An evidential fusion approach for activity recognition in ambient intelligence environments

Sebbak, Faouzi; Chibani, Abdelghani; Amirat, Yacine; Mokhtari, A.; Benhammadi, Farid

doi:10.1016/j.robot.2013.05.010

Cited by 15 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recognition rate (number of correctly recognized instances out of all instances in the test set) and F1-score (Eq. 23) are also compared with [21,29,43,54] and [6,37,38,45,48], respectively. We perform the activity level performance analysis through confusion matrices and F1-score.…”

Section: Evaluation and Discussionmentioning

confidence: 99%

“…Therefore, F1-score is applied, which incorporates both precision and recall and thus is more reliable. It can be observed that ARSH-SV has the highest F1-score in datasets, Kyoto7 (91%), Kasteren (91%) and Kasteren 10 (80%) compared to the existing approaches in [6,37,38,45,48]. The results show that in ARSH-SV, the activities are correctly recognized, while incorrect labels are correctly identified through confidence measure that remain useful in reducing the false positives effectively.…”

Section: Residents With a Pet -Datasetsmentioning

confidence: 91%

“…Most of the existing activity recognition approaches focus on the segmentation and recognition of the activities, while a few deal with the uncertainty and noise in the data at sensor level [17,28,45,46]. An evidential fusion approach exploits the combination rule of Dempster Shafer Theory (DST) to support conflict resolution in activity recognition (EFA-AR) by combining the sensed information and commonsense knowledge [45].…”

Section: Related Workmentioning

confidence: 99%

“…An evidential fusion approach exploits the combination rule of Dempster Shafer Theory (DST) to support conflict resolution in activity recognition (EFA-AR) by combining the sensed information and commonsense knowledge [45]. The two data fusion and reasoning approaches DST and Dynamic Bayesian Network are compared and their applicabilities are discussed under activity recognition scenario in [47].…”

Section: Related Workmentioning

confidence: 99%

“…Kasteren ARSH-SV 0.91 AR-SPM(C+LP) [6] 0.81 EFA-AR [45] 0.77 Murphy rule [45] 0.68 Dempster-Shafer rule [45] 0.54 Temporal EDN [48] 0.70 No time EDN [48] 0.45…”

Section: Residents With a Pet -Datasetsmentioning

confidence: 99%

See 4 more Smart Citations

Activity recognition in smart homes with self verification of assignments

2015

View full text Add to dashboard Cite

This is the accepted version of the paper.This version of the publication may differ from the final published version. Permanent repository link AbstractActivity recognition in smart homes provides valuable benefits in the field of health and elderly care by remote monitoring of patients. In health care, capabilities of both performing the correct recognition and reducing the wrong assignments are of high importance. The novelty of the proposed activity recognition approach lies in being able to assign a category to the incoming activity, while measuring the confidence score of the assigned category that reduces the false positives in the assignments. Multiple sensors deployed at different locations of a smart home are used for activity observations. For multi-class activity classification, we propose a binary solution using support vector machines, which simplifies the problem to correct/incorrect assignments. We obtain the confidence score of each assignment by estimating the activity distribution within each class such that the assignments with low confidence are separated for further investigation by a human operator. The proposed approach is evaluated using a comprehensive performance evaluation metrics. Experimental results obtained from nine publicly available smart home datasets demonstrate a better performance of the proposed approach compared to the state of the art.

show abstract

Section: Evaluation and Discussionmentioning

confidence: 99%

Section: Residents With a Pet -Datasetsmentioning

confidence: 91%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Kasteren ARSH-SV 0.91 AR-SPM(C+LP) [6] 0.81 EFA-AR [45] 0.77 Murphy rule [45] 0.68 Dempster-Shafer rule [45] 0.54 Temporal EDN [48] 0.70 No time EDN [48] 0.45…”

Section: Residents With a Pet -Datasetsmentioning

confidence: 99%

See 3 more Smart Citations