srjecsSRJECSSRJECS2788-9408https://doi.org/10.47310/srjecs.2026.v06i01.003Integrated Computer Vision and Adaptive Machine Learning for Real-Time Fall Detection and Personalized Elderly CareM. HamsaAhmedM. ShokhanAl-BarzinjiDepartment of Computer Networks Systems, College of Computer Science and Information Technology, University of Anbar, Ramadi, IraqDepartment of Computer Science, College of Computer Science and Information Technology, University of Anbar, Ramadi, IraqThe aging global population necessitates innovative solutions to address the increasing demand for elderly care. This research proposes the development of an intelligent robot designed to assist in elderly care by integrating Computer Vision (CV) and Machine Learning (ML) technologies. The robot aims to monitor daily activities, detect falls and provide companionship. The proposed system utilizes advanced CV algorithms to analyze real-time video feeds, enabling the robot to recognize and interpret human activities. Our primary contribution is the integration of real-time multi-modal data fusion with an adaptive learning loop, which continually refines its fall prediction and activity recognition models. ML models are employed to predict potential health risks and suggest preventive measures. This continuous learning allows the robot to adapt to the specific needs of each individual, offering personalized, proactive care. Preliminary results indicate the robot can accurately detect falls with 95% accuracy and demonstrates effective activity recognition, facilitating timely interventions. These findings suggest that the integration of computer vision and machine learning in robotic systems holds significant promise for improving elderly care services.