Accurate detection of fiducial points in a seismocardiogram (SCG) is a challenging research problem for its clinical application. In this paper, an automated method for detecting aortic valve opening (AO) instants using the dorsoventral component of SCG signal is proposed. This method does not require electrocardiogram (ECG) as a reference signal. After pre-processing the SCG, multiscale wavelet decomposition is carried out to get signal components in different wavelet subbands. The subbands having possible AO peaks are selected by a newly proposed dominant multiscale kurtosis (DMK) and dominant multiscale central frequency (DMCF) based criteria. The signal is reconstructed using selected subbands, and it is emphasized using the weights derived from proposed relative squared dominant multiscale kurtosis (RSDMK). The Shannon energy (SE) followed by autocorrelation coefficients are computed for systole envelope construction. Finally, AO peaks are detected by a Gaussian derivative filtering based scheme. The robustness of the proposed method is tested using clean and noisy SCG signals from CEBS database. Evaluation results show that the method can achieve an average sensitivity (Se) of 94%, prediction rate (+P) of 90% and detection accuracy (ACC) of 86% approximately over 4585 analyzed beats.

The aim of facial expression recognition (FER) algorithms is to extract discriminative features of a face. However, discriminative features for FER can only be obtained from the informative regions of a face. Also, each of the facial subregions have different impacts on different facial expressions. Local binary pattern (LBP) based FER techniques extract texture features from all the regions of a face, and subsequently the features are stacked sequentially. This process generates the correlated features among different expressions, and hence affects the accuracy. This research moves toward addressing these issues. The authors' approach entails extracting discriminative features from the informative regions of a face. In this view, they propose an informative region extraction model, which models the importance of facial regions based on the projection of the expressive face images onto the neural face images. However, in practical scenarios, neutral images may not be available, and therefore the authors propose to estimate a common reference image using Procrustes analysis. Subsequently, weighted‐projection‐based LBP feature is derived from the informative regions of the face and their associated weights. This feature extraction method reduces miss‐classification among different classes of expressions. Experimental results on standard datasets show the efficacy of the proposed method.

The phonocardiogram (PCG) signal indicates closing instants of atrio-ventricular and semilunar valves, and this information can also be extracted from two major profiles of a seismocardiographic (SCG) cycle. This paper presents a method to extract fundamental heart sounds from a SCG signal. The proposed method employs discrete wavelet transform (DWT) for signal decomposition, and subsequently, center of gravity (CoG) of power spectrum for each of the subbands is computed. Our method can optimally select wavelet subbands for any combination of sampling frequencies of the signal and number of decomposition levels. Based on proposed CoG criterion, the signal is reconstructed from a number of selected subbands, and instantaneous Hilbert envelope is constructed for localizing peaks of the signal. Finally, a simple decision rule is applied to annotate S1 and S2 sounds of the PCG signal. Experimental results show that the heart sound waves S1 and S2 can be well localized with the help of one SCG cycle without using a reference ECG cycle.

Cancer is one of the foremost reasons of death worldwide, with nearly 10 million deaths noted in 2020. Globally oral cancer has the sixth rank when compared to other cancers. It is lethal because most cases are noticed at advanced stages, which can be prevented if screened for or treated early, leading to a significant decrease in the mortality rate due to oral cancer. Thus, it becomes necessary to detect oral cancer at its pre-cancerous stages. In this work, a method for classifying oral cavity lesions into benign and malignant for binary classification and their pre-cancerous stages for multi-class classification exploring five different color spaces extracting color and texture features classified using a machine learning technique Light Gradient Boosting Machine (LightGBM) is proposed. The overall performance is satisfactory, outperforming the state-of-art methods in this task, with a testing accuracy of 99.25%, precision of 99.18%, recall of 99.31%, f1-score of 99.24% and specificity of 99.31% for the binary classification, and testing accuracy of 98.88%, precision of 98.86%, recall of 97.92%, f1-score of 98.38% and specificity of 99.03% for multi-class classification. The proposed method used hand-crafted features and a machine-learning classifier, making it less time-consuming and using bare minimum resources.