CAPHAR: context-aware personalized human activity recognition using associative learning in smart environments

The existing action recognition systems mainly focus on generalized methods to categorize human actions. However, the generalized systems cannot attain the same level of recognition performance for new users mainly due to the high variance in terms of human behavior and the way of performing actions, i.e. activity handling. The use of personalized models based on similarity was introduced to overcome the activity handling problem, but the improvement was found to be limited as the similarity was based on physiognomies rather than the behavior. Moreover, human interaction with contextual information has not been studied extensively in the domain of action recognition. Such interactions can provide an edge for both recognizing high-level activities and improving the personalization effect. In this paper, we propose the context-aware personalized human activity recognition (CAPHAR) framework which computes the class association rules between low-level actions/sensor activations and the contextual information to recognize high-level activities. The personalization in CAPHAR leverages the individual behavior process using a similarity metric to reduce the effect of the activity handling problem. The experimental results on the “daily lifelog” dataset show that CAPHAR can achieve at most 23.73% better accuracy for new users in comparison to the existing classification methods.

[1]  Thomas Plötz,et al.  Ensembles of Deep LSTM Learners for Activity Recognition using Wearables , 2017, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[2]  Wil M. P. van der Aalst,et al.  Woflan 2.0: A Petri-Net-Based Workflow Diagnosis Tool , 2000, ICATPN.

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

[4]  Paolo Fornacciari,et al.  IoT Wearable Sensor and Deep Learning: An Integrated Approach for Personalized Human Activity Recognition in a Smart Home Environment , 2019, IEEE Internet of Things Journal.

[5]  Johanna Völker,et al.  Self-tracking Reloaded: Applying Process Mining to Personalized Health Care from Labeled Sensor Data , 2016, Trans. Petri Nets Other Model. Concurr..

[6]  Juan Miguel García-Gómez,et al.  Process Mining for Individualized Behavior Modeling Using Wireless Tracking in Nursing Homes , 2013, Sensors.

[7]  Bernardo Nugroho Yahya,et al.  Context-based similarity measure on human behavior pattern analysis , 2019, Soft Comput..

[8]  Vaidehi Vijayakumar,et al.  OAFPM: optimized ANFIS using frequent pattern mining for activity recognition , 2019, The Journal of Supercomputing.

[9]  Bernt Schiele,et al.  Weakly Supervised Recognition of Daily Life Activities with Wearable Sensors , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Kai Tang,et al.  Kernel fusion based extreme learning machine for cross-location activity recognition , 2017, Inf. Fusion.

[11]  Diane J. Cook,et al.  Enhancing activity recognition using CPD-based activity segmentation , 2019, Pervasive Mob. Comput..

[12]  Deokjai Choi,et al.  Modeling and discovering human behavior from smartphone sensing life-log data for identification purpose , 2015, Human-centric Computing and Information Sciences.

[13]  Li Liu,et al.  Recognizing Complex Activities by a Probabilistic Interval-Based Model , 2016, AAAI.

[14]  Takuya Maekawa,et al.  Activity recognition with hand-worn magnetic sensors , 2013, Personal and Ubiquitous Computing.

[15]  Ramesh C. Jain,et al.  Human Behavior Analysis from Smartphone Data Streams , 2016, HBU.

[16]  Faicel Chamroukhi,et al.  An Unsupervised Approach for Automatic Activity Recognition Based on Hidden Markov Model Regression , 2013, IEEE Transactions on Automation Science and Engineering.

[17]  Iván Pau,et al.  The Elderly’s Independent Living in Smart Homes: A Characterization of Activities and Sensing Infrastructure Survey to Facilitate Services Development , 2015, Sensors.

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

[19]  Athanasios V. Vasilakos,et al.  GCHAR: An efficient Group-based Context - aware human activity recognition on smartphone , 2017, J. Parallel Distributed Comput..

[20]  Anthony Scime,et al.  Finding "persistent rules": Combining association and classification results , 2009, Expert Syst. Appl..

[21]  Tao Gu,et al.  Object relevance weight pattern mining for activity recognition and segmentation , 2010, Pervasive Mob. Comput..

[22]  Mi Zhang,et al.  MyBehavior: automatic personalized health feedback from user behaviors and preferences using smartphones , 2015, UbiComp.

[23]  Kuan-Rong Lee,et al.  A flexible sequence alignment approach on pattern mining and matching for human activity recognition , 2010, Expert Syst. Appl..

[24]  Wil M. P. van der Aalst,et al.  RapidProM: Mine Your Processes and Not Just Your Data , 2017, ArXiv.

[25]  Steffen Lohmann,et al.  Context-aware Web Engineering: Modeling and Applications , 2005, Rev. d'Intelligence Artif..

[26]  Kai Xing,et al.  A user activity pattern mining system based on human activity recognition and location service , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[27]  Guoqing Chen,et al.  Building an Associative Classifier Based on Fuzzy Association Rules , 2008, Int. J. Comput. Intell. Syst..

[28]  Timo Sztyler,et al.  newNECTAR: Collaborative active learning for knowledge-based probabilistic activity recognition , 2019, Pervasive Mob. Comput..

[29]  Jin-Hyuk Hong,et al.  Toward Personalized Activity Recognition Systems With a Semipopulation Approach , 2016, IEEE Transactions on Human-Machine Systems.

[30]  Young Jae Jang,et al.  Process Mining to Discover Shoppers’ Pathways at a Fashion Retail Store Using a WiFi-Base Indoor Positioning System , 2017, IEEE Transactions on Automation Science and Engineering.

[31]  Bernardo Nugroho Yahya,et al.  Contextual activity based Healthcare Internet of Things, Services, and People (HIoTSP): An architectural framework for healthcare monitoring using wearable sensors , 2018, Comput. Networks.

[32]  Jian Lu,et al.  An unsupervised approach to activity recognition and segmentation based on object-use fingerprints , 2010, Data Knowl. Eng..

[33]  Zhiying Wang,et al.  Activity recognition with weighted frequent patterns mining in smart environments , 2015, Expert Syst. Appl..

[34]  George Loukas,et al.  Location-Enhanced Activity Recognition in Indoor Environments Using Off the Shelf Smart Watch Technology and BLE Beacons , 2017, Sensors.

[35]  Sally I. McClean,et al.  Probabilistic Learning From Incomplete Data for Recognition of Activities of Daily Living in Smart Homes , 2012, IEEE Transactions on Information Technology in Biomedicine.

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

[37]  Hyunsoo Lee,et al.  The Effects of Housing Environments on the Performance of Activity-Recognition Systems Using Wi-Fi Channel State Information: An Exploratory Study , 2019, Sensors.

[38]  Paul Lukowicz,et al.  Collecting complex activity datasets in highly rich networked sensor environments , 2010, 2010 Seventh International Conference on Networked Sensing Systems (INSS).

[39]  Yen-Liang Chen,et al.  Mining associative classification rules with stock trading data - A GA-based method , 2010, Knowl. Based Syst..

[40]  János Abonyi,et al.  Compact fuzzy association rule-based classifier , 2008, Expert Syst. Appl..

[41]  Boudewijn F. van Dongen,et al.  On the Role of Fitness, Precision, Generalization and Simplicity in Process Discovery , 2012, OTM Conferences.

[42]  Abdulsalam Yassine,et al.  Mining Human Activity Patterns From Smart Home Big Data for Health Care Applications , 2017, IEEE Access.

[43]  Bernardo Nugroho Yahya,et al.  Hierarchical classification method based on selective learning of slacked hierarchy for activity recognition systems , 2017, Expert Syst. Appl..

[44]  Chengqi Zhang,et al.  Genetic algorithm-based strategy for identifying association rules without specifying actual minimum support , 2009, Expert Syst. Appl..

[45]  Zhisong Pan,et al.  Stock Market Prediction on High-Frequency Data Using Generative Adversarial Nets , 2018 .

[46]  Michal Kosinski,et al.  Mining Facebook Data for Predictive Personality Modeling , 2013, Proceedings of the International AAAI Conference on Web and Social Media.

[47]  Yufei Chen,et al.  Performance Analysis of Multi-Motion Sensor Behavior for Active Smartphone Authentication , 2018, IEEE Transactions on Information Forensics and Security.

[48]  Martin Atzmueller,et al.  Explicative human activity recognition using adaptive association rule-based classification , 2018, 2018 IEEE International Conference on Future IoT Technologies (Future IoT).

[49]  Luming Zhang,et al.  Action2Activity: Recognizing Complex Activities from Sensor Data , 2015, IJCAI.

[50]  Cari M. Whyne,et al.  Personalized Activity Recognition with Deep Triplet Embeddings , 2020, Sensors.

[51]  Chris D. Nugent,et al.  A Knowledge-Driven Approach to Activity Recognition in Smart Homes , 2012, IEEE Transactions on Knowledge and Data Engineering.

[52]  Lawrence B. Holder,et al.  Discovering Activities to Recognize and Track in a Smart Environment , 2011, IEEE Transactions on Knowledge and Data Engineering.

[53]  Ying Zhang,et al.  A Knowledge-Based Approach for Multiagent Collaboration in Smart Home: From Activity Recognition to Guidance Service , 2020, IEEE Transactions on Instrumentation and Measurement.

[54]  Héctor Pomares,et al.  Ontology-Based High-Level Context Inference for Human Behavior Identification , 2016, Sensors.

[55]  Diane J. Cook,et al.  Learning Setting-Generalized Activity Models for Smart Spaces , 2012, IEEE Intelligent Systems.

[56]  Xuemei Guo,et al.  Framework of Sequence Chunking for Human Activity Recognition Using Wearables , 2019, IVSP 2019.

[57]  Martha E. Pollack,et al.  An 'Object-Use Fingerprint': The Use of Electronic Sensors for Human Identification , 2007, UbiComp.

[58]  Shaohan Hu,et al.  DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing , 2016, WWW.

[59]  Juha Röning,et al.  Personalizing human activity recognition models using incremental learning , 2019, ESANN.

[60]  David S. Rosenblum,et al.  From action to activity: Sensor-based activity recognition , 2016, Neurocomputing.

[61]  Wil M. P. van der Aalst,et al.  Discovering more precise process models from event logs by filtering out chaotic activities , 2017, Journal of Intelligent Information Systems.

[62]  Sfar Hela,et al.  Early anomaly detection in smart home: A causal association rule-based approach , 2018, Artif. Intell. Medicine.

[63]  Yu Zhao,et al.  Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors , 2017, Mathematical Problems in Engineering.

[64]  Behrouz Minaei-Bidgoli,et al.  Multi objective association rule mining with genetic algorithm without specifying minimum support and minimum confidence , 2011, Expert Syst. Appl..

[65]  George D. Magoulas,et al.  Modeling human behavior in user-adaptive systems: Recent advances using soft computing techniques , 2005, Expert Syst. Appl..

[66]  Svetha Venkatesh,et al.  Recognition of emergent human behaviour in a smart home: A data mining approach , 2007, Pervasive Mob. Comput..

[67]  Elnaz Soleimani,et al.  Cross-Subject Transfer Learning in Human Activity Recognition Systems using Generative Adversarial Networks , 2019, Neurocomputing.

[68]  Gert R. G. Lanckriet,et al.  Recognizing Detailed Human Context in the Wild from Smartphones and Smartwatches , 2016, IEEE Pervasive Computing.

[69]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.