SlideShare a Scribd company logo
1 of 5
Download to read offline
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1015
Analysis of Obstacle Detection Using Ultrasonic Sensor
Christofer N. Yalung1, Cid Mathew S. Adolfo2
1Military Technological College, Muscat, Oman
2Military Technological College, Muscat, Oman
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract – Automation of the car braking system is an
important feature in the development of the smart car. The
ability of a smart car to detect and classify an obstructionthat
is in varying proximities from it play a vital roleinthesystem’s
design. In this study, EV3 Lego Mindstorm equipped with an
ultrasonic sensor was used as a model of a large scale vehicle.
EV3 Lego MIndstorm was programmed to slow down when it
is at a certain distance from the obstruction, and to stop when
it is 15 cm away from the obstruction. There were five
obstructions: wood, paper, cloth, plastic and metal.
The distance measurement of the ultrasonic sensor and the
Neural Network was used for the classification of the
obstruction and Multiple Correlation was used for obstacle
detection. There were 250 samples taken from the distance
measurements of five different types of obstruction, each with
a different cross sectional area, and a total recording timeof8
seconds. Overall, there is a high correlation coefficient in the
distance measurement of the different types of obstruction
materials. It is concluded that the ultrasonic sensor was able
to detect the five given types of obstruction. Classification
performance was very poor, which means that on the basis of
distance measurement, theultrasonicsensorcannot effectively
classify the types of obstructions.
Key Words: Ultrasonic Sensor, Obstacle detection,
Artificial neural network, Distance measurement
1.INTRODUCTION
Nowadays, automation in technology is widespread, this
can be seen on doors, electronic devices, cars and in
various industrial applications. This is made possible by
sensing devices, which serve as a medium between the
machine and the environment. Ultrasonic sensor is an
incredibly useful sensor in the field of automation. For
example, a mobile robot receives environmental
information, converts it into a signal and performs this
signalled task like avoiding obstacles (In this sentence you
should mention specifically the function of the ultrasonic
sensor). This particular type of sensor produces
satisfactory results and is cost effective. The algorithm for
distance calculation is based on the measurement of the
time of flight of the ultrasonic waves. The distance
between two objects can be measured using the ultrasonic
sensor. The technique of distance measurement is based
on the measurement of the elapsed time between the
emission of the wave and the reception of the echo. The
propagation of the ultrasonic wave is done at the sound
speed in the air (340 m/sec). A typical ultrasonic distance
sensor consists of two main elements. One element
produces sound, another catches reflected echo. Basically,
these pieces are a speaker and a microphone. The device
generates ultrasonic impulses and triggers the timer. The
other element registers the arrival of the sound impulse
and stops the timer. From this information it is possible to
calculate the distance travelled by the sound. It is usually
not difficult to select a sensor that suits the environmental
and mechanical requirements of a particular application,
or to evaluate the electronic features available with
different models. Still, many users may not be aware of the
acoustic subtleties that can have major effects on the
operation of the ultrasonic sensor and the measurements
being made with them [1]. The basic principle of sound
propagation, the effect of a wave when it strikes a solid
object and the reception of the reflected sound waves are
illustrated in Fig-1[2].
Fig-1: Ultrasonic sensor operations
The velocity of the sound in air is given by the equation
(1), this is used to calculate the speed of the sound in air.
The distance that sound travels is equal to the speed of
sound in the medium multiplied by the time that sound
travels[2].
(1)
The impulse width is proportional to the time required for
the echo return. This time is called time-of-flight (TOF) [3].
But there are other factors which may also affect the
propagation of sounds such as: ambient pressure, gas
density and humidity [4].
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1016
1.1 Trends of Ultrasonic Sensor
A research was conducted for the performance evaluation
of NXT ultrasonic sensor and Parallax Ping sensor for
distance measurement. An efficient method based on
piecewise linear regression was proposed to improve the
NXT ultrasonic sensor’s accuracy of distance measurement.
The emitter transmits a burst of ultrasound (inaudible
sounds) to the obstacle positioned in front ofthesensor.The
object reflects back to sensor receiver the signal and when
the echo is received the sensor generates an impulse [5].
Two ultrasonic sensors were used to achieve object
classification [6]. To complete this task, the authors have
proposed a fuzzy expert system having a dual knowledge
base - one statistical and the othera standardrule basedone.
Using this technique, they extracted and used 25 features
including parameters like beginning time, mass center, etc.
The task of outlier detection or novelty detection was
implemented using Support Vector Machine (SVM), this
contributed towards object classification. Human detection
is vital to many applications, for example, human-robot
interaction,unattendedgroundsensorsystems,smartrooms
[7].
The application of a one-class classifier using solely
ultrasonic sensors was trialed for human detection. This
approach was based on fuzzy rules that are extracted from
the signal features in time and frequency domains [8]. A
prototype of a mobile robot suitable for mapping was
presented. It used an ultrasonic sensor HC-SR04, which is a
cheap alternative for sensor mapping instead of an
expensive laser sensor. The hardware was based on ROMEO
BLE mainboard. The Software consisted of two parts:
firmware and application.Thefirmwarepart wasanArduino
source code project, written in C++ programming language,
which was deployed on the robot [9].
The method based on puddle detecting ability was
proposed, and the evaluation of the improved method had
been implemented according to experiment results. The
proposed method can be applied in support systems on
wheel chairs and white canes for improving safety. In this
research, the road surface condition distinction method was
developed considering the puddle condition. The four kinds
of road surface conditions were investigated. The
effectiveness of the proposed method was verified in all the
four conditions [10].
Infusing ultrasonic sensor data and multiple ultrasonic
sensor data while a mobile robot moves were proposed in
[11]. Another research was developed for improving a grid
map of the environment by triangulating multiple ultrasonic
sensor data [12]. Related study of using three sensors to
distinguish the plan from the corner and then build a map of
this environment were carried in[13].Neuralnetworkswere
applied to differentiate between different formsofobstacles:
plane, corner, edges,and cylindricalshapes[14]. Moreover,a
sensing method that classified the targetsurfaceasaplaneor
a cylinder, with a sensing system consisting of 4 sets of
ultrasonic aligned sensors were proposed in [15].
1.2 Aims and Significant of the Study
This study is aimed to obtain the distancemeasurementof
a moving vehicle with respect to the presence of five
different types of obstruction and in addition to this, to
perform a speed reduction at a specified distance from the
obstacle and to be able to fully stop the vehicle at a specific
distance. Moreover, the study seek to find the significance
and impact of the materials used in correlation with the
ability of the ultrasonicsensortomeasuredistanceprecisely.
Furthermore, Neural Network is implementedto classifythe
different types of obstacles based on the measured distance
over time, there were five materials to be classified namely:
wood, paper, cloth, plastic and metal. This study could
benefit the automotive industrybyapplyingsmartalgorithm
for obstacle detection, precise detection of an object. Road
safety could be improved by smart vehicle, through the
advanced processes of anautomaticbrakesystemappliedon
the vehicle.
2. Data Acquisition and Analysis
The data acquisition, process and output of the study are
shown in Fig-1, necessary equipment and procedures are
included.
Fig-2: Methodology of the study
To model an actual vehicle, a Lego Mindstorm EV3wasused,
it is equipped with an ultrasonic sensor. A program could be
downloaded with its processor. Fig-3a and Fig-3b show the
Lego Mindstorm EV3 and ultrasonic sensor.
DATA ACQUISITION
 EV3 ultrasonic
sensor
 Distance
measurement
 Five different types
of materials
PROCESS
 Forward motion
of the vehicle
 Transmit and
Receive of the
ultrasonic sound
wave
OUTPUT
 Distance measured
over time
 Reduce Vehicle
speed
 Obstacle detection
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1017
Fig-4 shows the program installed in the processor of the
vehicle, it is designed to run the two motors labeled A and B,
and reduce the speed of the model at a certain distance from
the obstacle. Finally, it must stop when it reaches the
distance of 15 cm from the obstruction. Also, data logging is
added in the program, so that data in terms of time and
distance could be acquired. The sampling rate per second
was set to 5, and data logging was set up to 8 seconds
In order to start the data recording, the vehicle is placed at
about 80 cm away from the obstacle. Then it traveled in a
straight path going to the obstruction. The five different
types of obstructions used were wood, laminated paper,
cloth, plastic, and metal, with the following area in square
centimeter: 375, 300, 2025, 840, 840, respectively.
To see the consistency of the result per each type of
obstruction, two trials of data collected.
Fig-3a: Lego Mindstorm
EV3
Fig-3b: EV3 ultrasonic sensor
Fig-4: Lego Mindstorm program
Data analysis among types of materials wasperformedusing
Multiple Correlation. Artificial Neural Network iscarried out
to determine the classification of the obstruction.
3. Data and Results
The information provided in Chart-1 shows the distance of
the vehicle from the obstruction. There are four obstruction
namely: wood, paper, cloth,plasticandmetal,differentcolors
were used to represent them in the chart. The initial distance
of the vehicle from the obstruction is about80cm.Asthetime
increases, the distance measured is supposed to decrease
because the vehicle is getting closer to the obstacle. Four of
the obstructions namely: wood, paper, glass and metal
displayed a common pattern. The measured distance is
erroneous for the rippled cloth, the sound waves was not
reflected efficiently, in returnthe vehiclefailedtoexecutethe
condition designed in the program. However, based on our
observation, when the cloth is perfectly flattened, thevehicle
was able to follow the specified program. Finally, for the
wood, paper, plastic and metal, there was a consistency of
the distance measured especially after four seconds and
onwards.
Chart-1: Distance of the vehicle from the obstruction
The information provided in Table-1showsapositiveperfect
positive correlation coefficient among the wood, paper,
plastic and metal. This means that ultrasonic sensor used in
this experiment resulted to the same pattern of distance
measurement and obtained approximately the same
measured value. This result is with exemption to the rippled
cloth which resulted in an almost low negative correlation
when compared to the above mentioned materials. This
signifies that there was a failure of the cloth to reflect sound
waves. On the other hand, the ultrasonic sensor was able to
detect the presence of the rippled cloth at a certain time, but
after about 3 seconds there was an error to the measured
distance.
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1018
Table-1 Multiple Correlation among five types of materials
wood paper cloth plastic Metal
wood 1.00
paper 1.00 1.00
cloth -0.48 -0.45 1.00
plastic 1.00 1.00 -0.46 1.00
metal 1.00 1.00 -0.47 1.00 1.00
Furthermore, to determine the consistency of the gathered
data, two trials were performed for each type of material, all
showed a perfect positive correlation, except for the cloth.
3.1 Neural Network Classification
Machine learning was used to classify the data into five
categories such as wood, paper, cloth, plastic and metal.
There were 205 samples taken from five different types of
obstructions, and 8 seconds of data logging. The neural
network architecture is shown in Fig-5, there were ten
hidden layer. The samplesweredividedintoTraining(75%),
Validation (15%) and Testing (15%). Majority of the data
was presented to the network during training, and the
network was adjusted based on its error. The function of
Validation is to stop the training when generalization stops
improving. Testing is an independent measure of network
performance.
Fig-5: Neural network architecture
Classification was performed using two different
network architecture, Fig-6showstheresultofclassification
at 10 hidden neurons and Fig-7 shows the result at 20
hidden neurons. Cross Entropy (CE) shows the result in
classification, having zero value means no error. Percent
Error (%E) indicates the fraction which are misclassified,
zero means no misclassification and 100 means maximum
misclassifications.
The results shows, there is approximately equal %E for
the two different artificial network architectures having,
69.9% and 69.23% for the 10 and 20 hidden neurons
respectively. The cross entropy during the training resulted
to 0.74487 and .792481 for the 10 and 20 hidden neurons
respectively. There was a very minimal improvement onthe
performance of the neural network architecturebydoubling
the number of hidden layers based on the given data.
Furthermore, it can be observed that classification was not
good as indicated by the higher value of Cross Entropy on
training, validation and testing. Therefore, the method of
distance measurement for the classification of the types of
obstruction using ultrasonic sensor executed poor results.
Fig-6: Neural network results at 10 hidden neurons
Fig-7: Neural Network results at 20 hidden neurons
4. CONCLUSIONS
In this study, the data were acquired using EV3 Lego
Mindstorm, ultrasonic sensor, different types of materials
and software programming. The analysis and interpretation
of the data were carried out using Multiple Correlation and
Neural Network. The vehicle was programmed to move
slowly as it approached near the obstruction, and stopped
when reached the distance of 15 cm.Therewerefivetypes of
obstruction namely: wood, paper, plastic and metal. Overall,
wood, paper, glass and metal displayed a common pattern
based on the measured distance, there was erroneousresult
for the rippled cloth.
The neural network classification shows poor performance
based on the gathered data. The percent error (%E)
recorded for 10 and 20 hidden neurons where 69.9% and
69.23% respectively. This means that classification of the
types of obstruction was not efficient by distance
measurement between the vehicle and theobstructionusing
the ultrasonic sensor. There is a positive perfect positive
correlation coefficient among the wood, paper, plastic and
metal. This means that ultrasonic sensor used in this
experiment perform the same pattern of distance
measurement given these materials. However, for the
rippled cloth, results showed an almost low negative
correlation when compared to the above mentioned
materials.
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1019
REFERENCES
[1] D. Masa, “Choosing an Ultrasonic Sensor for Proximity or
Distance Measurement Part 1: Acoustic Considerations”,
Feb. 1, 1997.
[Online]. http://www.sensorsmag.com/sensors/acoustic-
ultrasound/choosing-ultrasonic-sensor-proximity-or-
distance-measurement-825
Hands-on Activity: Measuring Distance with Sound Waves,
AMPS GK-12 Program, Polytechnic Institute of New York
University.
[Online].https://www.teachengineering.org/activities/v
iew/nyu_soundwaves_activity1
[2] D. Marioli, C. Narduzzi, C. Offelli, D. Petri, E. Sardini and
A. Taroni,“Digital time-of-flight measurement for
ultrasonic sensors,” IEEE Transaction on
Instrumentation and Measurement, vol. 41, pp. 93–97,
1992
[3] D. A. Bohn, “Environmental effects on the speed of
sound,” Journal ofAudio Engineering Society,vol.36,No.
4, April, 1988
[4] G. Găşpăresc andA.Gontean, "Performanceevaluationof
ultrasonic sensors accuracy in distance measurement,"
2014 11th International Symposium on Electronics and
Telecommunications (ISETC), Timisoara, 2014, pp. 1-4.
doi: 10.1109/ISETC.2014.7010761
[5] J.R. Llata, E.G. Sarabia, J.P. Oria," Fuzzy expert system
with doubleknowledge base for ultrasonic
classification," Expert Systems with
Applications 20 (2001) 347-355.
[6] Duin, Robert PW, et al. "Feature-based dissimilarity
space classification."Recognizing Patterns in Signals,
Speech, Images and Videos. Springer Berlin Heidelberg,
2010. 46-55
[7] Sonia, A. M. Tripathi, R. D. Baruah and S. B. Nair,
"Ultrasonic sensor-based human detector using one-
class classifiers," 2015IEEEInternational Conferenceon
Evolving and AdaptiveIntelligentSystems(EAIS),Douai,
2015, pp. 1-6.
doi: 10.1109/EAIS.2015.7368797
[8] A. Dimitrov and D. Minchev, "Ultrasonic sensor
explorer," 2016 19th International Symposium on
Electrical ApparatusandTechnologies(SIELA),Bourgas,
2016, pp. 1-5.
doi: 10.1109/SIELA.2016.7542987
S. Nakashima, S. Aramaki, Y. Kitazono, S. Mu, K. Tanaka
and S. Serikawa, "Road Surface Condition Distinction
Method Using Reflection Intensities Obtained by
Ultrasonic Sensor," 2016 International Symposium on
Computer, ConsumerandControl (IS3C),Xi'an,2016,pp.
120-123. doi: 10.1109/IS3C.2016.41
[9] H. Choset, K. Nagatani, and N. Lazar: “The Arc-
Transversal Median Algorithm: A Geometric Approach
to IncreasingUltrasonic SensorAzimuthAccuracy”,IEEE
Trans. on Robotics and Automation, Vol.19, No.3, pp.
513-523, 2003.
[10] O. Wijk, P. Jensfelt, and H. Christensen: “Triangulation
Based Fusion of Ultrasonic Sensor Data”, IEEE Proc, Int,
Conf. on Robotics andAutomation,pp.3419-3424,1998.
[11] Joen, H. J and B.K.Kim: “A study on world map building
for mobile robots with trial-aural ultrasonic sensor
system”,
IEEE Int, Conf. Robot.Autom, pp 2907- 2912, 1995.
[12] Barshan, B., B. Ayrulu, and S. W. Utete: “Neural
network-based target differentiation using sonar for
robotics applications”, IEEE Trans. Robot. Autom., Vol.
16, pp.435-442, 2000.
[13] I. Maâlej, M. Ouali and N. Derbel, "Modular ultrasonic
sensor platform for mobile robot," 2012 First
International Conference on Renewable Energies and
Vehicular Technology, Hammamet, 2012, pp. 477-483.
doi: 10.1109/REVET.2012.6195316
[14] R. A. Dimitrov and D. Minchev, "Ultrasonic sensor
explorer," 2016 19th International Symposium on
Electrical ApparatusandTechnologies(SIELA),Bourgas,
2016, pp. 1-5.
doi: 10.1109/SIELA.2016.7542987 Nicole, “Title of
paper with only first word capitalized,” J. Name Stand.
Abbrev., in press.

More Related Content

What's hot

Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...
Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...
Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...iosrjce
 
Detection air pollution based on infrared image processing
Detection air pollution based on infrared image processingDetection air pollution based on infrared image processing
Detection air pollution based on infrared image processingTELKOMNIKA JOURNAL
 
Video based smoke detection algorithms
Video based smoke detection algorithmsVideo based smoke detection algorithms
Video based smoke detection algorithmsAlexander Decker
 
HYPERSPECTRAL IMAGERY CLASSIFICATION USING TECHNOLOGIES OF COMPUTATIONAL INTE...
HYPERSPECTRAL IMAGERY CLASSIFICATION USING TECHNOLOGIES OF COMPUTATIONAL INTE...HYPERSPECTRAL IMAGERY CLASSIFICATION USING TECHNOLOGIES OF COMPUTATIONAL INTE...
HYPERSPECTRAL IMAGERY CLASSIFICATION USING TECHNOLOGIES OF COMPUTATIONAL INTE...IAEME Publication
 
A Survey on Ultrasound Beamforming Strategies
A Survey on Ultrasound Beamforming StrategiesA Survey on Ultrasound Beamforming Strategies
A Survey on Ultrasound Beamforming StrategiesIRJET Journal
 
STAGES OF REMOTE SENSING.
STAGES OF REMOTE SENSING.STAGES OF REMOTE SENSING.
STAGES OF REMOTE SENSING.SrimantaKarak
 
Displacement mechanical amplifiers designed on poly-silicon
Displacement mechanical amplifiers designed on poly-siliconDisplacement mechanical amplifiers designed on poly-silicon
Displacement mechanical amplifiers designed on poly-siliconIJECEIAES
 
Subspace_Discriminant_Approach_Hyperspectral.ppt
Subspace_Discriminant_Approach_Hyperspectral.pptSubspace_Discriminant_Approach_Hyperspectral.ppt
Subspace_Discriminant_Approach_Hyperspectral.pptgrssieee
 
A Novel Approach for Precise Motion Artefact Detection in Photoplethysmograph...
A Novel Approach for Precise Motion Artefact Detection in Photoplethysmograph...A Novel Approach for Precise Motion Artefact Detection in Photoplethysmograph...
A Novel Approach for Precise Motion Artefact Detection in Photoplethysmograph...AM Publications
 
Toward intelligent health monitoring system for space missions
Toward intelligent health monitoring system for space missionsToward intelligent health monitoring system for space missions
Toward intelligent health monitoring system for space missionsAboul Ella Hassanien
 
Accuracy Improvement of PM Measuring Instruments
Accuracy Improvement of PM Measuring InstrumentsAccuracy Improvement of PM Measuring Instruments
Accuracy Improvement of PM Measuring Instrumentsijtsrd
 
Indoor localisation and dead reckoning using Sensor Tag™ BLE.
Indoor localisation and dead reckoning using Sensor Tag™ BLE.Indoor localisation and dead reckoning using Sensor Tag™ BLE.
Indoor localisation and dead reckoning using Sensor Tag™ BLE.Abhishek Madav
 
LOCALIZATION ALGORITHM USING VARYING SPEED MOBILE SINK FOR WIRELESS SENSOR NE...
LOCALIZATION ALGORITHM USING VARYING SPEED MOBILE SINK FOR WIRELESS SENSOR NE...LOCALIZATION ALGORITHM USING VARYING SPEED MOBILE SINK FOR WIRELESS SENSOR NE...
LOCALIZATION ALGORITHM USING VARYING SPEED MOBILE SINK FOR WIRELESS SENSOR NE...ijasuc
 
Multisensor data fusion for defense application
Multisensor data fusion for defense applicationMultisensor data fusion for defense application
Multisensor data fusion for defense applicationSayed Abulhasan Quadri
 
Directional Analysis and Filtering for Dust Storm detection in NOAA-AVHRR Ima...
Directional Analysis and Filtering for Dust Storm detection in NOAA-AVHRR Ima...Directional Analysis and Filtering for Dust Storm detection in NOAA-AVHRR Ima...
Directional Analysis and Filtering for Dust Storm detection in NOAA-AVHRR Ima...Pioneer Natural Resources
 
Algorithm performance comparison for earthquake signal recognition on smartph...
Algorithm performance comparison for earthquake signal recognition on smartph...Algorithm performance comparison for earthquake signal recognition on smartph...
Algorithm performance comparison for earthquake signal recognition on smartph...TELKOMNIKA JOURNAL
 
LANDSLIDE EARLY WARNING SYSTEM
LANDSLIDE EARLY WARNING SYSTEMLANDSLIDE EARLY WARNING SYSTEM
LANDSLIDE EARLY WARNING SYSTEMvivatechijri
 
14 A Profibus-based Control System for Nuclear Physics Applications - The 6th...
14 A Profibus-based Control System for Nuclear Physics Applications - The 6th...14 A Profibus-based Control System for Nuclear Physics Applications - The 6th...
14 A Profibus-based Control System for Nuclear Physics Applications - The 6th...Cristian Randieri PhD
 
Sensors multi fault detection
Sensors multi fault detectionSensors multi fault detection
Sensors multi fault detectionSidra Khanam
 

What's hot (19)

Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...
Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...
Ion Beam Analytical Technique PIXE for Pollution Study at Dhaka Van de Graaff...
 
Detection air pollution based on infrared image processing
Detection air pollution based on infrared image processingDetection air pollution based on infrared image processing
Detection air pollution based on infrared image processing
 
Video based smoke detection algorithms
Video based smoke detection algorithmsVideo based smoke detection algorithms
Video based smoke detection algorithms
 
HYPERSPECTRAL IMAGERY CLASSIFICATION USING TECHNOLOGIES OF COMPUTATIONAL INTE...
HYPERSPECTRAL IMAGERY CLASSIFICATION USING TECHNOLOGIES OF COMPUTATIONAL INTE...HYPERSPECTRAL IMAGERY CLASSIFICATION USING TECHNOLOGIES OF COMPUTATIONAL INTE...
HYPERSPECTRAL IMAGERY CLASSIFICATION USING TECHNOLOGIES OF COMPUTATIONAL INTE...
 
A Survey on Ultrasound Beamforming Strategies
A Survey on Ultrasound Beamforming StrategiesA Survey on Ultrasound Beamforming Strategies
A Survey on Ultrasound Beamforming Strategies
 
STAGES OF REMOTE SENSING.
STAGES OF REMOTE SENSING.STAGES OF REMOTE SENSING.
STAGES OF REMOTE SENSING.
 
Displacement mechanical amplifiers designed on poly-silicon
Displacement mechanical amplifiers designed on poly-siliconDisplacement mechanical amplifiers designed on poly-silicon
Displacement mechanical amplifiers designed on poly-silicon
 
Subspace_Discriminant_Approach_Hyperspectral.ppt
Subspace_Discriminant_Approach_Hyperspectral.pptSubspace_Discriminant_Approach_Hyperspectral.ppt
Subspace_Discriminant_Approach_Hyperspectral.ppt
 
A Novel Approach for Precise Motion Artefact Detection in Photoplethysmograph...
A Novel Approach for Precise Motion Artefact Detection in Photoplethysmograph...A Novel Approach for Precise Motion Artefact Detection in Photoplethysmograph...
A Novel Approach for Precise Motion Artefact Detection in Photoplethysmograph...
 
Toward intelligent health monitoring system for space missions
Toward intelligent health monitoring system for space missionsToward intelligent health monitoring system for space missions
Toward intelligent health monitoring system for space missions
 
Accuracy Improvement of PM Measuring Instruments
Accuracy Improvement of PM Measuring InstrumentsAccuracy Improvement of PM Measuring Instruments
Accuracy Improvement of PM Measuring Instruments
 
Indoor localisation and dead reckoning using Sensor Tag™ BLE.
Indoor localisation and dead reckoning using Sensor Tag™ BLE.Indoor localisation and dead reckoning using Sensor Tag™ BLE.
Indoor localisation and dead reckoning using Sensor Tag™ BLE.
 
LOCALIZATION ALGORITHM USING VARYING SPEED MOBILE SINK FOR WIRELESS SENSOR NE...
LOCALIZATION ALGORITHM USING VARYING SPEED MOBILE SINK FOR WIRELESS SENSOR NE...LOCALIZATION ALGORITHM USING VARYING SPEED MOBILE SINK FOR WIRELESS SENSOR NE...
LOCALIZATION ALGORITHM USING VARYING SPEED MOBILE SINK FOR WIRELESS SENSOR NE...
 
Multisensor data fusion for defense application
Multisensor data fusion for defense applicationMultisensor data fusion for defense application
Multisensor data fusion for defense application
 
Directional Analysis and Filtering for Dust Storm detection in NOAA-AVHRR Ima...
Directional Analysis and Filtering for Dust Storm detection in NOAA-AVHRR Ima...Directional Analysis and Filtering for Dust Storm detection in NOAA-AVHRR Ima...
Directional Analysis and Filtering for Dust Storm detection in NOAA-AVHRR Ima...
 
Algorithm performance comparison for earthquake signal recognition on smartph...
Algorithm performance comparison for earthquake signal recognition on smartph...Algorithm performance comparison for earthquake signal recognition on smartph...
Algorithm performance comparison for earthquake signal recognition on smartph...
 
LANDSLIDE EARLY WARNING SYSTEM
LANDSLIDE EARLY WARNING SYSTEMLANDSLIDE EARLY WARNING SYSTEM
LANDSLIDE EARLY WARNING SYSTEM
 
14 A Profibus-based Control System for Nuclear Physics Applications - The 6th...
14 A Profibus-based Control System for Nuclear Physics Applications - The 6th...14 A Profibus-based Control System for Nuclear Physics Applications - The 6th...
14 A Profibus-based Control System for Nuclear Physics Applications - The 6th...
 
Sensors multi fault detection
Sensors multi fault detectionSensors multi fault detection
Sensors multi fault detection
 

Similar to Analysis of Obstacle Detection Using Ultrasonic Sensor

A Comparative Study of Sensors for Road Traffic Density Measurement
A Comparative Study of Sensors for Road Traffic Density MeasurementA Comparative Study of Sensors for Road Traffic Density Measurement
A Comparative Study of Sensors for Road Traffic Density MeasurementIJSRD
 
Research on Car Reversing Radar System Based on Ultrasonic
Research on Car Reversing Radar System Based on UltrasonicResearch on Car Reversing Radar System Based on Ultrasonic
Research on Car Reversing Radar System Based on UltrasonicEngineering Publication House
 
Ultra sonic range finding for distance measuring in coal mining
Ultra sonic range finding for distance measuring in coal miningUltra sonic range finding for distance measuring in coal mining
Ultra sonic range finding for distance measuring in coal miningeSAT Journals
 
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...IJMERJOURNAL
 
Intelligent travelling and home automation aid, for visually impaired
Intelligent travelling and home  automation aid, for visually impairedIntelligent travelling and home  automation aid, for visually impaired
Intelligent travelling and home automation aid, for visually impairedUmar Shuaib
 
Design and development of intelligent electronics travelling aid for visually...
Design and development of intelligent electronics travelling aid for visually...Design and development of intelligent electronics travelling aid for visually...
Design and development of intelligent electronics travelling aid for visually...eSAT Journals
 
Smoke detection in video for early warning using
Smoke detection in video for early warning usingSmoke detection in video for early warning using
Smoke detection in video for early warning usingeSAT Publishing House
 
Smoke detection in video for early warning using static and dynamic features
Smoke detection in video for early warning using static and dynamic featuresSmoke detection in video for early warning using static and dynamic features
Smoke detection in video for early warning using static and dynamic featureseSAT Journals
 
National Highway Alignment from Namakkal to Erode Using GIS
National Highway Alignment from Namakkal to Erode Using GISNational Highway Alignment from Namakkal to Erode Using GIS
National Highway Alignment from Namakkal to Erode Using GISIJERA Editor
 
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATAA DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATAgerogepatton
 
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATAA DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATAijaia
 
Granular Mobility-Factor Analysis Framework for enrichingOccupancy Sensing wi...
Granular Mobility-Factor Analysis Framework for enrichingOccupancy Sensing wi...Granular Mobility-Factor Analysis Framework for enrichingOccupancy Sensing wi...
Granular Mobility-Factor Analysis Framework for enrichingOccupancy Sensing wi...IJECEIAES
 
Conditioning Monitoring of Gearbox Using Different Methods: A Review
Conditioning Monitoring of Gearbox Using Different Methods: A ReviewConditioning Monitoring of Gearbox Using Different Methods: A Review
Conditioning Monitoring of Gearbox Using Different Methods: A ReviewIJMER
 
Evolution of a shoe-mounted multi-IMU pedestrian dead reckoning PDR sensor
Evolution of a shoe-mounted multi-IMU pedestrian dead reckoning PDR sensorEvolution of a shoe-mounted multi-IMU pedestrian dead reckoning PDR sensor
Evolution of a shoe-mounted multi-IMU pedestrian dead reckoning PDR sensoroblu.io
 
Analytical framework for optimized feature extraction for upgrading occupancy...
Analytical framework for optimized feature extraction for upgrading occupancy...Analytical framework for optimized feature extraction for upgrading occupancy...
Analytical framework for optimized feature extraction for upgrading occupancy...IJECEIAES
 
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...Eswar Publications
 
Vehicle density sensor system to manage traffic
Vehicle density sensor system to manage trafficVehicle density sensor system to manage traffic
Vehicle density sensor system to manage trafficeSAT Journals
 
Vehicle density sensor system to manage traffic
Vehicle density sensor system to manage trafficVehicle density sensor system to manage traffic
Vehicle density sensor system to manage trafficeSAT Publishing House
 
LIGHTWEIGHT INDOOR POSITIONING IN A REAL ENVIRONMENT BASED ON WIFI FINGERPRIN...
LIGHTWEIGHT INDOOR POSITIONING IN A REAL ENVIRONMENT BASED ON WIFI FINGERPRIN...LIGHTWEIGHT INDOOR POSITIONING IN A REAL ENVIRONMENT BASED ON WIFI FINGERPRIN...
LIGHTWEIGHT INDOOR POSITIONING IN A REAL ENVIRONMENT BASED ON WIFI FINGERPRIN...IRJET Journal
 

Similar to Analysis of Obstacle Detection Using Ultrasonic Sensor (20)

AIC39 (1)
AIC39 (1)AIC39 (1)
AIC39 (1)
 
A Comparative Study of Sensors for Road Traffic Density Measurement
A Comparative Study of Sensors for Road Traffic Density MeasurementA Comparative Study of Sensors for Road Traffic Density Measurement
A Comparative Study of Sensors for Road Traffic Density Measurement
 
Research on Car Reversing Radar System Based on Ultrasonic
Research on Car Reversing Radar System Based on UltrasonicResearch on Car Reversing Radar System Based on Ultrasonic
Research on Car Reversing Radar System Based on Ultrasonic
 
Ultra sonic range finding for distance measuring in coal mining
Ultra sonic range finding for distance measuring in coal miningUltra sonic range finding for distance measuring in coal mining
Ultra sonic range finding for distance measuring in coal mining
 
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
 
Intelligent travelling and home automation aid, for visually impaired
Intelligent travelling and home  automation aid, for visually impairedIntelligent travelling and home  automation aid, for visually impaired
Intelligent travelling and home automation aid, for visually impaired
 
Design and development of intelligent electronics travelling aid for visually...
Design and development of intelligent electronics travelling aid for visually...Design and development of intelligent electronics travelling aid for visually...
Design and development of intelligent electronics travelling aid for visually...
 
Smoke detection in video for early warning using
Smoke detection in video for early warning usingSmoke detection in video for early warning using
Smoke detection in video for early warning using
 
Smoke detection in video for early warning using static and dynamic features
Smoke detection in video for early warning using static and dynamic featuresSmoke detection in video for early warning using static and dynamic features
Smoke detection in video for early warning using static and dynamic features
 
National Highway Alignment from Namakkal to Erode Using GIS
National Highway Alignment from Namakkal to Erode Using GISNational Highway Alignment from Namakkal to Erode Using GIS
National Highway Alignment from Namakkal to Erode Using GIS
 
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATAA DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
 
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATAA DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
A DEEP LEARNING APPROACH FOR DENOISING AIR-COUPLEDULTRASONIC RESPONDS DATA
 
Granular Mobility-Factor Analysis Framework for enrichingOccupancy Sensing wi...
Granular Mobility-Factor Analysis Framework for enrichingOccupancy Sensing wi...Granular Mobility-Factor Analysis Framework for enrichingOccupancy Sensing wi...
Granular Mobility-Factor Analysis Framework for enrichingOccupancy Sensing wi...
 
Conditioning Monitoring of Gearbox Using Different Methods: A Review
Conditioning Monitoring of Gearbox Using Different Methods: A ReviewConditioning Monitoring of Gearbox Using Different Methods: A Review
Conditioning Monitoring of Gearbox Using Different Methods: A Review
 
Evolution of a shoe-mounted multi-IMU pedestrian dead reckoning PDR sensor
Evolution of a shoe-mounted multi-IMU pedestrian dead reckoning PDR sensorEvolution of a shoe-mounted multi-IMU pedestrian dead reckoning PDR sensor
Evolution of a shoe-mounted multi-IMU pedestrian dead reckoning PDR sensor
 
Analytical framework for optimized feature extraction for upgrading occupancy...
Analytical framework for optimized feature extraction for upgrading occupancy...Analytical framework for optimized feature extraction for upgrading occupancy...
Analytical framework for optimized feature extraction for upgrading occupancy...
 
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
 
Vehicle density sensor system to manage traffic
Vehicle density sensor system to manage trafficVehicle density sensor system to manage traffic
Vehicle density sensor system to manage traffic
 
Vehicle density sensor system to manage traffic
Vehicle density sensor system to manage trafficVehicle density sensor system to manage traffic
Vehicle density sensor system to manage traffic
 
LIGHTWEIGHT INDOOR POSITIONING IN A REAL ENVIRONMENT BASED ON WIFI FINGERPRIN...
LIGHTWEIGHT INDOOR POSITIONING IN A REAL ENVIRONMENT BASED ON WIFI FINGERPRIN...LIGHTWEIGHT INDOOR POSITIONING IN A REAL ENVIRONMENT BASED ON WIFI FINGERPRIN...
LIGHTWEIGHT INDOOR POSITIONING IN A REAL ENVIRONMENT BASED ON WIFI FINGERPRIN...
 

More from IRJET Journal

TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...IRJET Journal
 
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURESTUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTUREIRJET Journal
 
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...IRJET Journal
 
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsEffect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsIRJET Journal
 
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...IRJET Journal
 
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...IRJET Journal
 
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...IRJET Journal
 
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...IRJET Journal
 
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASA REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASIRJET Journal
 
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...IRJET Journal
 
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProP.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProIRJET Journal
 
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...IRJET Journal
 
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemSurvey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemIRJET Journal
 
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesReview on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesIRJET Journal
 
React based fullstack edtech web application
React based fullstack edtech web applicationReact based fullstack edtech web application
React based fullstack edtech web applicationIRJET Journal
 
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...IRJET Journal
 
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.IRJET Journal
 
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...IRJET Journal
 
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignMultistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignIRJET Journal
 
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...IRJET Journal
 

More from IRJET Journal (20)

TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
 
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURESTUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
 
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
 
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsEffect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil Characteristics
 
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
 
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
 
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
 
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
 
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASA REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADAS
 
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
 
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProP.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
 
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
 
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemSurvey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare System
 
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesReview on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridges
 
React based fullstack edtech web application
React based fullstack edtech web applicationReact based fullstack edtech web application
React based fullstack edtech web application
 
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
 
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
 
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
 
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignMultistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
 
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
 

Recently uploaded

Interview Cathodic-Protection (Corrosion).ppt
Interview Cathodic-Protection (Corrosion).pptInterview Cathodic-Protection (Corrosion).ppt
Interview Cathodic-Protection (Corrosion).pptArfanAli50
 
Pyrolysis process control: temperature control design and application for opt...
Pyrolysis process control: temperature control design and application for opt...Pyrolysis process control: temperature control design and application for opt...
Pyrolysis process control: temperature control design and application for opt...IJECEIAES
 
applications of diffrentiability in real life.pptx
applications of diffrentiability in real life.pptxapplications of diffrentiability in real life.pptx
applications of diffrentiability in real life.pptxananditam30
 
Est microproject.ppt 4th semester Diploma
Est microproject.ppt 4th semester DiplomaEst microproject.ppt 4th semester Diploma
Est microproject.ppt 4th semester DiplomaAnujJain917144
 
Introduction of Object Oriented Programming Language using Java. .pptx
Introduction of Object Oriented Programming Language using Java. .pptxIntroduction of Object Oriented Programming Language using Java. .pptx
Introduction of Object Oriented Programming Language using Java. .pptxPoonam60376
 
AI Powered Ecover creator that creates everything that you want
AI Powered Ecover creator that creates everything that you wantAI Powered Ecover creator that creates everything that you want
AI Powered Ecover creator that creates everything that you wantsuja868966
 
Network Enhancements on BitVisor for BitVisor Summit 12
Network Enhancements on BitVisor for BitVisor Summit 12Network Enhancements on BitVisor for BitVisor Summit 12
Network Enhancements on BitVisor for BitVisor Summit 12cjchen22
 
Introduction to Machine Learning Part1.pptx
Introduction to Machine Learning Part1.pptxIntroduction to Machine Learning Part1.pptx
Introduction to Machine Learning Part1.pptxPavan Mohan Neelamraju
 
Digital Fundamentals_ Global Ed - Thomas L Floyd.pdf
Digital Fundamentals_ Global Ed - Thomas L Floyd.pdfDigital Fundamentals_ Global Ed - Thomas L Floyd.pdf
Digital Fundamentals_ Global Ed - Thomas L Floyd.pdfdaniyalalihemani31
 
LESSON-1-DERIVATIVES.pptxvjjhggkkkkkhggfff
LESSON-1-DERIVATIVES.pptxvjjhggkkkkkhggfffLESSON-1-DERIVATIVES.pptxvjjhggkkkkkhggfff
LESSON-1-DERIVATIVES.pptxvjjhggkkkkkhggfffprincessfajarit21
 
Routing and Algorithms For VLSI design.pptx
Routing and Algorithms For VLSI design.pptxRouting and Algorithms For VLSI design.pptx
Routing and Algorithms For VLSI design.pptxPrateek718260
 
Permutation-and-Combinations.lecturressssssss
Permutation-and-Combinations.lecturressssssssPermutation-and-Combinations.lecturressssssss
Permutation-and-Combinations.lecturressssssssDANIELLEGASPI9
 
Design and Analysis of Algorithms (Knapsack Problem)
Design and Analysis of Algorithms (Knapsack Problem)Design and Analysis of Algorithms (Knapsack Problem)
Design and Analysis of Algorithms (Knapsack Problem)Sreedhar Chowdam
 
Utilizing leftover voids under a flyover
Utilizing leftover voids under a flyoverUtilizing leftover voids under a flyover
Utilizing leftover voids under a flyoveryogaraje2002
 
input buffering in lexical analysis in CD
input buffering in lexical analysis in CDinput buffering in lexical analysis in CD
input buffering in lexical analysis in CDHeadOfDepartmentComp1
 
Deceth series HLB value for hard surface cleaner applications.pdf
Deceth series HLB value for hard surface cleaner applications.pdfDeceth series HLB value for hard surface cleaner applications.pdf
Deceth series HLB value for hard surface cleaner applications.pdflzhao5
 
Demand for Penetration Testing Services.docx
Demand for Penetration Testing Services.docxDemand for Penetration Testing Services.docx
Demand for Penetration Testing Services.docxAardwolf Security
 
22CYT12 & Chemistry for Computer Systems_Unit-II-Corrosion & its Control Meth...
22CYT12 & Chemistry for Computer Systems_Unit-II-Corrosion & its Control Meth...22CYT12 & Chemistry for Computer Systems_Unit-II-Corrosion & its Control Meth...
22CYT12 & Chemistry for Computer Systems_Unit-II-Corrosion & its Control Meth...KrishnaveniKrishnara1
 
BaseBand-6630-Moshell-Commands .pdf
BaseBand-6630-Moshell-Commands      .pdfBaseBand-6630-Moshell-Commands      .pdf
BaseBand-6630-Moshell-Commands .pdfwafawafa52
 

Recently uploaded (20)

Interview Cathodic-Protection (Corrosion).ppt
Interview Cathodic-Protection (Corrosion).pptInterview Cathodic-Protection (Corrosion).ppt
Interview Cathodic-Protection (Corrosion).ppt
 
Neometrix Optical Balloon Theodolite.pptx
Neometrix Optical Balloon Theodolite.pptxNeometrix Optical Balloon Theodolite.pptx
Neometrix Optical Balloon Theodolite.pptx
 
Pyrolysis process control: temperature control design and application for opt...
Pyrolysis process control: temperature control design and application for opt...Pyrolysis process control: temperature control design and application for opt...
Pyrolysis process control: temperature control design and application for opt...
 
applications of diffrentiability in real life.pptx
applications of diffrentiability in real life.pptxapplications of diffrentiability in real life.pptx
applications of diffrentiability in real life.pptx
 
Est microproject.ppt 4th semester Diploma
Est microproject.ppt 4th semester DiplomaEst microproject.ppt 4th semester Diploma
Est microproject.ppt 4th semester Diploma
 
Introduction of Object Oriented Programming Language using Java. .pptx
Introduction of Object Oriented Programming Language using Java. .pptxIntroduction of Object Oriented Programming Language using Java. .pptx
Introduction of Object Oriented Programming Language using Java. .pptx
 
AI Powered Ecover creator that creates everything that you want
AI Powered Ecover creator that creates everything that you wantAI Powered Ecover creator that creates everything that you want
AI Powered Ecover creator that creates everything that you want
 
Network Enhancements on BitVisor for BitVisor Summit 12
Network Enhancements on BitVisor for BitVisor Summit 12Network Enhancements on BitVisor for BitVisor Summit 12
Network Enhancements on BitVisor for BitVisor Summit 12
 
Introduction to Machine Learning Part1.pptx
Introduction to Machine Learning Part1.pptxIntroduction to Machine Learning Part1.pptx
Introduction to Machine Learning Part1.pptx
 
Digital Fundamentals_ Global Ed - Thomas L Floyd.pdf
Digital Fundamentals_ Global Ed - Thomas L Floyd.pdfDigital Fundamentals_ Global Ed - Thomas L Floyd.pdf
Digital Fundamentals_ Global Ed - Thomas L Floyd.pdf
 
LESSON-1-DERIVATIVES.pptxvjjhggkkkkkhggfff
LESSON-1-DERIVATIVES.pptxvjjhggkkkkkhggfffLESSON-1-DERIVATIVES.pptxvjjhggkkkkkhggfff
LESSON-1-DERIVATIVES.pptxvjjhggkkkkkhggfff
 
Routing and Algorithms For VLSI design.pptx
Routing and Algorithms For VLSI design.pptxRouting and Algorithms For VLSI design.pptx
Routing and Algorithms For VLSI design.pptx
 
Permutation-and-Combinations.lecturressssssss
Permutation-and-Combinations.lecturressssssssPermutation-and-Combinations.lecturressssssss
Permutation-and-Combinations.lecturressssssss
 
Design and Analysis of Algorithms (Knapsack Problem)
Design and Analysis of Algorithms (Knapsack Problem)Design and Analysis of Algorithms (Knapsack Problem)
Design and Analysis of Algorithms (Knapsack Problem)
 
Utilizing leftover voids under a flyover
Utilizing leftover voids under a flyoverUtilizing leftover voids under a flyover
Utilizing leftover voids under a flyover
 
input buffering in lexical analysis in CD
input buffering in lexical analysis in CDinput buffering in lexical analysis in CD
input buffering in lexical analysis in CD
 
Deceth series HLB value for hard surface cleaner applications.pdf
Deceth series HLB value for hard surface cleaner applications.pdfDeceth series HLB value for hard surface cleaner applications.pdf
Deceth series HLB value for hard surface cleaner applications.pdf
 
Demand for Penetration Testing Services.docx
Demand for Penetration Testing Services.docxDemand for Penetration Testing Services.docx
Demand for Penetration Testing Services.docx
 
22CYT12 & Chemistry for Computer Systems_Unit-II-Corrosion & its Control Meth...
22CYT12 & Chemistry for Computer Systems_Unit-II-Corrosion & its Control Meth...22CYT12 & Chemistry for Computer Systems_Unit-II-Corrosion & its Control Meth...
22CYT12 & Chemistry for Computer Systems_Unit-II-Corrosion & its Control Meth...
 
BaseBand-6630-Moshell-Commands .pdf
BaseBand-6630-Moshell-Commands      .pdfBaseBand-6630-Moshell-Commands      .pdf
BaseBand-6630-Moshell-Commands .pdf
 

Analysis of Obstacle Detection Using Ultrasonic Sensor

  • 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072 © 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1015 Analysis of Obstacle Detection Using Ultrasonic Sensor Christofer N. Yalung1, Cid Mathew S. Adolfo2 1Military Technological College, Muscat, Oman 2Military Technological College, Muscat, Oman ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract – Automation of the car braking system is an important feature in the development of the smart car. The ability of a smart car to detect and classify an obstructionthat is in varying proximities from it play a vital roleinthesystem’s design. In this study, EV3 Lego Mindstorm equipped with an ultrasonic sensor was used as a model of a large scale vehicle. EV3 Lego MIndstorm was programmed to slow down when it is at a certain distance from the obstruction, and to stop when it is 15 cm away from the obstruction. There were five obstructions: wood, paper, cloth, plastic and metal. The distance measurement of the ultrasonic sensor and the Neural Network was used for the classification of the obstruction and Multiple Correlation was used for obstacle detection. There were 250 samples taken from the distance measurements of five different types of obstruction, each with a different cross sectional area, and a total recording timeof8 seconds. Overall, there is a high correlation coefficient in the distance measurement of the different types of obstruction materials. It is concluded that the ultrasonic sensor was able to detect the five given types of obstruction. Classification performance was very poor, which means that on the basis of distance measurement, theultrasonicsensorcannot effectively classify the types of obstructions. Key Words: Ultrasonic Sensor, Obstacle detection, Artificial neural network, Distance measurement 1.INTRODUCTION Nowadays, automation in technology is widespread, this can be seen on doors, electronic devices, cars and in various industrial applications. This is made possible by sensing devices, which serve as a medium between the machine and the environment. Ultrasonic sensor is an incredibly useful sensor in the field of automation. For example, a mobile robot receives environmental information, converts it into a signal and performs this signalled task like avoiding obstacles (In this sentence you should mention specifically the function of the ultrasonic sensor). This particular type of sensor produces satisfactory results and is cost effective. The algorithm for distance calculation is based on the measurement of the time of flight of the ultrasonic waves. The distance between two objects can be measured using the ultrasonic sensor. The technique of distance measurement is based on the measurement of the elapsed time between the emission of the wave and the reception of the echo. The propagation of the ultrasonic wave is done at the sound speed in the air (340 m/sec). A typical ultrasonic distance sensor consists of two main elements. One element produces sound, another catches reflected echo. Basically, these pieces are a speaker and a microphone. The device generates ultrasonic impulses and triggers the timer. The other element registers the arrival of the sound impulse and stops the timer. From this information it is possible to calculate the distance travelled by the sound. It is usually not difficult to select a sensor that suits the environmental and mechanical requirements of a particular application, or to evaluate the electronic features available with different models. Still, many users may not be aware of the acoustic subtleties that can have major effects on the operation of the ultrasonic sensor and the measurements being made with them [1]. The basic principle of sound propagation, the effect of a wave when it strikes a solid object and the reception of the reflected sound waves are illustrated in Fig-1[2]. Fig-1: Ultrasonic sensor operations The velocity of the sound in air is given by the equation (1), this is used to calculate the speed of the sound in air. The distance that sound travels is equal to the speed of sound in the medium multiplied by the time that sound travels[2]. (1) The impulse width is proportional to the time required for the echo return. This time is called time-of-flight (TOF) [3]. But there are other factors which may also affect the propagation of sounds such as: ambient pressure, gas density and humidity [4].
  • 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072 © 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1016 1.1 Trends of Ultrasonic Sensor A research was conducted for the performance evaluation of NXT ultrasonic sensor and Parallax Ping sensor for distance measurement. An efficient method based on piecewise linear regression was proposed to improve the NXT ultrasonic sensor’s accuracy of distance measurement. The emitter transmits a burst of ultrasound (inaudible sounds) to the obstacle positioned in front ofthesensor.The object reflects back to sensor receiver the signal and when the echo is received the sensor generates an impulse [5]. Two ultrasonic sensors were used to achieve object classification [6]. To complete this task, the authors have proposed a fuzzy expert system having a dual knowledge base - one statistical and the othera standardrule basedone. Using this technique, they extracted and used 25 features including parameters like beginning time, mass center, etc. The task of outlier detection or novelty detection was implemented using Support Vector Machine (SVM), this contributed towards object classification. Human detection is vital to many applications, for example, human-robot interaction,unattendedgroundsensorsystems,smartrooms [7]. The application of a one-class classifier using solely ultrasonic sensors was trialed for human detection. This approach was based on fuzzy rules that are extracted from the signal features in time and frequency domains [8]. A prototype of a mobile robot suitable for mapping was presented. It used an ultrasonic sensor HC-SR04, which is a cheap alternative for sensor mapping instead of an expensive laser sensor. The hardware was based on ROMEO BLE mainboard. The Software consisted of two parts: firmware and application.Thefirmwarepart wasanArduino source code project, written in C++ programming language, which was deployed on the robot [9]. The method based on puddle detecting ability was proposed, and the evaluation of the improved method had been implemented according to experiment results. The proposed method can be applied in support systems on wheel chairs and white canes for improving safety. In this research, the road surface condition distinction method was developed considering the puddle condition. The four kinds of road surface conditions were investigated. The effectiveness of the proposed method was verified in all the four conditions [10]. Infusing ultrasonic sensor data and multiple ultrasonic sensor data while a mobile robot moves were proposed in [11]. Another research was developed for improving a grid map of the environment by triangulating multiple ultrasonic sensor data [12]. Related study of using three sensors to distinguish the plan from the corner and then build a map of this environment were carried in[13].Neuralnetworkswere applied to differentiate between different formsofobstacles: plane, corner, edges,and cylindricalshapes[14]. Moreover,a sensing method that classified the targetsurfaceasaplaneor a cylinder, with a sensing system consisting of 4 sets of ultrasonic aligned sensors were proposed in [15]. 1.2 Aims and Significant of the Study This study is aimed to obtain the distancemeasurementof a moving vehicle with respect to the presence of five different types of obstruction and in addition to this, to perform a speed reduction at a specified distance from the obstacle and to be able to fully stop the vehicle at a specific distance. Moreover, the study seek to find the significance and impact of the materials used in correlation with the ability of the ultrasonicsensortomeasuredistanceprecisely. Furthermore, Neural Network is implementedto classifythe different types of obstacles based on the measured distance over time, there were five materials to be classified namely: wood, paper, cloth, plastic and metal. This study could benefit the automotive industrybyapplyingsmartalgorithm for obstacle detection, precise detection of an object. Road safety could be improved by smart vehicle, through the advanced processes of anautomaticbrakesystemappliedon the vehicle. 2. Data Acquisition and Analysis The data acquisition, process and output of the study are shown in Fig-1, necessary equipment and procedures are included. Fig-2: Methodology of the study To model an actual vehicle, a Lego Mindstorm EV3wasused, it is equipped with an ultrasonic sensor. A program could be downloaded with its processor. Fig-3a and Fig-3b show the Lego Mindstorm EV3 and ultrasonic sensor. DATA ACQUISITION  EV3 ultrasonic sensor  Distance measurement  Five different types of materials PROCESS  Forward motion of the vehicle  Transmit and Receive of the ultrasonic sound wave OUTPUT  Distance measured over time  Reduce Vehicle speed  Obstacle detection
  • 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072 © 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1017 Fig-4 shows the program installed in the processor of the vehicle, it is designed to run the two motors labeled A and B, and reduce the speed of the model at a certain distance from the obstacle. Finally, it must stop when it reaches the distance of 15 cm from the obstruction. Also, data logging is added in the program, so that data in terms of time and distance could be acquired. The sampling rate per second was set to 5, and data logging was set up to 8 seconds In order to start the data recording, the vehicle is placed at about 80 cm away from the obstacle. Then it traveled in a straight path going to the obstruction. The five different types of obstructions used were wood, laminated paper, cloth, plastic, and metal, with the following area in square centimeter: 375, 300, 2025, 840, 840, respectively. To see the consistency of the result per each type of obstruction, two trials of data collected. Fig-3a: Lego Mindstorm EV3 Fig-3b: EV3 ultrasonic sensor Fig-4: Lego Mindstorm program Data analysis among types of materials wasperformedusing Multiple Correlation. Artificial Neural Network iscarried out to determine the classification of the obstruction. 3. Data and Results The information provided in Chart-1 shows the distance of the vehicle from the obstruction. There are four obstruction namely: wood, paper, cloth,plasticandmetal,differentcolors were used to represent them in the chart. The initial distance of the vehicle from the obstruction is about80cm.Asthetime increases, the distance measured is supposed to decrease because the vehicle is getting closer to the obstacle. Four of the obstructions namely: wood, paper, glass and metal displayed a common pattern. The measured distance is erroneous for the rippled cloth, the sound waves was not reflected efficiently, in returnthe vehiclefailedtoexecutethe condition designed in the program. However, based on our observation, when the cloth is perfectly flattened, thevehicle was able to follow the specified program. Finally, for the wood, paper, plastic and metal, there was a consistency of the distance measured especially after four seconds and onwards. Chart-1: Distance of the vehicle from the obstruction The information provided in Table-1showsapositiveperfect positive correlation coefficient among the wood, paper, plastic and metal. This means that ultrasonic sensor used in this experiment resulted to the same pattern of distance measurement and obtained approximately the same measured value. This result is with exemption to the rippled cloth which resulted in an almost low negative correlation when compared to the above mentioned materials. This signifies that there was a failure of the cloth to reflect sound waves. On the other hand, the ultrasonic sensor was able to detect the presence of the rippled cloth at a certain time, but after about 3 seconds there was an error to the measured distance.
  • 4. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072 © 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1018 Table-1 Multiple Correlation among five types of materials wood paper cloth plastic Metal wood 1.00 paper 1.00 1.00 cloth -0.48 -0.45 1.00 plastic 1.00 1.00 -0.46 1.00 metal 1.00 1.00 -0.47 1.00 1.00 Furthermore, to determine the consistency of the gathered data, two trials were performed for each type of material, all showed a perfect positive correlation, except for the cloth. 3.1 Neural Network Classification Machine learning was used to classify the data into five categories such as wood, paper, cloth, plastic and metal. There were 205 samples taken from five different types of obstructions, and 8 seconds of data logging. The neural network architecture is shown in Fig-5, there were ten hidden layer. The samplesweredividedintoTraining(75%), Validation (15%) and Testing (15%). Majority of the data was presented to the network during training, and the network was adjusted based on its error. The function of Validation is to stop the training when generalization stops improving. Testing is an independent measure of network performance. Fig-5: Neural network architecture Classification was performed using two different network architecture, Fig-6showstheresultofclassification at 10 hidden neurons and Fig-7 shows the result at 20 hidden neurons. Cross Entropy (CE) shows the result in classification, having zero value means no error. Percent Error (%E) indicates the fraction which are misclassified, zero means no misclassification and 100 means maximum misclassifications. The results shows, there is approximately equal %E for the two different artificial network architectures having, 69.9% and 69.23% for the 10 and 20 hidden neurons respectively. The cross entropy during the training resulted to 0.74487 and .792481 for the 10 and 20 hidden neurons respectively. There was a very minimal improvement onthe performance of the neural network architecturebydoubling the number of hidden layers based on the given data. Furthermore, it can be observed that classification was not good as indicated by the higher value of Cross Entropy on training, validation and testing. Therefore, the method of distance measurement for the classification of the types of obstruction using ultrasonic sensor executed poor results. Fig-6: Neural network results at 10 hidden neurons Fig-7: Neural Network results at 20 hidden neurons 4. CONCLUSIONS In this study, the data were acquired using EV3 Lego Mindstorm, ultrasonic sensor, different types of materials and software programming. The analysis and interpretation of the data were carried out using Multiple Correlation and Neural Network. The vehicle was programmed to move slowly as it approached near the obstruction, and stopped when reached the distance of 15 cm.Therewerefivetypes of obstruction namely: wood, paper, plastic and metal. Overall, wood, paper, glass and metal displayed a common pattern based on the measured distance, there was erroneousresult for the rippled cloth. The neural network classification shows poor performance based on the gathered data. The percent error (%E) recorded for 10 and 20 hidden neurons where 69.9% and 69.23% respectively. This means that classification of the types of obstruction was not efficient by distance measurement between the vehicle and theobstructionusing the ultrasonic sensor. There is a positive perfect positive correlation coefficient among the wood, paper, plastic and metal. This means that ultrasonic sensor used in this experiment perform the same pattern of distance measurement given these materials. However, for the rippled cloth, results showed an almost low negative correlation when compared to the above mentioned materials.
  • 5. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072 © 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1019 REFERENCES [1] D. Masa, “Choosing an Ultrasonic Sensor for Proximity or Distance Measurement Part 1: Acoustic Considerations”, Feb. 1, 1997. [Online]. http://www.sensorsmag.com/sensors/acoustic- ultrasound/choosing-ultrasonic-sensor-proximity-or- distance-measurement-825 Hands-on Activity: Measuring Distance with Sound Waves, AMPS GK-12 Program, Polytechnic Institute of New York University. [Online].https://www.teachengineering.org/activities/v iew/nyu_soundwaves_activity1 [2] D. Marioli, C. Narduzzi, C. Offelli, D. Petri, E. Sardini and A. Taroni,“Digital time-of-flight measurement for ultrasonic sensors,” IEEE Transaction on Instrumentation and Measurement, vol. 41, pp. 93–97, 1992 [3] D. A. Bohn, “Environmental effects on the speed of sound,” Journal ofAudio Engineering Society,vol.36,No. 4, April, 1988 [4] G. Găşpăresc andA.Gontean, "Performanceevaluationof ultrasonic sensors accuracy in distance measurement," 2014 11th International Symposium on Electronics and Telecommunications (ISETC), Timisoara, 2014, pp. 1-4. doi: 10.1109/ISETC.2014.7010761 [5] J.R. Llata, E.G. Sarabia, J.P. Oria," Fuzzy expert system with doubleknowledge base for ultrasonic classification," Expert Systems with Applications 20 (2001) 347-355. [6] Duin, Robert PW, et al. "Feature-based dissimilarity space classification."Recognizing Patterns in Signals, Speech, Images and Videos. Springer Berlin Heidelberg, 2010. 46-55 [7] Sonia, A. M. Tripathi, R. D. Baruah and S. B. Nair, "Ultrasonic sensor-based human detector using one- class classifiers," 2015IEEEInternational Conferenceon Evolving and AdaptiveIntelligentSystems(EAIS),Douai, 2015, pp. 1-6. doi: 10.1109/EAIS.2015.7368797 [8] A. Dimitrov and D. Minchev, "Ultrasonic sensor explorer," 2016 19th International Symposium on Electrical ApparatusandTechnologies(SIELA),Bourgas, 2016, pp. 1-5. doi: 10.1109/SIELA.2016.7542987 S. Nakashima, S. Aramaki, Y. Kitazono, S. Mu, K. Tanaka and S. Serikawa, "Road Surface Condition Distinction Method Using Reflection Intensities Obtained by Ultrasonic Sensor," 2016 International Symposium on Computer, ConsumerandControl (IS3C),Xi'an,2016,pp. 120-123. doi: 10.1109/IS3C.2016.41 [9] H. Choset, K. Nagatani, and N. Lazar: “The Arc- Transversal Median Algorithm: A Geometric Approach to IncreasingUltrasonic SensorAzimuthAccuracy”,IEEE Trans. on Robotics and Automation, Vol.19, No.3, pp. 513-523, 2003. [10] O. Wijk, P. Jensfelt, and H. Christensen: “Triangulation Based Fusion of Ultrasonic Sensor Data”, IEEE Proc, Int, Conf. on Robotics andAutomation,pp.3419-3424,1998. [11] Joen, H. J and B.K.Kim: “A study on world map building for mobile robots with trial-aural ultrasonic sensor system”, IEEE Int, Conf. Robot.Autom, pp 2907- 2912, 1995. [12] Barshan, B., B. Ayrulu, and S. W. Utete: “Neural network-based target differentiation using sonar for robotics applications”, IEEE Trans. Robot. Autom., Vol. 16, pp.435-442, 2000. [13] I. Maâlej, M. Ouali and N. Derbel, "Modular ultrasonic sensor platform for mobile robot," 2012 First International Conference on Renewable Energies and Vehicular Technology, Hammamet, 2012, pp. 477-483. doi: 10.1109/REVET.2012.6195316 [14] R. A. Dimitrov and D. Minchev, "Ultrasonic sensor explorer," 2016 19th International Symposium on Electrical ApparatusandTechnologies(SIELA),Bourgas, 2016, pp. 1-5. doi: 10.1109/SIELA.2016.7542987 Nicole, “Title of paper with only first word capitalized,” J. Name Stand. Abbrev., in press.