Distributed mobile sensor
computing system called Cartel 5.
Collecting and process data will be send to portal
based upon the continuous queries which are processed by continuous query
processor on remote nodes and it’s include
a set of sensors installed in vehicles.
like GPS for monitoring the movements of vehicles.
CarTel includes, CafNet a networking stack that uses
opportunistic connection (e.g. Wi-Fi, Bluetooth) to transfer information
between portal and remote nodes.
currently does not offer a way to aggregate
information gathered across different users and it does not include machine
learning; it just replies to the queries based upon the data stored in
3-axis accelerometer and GPS mounted on the dashboard
to monitor road surface
Also differentiate potholes from other road anomalies.
collects the signals using accelerometer and use
machine-learning algorithms to identify potholes
signals are then passed through a series of signal
processing filters, where each filter is designed in such a way that it will
reject one or more non-pothole events (manholes, expansion joints, railroad crossing)
Collects the sensor data using three-axis
accelerometer and GPS
Sensor data has 4-tuples: current time, location,
velocity and three direction accelerations.
Cleaning the data before processing or analyzing it to
deal with technical challenges like GPS error, and transmission error
Analyses the Power Spectral Density (PSD) to detect
pavement roughness using Fourier transform.
The International Roughness Index (IRI) is calculated
based upon PSD. The pavement roughness is then classified in four levels
(excellent, good, qualified and unqualified) according to, the Technical Code
of Maintenance for Urban Road CJJ36-2006, one of the industry standards in
the People’s Republic of China.
The system provides the evaluation of a section of
road based upon its roughness. However, this system does not provide the
proper location of pothole, bump or manhole.