An essential tool for describing human emotion is facial expression. From morning tonight, people go through a broad spectrum of emotions that may be caused by their mental or physical health. The six major facial expressions of happy, sorrow, surprise, fear, disgust, and rage are now classified by psychology as six universal emotions, despite the fact that humans experience a broad variety of emotions. Facial muscle movements may be used to determine humane motions. The brow, lips, nose, and eyes are the four primary facial characteristics Facial recognition is a topic that is now the focus of much investigation. Finding a match between the input image and the images to red in the database is the aim of face recognition. Human- computer interaction and the solution to the problem of criminal identification depend on facial recognition. The data in face recognition tasks has a high intrinsic complexity, making the dimensionality reduction strategy essential. Picture space's dimensionality is decreased using PCA. In the domains of computer vision, image processing, pattern recognition and other areas, the modelling of the face using Gabor features has generated a lot of attention. The major justification for using the Gabor filter is its biological significance. Mammal primary visual cortex neurons have an accessible field profile that is oriented toward spatial frequency features. Additionally, Gabor filters may make advantage of well-known visual properties as spatial localization, orientation selectivity and spatial frequency feature. So, we are proposing this computational model approach for the detection of emotional changes using dataset from EMOTIC database by recognition system. In this approach we achieved around 88% accuracy which efficient and better when it's been compared with computer modeling Methodologies.

The examination of cardiac illness uses electrocardiograms (ECGs or EKGs), which are electrical recordings of the heart. This heart's electrical activity causes line drawings to appear on paper. A series of waves is the name for the peaks and valleys in the line tracings. There are six distinct waveforms in this sequence of waves, which may be identified as cardiac waves (P, Q, R, S, and T). The majority of older techniques for analyzing ECG signals to find PQRST used DSP techniques like wavelet transform and fast Fourier transform, as well as artificial neural networks. While the electrocardiogram (ECG) signal's P, Q, R, S, and T values are detected using a straightforward and reliable approach in this study, the Holter monitor is crucial in the long-term monitoring of serious heart abnormalities in cardiac monitoring. Once the recording has been made, it must be examined to identify any waveform anomalies that might indicate the presence of arrhythmias or other abnormalities in the heart. In order to avoid potential harm during crucial hours, the time needed for a medical professional to review the waveforms must be extended. The efficiency of detecting and monitoring arrhythmias is increased by bio signal processing in MATLAB applications. using MATLAB to identify cardiac waves by applying a simple mathematical procedure to get cardiac wave values and display these values on the ECG waves simultaneously. In place of clinical diagnosis, this programme will be focused on scientific research. In this method, baseline correction, denoising, and arrhythmia identification come after parameter extraction. Future research on irregular waveform recognition may be applied to various bio signal applications, such as EEG, EOG, ERG, and EMG monitoring, to enhance the efficiency of analyzing aberrations in irregular waveforms.

A complete and rigorous literature evaluation focused on the detection and elimination of artifacts from EEG signals was presented in the preceding chapter. Issue-wise solution approaches and their limitations were also discussed which ultimately resulted in identifying the gaps in the proposed work and scope of the research work. In this chapter, the detailed explanation of system design and its implementation is discussed. The main focus of the anticipated research is to identify and remove the unwanted signals known as artifacts from the recorded EEG signals. Request access from your librarian to read this chapter's full text.