Limits...
User Activity Recognition in Smart Homes Using Pattern Clustering Applied to Temporal ANN Algorithm.

Bourobou ST, Yoo Y - Sensors (Basel) (2015)

Bottom Line: In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen's temporal relations.The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms.Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical and Computer Engineering, Pusan National University, Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan 609-735, Korea. thomaserge@yahoo.fr.

ABSTRACT
This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things) based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen's temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home.

No MeSH data available.


User activity recognition in smart home [1].
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4481973&req=5

sensors-15-11953-f001: User activity recognition in smart home [1].

Mentions: Users’ daily activity generate patterns that play an important role in the smart home environment. These patterns are used to favor the recognition of user activity that is useful to improve the smart home applications in terms of efficiency and management energy, healthcare and security as shown in Figure 1. Indeed, the user activities inside the smart home environment have to be monitored and recorded in order to facilitate their control from the remote. Thus, user activity recognition gives the location and time of an activity. According to Figure 1, the abnormal activities in the user behavior can be revealed by constructing the normal behavioral patterns. So, Figure 1 describes the user monitoring in the smart home environment by using object sensors whose collected information is given to the machine learning algorithm as input. In addition, this information is processed by the system to detect anomalies in the user behavior. Therefore, the user can be assisted remotely after receiving an alert message if any unwanted behavior is revealed. Thus, one of the key points of this monitoring system is the ability to provide a response by recognizing the normal user behavior. Furthermore, the following Figure 1 describes the user monitoring in the smart home environment.


User Activity Recognition in Smart Homes Using Pattern Clustering Applied to Temporal ANN Algorithm.

Bourobou ST, Yoo Y - Sensors (Basel) (2015)

User activity recognition in smart home [1].
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4481973&req=5

sensors-15-11953-f001: User activity recognition in smart home [1].
Mentions: Users’ daily activity generate patterns that play an important role in the smart home environment. These patterns are used to favor the recognition of user activity that is useful to improve the smart home applications in terms of efficiency and management energy, healthcare and security as shown in Figure 1. Indeed, the user activities inside the smart home environment have to be monitored and recorded in order to facilitate their control from the remote. Thus, user activity recognition gives the location and time of an activity. According to Figure 1, the abnormal activities in the user behavior can be revealed by constructing the normal behavioral patterns. So, Figure 1 describes the user monitoring in the smart home environment by using object sensors whose collected information is given to the machine learning algorithm as input. In addition, this information is processed by the system to detect anomalies in the user behavior. Therefore, the user can be assisted remotely after receiving an alert message if any unwanted behavior is revealed. Thus, one of the key points of this monitoring system is the ability to provide a response by recognizing the normal user behavior. Furthermore, the following Figure 1 describes the user monitoring in the smart home environment.

Bottom Line: In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen's temporal relations.The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms.Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical and Computer Engineering, Pusan National University, Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan 609-735, Korea. thomaserge@yahoo.fr.

ABSTRACT
This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things) based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen's temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home.

No MeSH data available.