• Corpus ID: 52143652

Tensor Embedding: A Supervised Framework for Human Behavioral Data Mining and Prediction

@article{Hosseinmardi2018TensorEA,
  title={Tensor Embedding: A Supervised Framework for Human Behavioral Data Mining and Prediction},
  author={Homa Hosseinmardi and Amir Ghasemian and Shrikanth S. Narayanan and Kristina Lerman and Emilio Ferrara},
  journal={ArXiv},
  year={2018},
  volume={abs/1808.10867}
}
Today's densely instrumented world offers tremendous opportunities for continuous acquisition and analysis of multimodal sensor data providing temporal characterization of an individual's behaviors. Is it possible to efficiently couple such rich sensor data with predictive modeling techniques to provide contextual, and insightful assessments of individual performance and wellbeing? Prediction of different aspects of human behavior from these noisy, incomplete, and heterogeneous bio-behavioral… 

Figures and Tables from this paper

Learning Behavioral Representations from Wearable Sensors

TLDR
This work uses a non-parametric Bayesian approach to model sensor data from multiple people and discover the dynamic behaviors they share and applies this method to data collected from sensors worn by a population of hospital workers and shows that the learned states can cluster participants into meaningful groups and better predict their cognitive and psychological states.

Individualized Context-Aware Tensor Factorization for Online Games Predictions

TLDR
The proposed NICE model identifies individual behavioral differences in different contexts by learning latent representations of users and contexts through non-negative tensor factorization and substantially improves the prediction of winning outcome, individual user performance, and user engagement.

Deep Neural Networks for Optimal Team Composition

TLDR
A directed co-play network is generated, whose links' weights depict the effect of teammates on players' performance, and a measure of network influence that captures skill transfer from player to player over time is proposed.

User-Based Collaborative Filtering Mobile Health System

TLDR
A user-based collaborative filtering mobile health system that predicts users based on the health information from their cohort using mobile devices, wearables, and sensors that demonstrates strong interpretability, predictability, and usability.

Social, Cultural, and Behavioral Modeling: 13th International Conference, SBP-BRiMS 2020, Washington, DC, USA, October 18–21, 2020, Proceedings

TLDR
This research compliments existing text mining and behavior modeling approaches by offering a language agnostic methodology with lower dimensionality than topic modeling, and focuses on three features often overlooked: document structure, emoji use, and consistency of behavior.

References

SHOWING 1-10 OF 53 REFERENCES

Tensor Regression with Applications in Neuroimaging Data Analysis

TLDR
A new family of Tensor regression models that efficiently exploit the special structure of tensor covariates are proposed and ultrahigh dimensionality is reduced to a manageable level, resulting in efficient estimation and prediction.

Learning from Multiway Data: Simple and Efficient Tensor Regression

TLDR
Subsampled tensor projected gradient is introduced, built upon projected gradient method with fast tensor power iterations, leveraging randomized sketching for further acceleration and demonstrates superior empirical performance on both multi-linear multitask learning and spatio-temporal applications.

Kernelization of Tensor-Based Models for Multiway Data Analysis: Processing of Multidimensional Structured Data

TLDR
Besides unsupervised tensor decompositions, supervised tensor subspace regression and classification formulations have been also successfully applied to a variety of fields including chemometrics, signal processing, computer vision, and neuroscience.

Tensor Learning for Regression

TLDR
Experiments conducted for the problems of head-pose, human-age, and 3-D body-pose estimations using real data from publicly available databases verified not only the superiority of tensors over their vector counterparts but also the efficiency of the proposed algorithms.

Higher Order Partial Least Squares (HOPLS): A Generalized Multilinear Regression Method

TLDR
A systematic comparison on both synthetic data and real-world decoding of 3D movement trajectories from electrocorticogram signals demonstrate the advantages of HOPLS over the existing methods in terms of better predictive ability, suitability to handle small sample sizes, and robustness to noise.

Objective assessment of depressive symptoms with machine learning and wearable sensors data

TLDR
Analyzing the features and their relation to depressive symptoms, it was found that poor mental health was accompanied by more irregular sleep, less motion, fewer incoming messages, less variability in location patterns, and higher asymmetry of EDA between the right and the left wrists.

Supervised Nonnegative Tensor Factorization with Maximum-Margin Constraint

TLDR
The proposed Supervised Non-negative Tensor Factorization with Maximum-Margin Constraint (SNTFM2) formulates the optimal discriminative factorization of non-negative tensorial data as a coupled least-squares optimization problem via a maximum-margin method.

Assessing feature relevance in NPLS models by VIP

Structural Deep Network Embedding

TLDR
This paper proposes a Structural Deep Network Embedding method, namely SDNE, which first proposes a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non- linear network structure and exploits the first-order and second-order proximity jointly to preserve the network structure.
...