Proximity-Based Active Learning on Streaming Data: A Personalized Eating Moment Recognition

Detecting when eating occurs is an essential step toward automatic dietary monitoring, medication adherence assessment, and diet-related health interventions. Wearable technologies play a central role in designing unubtrusive diet monitoring solutions by leveraging machine learning algorithms that work on time-series sensor data to detect eating moments. While much research has been done on developing activity recognition and eating moment detection algorithms, the performance of the detection algorithms drops substantially when the model trained with one user is utilized by a new user. To facilitate development of personalized models, we propose PALS, Proximity-based Active Learning on Streaming data, a novel proximity-based model for recognizing eating gestures with the goal of significantly decreasing the need for labeled data with new users. Particularly, we propose an optimization problem to perform active learning under limited query budget by leveraging unlabeled data. Our extensive analysis on data collected in both controlled and uncontrolled settings indicates that the F-score of PLAS ranges from 22% to 39% for a budget that varies from 10 to 60 query. Furthermore, compared to the state-of-the-art approaches, off-line PALS, on average, achieves to 40% higher recall and 12\% higher f-score in detecting eating gestures.

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

[2]  K. Flegal,et al.  Prevalence and trends in obesity among US adults, 1999-2000. , 2002, JAMA.

[3]  Mi Zhang,et al.  BodyBeat: a mobile system for sensing non-speech body sounds , 2014, MobiSys.

[4]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[5]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[6]  Li Guo,et al.  Mining Multi-Label Data Streams Using Ensemble-Based Active Learning , 2012, SDM.

[7]  Ulrike von Luxburg,et al.  Cluster Identification in Nearest-Neighbor Graphs , 2007, ALT.

[8]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[9]  Nada Lavrac,et al.  Stream-based active learning for sentiment analysis in the financial domain , 2014, Inf. Sci..

[10]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[11]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[12]  Xiaodong Lin,et al.  Active Learning from Data Streams , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[13]  Norbert Wehn,et al.  Activity recognition and nutrition monitoring in every day situations with a textile capacitive neckband , 2013, UbiComp.

[14]  B. J. Fogg Healthy Living with Persuasive Technologies : Framework , Issues , and Challenges , 2009 .

[15]  Yujie Dong,et al.  Detecting Periods of Eating During Free-Living by Tracking Wrist Motion , 2014, IEEE Journal of Biomedical and Health Informatics.

[16]  Tom Baranowski,et al.  Eating Patterns, Dietary Quality and Obesity , 2001, Journal of the American College of Nutrition.

[17]  Xiaodong Lin,et al.  Active Learning From Stream Data Using Optimal Weight Classifier Ensemble , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[18]  Zoubin Ghahramani,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[19]  David A. Cohn,et al.  Improving generalization with active learning , 1994, Machine Learning.

[20]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[21]  D. Cook,et al.  Smart Home-Based Health Platform for Behavioral Monitoring and Alteration of Diabetes Patients , 2009, Journal of diabetes science and technology.

[22]  Thad Starner,et al.  Detecting Mastication: A Wearable Approach , 2015, ICMI.

[23]  David Cohn,et al.  Active Learning , 2010, Encyclopedia of Machine Learning.

[24]  Fernando De la Torre,et al.  Facing Imbalanced Data--Recommendations for the Use of Performance Metrics , 2013, 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction.

[25]  Koji Yatani,et al.  BodyScope: a wearable acoustic sensor for activity recognition , 2012, UbiComp.

[26]  Geoff Holmes,et al.  Active Learning with Evolving Streaming Data , 2011, ECML/PKDD.

[27]  Gregory D. Abowd,et al.  EarBit: Using Wearable Sensors to Detect Eating Episodes in Unconstrained Environments , 2017, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[28]  Gregory D. Abowd,et al.  A practical approach for recognizing eating moments with wrist-mounted inertial sensing , 2015, UbiComp.