Search

Emotion is a natural feeling which is distinguished from reasoning or knowledge, it is a strong feeling derived from one’s circumstance or surroundings. With the increase in man to machine interaction, speech analysis has become an integral part in reducing the gap between physical and digital world. An important sub field within this domain is the recognition of emotion in speech signals, which was traditionally studied in linguistics and psychology. Speech emotion recognition is a field having diverse applications. When implemented the Speech Emotion Recognition (SER) will be able to understand different human emotion such as anger, fear, happiness, sadness etc. Speech is a medium of expression of one’s perspective or feelings to other. Emotion recognition from audio signal requires feature extraction and classifier training. The feature vector consists of elements of the audio signal which characterize speaker specific features such as tone, pitch, energy, which is crucial to train the classifier model to recognize a particular emotion accurately. Thus, with the help of SER we can make conversations between human and computer more realistic and natural. Automatic Speech Emotion Recognition (SER) is a current research topic in the field of Human Computer Interaction (HCI) with wide range of applications. The speech features such as, Mel Frequency cepstrum coefficients (MFCC) and Mel Energy Spectrum Dynamic Coefficients (MEDC) are extracted from speech utterance. The Support Vector Machine (SVM) is used as classifier to classify different emotional states such as anger, happiness, sadness, neutral, fear, from Berlin emotional database.

The primary goal of this thesis is to simulate the causes of human face ageing and to detect skin illnesses. This project combines the capabilities of a Deep Learning model, notably EfficientDet, with the capabilities of a machine learning model and Advanced Computer Vision to identify and locate aging and skin disease. In an uploaded photo there are irregularities which can be detected. The appearance of age-related face changes is determined by a variety of factors. Wrinkles, dark patches, and swollen eyes are all variables to consider. The TensorFlow Objection Detection API is used to investigate the factors. TensorFlow Zoo's EfficientDet model is pre-trained. The proposed models are found to be effective based on the outcomes. Very effective in predicting the indications of ageing in people of all ages. Python was used to implement this project.

The prediction of violent-crime occurrences such as rape, murder, kidnapping, robbery etc. is very important to avoid the negative consequences like injuries, deaths ,social and economic loss. If this prediction is done accurately many lives could be saved, which can be done primarily by efficient police patrolling. This paper surveys various prediction methodologies adopted by each researcher in crime prediction using machine learning techniques, also discusses the advantages and disadvantages, various crime prediction methods, put forth the new insights to improve the efficiency .