Bipart: Learning Block Structure for Activity Detection

  title={Bipart: Learning Block Structure for Activity Detection},
  author={Yang Mu and Henry Z. Lo and Wei Ding and Kevin Michael Amaral and Scott E. Crouter},
  journal={IEEE Transactions on Knowledge and Data Engineering},
Physical activity consists of complex behavior, typically structured in bouts which can consist of one continuous movement (e.g., exercise) or many sporadic movements (e.g., household chores). Each bout can be represented as a block of feature vectors corresponding to the same activity type. This paper introduces a general distance metric technique to use this block representation to first predict activity type, and then uses the predicted activity to estimate energy expenditure within a novel… 

Bag-of-Words Method Applied to Accelerometer Measurements for the Purpose of Classification and Energy Estimation

An innovative and highly accurate regression method which uses an intermediary two-stage classification step to better direct the regression of energy expenditure values from accelerometer counts and uses a gaussian mixture model to learn the dictionary upon which the bag-of-words model is built.

Learning weighted distance metric from group level information and its parallel implementation

This paper introduces a learning technique for weighted-distance metric, a semi-supervised method that learns labeled information from training set and identifies groups among the samples from test set to form a metric space.

A Survey on Energy Expenditure Estimation Using Wearable Devices

The article provides an overview of existing work in this evolving field, categorizes it, and makes publicly available an EEE dataset, one of the most valuable resources for the development of the field but generally not provided by researchers due to the high cost of collection.

Estimating physical activity in youth using an ankle accelerometer

Compared to the K4b2, the ankle VM2RM provided similar estimates to measured values during unstructured play and provides a feasible wear location for future studies.

υ-Support vector machine based on discriminant sparse neighborhood preserving embedding

The theoretical analysis demonstrates that υ-DSNPESVM is a reasonable maximum margin classifier and can obtain a very lower generalization error upper bound by minimizing the integration model and the upper bound of margin error.

Mitigating Class-Boundary Label Uncertainty to Reduce Both Model Bias and Variance

A new approach is investigated to handle inaccuracy and uncertainty in the training data labels, which are inevitable in many applications where labels are conceptual entities and labeling is performed by human annotators, and it is shown that this new approach improves model performance and reduces model variance.

SummerTime: Variable-length Time Series Summarization with Application to Physical Activity Analysis

SummerTime seeks to summarize global time-series signals and provides a fixed-length, robust representation of the variable-length time series, using Gaussian Mixture models over small same-length disjoint windows in the time series to group local data into clusters.

Activity recognition and intensity estimation in youth from accelerometer data aided by machine learning

This study formulated the issue as a machine learning problem—using a diverse set of 19 physical activities commonly performed by youth—via two approaches: activity recognition and intensity estimation and implemented a distance metric learning method called DML-KNN that utilizes time-frequency features and is capable of effectively classifying both continuous and intermittent movement in youth subjects.

Face Recognition from Multiple Images per Subject

A Bipart framework is proposed to take advantage of group information to improve classification performance in the testing set as well as in the training set, and is generalized to allow both subspace learning and distance metric learning methods totake advantage of this group information.



A Practical Approach to Recognizing Physical Activities

This paper presents an approach to building a system that exhibits these properties and provides evidence based on data for 8 different activities collected from 12 different subjects, and indicates that the system has an accuracy rate of approximately 90% while meeting the requirements.

Artificial neural networks to predict activity type and energy expenditure in youth.

ANNs can be used to predict both PA type and PAEE in children and adolescents using count data from a single waist mounted accelerometer.

Refined two-regression model for the ActiGraph accelerometer.

The refined two-regression model should eliminate the misclassification of transitional minutes when changing activities that start and stop in the middle of a minute on the ActiGraph clock, thus improving the estimate of free-living energy expenditure.

A novel method for using accelerometer data to predict energy expenditure.

A new two-regression model relating Actigraph activity counts to energy expenditure over a wide range of physical activities is developed and is more accurate for the prediction of energy expenditure than currently published regression equations using the Actigraph accelerometer.

Evaluation of artificial neural network algorithms for predicting METs and activity type from accelerometer data: validation on an independent sample.

This study develops new nnets based on a larger, more diverse, training data set and applies these nnet prediction models to an independent sample to evaluate the robustness and flexibility of this machine-learning modeling technique.

Distance Metric Learning with Application to Clustering with Side-Information

This paper presents an algorithm that, given examples of similar (and, if desired, dissimilar) pairs of points in �”n, learns a distance metric over ℝn that respects these relationships.

Real-Time Recognition of Physical Activities and Their Intensities Using Wireless Accelerometers and a Heart Rate Monitor

A real-time algorithm for automatic recognition of not only physical activities, but also, in some cases, their intensities, using five triaxial wireless accelerometers and a wireless heart rate monitor is presented.

Patch Alignment for Dimensionality Reduction

A new dimensionality reduction algorithm is developed, termed discrim inative locality alignment (DLA), by imposing discriminative information in the part optimization stage, and thorough empirical studies demonstrate the effectiveness of DLA compared with representative dimensionality Reduction algorithms.

Local discriminative distance metrics ensemble learning

Distance Metric Learning for Large Margin Nearest Neighbor Classification

This paper shows how to learn a Mahalanobis distance metric for kNN classification from labeled examples in a globally integrated manner and finds that metrics trained in this way lead to significant improvements in kNN Classification.