DSN679668 1 8

DSN679668 1 8 Research Article International Journal of Distributed Sensor Networks 2016, Vol 12(12) � The Author(s) 2016 DOI 10 1177/1550147716679668 ijdsn sagepub com Energy efficient recognition of[.]

International Journal of Distributed Sensor Networks

2016, Vol 12(12)

Ó The Author(s) 2016 DOI: 10.1177/1550147716679668 ijdsn.sagepub.com

Energy-efficient recognition of human

activity in body sensor networks via

compressed classification

Ling Xiao, Renfa Li, Juan Luo and Zhu Xiao

Abstract

Energy efficiency is an important challenge to broad deployment of wireless body sensor networks for long-term physical movement monitoring Inspired by theories of sparse representation and compressed sensing, the power-aware com-pressive classification approach SRC-DRP (sparse representation–based classification with distributed random projec-tion) for activity recognition is proposed, which integrates data compressing and classification Random projection as a data compression tool is individually implemented on each sensor node to reduce the amount of data for transmission Compressive classification can be applied directly on the compressed samples received from all nodes This method was validated on the Wearable Action Recognition Dataset and implemented on embedded nodes for offline and online experiments It is shown that our method reduces energy consumption by approximately 20% while maintaining an activ-ity recognition accuracy of 88% at a compression ratio of 0.5

Keywords

Activity recognition, sparse representation, compressed sensing, random projection, energy efficiency, body sensor networks

Date received: 20 June 2016; accepted: 18 October 2016

Academic Editor: Joel Rodrigues

Introduction

Physical activity monitoring and classification using

wearable sensors have become one of the most

attrac-tive research areas in recent years due to a wide range

of health-related applications,1in fields such as disease

monitoring and diagnosis,2child and elderly care,3and

rehabilitation and assisted living.4 A number of tiny

wireless sensors, strategically attached to the human

body, can constitute a wireless body sensor network

(WBSN), promising to offer inexpensive, continuous,

and remote health monitoring of people in their normal

living environment Long-term physical fitness

moni-toring requires continuous sensing, since physical

activ-ity can occur at any time and require to be classified by

the incoming stream of sensor data The battery

limita-tions of the WBSN severely limit the maximum

deploy-ment time for continuous monitoring Therefore, it is

necessary to design power-efficient signal-processing approaches on the sensor nodes to minimize the energy consumption while offering sufficient classification accuracy and real-time responsiveness Our work explores energy-efficient relationships not only on clas-sification but also on sensing and communication

In recent years, the theories of sparse representation and compressed sensing (CS)5have been gaining atten-tion in the area of signal processing Sparse signal repre-sentation has emerged as a successful tool for analyzing

a large class of signals CS enables the reconstruction of

College of Computer Science and Electronic Engineering, Hunan University, Changsha, China

Corresponding author:

Ling Xiao, Hunan University, Changsha 410082, China.

Email: xiaolingiit@gmail.com

Creative Commons CC-BY: This article is distributed under the terms of the Creative Commons Attribution 3.0 License

(http://www.creativecommons.org/licenses/by/3.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (http://www.uk.sagepub.com/aboutus/ openaccess.htm).

sparse and compressible signals from a small number of

non-adaptive linear measurements in the form of

ran-dom projection (RP) RP6refers to the tool of

project-ing a set of points from a high-dimensional space to a

randomly chosen low-dimensional subspace RP is

firmly evidenced as a near-optimal measurement

scheme as a part of CS.7In many applications, we are

not interested in obtaining a precise signal recovery, but

rather in making some kind of detection or

classifica-tion decision Inspired by CS, compressive classificaclassifica-tion

(CC) appeared in Davenport et al.8CC is designed to

directly classify such compressed samples without the

need to recover the original signals

CC has advantages when it is applied in physical

activity recognition of WBSN Dimensionality

reduc-tion by RP is data independent, whereas popular

dimensionality reduction approaches such as principal

component analysis (PCA) and linear discriminant

analysis (LDA) are data dependent; our classification

method can easily add a new class of activity as well as

remove existing classes Furthermore, RP can be

imple-mented on embedded nodes of WBSN as a

computa-tionally simple method, while PCA or LDA can be too

computationally expensive to implement on nodes

because of the computational burden of eigenvalue

decompositions In addition, dimensionality reduction

also reduces the computational cost so that

classifica-tion can be implemented in real time RP on sensors

cuts down the communication cost by lowering the

amount of sensed data to be transferred from nodes to

a base station, a significant sensor source of energy

consumption Moreover, if compressing and sensing

can be implemented on sensors’ hardware at the same

time, just like a new single-pixel compressive camera,

the power consumption of sensors for sampling and

processing can be further reduced

Our energy-efficient CC approach is novel in the

fol-lowing two aspects: (1) data compression by RP on

resource-constrained WBSN platforms and (2) activity

classification by sparse representation and CS

operat-ing directly on the compressed samples To the best of

our knowledge, it is the first study that explores both

classification and data compression together to satisfy

the usability requirements for a long-term monitoring

environment

The rest of the article is organized as follows: In

sec-tion ‘‘Related works,’’ related works are summarized

The spare representation classification algorithm is

reviewed in section ‘‘Background on SRC.’’ Section

‘‘Proposed compressed classification’’ describes the

pro-posed classification approach in detail The

experimen-tal results and analysis are presented in section

‘‘Experimental results.’’ Section ‘‘Conclusion’’

con-cludes the article and gives possible directions to future

work

Related works WBSNs with multiple inertial sensors are widely used

in various studies on human body movement Recent work involves prototyping wearable sensor systems and developing pattern recognition, as well as machine-learning algorithms, to model and recognize human activities As for the recognition techniques, a large number of classification methods have been investi-gated.9 Some studies incorporated the idea of simple heuristic classifier, whereas others employed more gen-eric and automatic methods from the machine-learning literature including the decision trees, nearest neighbor (NN), Bayesian networks, support vector machines (SVMs), artificial neural networks (ANN), and hidden Markov model (HMM) Inspired by sparse representation–based classification (SRC) for face rec-ognition,10 Yang et al.11 and Zhang and Sawchuk12 extended SRC to activity recognition in body sensor networks (BSNs) Compared to the similar work of Yang et al.11 and Zhang and Sawchuk,12our research utilizes the theory of sparse representation and CS to combine both classification and data compression Compressed classification operates on data acquired by

a compressed sampling technique This article exploits the ability of compressed classification to conserve sen-sor energy for communication while preserving accu-rate activity recognition precision

Most of the classification methods usually process and analyze raw signals sampled from sensor nodes after transmission to a centralized server These methods can result in nodes forwarding a great deal of data to a base station, which could not be applied to the limited band-width and energy resources of WBSN However, com-munication generally consumes more energy than local computation From the energy preservation point, it is more beneficial to perform signal processing on individ-ual nodes, such as feature extraction13and local activity classification.14Wu et al.15developed a data compression approach via inter-node collaboration and overhearing

Au et al.16 dynamically scheduled sensor-measurement episodes to reduce energy consumption Ghasemzandeh

et al.17dynamically selected and activated motion sensors

to reduce the amount of active nodes However, some methods are too complex to be implemented on embedded sensor platforms, and this article exploits a lightweight signal-processing approach on resource-constrained sensor nodes for energy efficiency

Background on SRC One of the most successful applications of the sparse representation and CS in pattern recognition is the SRC algorithm for face recognition,10 which uses the whole set of training samples as a redundant dictionary and casts a recognition problem as one of

discriminatively finding a sparse representation of the

test image as a linear combination of training images

Consider an activity recognition problem with C

dif-ferent classes Each class i has ni training samples,

Vi=½vi, 1, vi, 2, , vi, ni 2Rm 3 n i, each vi,ni have m

attributes If the test sample vk,test belongs to the ith

class, vk,testwill approximately lie in the linear span of

the training samples associated with the ith class

vk, test= ak, 1vk, 1+ ak, 2vk, 2+   + ak, n kvk, nk ð1Þ

for some scalars ai, j2R, j = 1, 2, , ni

Since the membership i of the test sample is initially

unknown, we construct a redundant dictionary V for

the entire training set as the concatenation of n training

samples

ð2Þ

where n = n1+ n2+   + nk, then the linear

represen-tation of vk,testcan be rewritten in terms of all training

samples as

where a = 0,½    0, ak, 1, ak, 2   ak, ni, 0,   0Tis a

coef-ficient vector whose entries are zero except those

associ-ated with the kth class As the entries of the vector a

encode the identity of the test sample vk,test, it attempts

to obtain it by solving the linear system of equations

Assuming there is a set of J wearable sensor nodes

attached to the human body, each consists of a

three-axis accelerometer (x, y, z) and a two-three-axis gyroscope

(u, r) A sample s of activity signal at a node contains

five measurement values

and an action segment of a window size of h at node j

can be represented as an 5 h 3 1 vector

For our activity classification, we required no feature

extraction from the time series of data and directly used the

raw measurements of activity sequence to form a vector v

Proposed compressed classification

If the SRC method is used on the raw motion vectors,

then continuous transmission of the complete sensor

data to a base station would rapidly deplete the sensor

node’s batteries Our goal is to minimize the number of

bits transmitted while reliably preserving the signal

information at a minimum implementation cost on the

embedded nodes CS theory implies that the precise

choice of the number of features should not be critical

for classification problems: a small number of random features contain enough information to preserve the underlying local structure and hence to correctly clas-sify any test sample

To reduce power consumption requirements, the proposed activity classification framework consists of two steps, as shown in Figure 1: (1) distributed random projection (DRP) is operated individually on each sen-sor node and (2) the back-end device such as PC runs the SRC method on the compressed samples received from all nodes Data compression by RP can be imple-mented on the nodes of a WBSN for minimizing the amount of data to be transferred wirelessly from the nodes to the base station

DRP

RP has recently been viewed as a powerful tool for dimensionality reduction Given a M 3 N random matrix F, whose columns have unit length, the original N-dimensional sampled data v2RN 3 1 is projected onto a M-dimensional (M N) vector ~v 2RM 3 1, the dimensionality reduction process is a simple matrix multiplication, given by

~

vM 3 1= FM 3 NvN 3 1 ð6Þ

Ideally, we wish to ensure that F preserves pair-wise distances approximately between all pairs of signals for

RP That is to say, for any two vectors, v1and v2, the distance between them is approximately preserved

for small g.0 One of the important results in Lu and

Do18from CS theory is the restricted isometry property (RIP), which states that equation (7) is indeed satisfied with overwhelming probability by certain random matrices

It is well known that many types of random mea-surement matrices follow RIP Perhaps, the most pro-minent M 3 N random matrices F whose entries fm, n are independent are identically distributed and formed

by (1) a Gaussian distribution fm, n;N (0, 1), (2) a Bernoulli distribution P(fm, n= 6 1) = 1=2, and (3) a sparse binary matrix such as

8

>

The above three types of random matrices have been proven to satisfy the RIP with very high probability.19

In this article, we consider a special sparse binary matrix, where f has exactly d of the ones in each

column (d N), and all the other entries are equal to

zero It has been shown20that such matrices can satisfy

a weaker form of the RIP property

Compared with RP, the traditional dimensionality

reduction methods such as PCA or LDA are with no

guarantee that distances between the original and

pro-jected signals are well preserved Additionally, RP is

computationally very simple: projecting the

N-dimen-sional data into M-dimenN-dimen-sional by random matrix F is

just a matrix multiplication and takes O(MN)

complex-ity Considering RP has computational advantages, we

argue that RP is especially suitable for our purpose

In the case of several sensor nodes attached on

vari-ous locations of the body for activity recognition, RP is

individually processed in a distributed fashion on each

sensor node On each node j, the original sampled

vec-tor vj2RN is projected to a low-dimensional vector

~

vj2RMby RP matrix Fj, they are

Each sensor sends the projection vector ~vjto the base

station

SRC with DRP

The base station collects J sensors’ vector ~v of RP For

each sensor j, we construct a new redundant dictionary

matrix ~V

~

For each sensor data, the sparse representation of aj

of ~vk, test satisfies the following linear system

~

vk, test= ~Vjaj+ e ð11Þ

where aj is a coefficient vector of the sensor j and e is the approximation error term modeling measurement errors

After projection, typically, the dimension N is much smaller than the number n of all training samples Therefore, the new linear system (11) is underdeter-mined, and the desired aj is the unique solution to the following optimization problem

^

After the sparsest representation aj is recovered, we project the coefficients onto each class subspaces Subsequently, the membership of the test sample vk,test

is assigned to the class with the smallest residual

ri(vk, test) = arg min

i

j = 1

~vk, test ~Vjdi(^aj)



2,

where di(^aj) =½0,    0, 1, 1    1

|fflfflfflffl{zfflfflfflffl}

i , 0,    0

Figure 1 Activity recognition system architecture Sensor placement on subject’s body (WS: waist; RW: right wrist; LW: left wrist; RL: right leg; LL: left leg).

The algorithm below summarizes the complete

rec-ognition procedure of sparse classification with RP

Experimental results

WARD dataset

In this work, we used a publicly available dataset called

wearable action recognition database (WARD), which

is provided by Yang et al.21 of the University of

California, Berkeley The data were recorded by five

sensor nodes, containing a three-axis accelerometer and

a two-axis gyroscope, which were attached to body

parts: one on the waist, two on the wrists, and two on

the ankles The dataset consists of data recorded from

20 participants with different gender, age, height, and

weight for 13 action categories: (1) stand (ST), (2) sit

(SI), (3) lie down (LI), (4) walk forward (WF), (5) walk

left-circle (WL), (6) walk right-circle (WR), (7) turn left

(TL), (8) turn right (TR), (9) go upstairs (UP), (10) go

downstairs (DO), (11) jog (JO), (12) jump (JU), and

(13) push wheelchair (PU) Each participant performs

five trials for each action In total, there are 1300

(20 3 13 3 5) activity sequences

Offline experiment

We first processed the WARD dataset offline in

MATLAB SGPL1(Spectral Projected Gradient for l1

-minimization) toolbox22 was used to solve the sparse

recovery problem in equation (12)

Experiment design Only minimal preprocessing for

med-ian filtering with a five-point moving average was

applied to the raw sampled data in order to remove

any abnormal noise spikes produced by the sensors

The training set and the test set were designed as

fol-lows For each motion sequence in the WARD

data-base, we randomly selected a window size of 40 samples

(h = 40) without overlapping, which corresponds to

2 s given the 20 Hz sampling rate The dimension of an

activity vector v of a sensor is 200 (2 s 3 20 Hz 3 5

values) In total, there were 1300 training examples

The 20-fold leave-one-subject-out-validation approach

was performed to obtain the subject-independent

classifi-cation results, where all the training examples from one

subject were withheld for testing and the rest of the

train-ing examples from the remaintrain-ing subjects were used for

training In our offline experiment, we considered four

types of random matrices: Gaussian, Bernoulli, very

sparse, and special sparse binary For each kind of

ran-dom matrix, the validation process was repeated 10

times; a group of RP matrices was generated randomly

every time Each group of RP matrices consists of five

random matrices Fj, each matrix corresponds to one

sensor node, respectively

Activity recognition performance To investigate the classifi-cation robustness of the proposed SRC-DRP algorithm for dimensionality reduction by RP, we selected five different compression ratios (CRs; 0, 0.3, 0.5, 0.7, and 0.9) CR is defined as (N-M)/N Table 1 gives the mean and standard deviation for activity-recognition accura-cies of the SRC-DRP approach under four types of RP random matrices with various CRs; the first column indicates the ratio of compression

First, we obtained an activity-recognition accuracy

of 90.23% when the SRC-DRP was applied to the raw data with no compression (CR = 0) From Table 1,

we calculated the one-way analysis of variance values among the average-recognition accuracies and standard deviation using four types of matrices at four different CRs (0.3, 0.5, 0.7, and 0.9) For example, for a CR of 0.5, the p-value equals 0.902, which is larger than 0.05 This means their difference is considered to be not sta-tistically significant We can get similar results for the other three CRs

We also compared the recognition performances of

RP with the conventional dimensionality reduction methods such as PCA, and then provided the results on the last column of Table 1 We show that RP yields results of activity-recognition accuracy comparable to PCA under the four types of RP random matrices with the same CR However, using RP is computationally and significantly less expensive than using PCA Moreover, it is interesting to see that the recognition accuracies under four kinds of random matrices are not statistically significant in their difference at the same

CR The special sparse binary matrix for RP is more suitable to be implemented on the sensor platforms because of the much lower computation costs with little loss in recognition accuracy We explored a very sparse

RP matrix to be implemented on the wireless wearable sensor platforms in our latter experiments

We further assessed the impact of varying data dimension on the computational costs of our method

Algorithm Sparse representation classification after distributed random projection (SRC-DRP).

1: Input: A set of stacked training samples

V = ½v 1, 1 , v 1, 2 , , v k, n k T, a test sample v k, test on a sensor node j, a random projection matrix F j , and an optional error tolerance e.0

2: Projection:

ev k, test = Fjvk, testeV j = FjVj 3: Normalize the columns of e Vjand ev k, test 4: Solve the problem:

ba j = arg min a j

1 subject to  ev k, test  e Vjaj

5: Compute the residuals

ri( ev k, test ) = arg min P J

j = 1  ev k, test  e Vjdi( ba j )

6: Output: label (vk, test) = arg min r i ( ev k, test )

We recorded the total time for classifying all the test

samples and then divided it by the number of samples,

hence obtaining the average computation time for each

test sample The PC we used has an Intel Pentium Dual

2.16 GHz CPU and 952 MB RAM It is validated that

dimensionality reduction also reduces the

computa-tional costs Figure 2 shows the computation time

against various CRs for classifying one test sample and

average recognition accuracy by SRC-DRP under very

sparse RP matrices

Online experiment

To characterize the real-time performance and the

energy consumption of the SRC-DRP method, online

experiments were performed on realistic sensor nodes

Sensor node platform The sensor node includes a TI

MSP430 microcontroller with 10 KB RAM, a Chipcon

CC2420 IEEE 802.15.4 compliant radio, and two AA

batteries The sensor board incorporates a three-axis

accelerometer and a two-axis gyroscope; each axis is

reported as a 12-bit value to a node Sensor nodes

com-municate with a base station attached to a PC through

a USB port Just like the WARD dataset, we also used

five sensors

Experiment design We chose the very special sparse bin-ary projection matrices (d = 10) for RP on the embedded platform and implemented RP onboard the node with embedded intelligence

Since our aim is to study the feasibility of RP on the embedded node platforms, instead of acquiring data from inertial sensors directly, we alternatively used the serial port to input the WARD database records sampled at 20 Hz and to output the inertial data RP was implemented on each sensor node every 2 s, and the inertial data were compressed to an active segment

of 200 dimensions (corresponding to a five-axis data with duration of 2 s at a sampling rate of 20 Hz) Then, the compressed data were transmitted using its IEEE 802.15.4-compliant radio to a base station Activity recognition for compressed samples was per-formed on a PC

Activity-recognition performance To further validate the performance of the SRC-DRP method, four common classifiers were chosen for comparison The classifiers were NN, nearest subspace (NS), Bayesian networks, and SVM The average recognition accuracies of subject-independent for four classifiers are given in Table 2 When considering the CRs as 0.3, 0.5, 0.7, and 0.9, we calculated the t-test values of the mean recogni-tion accuracies and standard deviarecogni-tion by comparing the SRC-DRP with other classifiers, respectively Take the CR of 0.5 as an example where the p-value between SRC-DRP and NS equals 0.0001 (p \ 0.05), indicating that their difference is considered to be extremely statis-tically significant We can get similar results with the other three CRs Table 3 shows that for the same CR, the SRC-DRP classifier achieves the highest average recognition rate than the other classifiers

Energy evaluation To measure the energy consumption

of a node, we obtained real-time data via inertial sen-sors The total energy consumption on sensor nodes consists of three main processes: (1) sensor sampling, (2) radio transmission, and (3) data processing The power consumption by sensor sampling depends on the

Table 1 Activity-recognition accuracies of the SRC-DRP approach.

SRC: sparse representation–based classification; DRP: distributed random projection; PCA: principal component analysis.

Figure 2 Average accuracies and processing time of SRC-DRP

under sparse binary random matrix.

types of the sensors and sampling frequency In

addi-tion, the energy consumption for storing data in the

local flash memory is relatively low Data processing is

sensitive to the complexity of the code execution on the

CPU

To evaluate the energy consumption of operation on

the sensor node, a 10.1-O resistor was placed in the

energy path of the platform The voltage was measured

by an oscilloscope, and the responding current and

energy consumption were calculated The sampling

rates for both accelerometer and gyroscope were set to

20 Hz The raw sensor data was logged to flash Figure

3 presents the power consumption of a node within an

operation period of 5 s; the CR is set to 0.5 Figure 3

shows the gyroscope sampling, and the continuously

transmitting raw accelerometer draws the most energy

Additionally, the power consumption by performing

RP on the sensor nodes is relatively inexpensive, and

the energy saved in terms of reduced flash logging and

data transmissions is more than compensating for the

energy cost of processing additional RP Compared with the case without compression, transmitting the compressed data by RP every 2 s reduced the energy consumption of transmission by 47%

Accordingly, Table 3 compares the energy consump-tion and the resulting node lifetime (calculated for two

3000 mAh batteries at 3.7 V) of the proposed approach for three different kinds of CRs For each node, the embedded RP code to compress an active sequence of

200 dimensions is executed in 26 ms (CR is 0.5) and

28 ms (CR is 0.7) The results show that data compres-sion by RP achieves the energy consumption reduction

of 18.7% and 26.1% with a node lifetime extension of 23.2% and 35.6.7%, for CR is 0.5 and 0.7, respectively, when compared with no compression used

We also found that the gyroscope sampling process consumes a large amount of energy Since the energy consumption of sampling depends on the hardware implementation and the sampling frequency, if the com-pressive sampling can be realized in sensor hardware, the energy consumption can be significantly reduced

Conclusion The aim of this article is to exploit the effectiveness of compressive classifiers in action recognition To our knowledge, it is the first study that explores both classi-fication and data compressing together in order to max-imize the deployment time of BSN for the continuous monitoring while maintaining sufficient classification accuracy An energy efficiency compressed classifica-tion approach for human activity recogniclassifica-tion is pro-posed Our approach uses RP to reduce the dimension

of sample data processed directly on the sensor node instead of transmitting raw sampled data to the base station

Recognition performance was validated on the WARD database and real nodes for offline and online experiments The recognition accuracy of our method only decreases slightly under RP We also measure the energy consumption of a node using RP It has been validated that the computation of light RP data com-pression only consumes a litter code execution time and

Table 3 Node lifetime with different compression radios.

Life time (h) (2 3

3000 mAh at 3.7 V)

Figure 3 Energy profile of the sensor platform for each

operation.

Table 2 Activity recognition accuracies of the four approaches.

Compression ratio Activity recognition accuracies (%) (mean 6 standard deviation)

SRC: sparse representation–based classification; DRP: distributed random projection; PCA: principal component analysis.

energy while reducing the amount of data to transmit,

as well as resulting in the limited lifetime extension,

compared with no data compression

Our ongoing work will be carried out both

theoreti-cally and practitheoreti-cally We are going to find the

analyti-cal relationship between the RIP constants and the

standard deviation of the results with the theory

devel-opment of CS This will give a solid foundation to

determine the number of projections required to get

robust activity recognition results We will also test the

proposed algorithms in a real-time experiment with a

large group of persons

Declaration of conflicting interests

The author(s) declared no potential conflicts of interest with

respect to the research, authorship, and/or publication of this

article.

Funding

The author(s) disclosed receipt of the following financial

sup-port for the research, authorship, and/or publication of this

article: This work was supported by the National Natural

Science Foundation of China (61300219).

References

1 Bulling A, Blanke U and Schiele B A tutorial on human

activity recognition using body-worn inertial sensors.

ACM Comput Surv 2014; 46(3): 1–33.

2 Rigas G, Tzallas AT, Tsipouras MG, et al Assessment

of tremor activity in the Parkinson’s disease using a set

of wearable sensors IEEE T Inf Technol B 2012; 16(3):

478–487.

3 Nam YY and Park JW Child activity recognition based

on cooperative fusion model of a triaxial accelerometer

and a barometric pressure sensor IEEE J Biomed Health

Inf 2013; 17(2): 420–426.

4 Grunerbl A, Muaremi A, Osmani V, et al

Smartphone-based recognition of state and state changes in bipolar

disorder patients IEEE J Biomed Health Inf 2015; 19(2):

140–148.

5 Donoho D Compressed sensing IEEE T Inform Theory

2006; 52(4): 1289–1306.

6 Dasgupta S Experiments with random projections In:

Proceedings of the 16th conference uncertainty in artificial

intelligence, San Francisco, CA, 30 June–3 July 2000,

pp.143–151 New York: ACM.

7 Cande´s E and Tao T Near-optimal signal recovery from

random projections: universal encoding strategies? IEEE

T Inform Theory 2006; 52(12): 5406–5425.

8 Davenport M, Duarte M, Wakin M, et al The smashed filter for compressive classification and target recogni-tion In: Proceedings of the SPIE symposium electron ima-ging: compute imaging, San Jose, CA, 16–20 January

2007, pp.326–330.

9 Preece SJ, Goulermas JY, Kenney LP, et al Activity identification using body-mounted sensors—a review of classification techniques Physiol Meas 2009; 30(4): R1–R33.

10 Wright J, Yang A, Ganesh A, et al Robust face recogni-tion via sparse representarecogni-tion IEEE T Pattern Anal 2009; 31(2): 210–227.

11 Yang A, Jafari R, Shankar S, et al Distributed recogni-tion of human acrecogni-tions using wearable morecogni-tion sensor net-works J Ambient Intell Smart Environ 2009; 1: 103–115.

12 Zhang M and Sawchuk AA Human daily activity recog-nition with spare representation using wearable sensors IEEE J Biomed Health Inf 2013; 17(3): 553–560.

13 Ghasemzadeh H and Jarari R Physical movement moni-toring using body sensor networks: a phonological approach to construct spatial decision trees IEEE T Industr Inform 2011; 7(1): 66–77.

14 Ghasemzadeh H, Loseu V and Jafari R Structural action recognition in body sensor networks: distributed classifi-cation based on string matching IEEE T Inf Technol Biomed 2010; 14(2): 425–435.

15 Wu CH and Tseng YC Data compression by temporal and spatial correlations in a body-area sensor network: a case study in pilates motion recognition IEEE T Mobile Comput 2011; 10(10): 1459–1472.

16 Au L, Bui A, Batalin M, et al CARER: efficient dynamic sensing for continuous activity monitoring In: Proceed-ings of the 33st annual international conference of the IEEE engineering in medicine and biology society, Boston,

MA, 30 August–3 September 2011 New York: IEEE.

17 Ghasemzadeh H, Guenterberg E and Jafari R Energy-efficient information driven coverage for physical move-ment monitoring in body sensor networks IEEE J Sel Area Comm 2009; 27(1): 58–69.

18 Lu Y and Do M Sampling signals from a union of sub-spaces IEEE Signal Proc Mag 2008; 25(2): 41–47.

19 Achlioptas D Database-friendly random projections: Johnson-Lindenstrauss with binary coins J Comput Syst Sci 2003; 66: 671–678.

20 Baraniuk R, Davenport M, Devore R, et al A simple proof of the restricted isometry property for random matrices Constr Approx 2008; 28(3): 253–263.

21 Yang A, Kuryloski P and Bajcsy R WARD: a wearable action recognition database, 2009, http://www.eecs.berke-ley.edu/;yang/software/WAR/

22 Berg E and Friedlander MP SPGL1: a solver for large-scale sparse reconstruction, 2007, http://www.cs.ubc.ca/ labs/scl/spgl1