Two phase ensemble classifier for smartphone based human activity recognition independent of hardware configuration and usage behaviour

Human activity recognition is an important technology in pervasive computing as it provides valuable information for smart healthcare and assisted living applications. Use of smartphones for activity recognition poses new challenges due to variation in hardware configuration and usage behaviour like how the smartphone is kept. Only a few recent works address one or more of these challenges. Consequently, in this paper we present a two phase activity recognition framework for identifying both static and dynamic activities addressing above mentioned challenges using smart handhelds. The framework through feature selection and ensemble classifier, address the variance due to different hardware configuration and usage behaviour. The two-phase framework is implemented and tested on real dataset collected from ten users with six different device configurations. Data is collected from accelerometer only as this sensor is available in any kind of smart handheld devices. In the first phase, the best training set is identified that is fed to the ensemble as input. In the next phase, the classifier based ensemble gives the final output through majority voting. It is observed that, with our proposed two phase classification, the accuracy level of 98% can be achieved for activity recognition while maintaining energy efficiency as only time domain features are considered.

[1]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[2]  Duc A. Tran,et al.  The 11th International Conference on Mobile Systems and Pervasive Computing (MobiSPC-2014) A Study on Human Activity Recognition Using Accelerometer Data from Smartphones , 2014 .

[3]  Miguel A. Labrador,et al.  Centinela: A human activity recognition system based on acceleration and vital sign data , 2012, Pervasive Mob. Comput..

[4]  Lin Sun,et al.  Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations , 2010, UIC.

[5]  Ana M. Bernardos,et al.  Activity logging using lightweight classification techniques in mobile devices , 2012, Personal and Ubiquitous Computing.

[6]  Davide Anguita,et al.  Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine , 2012, IWAAL.

[7]  Duc Ngoc Tran,et al.  Human Activities Recognition in Android Smartphone Using Support Vector Machine , 2016, 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS).

[8]  S. J. Redmond,et al.  Sensors-Based Wearable Systems for Monitoring of Human Movement and Falls , 2012, IEEE Sensors Journal.

[9]  Wanmin Wu,et al.  Classification Accuracies of Physical Activities Using Smartphone Motion Sensors , 2012, Journal of medical Internet research.

[10]  James M. Keller,et al.  Day or Night Activity Recognition From Video Using Fuzzy Clustering Techniques , 2014, IEEE Transactions on Fuzzy Systems.

[11]  Richard Weber,et al.  A wrapper method for feature selection using Support Vector Machines , 2009, Inf. Sci..

[12]  Paul J. M. Havinga,et al.  Towards Physical Activity Recognition Using Smartphone Sensors , 2013, 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing.

[13]  Sian Lun Lau,et al.  Supporting patient monitoring using activity recognition with a smartphone , 2010, 2010 7th International Symposium on Wireless Communication Systems.

[14]  Doruk Coskun,et al.  Phone position/placement detection using accelerometer: Impact on activity recognition , 2015, 2015 IEEE Tenth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP).

[15]  Subir Biswas,et al.  Body posture identification using hidden Markov model with a wearable sensor network , 2008, BODYNETS.

[16]  Bo Ding,et al.  Unsupervised Feature Learning for Human Activity Recognition Using Smartphone Sensors , 2014, MIKE.

[17]  Deborah Estrin,et al.  Using mobile phones to determine transportation modes , 2010, TOSN.

[18]  Maxim A. Batalin,et al.  MEDIC: Medical embedded device for individualized care , 2008, Artif. Intell. Medicine.

[19]  Amparo Alonso-Betanzos,et al.  Filter Methods for Feature Selection - A Comparative Study , 2007, IDEAL.

[20]  Rong Yang,et al.  PACP: A Position-Independent Activity Recognition Method Using Smartphone Sensors , 2016, Inf..

[21]  Ye Li,et al.  Identifying typical physical activity on smartphone with varying positions and orientations , 2015, Biomedical engineering online.

[22]  Weisong Shi,et al.  Chameleon: personalised and adaptive fall detection of elderly people in home-based environments , 2016, Int. J. Sens. Networks.

[23]  S. Dinakaran,et al.  Role of Attribute Selection in Classification Algorithms , 2013 .

[24]  Henk J Stam,et al.  A prospective study on physical activity levels after spinal cord injury during inpatient rehabilitation and the year after discharge. , 2008, Archives of physical medicine and rehabilitation.

[25]  Subir Biswas,et al.  Remote monitoring of soldier safety through body posture identification using wearable sensor networks , 2008, SPIE Defense + Commercial Sensing.

[26]  Huiru Zheng,et al.  Activity Monitoring Using a Smart Phone's Accelerometer with Hierarchical Classification , 2010, 2010 Sixth International Conference on Intelligent Environments.

[27]  Daniela M. Witten,et al.  An Introduction to Statistical Learning: with Applications in R , 2013 .

[28]  Claudio Bettini,et al.  COSAR: hybrid reasoning for context-aware activity recognition , 2011, Personal and Ubiquitous Computing.

[29]  Alexander Horsch,et al.  Separating Movement and Gravity Components in an Acceleration Signal and Implications for the Assessment of Human Daily Physical Activity , 2013, PloS one.

[30]  Hanghang Tong,et al.  Activity recognition with smartphone sensors , 2014 .

[31]  Ron Cottam,et al.  Hierarchy and the Nature of Information , 2016, Inf..

[32]  Lei Wang,et al.  Analysis of filtering methods for 3D acceleration signals in body sensor network , 2011, International Symposium on Bioelectronics and Bioinformations 2011.

[33]  Gheorghe Sebestyen,et al.  Human activity recognition and monitoring for elderly people , 2016, 2016 IEEE 12th International Conference on Intelligent Computer Communication and Processing (ICCP).

[34]  Amitava Mukherjee,et al.  Hidden Markov model a tool for recognition of human contexts using sensors of smart mobile phone , 2017 .

[35]  Basel Kikhia,et al.  Optimal Placement of Accelerometers for the Detection of Everyday Activities , 2013, Sensors.

[36]  Jianzhong Zhang,et al.  An Ensemble Approach for Activity Recognition with Accelerometer in Mobile-Phone , 2014, 2014 IEEE 17th International Conference on Computational Science and Engineering.

[37]  Mikolaj Baszun,et al.  Remote patient monitoring system and a medical social network , 2010, Int. J. Soc. Humanist. Comput..

[38]  John Nelson,et al.  Activity recognition with smartphone support. , 2014, Medical engineering & physics.

[39]  Hui Wang,et al.  POSTECH's U-Health Smart Home for elderly monitoring and support , 2010, 2010 IEEE International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM).

[40]  Fatos Xhafa,et al.  Smart care spaces: pervasive sensing technologies for at-home care , 2014, Int. J. Ad Hoc Ubiquitous Comput..

[41]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[42]  Bernt Schiele,et al.  Multi-graph Based Semi-supervised Learning for Activity Recognition , 2009, 2009 International Symposium on Wearable Computers.

[43]  Shin-Dug Kim,et al.  Subject-independent human activity recognition using Smartphone accelerometer with cloud support , 2015, Int. J. Ad Hoc Ubiquitous Comput..

[44]  Changhai Wang,et al.  Position-independent activity recognition model for smartphone based on frequency domain algorithm , 2013, Proceedings of 2013 3rd International Conference on Computer Science and Network Technology.

[45]  J. K. Mandal,et al.  Activity recognition system using inbuilt sensors of smart mobile phone and minimizing feature vectors , 2015, Microsystem Technologies.

[46]  Diane J. Cook,et al.  Ambient and smartphone sensor assisted ADL recognition in multi-inhabitant smart environments , 2016, J. Ambient Intell. Humaniz. Comput..