotion. In addition, pre-processing and classification phases also play a key role in improving the accuracy of ASER system. Therefore, this paper proposes a deep learning convolutional neural network (DLCNN)-based ASER model, hereafter denoted with ASERNet. In addition, the speech denoising is employed with spectral subtraction (SS) and the extraction of deep features is done using integration of linear predictive coding (LPC) with Mel-frequency Cepstrum coefficients (MFCCs). Finally, DLCNN is employed to classify the emotion of speech from extracted deep features using LPC-MFCC. The simulation results demonstrate the superior performance of the proposed ASERNet model in terms of quality metrics such as accuracy, precision, recall, and F1-score, respectively, compared to state-of-the-art ASER approaches.