Tesis Telecomunicaciones

Permanent URI for this collectionhttp://repositorio.uta.edu.ec/handle/123456789/34848

Browse

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Sistema automático de detección de extorsiones mediante el análisis de señales de la voz
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2024-08) Tinta Capuz, Carlos Jair; Castro Martin, Ana Pamela
    This project presents the implementation of an automatic system to detect extortion through the analysis of voice signals. This system has been designed to identify extortive language, being an essential tool for security and crime prevention. The architecture of the system is divided into three main layers. In the first, speech recognition and feature extraction is done internally with specific libraries. Extortionist and non-extortionist phrases are classified to train the detection model and ensure accuracy in distinguishing both types of language. A set of sentences classified as extortionate and non-extortionate is incorporated for training. This dataset is used to train the detection model, ensuring that the system can distinguish between the two types of language. The intermediate layer uses advanced natural language processing (NLP) and machine learning techniques with the RandomForestClassifier model, selected for its reliability and efficiency. This system processes and classifies sentences according to their content, ensuring accurate and robust detection of extortionate language. The presentation layer includes a graphical user interface (GUI) developed with Tkinter. This interface allows users to interact with the system intuitively by activating the microphone to record their voice and receive an immediate assessment of the presence of extortionate language. The GUI improves the accessibility and usability of the system. This prototype represents a significant advance in extortion detection with 92% accuracy according to system tests, providing an efficient solution. It is anticipated that this tool will meet the growing demand for intelligent security systems, helping organizations stay ahead in the fight against crime.