Integration of AI, ML, and DL Technologies in Project Management for Data Security-Based Face Recognition Attendance Systems

Abstrak

With deep gratitude, this book is compiled as an effort to explore and delve deeper into the implementation of facial recognition technology in employee attendance management. In an era where technology increasingly plays a key role in operational efficiency and information security, a profound understanding of facial recognition-based attendance systems becomes increasingly important. This book aims not only to identify the roles of Machine Learning (ML), Deep Learning (DL), and Artificial Intelligence (AI) technologies in the development of attendance systems but also to highlight the challenges, risk management, and impacts of integrating this technology into human resource management. This book aims to develop and test a model for integrating advanced technology into a facial recognition-based attendance system in vocational high schools (SMK) to improve system security and efficiency.

The method used is quantitative with an experimental approach, which involves systematic experimental design to test models with various parameters, and evaluation techniques. To fulfill the research objectives, prediction and detection of anomalous patterns in attendance data were carried out by referring to facial recognition theory, resource management, and reward and punishment systems along with the integration of various technology models. The novelty of this book lies in the development of intelligent Machine Learning (ML), Deep Learning (DL), and Artificial Intelligence (AI) models to predict teacher absenteeism patterns based on relevant factors, which provide innovative solutions to improve the efficiency and security of the attendance system overall. In addition, integrating advanced technology in attendance project management provides a new contribution to the IT project management literature, especially in the scope of attendance in the educational environment.

The integration of technology used in this book is ML, DL, AI, Liveness detection, and data encryption using the AES algorithm with a focus on security, accuracy, and efficiency of the attendance system. The research sample used was a dataset obtained through a facial recognition-based attendance system for vocational school teachers with a total of 998 samples. This book was conducted in the Google Colab virtual notebook environment with the Python programming language and scikit-learn as supporting libraries. Various techniques such as K- means clustering, ensemble voting, classification, and regression are used in training and testing models to find absenteeism patterns, detect anomalous patterns, and perform prediction tasks.