Multi-resident type recognition based on ambient sensors activity

Abstract With the development of sensing and intelligent technologies, ambient sensor-based activity recognition is attracting more attention for a wide range of applications. One of the technology challenges is the recognition of the activity performer in a multi-occupancy scenario. This paper proposes a multi-label Markov Logic Network classification method to recognize resident types based on their activity habits and preference. The activity preference mainly includes time sequence preference, duration and period preference, and the location preference of a basic entity or action events. According to the resident type (gender, age bracket, job), the further reasoning work is the family role (mother, father, daughter and so on.) recognition. We have designed simple and combined preferences to test and evaluate our proposed method. Initial experiments have produced good performance in many cases proving this solution is an efficient and feasible method for resident type recognition which could be applied to real-world scenarios.

[1]  Li-Chen Fu,et al.  Nonparametric Activity Recognition System in Smart Homes Based on Heterogeneous Sensor Data , 2019, IEEE Transactions on Automation Science and Engineering.

[2]  Diane J. Cook,et al.  Human Activity Recognition and Pattern Discovery , 2010, IEEE Pervasive Computing.

[3]  Abdelhamid Bouchachia,et al.  Multi-resident Activity Recognition Using Incremental Decision Trees , 2014, ICAIS.

[4]  Jaeryoung Lee,et al.  Identification of the User's Habits based on Activity Information , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[5]  Qing Zhang,et al.  Multi-Resident Activity Monitoring in Smart Homes: A Case Study , 2018, 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops).

[6]  Cem Ersoy,et al.  Multi-resident activity tracking and recognition in smart environments , 2017, Journal of Ambient Intelligence and Humanized Computing.

[7]  Pedro M. Domingos,et al.  Discriminative Training of Markov Logic Networks , 2005, AAAI.

[8]  Chris D. Nugent,et al.  Using duration to learn activities of daily living in a smart home environment , 2010, 2010 4th International Conference on Pervasive Computing Technologies for Healthcare.

[9]  Brendon J. Woodford,et al.  Dynamic Real-Time Segmentation and Recognition of Activities Using a Multi-feature Windowing Approach , 2017, PAKDD.

[10]  Diane J. Cook,et al.  Recognizing independent and joint activities among multiple residents in smart environments , 2010, J. Ambient Intell. Humaniz. Comput..

[11]  Matthew Richardson,et al.  Markov Logic , 2008, Probabilistic Inductive Logic Programming.

[12]  Pedro M. Domingos,et al.  Efficient Weight Learning for Markov Logic Networks , 2007, PKDD.

[13]  Tao Zhu,et al.  A hybrid approach to inferring the Internet of Things for complex activity recognition , 2019, EURASIP Journal on Wireless Communications and Networking.

[14]  Mohammed Feham,et al.  Modeling interaction in multi-resident activities , 2017, Neurocomputing.

[15]  Bernhard Pfahringer,et al.  Conjunctive Normal Form , 2010, Encyclopedia of Machine Learning.

[16]  Susan Elias,et al.  Hierarchical activity recognition for dementia care using Markov Logic Network , 2014, Personal and Ubiquitous Computing.

[17]  Minh-Son Nguyen,et al.  Resident Identification in Smart Home by Voice Biometrics , 2018, FDSE.

[18]  Susanne Biundo-Stephan,et al.  Approximate Online Inference for Dynamic Markov Logic Networks , 2011, 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence.

[19]  Thinagaran Perumal,et al.  Multi label classification on multi resident in smart home using classifier chains , 2018 .

[20]  Chunyan Miao,et al.  Multi-Resident Activity Recognition with Unseen Classes in Smart Homes , 2018, 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI).

[21]  Özlem Durmaz Incel,et al.  ARAS human activity datasets in multiple homes with multiple residents , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

[22]  Valentin Goranko,et al.  Logic in Computer Science: Modelling and Reasoning About Systems , 2007, J. Log. Lang. Inf..

[23]  Yi-Ting Chiang,et al.  Interaction models for multiple-resident activity recognition in a smart home , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[24]  Abdenour Bouzouane,et al.  Recognizing multi-resident activities in non-intrusive sensor-based smart homes by formal concept analysis , 2018, Neurocomputing.

[25]  Thinagaran Perumal,et al.  Modeling activity recognition of multi resident using label combination of multi label classification in smart home , 2017 .