Consensus inference on mobile phone sensors for activity recognition

Published on Mar 20, 2016 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
· DOI :10.1109/ICASSP.2016.7472086
Huan Songg1
Estimated H-index: 1
(ASU: Arizona State University),
Jayaraman J. Thiagarajan14
Estimated H-index: 14
(LLNL: Lawrence Livermore National Laboratory)
+ 2 AuthorsPavan Turaga24
Estimated H-index: 24
(ASU: Arizona State University)
The pervasive use of wearable sensors in activity and health monitoring presents a huge potential for building novel data analysis and prediction frameworks. In particular, approaches that can harness data from a diverse set of low-cost sensors for recognition are needed. Many of the existing approaches rely heavily on elaborate feature engineering to build robust recognition systems, and their performance is often limited by the inaccuracies in the data. In this paper, we develop a novel two-stage recognition system that enables a systematic fusion of complementary information from multiple sensors in a linear graph embedding setting, while employing an ensemble classifier phase that leverages the discriminative power of different feature extraction strategies. Experimental results on a challenging dataset show that our framework greatly improves the recognition performance when compared to using any single sensor.
  • References (21)
  • Citations (6)
📖 Papers frequently viewed together
2 Citations
2011SMC: Systems, Man and Cybernetics
23 Citations
2008ICPR: International Conference on Pattern Recognition
2 Authors (Ying Sun, Hairong Qi)
14 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
Nov 1, 2014 in ASILOMAR (Asilomar Conference on Signals, Systems and Computers)
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 14
Last. Ramanathan Nachiappan (SSN: Sri Sivasubramaniya Nadar College of Engineering)H-Index: 1
view all 5 authors...
Emergence of numerous modalities for data generation necessitates the development of machine learning techniques that can perform efficient inference with multi-modal data. In this paper, we present an approach to learn discriminant low-dimensional projections from supervised multi-modal data. We construct intra- and inter-class similarity graphs for each modality and optimize for consensus projections in the kernel space. Features obtained with these projections can then be used to train a clas...
1 CitationsSource
We resolve two problems regarding subspace distances that have arisen considerably often in applications: How could one define a notion of distance between (i) two linear subspaces of different dimensions, or (ii) two affine subspaces of the same dimension, in a way that generalizes the usual Grassmann distance between equidimensional linear subspaces? We show that (i) is the distance of a point to a Schubert variety, and (ii) is the distance in the Grassmannian of affine subspaces, both regarde...
17 Citations
#1Jayaraman J. Thiagarajan (ASU: Arizona State University)H-Index: 14
#2Karthikeyan Natesan Ramamurthy (ASU: Arizona State University)H-Index: 14
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 28
view all 3 authors...
In complex visual recognition tasks, it is typical to adopt multiple descriptors, which describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can be fused into a unified feature space in a principled manner using kernel methods. Sparse models that generalize well to the test data can be learned in the unified kernel space, and appropriate constraints can be incorporated for application in supervised and unsupervised learn...
52 CitationsSource
#1Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 14
Last. Andreas SpaniasH-Index: 28
view all 4 authors...
Image understanding has been playing an increasingly crucial role in several inverse problems and computer vision. Sparse models form an important component in image understanding, since they emulate the activity of neural receptors in the primary visual cortex of the human brain. Sparse methods have been utilized in several learning problems because of their ability to provide parsimonious, interpretable, and efficient models. Exploiting the sparsity of natural signals has led to advances in se...
14 Citations
#1Narayan Kovvali (ASU: Arizona State University)H-Index: 9
#2Mahesh K. Banavar (ASU: Arizona State University)H-Index: 14
Last. Andreas SpaniasH-Index: 28
view all 3 authors...
The Kalman filter is the Bayesian optimum solution to the problem of sequentially estimating the states of a dynamical system in which the state evolution and measurement processes are both linear and Gaussian. Given the ubiquity of such systems, the Kalman filter finds use in a variety of applications, e.g., target tracking, guidance and navigation, and communications systems. The purpose of this book is to present a brief introduction to Kalman filtering. The theoretical framework of the Kalma...
13 Citations
Jun 23, 2013 in CVPR (Computer Vision and Pattern Recognition)
#1Vinay Venkataraman (ASU: Arizona State University)H-Index: 7
#2Pavan Turaga (ASU: Arizona State University)H-Index: 24
Last. Steven L. Wolf (Emory University)H-Index: 69
view all 6 authors...
In this paper, we propose a novel shape-theoretic framework for dynamical analysis of human movement from 3D data. The key idea we propose is the use of global descriptors of the shape of the dynamical attractor as a feature for modeling actions. We apply this approach to the novel application scenario of estimation of movement quality from a single-marker for future usage in home-based stroke rehabilitation. Using a dataset collected from 15 stroke survivors performing repetitive task therapy, ...
23 CitationsSource
#1Mi Zhang (SC: University of Southern California)H-Index: 19
#2Alexander A. Sawchuk (SC: University of Southern California)H-Index: 27
Human daily activity recognition using mobile personal sensing technology plays a central role in the field of pervasive healthcare. One major challenge lies in the inherent complexity of human body movements and the variety of styles when people perform a certain activity. To tackle this problem, in this paper, we present a novel human activity recognition framework based on recently developed compressed sensing and sparse representation theory using wearable inertial sensors. Our approach repr...
109 CitationsSource
#1Qun Li (Beijing University of Posts and Telecommunications)H-Index: 2
#2Honggang Zhang (Beijing University of Posts and Telecommunications)H-Index: 14
Last. Le An (UCR: University of California, Riverside)H-Index: 18
view all 5 authors...
A reference-based algorithm for scene image categorization is presented in this letter. In addition to using a reference-set for images representation, we also associate the reference-set with training data in sparse codes during the dictionary learning process. The reference-set is combined with the reconstruction error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. After dictionaries are constructed, Locality-constrained Linear Cod...
22 CitationsSource
#1Mi Zhang (SC: University of Southern California)H-Index: 19
#2Alexander A. Sawchuk (SC: University of Southern California)H-Index: 27
Human activity recognition is important for many applications. This paper describes a human activity recognition framework based on feature selection techniques. The objective is to identify the most important features to recognize human activities. We first design a set of new features (called physical features) based on the physical parameters of human motion to augment the commonly used statistical features. To systematically analyze the impact of the physical features on the performance of t...
131 CitationsSource
Jun 20, 2011 in ICOST (International Conference on Smart Homes and Health Telematics)
#1Barnan Das (WSU: Washington State University)H-Index: 10
#2Chao Chen (WSU: Washington State University)H-Index: 10
Last. Diane J. Cook (WSU: Washington State University)H-Index: 54
view all 4 authors...
The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart home-based prompting system can enhance these technologies to deliver in-home interventions to a user for timely reminders or a brief instruction describing the way a task should be done for successful completion. This technology is in high demand with the desire for people who have physical or cognitive limitations to live independently in the...
14 CitationsSource
Cited By6
#1Huan Song (ASU: Arizona State University)H-Index: 4
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 14
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 28
view all 4 authors...
Building highly nonlinear and nonparametric models is central to several state-of-the-art machine learning systems. Kernel methods form an important class of techniques that induce a reproducing kernel Hilbert space (RKHS) for inferring non-linear models through the construction of similarity functions from data. These methods are particularly preferred in cases where the training data sizes are limited and when prior knowledge of the data similarities is available. Despite their usefulness, the...
12 CitationsSource
#1Michael Stanley (NXP Semiconductors)H-Index: 2
#2Jongmin Lee (NXP Semiconductors)H-Index: 1
While it may be attractive to view sensors as simple transducers which convert physical quantities into electrical signals, the truth of the matter is more complex. The engineer should have a proper understanding of the physics involved in the conversion process, including interactions with other measurable quantities. A deep understanding of these interactions can be leveraged to apply sensor fusion techniques to minimize noise and/or extract additional information from sensor signals. Advances...
4 Citations
Mar 5, 2017 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Huan Song (ASU: Arizona State University)H-Index: 4
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 14
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 28
view all 5 authors...
Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this paper, we propose an alternative approach that creates dense embeddings for data using the kernel similarities and adopts a deep neural network architecture for fusing the embeddings. In order to improv...
9 CitationsSource
Dec 1, 2016 in ISSPIT (International Symposium on Signal Processing and Information Technology)
#1Jongmin Lee (ASU: Arizona State University)H-Index: 4
#2Michael Stanley (NXP Semiconductors)H-Index: 2
Last. Cihan Tepedelenlioglu (ASU: Arizona State University)H-Index: 26
view all 4 authors...
Interpreting sensor data in Internet-of-Things applications is a challenging problem particularly in embedded systems. We consider sensor data analytics where machine learning algorithms can be fully implemented on an embedded processor/sensor board. We develop an efficient real-time realization of a Gaussian mixture model (GMM) for execution on the NXP FRDM-K64F embedded sensor board. We demonstrate the design of a customized program and data structure that generates real-time sensor features, ...
17 CitationsSource
Feb 2, 2016 in ICIP (International Conference on Image Processing)
#1Huan Song (ASU: Arizona State University)H-Index: 4
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 14
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 28
view all 4 authors...
In complex visual recognition systems, feature fusion has become crucial to discriminate between a large number of classes. In particular, fusing high-level context information with image appearance models can be effective in object/scene recognition. To this end, we develop an auto-context modeling approach under the RKHS (Reproducing Kernel Hilbert Space) setting, wherein a series of supervised learners are used to approximate the context model. By posing the problem of fusing the context and ...
2 CitationsSource