Access the full text.
Sign up today, get DeepDyve free for 14 days.
(2012)
References Abadi
Chingyi Lin, R. Marculescu (2020)
Model Personalization for Human Activity Recognition2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)
[ (2020)
Towards understanding attention-based speech recognition modelsIEEE Access 8 (2020), 8
S. Dongen, Anton Enright (2012)
Metric distances derived from cosine similarity and Pearson and Spearman correlationsArXiv, abs/1208.3145
[ (2019)
Understanding learning dynamics of language models with SVCCAProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019
D. Heldman, Denzil Harris, T. Felong, Kelly Andrzejewski, E. Dorsey, J. Giuffrida, Barry Goldberg, M. Burack (2017)
Telehealth Management of Parkinson’s Disease Using Wearable Sensors: An Exploratory StudyDigital Biomarkers, 1
Jorge Reyes-Ortiz, L. Oneto, A. Samà, X. Parra, D. Anguita (2016)
Transition-Aware Human Activity Recognition Using SmartphonesNeurocomputing, 171
Xiaodong Qu, Qingtian Mei, Peiyan Liu, Timothy Hickey (2020)
Using EEG to Distinguish Between Writing and Typing for the Same Cognitive Task
T. Hastie, R. Tibshirani, J. Friedman (2001)
The Elements of Statistical Learning
Jindong Wang, Yiqiang Chen, Shuji Hao, Xiaohui Peng, Lisha Hu (2017)
Deep Learning for Sensor-based Activity Recognition: A SurveyArXiv, abs/1707.03502
Allah Sargano, Xiaofeng Wang, P. Angelov, Z. Habib (2017)
Human action recognition using transfer learning with deep representations2017 International Joint Conference on Neural Networks (IJCNN)
[ (2010)
Remember and transfer what you have learned-recognizing composite activities based on activity spottingProceedings of the International Symposium on Wearable Computers (ISWC) 2010. IEEE
[ (2009)
Imagenet: A large-scale hierarchical image databaseProceedings of the 2009 IEEE conference on Computer Vision and Pattern Recognition. Ieee, 2009
T. Evgeniou, M. Pontil (2004)
Regularized multi--task learningProceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
[ (2016)
Technology in ParkinsonMovement Disorders, 31
Ranadeep Deb, Ganapati Bhat, Sizhe An, Holly Shill, U. Ogras (2021)
Trends in Technology Usage for Parkinson's Disease Assessment: A Systematic Review
Benjamin O’Brien, T. Gisby, I. Anderson (2014)
Stretch sensors for human body motion, 9056
[ (2018)
Could wearable and mobile technology improve the management of essential tremor? Frontiers in Neurology 9 (2018), 257:1–257:8Could wearable and mobile technology improve the management of essential tremor? Frontiers in Neurology 9 (2018)
Ziyuan Zhao, Jinxuan Hu, Zeng Zeng, Xulei Yang, Peisheng Qian, B. Veeravalli, Cuntai Guan (2022)
MMGL: Multi-Scale Multi-View Global-Local Contrastive Learning for Semi-Supervised Cardiac Image Segmentation2022 IEEE International Conference on Image Processing (ICIP)
J. Daneault (2018)
Could Wearable and Mobile Technology Improve the Management of Essential Tremor?Frontiers in Neurology, 9
[ (2015)
Keras(2015). Retrieved from https://keras.io.
Hoo-Chang Shin, H. Roth, Mingchen Gao, Le Lu, Ziyue Xu, Isabella Nogues, Jianhua Yao, D. Mollura, R. Summers (2016)
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer LearningIeee Transactions on Medical Imaging, 35
[ (2015)
TensorFlow: Large-scale machine learning on heterogeneous systemsSoftware available from tensorflow.org.
Ganapati Bhat, Nicholas Tran, Holly Shill, U. Ogras (2020)
w-HAR: An Activity Recognition Dataset and Framework Using Low-Power Wearable DevicesSensors (Basel, Switzerland), 20
Judit Bort-Roig, N. Gilson, A. Puig-Ribera, R. Contreras, S. Trost (2014)
Measuring and Influencing Physical Activity with Smartphone Technology: A Systematic ReviewSports Medicine, 44
(2015)
TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. URL http://tensorflow.org/. Software available from tensorflow.org
D. Cook, Kyle Feuz, N. Krishnan (2013)
Transfer learning for activity recognition: a surveyKnowledge and Information Systems, 36
Renjie Ding, Xue Li, Lanshun Nie, Jiazhen Li, Xiandong Si, Dianhui Chu, Guozhong Liu, D. Zhan (2018)
Empirical Study and Improvement on Deep Transfer Learning for Human Activity RecognitionSensors (Basel, Switzerland), 19
Ziyuan Zhao, Kaixin Xu, Shumeng Li, Zeng Zeng, Cuntai Guan (2022)
MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels
D. Micucci, M. Mobilio, Paolo Napoletano (2016)
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from SmartphonesApplied Sciences, 7
A. Schwaighofer, Volker Tresp, Kai Yu (2004)
Learning Gaussian Process Kernels via Hierarchical Bayes
B. Chikhaoui, Frank Gouineau, Martin Sotir (2018)
A CNN Based Transfer Learning Model for Automatic Activity Recognition from Accelerometer Sensors
Train a CNN classifier for each user cluster (UC) obtained in step 1
Ulf Blanke, B. Schiele (2010)
Remember and transfer what you have learned - recognizing composite activities based on activity spottingInternational Symposium on Wearable Computers (ISWC) 2010
Aiguo Wang, Guilin Chen, Jing Yang, Shenghui Zhao, Chih-Yung Chang (2016)
A Comparative Study on Human Activity Recognition Using Inertial Sensors in a SmartphoneIEEE Sensors Journal, 16
M. Oquab, L. Bottou, I. Laptev, Josef Sivic (2014)
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks2014 IEEE Conference on Computer Vision and Pattern Recognition
Sizhe An, Y. Tuncel, T. Basaklar, G. Krishnakumar, Ganapati Bhat, U. Ogras (2021)
MGait: Model-Based Gait Analysis Using Wearable Bend and Inertial SensorsACM Trans. Internet Things, 3
T. Hur, J. Bang, Thien Huynh-The, Jongwon Lee, Jee-In Kim, Sungyoung Lee (2018)
Iss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity RecognitionSensors (Basel, Switzerland), 18
Ari Morcos, M. Raghu, Samy Bengio (2018)
Insights on representational similarity in neural networks with canonical correlation
Oscar Lara, M. Labrador (2013)
A Survey on Human Activity Recognition using Wearable SensorsIEEE Communications Surveys & Tutorials, 15
Ganapati Bhat, Ranadeep Deb, U. Ogras (2019)
OpenHealth: Open-Source Platform for Wearable Health MonitoringIEEE Design & Test, 36
A. Quattoni, M. Collins, Trevor Darrell (2008)
Transfer learning for image classification with sparse prototype representations2008 IEEE Conference on Computer Vision and Pattern Recognition
John Blitzer, Ryan McDonald, Fernando Pereira (2006)
Domain Adaptation with Structural Correspondence Learning
[ (2017)
Human action recognition using transfer learning with deep representationsProceedings of the 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, 2017
W. Maetzler, J. Klucken, M. Horne (2016)
A clinical view on the development of technology‐based tools in managing Parkinson's diseaseMovement Disorders, 31
Rajat Raina, Alexis Battle, Honglak Lee, Ben Packer, A. Ng (2007)
Self-taught learning: transfer learning from unlabeled data
A. Akbari, R. Jafari (2019)
Transferring Activity Recognition Models for New Wearable Sensors with Deep Generative Domain Adaptation2019 18th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Gelan Yang, Wei Tan, Huixia Jin, Tuo Zhao, Li Tu (2019)
Review wearable sensing system for gait recognitionCluster Computing
(2016)
Human activity recognition with smartphone sensors using deep learning neural networks
[ (2011)
Activity recognition using cell phone accelerometersACM SigKDD Explorations Newsletter, 12
M. Salem, S. Taheri, Jiann-Shiun Yuan (2018)
ECG Arrhythmia Classification Using Transfer Learning from 2- Dimensional Deep CNN Features2018 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Andreas Argyriou, T. Evgeniou, M. Pontil (2008)
Convex multi-task feature learningMachine Learning, 73
Siwei Feng, Marco Duarte (2019)
Few-Shot Learning-Based Human Activity RecognitionArXiv, abs/1903.10416
Seyed Rokni, Marjan Nourollahi, Hassan Ghasemzadeh (2018)
Personalized Human Activity Recognition Using Convolutional Neural Networks
M. Shoaib, S. Bosch, Özlem Incel, H. Scholten, P. Havinga (2015)
A Survey of Online Activity Recognition Using Mobile PhonesSensors (Basel, Switzerland), 15
Sinno Pan, Qiang Yang (2010)
A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 22
M. Raghu, Chiyuan Zhang, J. Kleinberg, Samy Bengio (2019)
Transfusion: Understanding Transfer Learning for Medical Imaging
Jia Deng, Wei Dong, R. Socher, Li-Jia Li, K. Li, Li Fei-Fei (2009)
ImageNet: A large-scale hierarchical image database2009 IEEE Conference on Computer Vision and Pattern Recognition
J. Yosinski, J. Clune, Yoshua Bengio, Hod Lipson (2014)
How transferable are features in deep neural networks?
Edinburgh Research Explorer Understanding Learning Dynamics Of Language Models with SVCCA
Evaluate the accuracy for unseen UCs using the classi-fiers trained in step 2
Wenyuan Dai, Qiang Yang, Gui-Rong Xue, Yong Yu (2007)
Boosting for transfer learning
D. Anguita, A. Ghio, L. Oneto, X. Parra, Jorge Reyes-Ortiz (2013)
A Public Domain Dataset for Human Activity Recognition using Smartphones
[ (2018)
ECG arrhythmia classification using transfer learning from 2-dimensional deep CNN featuresProceedings of the 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS). IEEE, 2018
Matthew Zeiler (2012)
ADADELTA: An Adaptive Learning Rate MethodArXiv, abs/1212.5701
J. Schlachetzki, J. Barth, F. Marxreiter, Julia Goßler, Z. Kohl, Samuel Reinfelder, H. Gassner, K. Aminian, B. Eskofier, J. Winkler, J. Klucken (2017)
Wearable sensors objectively measure gait parameters in Parkinson’s diseasePLoS ONE, 12
A. Espay, P. Bonato, Fatta Nahab, W. Maetzler, J. Dean, J. Klucken, B. Eskofier, A. Merola, F. Horak, A. Lang, R. Reilmann, J. Giuffrida, A. Nieuwboer, M. Horne, Max Little, I. Litvan, T. Simuni, E. Dorsey, M. Burack, Ken Kubota, A. Kamondi, C. Godinho, J. Daneault, G. Mitsi, Lothar Krinke, J. Hausdorff, B. Bloem, S. Papapetropoulos (2016)
Technology in Parkinson's disease: Challenges and opportunitiesMovement Disorders, 31
Andreas Argyriou, T. Evgeniou, M. Pontil (2006)
Multi-Task Feature Learning
Jennifer Kwapisz, Gary Weiss, Samuel Moore (2011)
Activity recognition using cell phone accelerometersSIGKDD Explor., 12
Hirotaka Hachiya, Masashi Sugiyama, N. Ueda (2012)
Importance-weighted least-squares probabilistic classifier for covariate shift adaptation with application to human activity recognitionNeurocomputing, 80
(2014)
Jetson Xavier NX Developer Kit
Human activity recognition (HAR) has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with known users and then using the same classifier for new users. However, the accuracy for new users can be low with this approach if their activity patterns are different than those in the training data. At the same time, training from scratch for new users is not feasible for mobile applications due to the high computational cost and training time. To address this issue, we propose a HAR transfer learning framework with two components. First, a representational analysis reveals common features that can transfer across users and user-specific features that need to be customized. Using this insight, we transfer the reusable portion of the offline classifier to new users and fine-tune only the rest. Our experiments with five datasets show up to 43% accuracy improvement and 66% training time reduction when compared to the baseline without using transfer learning. Furthermore, measurements on the hardware platform reveal that the power and energy consumption decreased by 43% and 68%, respectively, while achieving the same or higher accuracy as training from scratch. Our code is released for reproducibility.1
ACM Transactions on Computing for Healthcare (HEALTH) – Association for Computing Machinery
Published: Mar 16, 2023
Keywords: Transfer learning
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.