Theses, Dissertations & Reports
Permanent URI for this communityhttp://dspace.iiuc.ac.bd/handle/88203/66
Browse
Item Unsafe Driving Behavior Detection By Using CNN Deep Learning Method.(International Islamic University Chittagong, 2024-06) Adnan, ShihabThe complex nature of human behaviour and the numerous factors contributing to distractions on the road, particularly in terms of the limited ability to provide precise and timely early warnings, are addressed in this paper through the introduction of a novel method. The proposed method aims to enhance the detection of distracted driver behaviour using modified CNN transfer learning. By employing transfer learning within the Convolutional Neural Networks framework, the method seeks to tackle the intricate challenges associated with identifying distracted driving behaviours. The experimental results demonstrate an overall accuracy of approximately 99%, with the highest achieved accuracy reaching 99.46% on a publicly available dataset. This highlights the effectiveness of the proposed approach in significantly improving the precision of distracted driver behaviour detection.