e to 
ore, 
ove 
or 
ing 
the 
r of 
hen 
heir 
‘the 
; of 
tion 
best 
| of 
ent 
the 
e of 
sure 
the 
the 
k is 
tion 
and 
tion 
ited 
the 
two 
tor. 
be 
1ing 
rom 
ver 
t is 
obal 
nes 
'st 
trian 
red: 
can 
rates 
ce’s 
used 
or 
d an 
/ far 
use 
other context information such as “user activity” have increased 
over the last few years (Baldauf et al., 2007). The primary 
contexts relevant to the navigation services in a mobile device 
can be divided into three categories: Environment, user, and 
device. As listed in table 1, Environment contexts include time 
and location of the user which are two fundamental dimensions 
of ubiquitous computation and have been discussed in various 
studies (Choujaa & Dulay, 2008). In contrast, detecting user’s 
activity is still an open topic in context-aware systems. User 
activity context refers to a sequence of motion patterns usually 
executed by a single person and at least lasting for a short 
duration of time, on the order of tens of seconds. In navigation 
services, another important issue is that “where the device is 
located with respect to the user”. In PNS, usually a mobile 
device can be carried out by the user in an arbitrary placement 
and orientation (e.g. in the pocket, in hand, on belt, in backpack, 
on vehicle's seat, etc.). 
Table 1. Contextual information coping with the proposed 
navigation systems 
  
  
  
  
  
  
  
  
  
  
Context type Context Values/samples 
: Time of the day/night, 
: Time Weekend/weekday, … 
Environment - 
Location Outdoor, Indoor, close by point 
of interests, ... 
Static, Walking, Running, Stair 
User Activity up-down, Elevator, Driving, 
Cycling, ... 
Orientation Horizontal/Vertical, F ace- 
up/down, Landscape/Portrait 
Dangling with hand swing, 
Texting (with one/two hand), In 
; placement | a pocket (pants, jacket), In hand 
Device bag, RIDE eK On belt, 
Talking (close to ear/speaker) 
Sensor Availability and Accuracy 
Network Availability 
Battery Power level 
  
  
  
  
The contexts that are useful for vision-aided system include: 
device orientation (e.g. face-up/down, vertical or portrait 
modes), device location (Texting with 1 hand or 2 hand mode) 
and activity of the user (e.g. walking mode). By texting we refer 
to the position of the user while texting and therefore it includes 
all similar positions such as surfing, playing, reading and etc. 
Texting mode requires the user to hold the device in front of 
himself using one or both hands. Since information gathered by 
a single sensor can be very limited and may not be fully reliable 
and accurate, in this research a new approach has been proposed 
based on the multi-sensor fusion to improve the accuracy and 
robustness of context aware system (Saeedi et al., 2011). 
3.1 Context Recognition Module 
Most of the current approaches for context recognition are data- 
driven (Yang, et al., 2010; Pei, et al., 2010). In this research we 
aim at integrating the data-driven paradigm with the knowledge- 
oriented paradigm to solve context detection problems 
considering expert's rules and other information sources. 
Activity recognition module follows a hierarchical approach 
(Avci, 2010) for fusing accelerometer and gyroscope sensors in 
feature level. As it is shown in figure 3, the raw data captured 
by sensors is pre-processed for calibration and noise reduction. 
Then, signal processing and statistical algorithm are used to 
derive an appropriate set of features from the measurements. 
The potential number of features that can be used is numerous; 
however, the used features need to be carefully selected to 
perform real-time and robust context recognition. After feature 
extraction, pattern recognition techniques can be used to 
classify the feature space. There is a wide variety of 
classification techniques and often selecting the best one 
depends on the application (Saeedi et al., 2011). 
   
   
Sensor 
Level 
    
        
    
     
Acc]. ; - 
RA d Entropy 
Activity 
Met Recognition. 
Feature Selection 
  
Other | 
Sensors | Energy 
    
F igure 3. Feature recognition module (Saeedi et al., 2011) 
Figure 4 presents an example of accelerometer sensors’ output 
in different placement scenarios after sensor calibration and 
low-pass filtering. Some modes are easy to identify, such as the 
dangling mode in which accelerometer has significantly large 
magnitude due to the arm swing. However, other modes are 
quite similar to each other and require pattern recognition 
algorithms for classification. 
Context (Activity) Recognition using accelerometer Signal 
:Où be! ace 
    
celerometer signal 
ac 
  
Time (sec) 
Figure 4. Tri-axial accelerometers output in different placement 
mode 
In this research the following features (table 2) has been used in 
time and frequency domains for context detection based on 
inertial data. 
Table 2. The useful time and frequency domain features for 
context detection 
  
  
  
  
  
Feature Space Description 
N 
Mean y= Yi) 
N=1 
5 N 
S o . 1 2 
E 2 Variance Var — G3 2,0 ES y) ) 2 
as — 
o 9 E 
B Inter-axis it has good results in detecting 
= Correlation device orientation and placement 
Zero or Mean useful for detecting device 
Crossing Ratio placement 
  
computes the power of the discrete 
  
  
8 Frequenc 
S 4 y Fourier Transform for a given 
E Range Power 
á 5 frequency band 
23 Spectral distinguish inactive activities from 
g S Energy dynamic activities 
= m Spectral a measure of the distribution of the 
e p frequency components in the 
m. Entropy 
  
  
  
  
frequency band 
  
In order to increase robustness of activity recognition and 
reduce computations, a k-NN based feature selection method is 
applied and a set of twelve features has been selected with the 
219