Real-time Recognition of Interleaved Activities Based on Ensemble Classifier of Long Short-Term Memory with Fuzzy Temporal Windows

In this paper, we present a methodology for Real-Time Activity Recognition of Interleaved Activities based on Fuzzy Logic and Recurrent Neural Networks. Firstly, we propose a representation of binary-sensor activations based on multiple Fuzzy Temporal Windows. Secondly, an ensemble of activity-based classifiers for balanced training and selection of relevant sensors is proposed. Each classifier is configured as a Long Short-Term Memory with self-reliant detection of interleaved activities. The proposed approach was evaluated using well-known interleaved binary-sensor datasets comprised of activities of daily living.

[1]  Alexey Stakhov,et al.  The Golden Section and Modern Harmony Mathematics , 1998 .

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

[3]  Chris D. Nugent,et al.  Fuzzy Fog Computing: A Linguistic Approach for Knowledge Inference in Wearable Devices , 2017, UCAmI.

[4]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

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

[6]  Timo Sztyler,et al.  Unsupervised recognition of interleaved activities of daily living through ontological and probabilistic reasoning , 2016, UbiComp.

[7]  Gwenn Englebienne,et al.  An activity monitoring system for elderly care using generative and discriminative models , 2010, Personal and Ubiquitous Computing.

[8]  Franco Cicirelli,et al.  On the Design of Smart Homes: A Framework for Activity Recognition in Home Environment , 2016, Journal of Medical Systems.

[9]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[10]  Chris D. Nugent,et al.  Real-time fuzzy linguistic analysis of anomalies from medical monitoring devices on data streams , 2016, PervasiveHealth.

[11]  Huiru Zheng,et al.  A Multi Agent Approach to Facilitate the Identification of Interleaved Activities , 2018, DH.

[12]  Diane J Cook,et al.  Tracking Activities in Complex Settings Using Smart Environment Technologies. , 2009, International journal of biosciences, psychiatry, and technology.

[13]  Chris D. Nugent,et al.  Ensemble classifier of long short-term memory with fuzzy temporal windows on binary sensors for activity recognition , 2018, Expert Syst. Appl..

[14]  Xiaoqing Feng,et al.  Real time activity recognition on streaming sensor data for smart environments , 2016, 2016 International Conference on Progress in Informatics and Computing (PIC).

[15]  Abdenour Bouzouane,et al.  Assistance in smart homes: Combining passive RFID localization and load signatures of electrical devices , 2014, 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[16]  Josef Hallberg,et al.  A new approach based on temporal sub-windows for online sensor-based activity recognition , 2018 .

[17]  Araceli Sanchis,et al.  Activity Recognition Using Hybrid Generative/Discriminative Models on Home Environments Using Binary Sensors , 2013, Sensors.

[18]  Diane J. Cook,et al.  Activity recognition on streaming sensor data , 2014, Pervasive Mob. Comput..

[19]  Jonathan H. Chan,et al.  Evolution of Smart Homes for the Elderly , 2017, WWW.

[20]  Abdenour Bouzouane,et al.  Human activity recognition in smart homes: Combining passive RFID and load signatures of electrical devices , 2014, 2014 IEEE Symposium on Intelligent Agents (IA).

[21]  Héctor Pomares,et al.  Window Size Impact in Human Activity Recognition , 2014, Sensors.

[22]  Yunchuan Sun,et al.  ERAR: An Event-Driven Approach for Real-Time Activity Recognition , 2015, 2015 International Conference on Identification, Information, and Knowledge in the Internet of Things (IIKI).

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