DCR-OL is a Distributed Collaborative Reasoning multi-agent model with an Online Learning that aims to identify human activities in smart homes from distributed, heterogeneous and dynamic sensor data. In this model, distributed learning agents with diverse classifiers, detect sensor stream data, make local predictions, communicate and collaborate to identify current activities. Then, they learn from their collaborations to improve their own performance in activity recognition. Conflict resolution strategies are applied to generate one final predicted activity when the local predicted activity of an agent is different from received predicted activities of other agents. In this paper, two conflict resolution strategies using online learning, w-max-trust and w-max-freq, are proposed. We experimentally test these strategies by performing an evaluation study on the Aruba dataset. The obtained results indicate an enhancement in terms of accuracy and F-measure metrics compared to the offline strategies max-trust and max-freq and also to the online existing one max-wPerf .