Comparative study of machine learning algorithms for activity recognition with data sequence in home-like environment

Activity recognition is a key problem in multi-sensor systems. With data collected from different sensors, a multi-sensor system identifies activities performed by the inhabitants. Since an activity always lasts a certain duration, it is beneficial to use data sequence for the desired recognition. In this work, we experiment several machine learning techniques, including Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Meta-Layer Network for solving this problem. We observe that (1) compare with “single-frame” activity recognition, data sequence based classification gives better performance; and (2) directly using data sequence information with a simple “mete layer” network model yields a better performance than memory based deep learning approaches.

[1]  Bart Selman,et al.  Unstructured human activity detection from RGBD images , 2011, 2012 IEEE International Conference on Robotics and Automation.

[2]  Michael C. Mozer,et al.  The Neural Network House: An Environment that Adapts to its Inhabitants , 1998 .

[3]  Norbert Wehn,et al.  Monitoring household activities and user location with a cheap, unobtrusive thermal sensor array , 2014, UbiComp.

[4]  Diane J. Cook,et al.  How smart are our environments? An updated look at the state of the art , 2007, Pervasive Mob. Comput..

[5]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[6]  Yiannis Kompatsiaris,et al.  Activity detection and recognition of daily living events , 2013, MIIRH '13.

[7]  Hong Sun,et al.  Promises and Challenges of Ambient Assisted Living Systems , 2009, 2009 Sixth International Conference on Information Technology: New Generations.

[8]  Deva Ramanan,et al.  Detecting activities of daily living in first-person camera views , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Thomas B. Moeslund,et al.  Distributed Computing and Monitoring Technologies for Older Patients , 2016, SpringerBriefs in Computer Science.

[10]  Alanson P. Sample,et al.  IDSense: A Human Object Interaction Detection System Based on Passive UHF RFID , 2015, CHI.

[11]  Liming Chen,et al.  Dynamic sensor data segmentation for real-time knowledge-driven activity recognition , 2014, Pervasive Mob. Comput..

[12]  Gwenn Englebienne,et al.  Accurate activity recognition in a home setting , 2008, UbiComp.

[13]  David Wetherall,et al.  Recognizing daily activities with RFID-based sensors , 2009, UbiComp.

[14]  Rajeev Srivastava,et al.  Multiview human activity recognition system based on spatiotemporal template for video surveillance system , 2015, J. Electronic Imaging.

[15]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[16]  Lasitha Piyathilaka,et al.  Gaussian mixture based HMM for human daily activity recognition using 3D skeleton features , 2013, 2013 IEEE 8th Conference on Industrial Electronics and Applications (ICIEA).

[17]  Guillermo Ricardo Simari,et al.  The Added Value of Argumentation , 2013 .

[18]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[19]  Matthai Philipose,et al.  Egocentric recognition of handled objects: Benchmark and analysis , 2009, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[20]  Chris D. Nugent,et al.  Dynamic similarity-based activity detection and recognition within smart homes , 2012, Int. J. Pervasive Comput. Commun..

[21]  Luis González Abril,et al.  Mobile activity recognition and fall detection system for elderly people using Ameva algorithm , 2017, Pervasive Mob. Comput..

[22]  Ahmed H. Tewfik,et al.  A feature combination approach for the detection of early morning bathroom activities with wireless sensors , 2007, HealthNet '07.

[23]  Daniel P. Siewiorek,et al.  Activity recognition and monitoring using multiple sensors on different body positions , 2006, International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06).

[24]  Kent Larson,et al.  Activity Recognition in the Home Using Simple and Ubiquitous Sensors , 2004, Pervasive.

[25]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[26]  Ahmad Lotfi,et al.  Smart homes for the elderly dementia sufferers: identification and prediction of abnormal behaviour , 2012, J. Ambient Intell. Humaniz. Comput..

[27]  Araceli Sanchis,et al.  Sensor-based Bayesian detection of anomalous living patterns in a home setting , 2014, Personal and Ubiquitous Computing.

[28]  Chunyan Miao,et al.  A first step towards explained activity recognition with computational abstract argumentation , 2016, 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[29]  Tamer Nadeem,et al.  Wearable Sensing Framework for Human Activity Monitoring , 2015, WearSys '15.