Corpus ID: 6213527

Multi-task Learning for Predicting Health , Stress , and Happiness

@inproceedings{Jaques2016MultitaskLF,
  title={Multi-task Learning for Predicting Health , Stress , and Happiness},
  author={Natasha Jaques and Sara Taylor and Ehimwenma Nosakhare and Akane Sano and Rosalind W. Picard},
  year={2016}
}
Multi-task Learning (MTL) is applied to the problem of predicting next-day health, stress, and happiness using data from wearable sensors and smartphone logs. Three formulations of MTL are compared: i) Multi-task Multi-Kernel learning, which feeds information across tasks through kernel weights on feature types, ii) a Hierarchical Bayes model in which tasks share a common Dirichlet prior, and iii) Deep Neural Networks, which share several hidden layers but have final layers unique to each task… Expand

Figures and Tables from this paper

Predicting Tomorrow's Mood, Health, and Stress Level using Personalized Multitask Learning and Domain Adaptation
TLDR
Empirical results show that the new personalized models — a MTL deep neural network, and a Gaussian Process with DA — both significantly outperform their generic counterparts, providing substantial performance enhancements in automatic prediction of continuous levels of tomorrow’s reported mood, stress, and physical health based on data through today. Expand
Personalized Driver Stress Detection with Multi-task Neural Networks using Physiological Signals
TLDR
A multi-task learning based neural network approach (with hard parameter sharing of mutual representation and task-specific layers) for personalized stress recognition using skin conductance and heart rate from wearable devices is suggested. Expand
Model Adaptation and Personalization for Physiological Stress Detection
TLDR
A deep reconstruction classification network and multi-task learning for domain adaption and personalization of stress recognition models and MTL based neural network approach with hard parameter sharing of mutual representation and task-specific layers is utilized to acquire personalized models. Expand
Multi-task neural networks for personalized pain recognition from physiological signals
  • D. Martinez, Rosalind W. Picard
  • Psychology, Computer Science
  • 2017 Seventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)
  • 2017
TLDR
A multi-task learning approach based on neural networks that accounts for individual differences in pain responses while still leveraging data from across the population is implemented. Expand
Multimodal autoencoder: A deep learning approach to filling in missing sensor data and enabling better mood prediction
TLDR
Empirical results demonstrate that the MMAE is able to predict the feature values from multiple missing modalities more accurately than reconstruction methods such as principal components analysis (PCA), and it can provide robust mood prediction even when up to three quarters of the data sources are lost. Expand
Outliers in Smartphone Sensor Data Reveal Outliers in Daily Happiness
TLDR
This paper proposes a new approach that advances emotional state prediction by extracting outlier-based features and by mitigating the subjectivity in capturing ground-truth information and demonstrates prediction performance improvements of up to 13% in AUC and 27% in F-score compared to the traditional modelling approaches. Expand
Active one-shot learning for personalized human affect estimation
TLDR
This model demonstrates the ability to learn an active learner that achieves high accuracy, learns to become data efficient, and introduces model personalization to match or outperform fully supervised and population-level models. Expand
MUSER: MUltimodal Stress detection using Emotion Recognition as an Auxiliary Task
TLDR
This work proposes MUSER – a transformer-based model architecture and a novel multi-task learning algorithm with speed-based dynamic sampling strategy that is effective for stress detection with both internal and external auxiliary tasks, and achieves state-of-the-art results. Expand
Probabilistic latent variable modeling for predicting future well-being and assessing behavioral influences on mood, stress and health
TLDR
A real-world dataset from a population of college students and interpretable machine learning methods are used to predict future mood, stress and health, uncover how combinations of health behaviors work together to influence well-being, and understand how to make evidence-based recommendations to individuals looking to improve their well- Being. Expand
Mood Detection from Physical and Neurophysical Data Using Deep Learning Models
TLDR
This is the very first attempt to analyze the neurophysical conditions of the users by evaluating deep learning models for mood analysis and enriching physical characteristics with neurophysical parameters. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 23 REFERENCES
Multi-task , Multi-Kernel Learning for Estimating Individual Wellbeing
We apply a recently proposed technique – Multi-task Multi-Kernel Learning (MTMKL) – to the problem of modeling students’ wellbeing. Because wellbeing is a complex internal state consisting of severalExpand
Predicting students' happiness from physiology, phone, mobility, and behavioral data
TLDR
In order to model students' happiness, machine learning methods are applied to data collected from undergrad students monitored over the course of one month each, to achieve 70% classification accuracy of self-reported happiness on held-out test data. Expand
Multi-task and multi-view learning of user state
TLDR
This work discusses how two recent machine learning concepts, multi-view learning and multi-task learning, can be adapted for user state recognition, and illustrates how they can be effectively combined in a unified model by introducing a novel algorithm. Expand
Prediction of Happy-Sad mood from daily behaviors and previous sleep history
  • A. Sano, A. Z. Yu, +5 authors Rosalind W. Picard
  • Psychology, Computer Science
  • 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2015
TLDR
Behavioral factors including the frequency of negative social interactions, and negative emails, and total academic activity hours showed the best performance in separating the Happy-Sad mood groups. Expand
Multi-Task Learning for Classification with Dirichlet Process Priors
TLDR
Experimental results on two real life MTL problems indicate that the proposed algorithms automatically identify subgroups of related tasks whose training data appear to be drawn from similar distributions are more accurate than simpler approaches such as single-task learning, pooling of data across all tasks, and simplified approximations to DP. Expand
Daily Stress Recognition from Mobile Phone Data, Weather Conditions and Individual Traits
TLDR
This paper proposes an alternative approach providing evidence that daily stress can be reliably recognized based on behavioral metrics, derived from the user's mobile phone activity and from additional indicators, such as the weather conditions and the personality traits, which have strong predictive power. Expand
Multimodal affect recognition in learning environments
TLDR
A unified approach, based on a mixture of Gaussian Processes, for achieving sensor fusion under the problematic conditions of missing channels and noisy labels, achieves accuracy of over 86%, significantly outperforming classification using the individual modalities, and several other combination schemes. Expand
Measuring college students' sleep, stress, mental health and wellbeing with wearable sensors and mobile phones
This thesis carries out a series of studies and develops a methodology and tools to measure and analyze ambulatory physiological, behavioral and social data from wearable sensors and mobile phonesExpand
Neural network multitask learning for traffic flow forecasting
  • Feng Jin, Shiliang Sun
  • Computer Science
  • 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
  • 2008
TLDR
Comprehensive experiments on urban vehicular traffic flow data and comparisons with STL show that MTL in BP neural networks is a promising and effective approach for traffic flow forecasting. Expand
Multimodal semi-automated affect detection from conversational cues, gross body language, and facial features
TLDR
A multimodal affect detector that combines conversational cues, gross body language, and facial features, and linear discriminant analyses to discriminate between naturally occurring experiences of boredom, engagement/flow, confusion, frustration, delight, and neutral is developed and evaluated. Expand
...
1
2
3
...