A Transferred Daily Activity Recognition Method Based on Sensor Sequences
Pages 1001 - 1028
Abstract
The feature-based transfer learning method has become popular for transferred daily activity recognition in heterogeneous smart home environment since the feature-based transfer learning can reduce the difference between the source smart home environment and the target smart home environment. However, feature-based transfer learning has a poor recognition effect on daily activity recognition, for example, when several daily activities with similar features are transferred by feature similarity, the recognition results may be wrong. To improve recognition performance between similar daily activities, this paper presents a novel daily activity recognition method based on sensor sequence similarity and a global similarity calculation method based on random sampling. Firstly, the sensor similarity between source domain and target domain will be calculated to generate the sensor mapping matrix. Secondly, the features are extracted from all the samples of daily activities to calculate the similarities. Thirdly, the sensor similarity matrix is employed to calculate the sensor sequence similarity between the samples. Finally, the source domain samples with high similarity are chosen as similar samples to calculate global similarities with a random sampling method. The best matching source sample will be selected and the label is sent to the target sample. To evaluate our method, we use four public datasets to prove the validity of our method. The result of the experiment shows that our method is better than other commonly used methods.
References
[1]
Abidine BM, Fergani L, Fergani B, and Oussalah M The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition Pattern Anal Appl 2018
[2]
Lu Lu, Qing-ling C, and Yi-Ju Z Activity recognition in smart homes Multimedia Tools Appl 2017
[3]
Saeedi R and Gebremedhin AH A signal-level transfer learning framework for autonomous reconfiguration of wearable systems IEEE Trans Mob Comput 2020
[4]
Wang J, Chen Y, Hu L, Peng X, Yu PS (2018) Stratified transfer learning for cross-domain activity recognition. In: 2018 IEEE international conference on pervasive computing and communications (PerCom).
[5]
Alam MR, Reaz MBI, and Ali MAM A review of smart homes—past, present, and future IEEE Trans Syst Man Cybernet Part C 2012
[6]
Chen W-H, Chen Y (2017) An ensemble approach to activity recognition based on binary sensor readings. In: 2017 IEEE 19th international conference on e-health networking, applications and services (Healthcom).
[7]
Cook DJ and Krishnan NC Activity learning: discovering, recognizing, and predicting human behavior from sensor data 2015 New York Wiley
[8]
Pan SJ and Yang Q A survey on transfer learning IEEE Trans Knowl Data Eng 2010
[9]
Olivas ES, Guerrero JDM, Sober MM (2009) Handbook of research on machine learning applications and trends. Information Science Reference
[10]
Deng W, Xu J, Gao X-Z, and Zhao H An enhanced MSIQDE algorithm with novel multiple strategies for global optimization problems IEEE Trans Syst Man Cybernet Syst 2020
[11]
Cook D, Feuz KD, and Krishnan NC Transfer learning for activity recognition: a survey Knowl Inf Syst 2013
[12]
Myagmar B, Li J, Kimura S (2018) A novel supervised heterogenuos feature transfer learning scheme for ADL recognition. In: 2018 international symposium on intelligent signal processing and communication systems (ISPACS).
[13]
Gargees R, Keller J, and Popescu M Early illness recognition in older adults using transfer learning IEEE 2017
[14]
Mutegeki R, Han DS (2019) Feature-representation transfer learning for human activity recognition. In: The 10th international conference on ICT convergence.
[15]
Diethe T, Twomey N, Flach P (2016) Active transfer learning for activity recognition. In: European symposium on artificial neural networks, computational intelligence and machine learning
[16]
Chiang Y, Hsu JY (2012) Knowledge transfer in activity recognition using sensor profile. In: International conference on ubiquitous intelligence & computing & international conference on autonomy.
[17]
Chiang Y-T, Lu C-H, and Hsu JY-J A feature-based knowledge transfer framework for cross-environment activity recognition toward smart home applications IEEE Trans Human-Mach Syst 2017
[18]
Jethanandani M, Sharma A, Perumal T, and Changd J-R Multi-label classification based ensemble learning for human activity recognition in smart home Internet Things 2020
[19]
Lu CH, Chiang YT (2014) An instantiation of the multiple-transfer framework to reduce efforts in context model learning for new users in smart homes. In: Tenth international conference on intelligent information hiding & multimedia signal processing.
[20]
Lu CH, Chiang YT (2014) A multiple-transfer framework for learning context models for dynamic smart-home environments. In: 2014 IEEE international conference on consumer electronics—Taiwan.
[21]
Deng Wu, Junjie Xu, Zhao H, and Song Y A novel gate resource allocation method using improved PSO-based QEA IEEE Trans Intell Transp Syst 2020
[22]
Rashidi P and Cook DJ Activity knowledge transfer in smart environments Pervasive Mob Comput 2011
[23]
Feuz KD, Cook DJ (2015) Transfer learning across feature-rich heterogeneous feature spaces via feature-space remapping (FSR). ACM
[24]
Samarah S, ALZamil MGH, Rawashdeh M, and Shamim Hossain M Transferring activity recognition models in FOG computing architecture J Parallel Distrib Comput 2018
[25]
Prabono AG, Yahya BN, and Lee S-L Atypical sample regularizer autoencoder for cross-domain human activity recognition Inf Syst Front 2020
[26]
Sanabria AR and Ye J Unsupervised domain adaptation for activity recognition across heterogeneous datasets Pervasive Mobile Comput 2020
[27]
Arifoglu D, Bouchachia A (2019) Abnormal behaviour detection for dementia sufferers via transfer learning and recursive auto-encoders. In: International conference on pervasive computing and communications workshops.
[28]
Chiang Y, Fang W-C, Hsu JY (2013) Knowledge source selection by estimating distance between datasets. In: 2012 conference on technologies and applications of artificial intelligence.
[29]
Xiao Z, Xu X, and Xing H A federated learning system with enhanced feature extraction for human activity recognition Knowl Based Syst 2021
[30]
Zhang H, Xiao Z, Wang J, et al. A novel IoT-perceptive human activity recognition (HAR) approach using multihead convolutional attention IEEE Internet Things J 2019
[31]
Zamil MGHAl and Samarah S Dynamic event classification for intrusion and false alarm detection in vehicular ad hoc networks Int J Inf Commun Technol 2016
[32]
Lin K, Wang W, Bi Y, Qiu M, and MehediHassan M Human localization based on inertial sensors and fingerprints in the Industrial Internet of Things Comput Netw 2016
[33]
Ding R, Li X, Nie L, Li J, and Si X Empirical study and improvement on deep transfer learning for human activity recognition Sensors 2018
[34]
Deng W, Shang S, Cai X, Zhao H, Zhou Y, Chen H, and Deng W Quantum differential evolution with cooperative coevolution framework and hybrid mutation strategy for large scale optimization Knowl-Based Syst 2021 224 107080
Recommendations
Event-driven daily activity recognition with enhanced emergent modeling
Highlights- The activity modeling method based on the emergent paradigm and the directed-weighted network can fully extract feature structure.
AbstractWith the population aging, elderly health monitoring is triggering more studies on daily activity recognition as the fundamental of ambient assisted living. It is remarkable that activity recognition remains difficulties including how ...
A multi-sensor deep learning approach for complex daily living activity recognition
DigiBiom '22: Proceedings of the 2022 Workshop on Emerging Devices for Digital BiomarkersWith the ever increasing elderly population, human activity trackers can help monitor the daily physical activities performed by the elderly in order to contribute towards improvements in independent living and quality of life.
Little activity ...
Towards unobtrusive detection and realistic attribute analysis of daily activity sequences using a finger-worn device
Detection and analysis of activities of daily living (ADLs) are important in activity tracking, security monitoring, and life support in elderly healthcare. Recently, many research projects have employed wearable devices to detect and analyze ADLs. ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 11 July 2022
Accepted: 07 June 2022
Author Tags
Qualifiers
- Research-article
Funding Sources
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Feb 2025