The study aims to classify the addicts and non addicts based on behavioral characteristics of an individual. The target age group is 18yrs – 21yrs. Previously the screening process of addicts includes questionnaire-based tests and lab tests. The questions asked in the questionnaires are quite straight forward i.e., if an individual is smoking, or how many times he/she smokes, how many drinks(alcohol) he/she takes during a day or a week. Our research focuses on the collection of indigenous data of addicts. We follow different family structure and cultural values as compared to the west, henceforth, there is a need to highlight those issues and gain awareness about the type of addiction in which our youth is caught up. We aim to design scenarios which require certain feedback from the individuals. At first, they will be tested on the addicts and later on the random population. Our research may require expertise from the psychology domain for designing the tools/instruments for data collection and understanding the collected data. Secondly our research may require some expertise in embedded systems, and brain signal processing. Our data collection would be extensive which requires the detailed examination of the behavioral characteristics of addicts and non addicts therefore we need to use the latest trends and technology in order to assess addicted behaviors.
1- Literature Review and Theoretical Framework:
Description- Completion of a literature review and establishment of the theoretical framework that informs the modeling of behavioral
2- Data Collection and Analysis:
Description: Initiation of data collection processes, including surveys, interviews, and observations, to gather insights into the behavioral
patterns of drug-addicted students.
3- Model Development:
Description: Development of a comprehensive model that incorporates psychological and sociological factors influencing the behavior of
4- Validation and Testing:
Description: Validation of the developed model through testing and analysis of its effectiveness in capturing and predicting behavioral