Elders who live alone are vulnerable population at risk. Despite telemedicine and clinical home monitoring are effective to provide health care, accidents at home are still one of the major risk factors. Important efforts have been done in home monitoring systems to detect potential scenarios of risk. However, the complex technological interaction has a negative impact on the user and intrusive or wearable devices are not recommended. Sensorized houses solve this problem, recording the behaviour of elders at home without a direct interaction. However, the detection of health-risk scenarios is a complex issue, since the large amount temporal data registered by sensors must be correctly interpreted. In such a case, Artificial Intelligence techniques have been used to automatically identify abnormal behaviors. Due to the number false positives of these techniques, the human intervention is still necessary. We consider that a semiautomatic approach, abstracting and visualizing the recorded temporal information, is a more suitable approach. In this work, we propose a specialised visualization model that helps system supervisors to identify through visual mining techniques most common scenarios of risk. We illustrate our proposal in a specific home monitoring system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.