DCR-OL is a Distributed Collaborative Reasoning multi-agent model with an Online Learning thataims to identify human activities in smart homes from distributed, heterogeneous and dynamicsensor data. In this model, dis...DCR-OL is a Distributed Collaborative Reasoning multi-agent model with an Online Learning thataims to identify human activities in smart homes from distributed, heterogeneous and dynamicsensor data. In this model, distributed learning agents with diverse classifiers, detect sensorstream 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 thelocal 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-maxfreq,are proposed. We experimentally test these strategies by performing an evaluation studyon the Aruba dataset. The obtained results indicate an enhancement in terms of accuracy and Fmeasuremetrics compared to the offline strategies max-trust and max-freq and also to the onlineexisting one max-wPerf .展开更多
文摘DCR-OL is a Distributed Collaborative Reasoning multi-agent model with an Online Learning thataims to identify human activities in smart homes from distributed, heterogeneous and dynamicsensor data. In this model, distributed learning agents with diverse classifiers, detect sensorstream 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 thelocal 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-maxfreq,are proposed. We experimentally test these strategies by performing an evaluation studyon the Aruba dataset. The obtained results indicate an enhancement in terms of accuracy and Fmeasuremetrics compared to the offline strategies max-trust and max-freq and also to the onlineexisting one max-wPerf .
