03-05-2013, 02:00 PM
Cell Phones Based Using Driving Safe
Cell Phones Based Using Driving.pdf (Size: 1.11 MB / Downloads: 29)
Abstract
No matter how many our elders told about the ill-effects of
using cell phones while driving. but how many of us have taken their
advices seriously.well we think not even thirty percent isn’t it? but
whether we like it or not, it is one of the major reasons for number of
accidents that are happening now adyas.even doctors is as fatal as
driving our car after drinking our drinking. it can lead to various
disastrous major miss-happenings. mobile smartphones today are
equipped with numerous sensors that can help to aid in safety
enhancements for drivers on the road. In this paper, we use the three-axis
accelerometer of an Android-based smartphone to record and analyze
various driver behaviors and external road conditions that could
potentially be hazardous to the health of the driver, the neighboring
public, and the automobile.
INTRODUCTION
certainly there has been large number of figures that shows that people
have used their mobile phones just before their accidents . studies have
shown that if people reduce their usage of cell phone while driving, it can
cut off the accident rates too. we are focused on arriving at our
destination as quickly as possible. However, with this lifestyle, we are
not always aware of all the dangerous conditions that are experi-enced
while operating an automobile. Factors such as sudden vehicle
maneuvers and hazardous road conditions, which often contribute to
accidents, are not always apparent to the person behind the wheel. In
recent years, there has been tremendous growth in smartphones
embedded with numerous sensors such as accelerometers, Global Positioning
Systems (GPSs), magnetometers, multiple microphones, and
even cameras [1]–[3]. The scope of sensor networks has expanded into
many application domains such as intelligent transportation systems that
can provide users with new functionalities previously unheard of [4].
Experimental automobiles in the past have included certain sensors to
record data preceding test crashes [5], [6].
RELATED WORK
Analysis of external sensors data for vehicle performance is a large
area of study. Some work has been done in the form of theoretical
research and development in a practical design. The main ideas of
our work focus on mapping anomalies of a road’s surface and
classifying different driving behaviors.
There has been some work in the field of road analysis, specifically
road anomaly detection. Nericell [1] is a system researched and developed
by Microsoft that detects traffic honking, bumps, and vehicle
braking using external sensors. For detection, it uses multiple external
sensors such as a microphone, GPS, accelerometer, and Global System
for Mobile communications radio for traffic localization. Pothole Patrol
[15] is another system that monitors road conditions using GPS and an
external accelerometer. The system was deployed for testing in taxis
using a convenient method to identify fatigued surfaces of a road.
Tracking and analyzing driving behavior is an ongoing ITS study.
University of California Berkeley’s Mobile Millennium project is a
traffic-monitoring system that uses GPS data to obtain individual
vehicle location information.
Phone Orientation and Location
The orientation of the phone is a variable that may be constantly
changing with the movement of the vehicle, and so might be arbitrarily
placed inside the vehicle when the driver enters. The phone’s
orientation for each experiment remained the same, with the y-axis
pointing toward the front of the vehicle and the screen (z-axis) facing
the roof. A holster that was provided with the phone was used along
with velcro to secure the phone to the vehicle’s surface. To obtain
appropriate data, the phone was tested in multiple locations for each
experiment before a final decision was declared. These locations are
shown in Fig. 3(b) as locations 1–5. The specific surface used was
dependent on which experiment was being performed. For the road
condition analysis, it was firmly secured to the floorboard of the
front passenger section shown in Fig. 3(a). For analyzing driver
behavior, the phone was fastened on the center console, i.e., loc. 1 in
Fig. 3(b). The driving behavior experiments each had a time duration
of less than 2 min, which incorporated multiple maneuvers, whereas
road condition measurements varied, lasting for the length of the
road being measured.
CONCLUSION
Our road classification system resulted in high accuracy, making it
possible to conclude on the state of a particular road. Along with these
findings, an analysis of a driver behavior for safe and sudden maneuvers,
such as vehicle accelerations and lane changes, has been identified,
which can advise drivers who are unaware of the risks they are
potentially creating for themselves and neighboring vehicles. The
direction of lane change, as well as safe acceleration, compared with
sudden accelera-tion, was easily distinguishable. Using a multiple-axis
classification method for bumps increased the bump and pothole
classification accu-racy, resulting in a better road anomaly detection
system. Being fueled by demand, future advancements in embedded
hardware will yield the smartphone and its sensors to be more powerful
devices in terms of processing, sensitivity, and accuracy, paving the way
for many more in-novative applications.