“…However, the list of objects used for different activities may not be always extracted from web and mapping them to the actual deployed sensors is also complicated. Dimitrov et al [4] propose another unsupervised activity recognition approach that utilizes background domain knowledge about user activities and environment such as which objects are used for an activity. Unfortunately, such background knowledge may not be available.…”
Section: Related Workmentioning
confidence: 99%
“…Either the resident has to keep record of all the activities which is not convenient or we need to use cameras and label each activity manually which may not be practical. There are some existing unsupervised activity recognition algorithms that do not need ground truth ( [13], [16], [4]). They either require to mine activity models from web definitions or depend on domain knowledge about activities and the environment (e.g., which objects are used during an activity).…”
We present AALO: a novel Activity recognition system for single person smart homes using Active Learning in the presence of Overlapped activities. AALO applies data mining techniques to cluster in-home sensor firings so that each cluster represents instances of the same activity. Users only need to label each cluster as an activity as opposed to labeling all instances of all activities. Once the clusters are associated to their corresponding activities, our system can recognize future activities. To improve the activity recognition accuracy, our system preprocesses raw sensor data by identifying overlapping activities. The evaluation of activity recognition performance on a 26-day dataset shows that compared to Naive Bayesian (NB), Hidden Markov Model (HMM), and Hidden Semi Markov Model (HSMM) based activity recognition systems, our average time slice error (24.15%) is much lower than NB (53.04%), and similar to HMM (29.97%) and HSMM (26.29%). Thus, our active learning based approach performs as good as the state of the art supervised techniques (HMM and HSMM).
“…However, the list of objects used for different activities may not be always extracted from web and mapping them to the actual deployed sensors is also complicated. Dimitrov et al [4] propose another unsupervised activity recognition approach that utilizes background domain knowledge about user activities and environment such as which objects are used for an activity. Unfortunately, such background knowledge may not be available.…”
Section: Related Workmentioning
confidence: 99%
“…Either the resident has to keep record of all the activities which is not convenient or we need to use cameras and label each activity manually which may not be practical. There are some existing unsupervised activity recognition algorithms that do not need ground truth ( [13], [16], [4]). They either require to mine activity models from web definitions or depend on domain knowledge about activities and the environment (e.g., which objects are used during an activity).…”
We present AALO: a novel Activity recognition system for single person smart homes using Active Learning in the presence of Overlapped activities. AALO applies data mining techniques to cluster in-home sensor firings so that each cluster represents instances of the same activity. Users only need to label each cluster as an activity as opposed to labeling all instances of all activities. Once the clusters are associated to their corresponding activities, our system can recognize future activities. To improve the activity recognition accuracy, our system preprocesses raw sensor data by identifying overlapping activities. The evaluation of activity recognition performance on a 26-day dataset shows that compared to Naive Bayesian (NB), Hidden Markov Model (HMM), and Hidden Semi Markov Model (HSMM) based activity recognition systems, our average time slice error (24.15%) is much lower than NB (53.04%), and similar to HMM (29.97%) and HSMM (26.29%). Thus, our active learning based approach performs as good as the state of the art supervised techniques (HMM and HSMM).
“…Research in accurate detection and summarization of these daily activities has progressed significantly over the last decade [19,34,23,35,9] which enables long-term monitoring of a resident's in-home activities, learning normal behavior, and detecting deviation from normal behavior i.e., anomalies. Reliable anomaly detection in daily in-home activities is the most important component of many home health care applications such as assessing behavioral rhythms [32,10], and monitoring cognitive decline [14,24].…”
Advances in wireless sensor networks have enabled the monitoring of daily activities of elderly people. The goal of these monitoring applications is to learn normal behavior in terms of daily activities and look for any deviation, i.e., anomalies, so that alerts can be sent to relatives or caregivers. However, human behavior is very complex, and many existing anomaly detection systems are too simplistic which cause many false alarms, resulting in unreliable systems. We present Holmes, a comprehensive anomaly detection system for daily in-home activities. Holmes accurately learns a resident's normal behavior by considering variability in daily activities based not only on a per day basis, but also considering specific days of the week, different time periods such as per week and per month, and collective, temporal, and correlation based features. This approach of learning complicated normal behaviors reduces false alarms. Also, based on resident and expert feedback, Holmes learns semantic rules that explain specific variations of activities in specific scenarios to further reduce false alarms. We evaluate Holmes using data collected from our own deployed system, public data sets, and data collected by a senior safety system provider company from an elderly resident's home. Our evaluation shows that compared to state of the art systems, Holmes reduces false positives and false negatives by at least 46% and 27%, respectively.
“…The difficulty of the unsupervised method is the problem of data labeling. Researchers have now proposed some unsupervised methods to solve the problem of data annotation, such as frequent sensor mining methods [28], and frequent periodic pattern mining methods [29], activity modeling based on low-dimensional feature space [30], probabilistic model [31,32], and retrieval of activity definition, using Web mining [33].…”
With the development of population aging, the recognition of elderly activity in smart homes has received increasing attention. In recent years, single-resident activity recognition based on smart homes has made great progress. However, few researchers have focused on multi-resident activity recognition. In this paper, we propose a method to recognize two-resident activities based on time clustering. First, to use a de-noising method to extract the feature of the dataset. Second, to cluster the dataset based on the begin time and end time. Finally, to complete activity recognition using a similarity matching method. To test the performance of the method, we used two two-resident datasets provided by Center for Advanced Studies in Adaptive Systems (CASAS). We evaluated our method by comparing it with some common classifiers. The results show that our method has certain improvements in the accuracy, recall, precision, and F-Measure. At the end of the paper, we explain the parameter selection and summarize our method.
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.