Abstract— Recently, many interestingsystems on mobile phone are introduced to prevent the dangerous activity oftexting while driving (T&D).
However these systems require user’s manualinput to block the texting activity or some extra devices are used to identifyuser’s location and also some localization techniques are used. Here the ideais to propose a method which is able to detect T&D without any userintervention. To implement this idea various smart phone embedded sensors suchas gyroscopes, accelerometers and GPS are used. They are used to collect theinformation such as touch strokes, holding orientation and vehicle speed. Usingthese patterns the whether the T&D is existing or not identified.Keywords— Vehicles, Smartphones, Global Positioning System, Accelerometers.I.INTRODUCTIONSmartphones are small computers which uses android as operating system.
Datacommunication between the people/user has become faster using smart phones.Calling and texting otherwise called as messaging is the most important andbasic activity that has been done using smart phones. But texting while drivinghas become most common habit between the drivers. This is one of the mosthazardous thing performed by the users of smart phone. This act becomes majordistraction from driving. This leads to road accidents and causes damage to thedrivers and also other common people. Usage of mobile phones while driving canaffect your alertness of surroundings, which leads to accidents. This term inshort is referred to as T&D that is Texting while Driving.
This isconsidered as one of the top most dangerous activity done by the drivers. Aresearch says that, the drivers who send messages while driving are 23 timesmore likely to experience a crash on others when compared to other drivers whoare dialing, talking or listening. Even though, many laws are imposed to avoidT&D, the users are involving in this activity. To stop these activity ofdrivers and to identify the T&D, many mobile apps are now developed andpractised between the users.
Thissystem does not require any manual input from the driver. This acts as themajor advantage of this over other T&D system. In other detection systemthe major problem is they require user input or activation or it eitherdisables all the mobile phones in the user location (such as car) , this causesunnecessary inconvenience to the users. The key challenge is detecting whetherthe mobile phone belongs to driver or passenger. For this purpose, some systemsuses camera to monitor driver’s activities. But this method is infrastructureheavy and required high hardware facilities to implement real time videoprocessing. Some of the works are done for detecting T basedlocalization. Here some extra devices in combination with mobile phone workcollaboratively to determine the user location.
To enlighten this idea mostsuccessfully a method which does not require any extra devices except user’smobile phone was needed. Here are somepatters that is used to distinguish between the driver and the passenger. Pattern1:Editing messages after the car speed is decreased.
Pattern2: Stop editing when the car is taking turns.Pattern3: Holding the mobile phone uprightly while editing the messages.Thereforeby using this system the T&D patterns are identified by the data collectedthe smart phones and the other embedded sensors like accelerometers, gyroscopesand GPS. The other important factor is that, this system does not try to readthe content of the messages. Therefore privacy is preserved here.
II.RELATED WORKSTheexisting system to prevent T&D there are two categories, the first one iswhich simply blocks all the messages from the user end. The best example forthis is driver mode or bike mode available in the mobile phones. But thisexisting system does not identify the drivers mobile with the passengers. Thenext category is identifying whether the mobile is used drivers or passengersand it blocks the driver’s mobile only. In this method identifying the locationof the mobile phone in the vehicle is important.
For this localizationtechniques are used to identify the driver’s location. However this approachhas some drawbacks that identifying the driver’s location requires some specialsensors and required high deployment cost. Identification of driver’s locationand driving patters in also infrastructure heavy and intrusive.Thereforefor overcoming these drawbacks infrastructure-less approach is required. Thatis identifying the driver’s usage of mobile without any extra devises excepthis/her own mobile phone.III.TOUCH STROKE DETECTIONHere the touch strokesare identified by using the gyroscope data. Using the training data set a touchstroke template is constructed.
On this gyroscope data the template is utilizedas wavelet basis and they carry out wavelet transform. According to theoccurrence of touch strokes the significant peaks and the location of the peaksare selected.IV.LITRATURE SURVEY1SAFECAM: Analyzingintersection related driver behaviours using multi sensor smart phonesThisuses embedded sensors on the phone .It is used in tracking different drivingconditions.
It also makes use of vision based algorithms to detect criticaldriving behaviours including taking unsafe turns. The results demonstrate thatthe safe cam is effective in detecting real-road driving environments and alertdrivers during dangerous situation. 2Leveraging smart phonescameras for collaborative road advisoriesItprovides a effective driver assistance services using ever richer set ofsensors. It provides assistance for the drivers in services like trafficadvisory and road condition monitoring .This paper introduce a sensing platformcalled as windshield-mounted smart phones.
It uses a prototype called as signalguru, it predicts the schedule of traffic signals and also enabling Green LightOptimal Speed Advisory (GLOSA)3Driving style recognitionusing smart phone as a sensor platformInthis system, a novel method that uses dynamic time warping (DTW) and smartphone based sensor-fusion is used. They detect and recognize the driver actionswithout external processing. It performs the pattern recognition research bycombining the inter-axial data from multiple sensors into a single one that issingle classifier.4Drive safe: an app foralerting inattentive drivers and scoring driving behavioursThisapplication uses computer vision and pattern recognition techniques to alertduring their unsafe driving behaviours. The inbuilt sensors present are able todetect in attentive driving behaviours and also evaluating the quality ofdriving at the same time. It produces sound alarms in case of unsafe driving.It becomes the first application for smart phones to detect the drivingbehaviours.5Detection of dangerous corneringin GNSS –Data driven insurance telematics Thisapplication introduces loss functions designed for applications.
It mainly aimsto minimize the number of missed detections and false alarms, this estimatesthe risk level in each turning and cornering event. This estimation only usesGNSS (Global Navigation Satellite System) measurements. It also supportsreal-time value added services. 6Safe driving using mobilephonesInthis paper the system available makes use of three axis accelerometer ofandroid based smart phone. It records and analyzes various driver behaviours.
It also alerts about the external road conditions that would be hazardous forthe drivers. By using the real-time analysis and auditory, we can increase thedriver’s overall awareness.7Sensing driver phone use withacoustic ranging through car speakersInthis system the fundamentally addressed problem is differentiating driver’s andpassenger’s mobile phone. In this system, it leverages the stereoinfrastructure, particularly speakers and Bluetooth. Using car stereo, a customizedhigh frequency beeps are produced. Sequential change-point detection scheme isused to time the arrival and phone’s distance from the car’s centre isestimated.
8Driver behaviour analyses forsafe drivingThispaper provides some well-established techniques for driver’s inattentionmonitoring and recent solutions for exploiting mobile technologies such assmart phone and wearable devices .It primary aim is safe driving and usesactive systems for car-to-car communication to support vehicle adhoc network VANET.9Determining driver phone useby exploiting smart phone integrated sensorsThissystem uses embedded sensors in smart phones for capturing the centripetalacceleration. Their differences are obtained. This is a low infrastructureapproach. It has different turn size and difference in the driving speed. Thismethod is adopted in many traffic related safety applications.
10Detecting driver’s smartphone usage via non intrusively sensing driving dynamicsHere,in this paper TEXIVE is implementedwhich detects the texting operations during driving. It also notices theirregularities and rich micro-movements of the users. TEXIVE is very accuratethat the dangerous driving behaviours are identified without any extra devicesrather than smart phone.11Automatic identification ofdriver’s smart phone exploiting common vehicle riding actionsThispaper gives the solution to the problem of distracted driving by giving aevent-driven solution called as Automatic Identification of Driver’s Smartphone (AIDS).It makes use of features that are available for identifying thedriver’s phone. It uses electromagnetic field spikes to differentiate driver’sphone from the passengers in the car.12Improved vehicle steeringpattern recognition by using selected sensor data Inthis paper recognition accuracy of vehicle steering patterns are improved.
Thispaper presents a new method to reduce both energy and computation complexity.Different statistical modes are identified and statistical sensor features arereflected. Real-time accuracy is produced in steering modes. Different machinelearning modes are compared to produce improved classifier training.13Full auto-Calibration of asmart phone on board a vehicle using IMU and GPS embedded sensorsHerea study is conducted, to identify how powerful some of the low cost sensorslife IMU (Inertial Measurement Unit) and GPS are useful for intelligentvehicles.
The relation between the smart phone reference system and vehiclereference system are identified by accelerometer and gyroscope. Based onlongitudinal vertical acceleration on automatic method is proposed to calibratea smart phone using IMU and GPS. Here filter algorithm is used to decrease theimpact of IMU noise.14Smart phone-based sensorfusion for improved vehicular navigationByfusion sensor data on smart phone a system for car navigation is proposed here.To support GPS, both the internal sensor and care sensors are used. To fuse thedata from different sensor’s streams strap down algorithm and Kalman filtersare used. The speed information of the car is give by car sensors and gyroscopeact as internal sensor.15Smart phone-based adaptivedriving maneuver detection: A large-scale evaluation studyThispaper, builds a statistical model of the driver, vehicle and the smart phoneand an adaptive driving maneuver detection methods is proposed.
Thiscombination is done using multivariate normal model. To detect risky drivingbehaviours a mechanism is know as training mechanism is adopted. I adaptsprofiling model to the driver and road topology.16Detecting driver distractionusing smart phoneItthis paper a ubiquitous camera feature is used to differentiated driver’s phonefrom the passengers. Here the key factor is non-intrusive detection of thesmart phone. No manual input from the driver phone is needed.
It does not relyon any other hardware devices. This method provides a very accuratelocalization of the driver’s phone from the other users in the car.17Senspeed: sensing drivingconditions to estimate vehicle speed in urban environmentsInthis paper, a system is proposed that the smart phone sensors are used toestimate the vehicle speed.Thissystem is mainly useful when GPS is unavailable or irregular in Urban areas.The estimation of acceleration errors and large deviations are found here. Anddeviation between the estimated and the real one are calculated. The changes inthe acceleration errors are corrected when needed. These points are called asreference points.
18Body sensor networks fordriver distraction identificationInthis paper, Controller Area Network (CAN) is used in this system for detectingdriver distractions. It mainly focus on leg and head movements of the drivers.It detects upto a high accuracy of distraction over 90%.
Using this highlyreliable reduces the density of the accidents that are caused using driverdistractions.19Detecting driver phone callsin a moving vehicle based on voice featuresInthis paper, a system is proposed to monitor the smart phone activities and italso blocks the calls that are coming to the driver while driving. It alsoconcentrates on phone position on the vehicle. It blocks the calls from thephone that comes to the driver’s location. This method is position-independent.It also reduces the noise that is produced from in and around the vehicle’slocation.20Development of theeco-driving and safe-driving comp0nents using vehicle informationHere,some components which can obtain and access the eco-driving and safe driving,the vehicle information is obtained through CAN (Controller Area Network).
Itis inner vehicle network protocol. It uses Bluetooth network to transfer theinformation between the modules. V.SUMMARY OF THE SURVEYSomeof the applications are listed are listed and their techniques are examined andcompared in this paper.
Majority of the systems uses mobile phone in-builtsensors like GPS, accelerometers and gyroscopes sensors are used to identifythe location of the driver’s mobile and find their pattern of driving.VI.CONCLUSIONInthis paper, to detect T&D we are submitting a novel method to make itsimple.
Here we using the authoritymethod with some patterns that will guide us how smart phones are used inmoving vehicles. The associated information about some build in sensors in thesmart phones are collected and these sensors are analysed with hypothesistesting and checked for T&D patterns match. The outcome of this approachwill achieve good detection accuracy. This proposed T&D method could beappropriate for usage based insurance. Many anti T&D mobile phoneapplications are sustain with this method. REFERENCES1.Sensing Driver Phone Use withAcoustic Ranging through Car Speakers. Jie Yang, Student Member, IEEE, SimonSidhom, Gayathri Chandrasekaran, Tam Vu, Hongbo Liu, Student Member, IEEE,Nicolae Cecan, Yingying Chen, Senior Member, IEEE, Marco Gruteser, and RichardP.
Martin, Member, IEEE.2. Detectionof Dangerous Cornering in GNSS-Data-Driven Insurance Telematics JohanWahlström, Isaac Skog, Member, IEEE, and Peter Händel, Senior Member, IEEE.
3. Driver BehaviorAnalysis for Safe Driving: A Survey Sinan Kaplan, Mehmet Amac Guvensan,Member,IEEE, Ali Gokhan Yavuz,and Yasin Karalurt.4.Determining Driver Phone Use byExploiting Smartphone Integrated Sensors.
Yan Wang, Yingying (Jennifer) Chen, Jie Yang, Marco Gruteser, Richard P.Martin, Hongbo Liu, Luyang Liu, and Cagdas Karatas5.Detecting Driver’s SmartphoneUsage via Nonintrusively Sensing Driving Dynamics. Cheng Bo, Xuesi Jian, TaehoJung, Junze Han, Xiang-Yang Li, Fellow, IEEE, Xufei Mao, Member, IEEE, and YuWang, Senior Member, IEEE.6.
Automatic Identi?cation ofDriver’s Smartphone Exploiting Common Vehicle-Riding Actions. Homin Park,DaeHan Ahn, Taejoon Park , Member, IEEE, and Kang G. Shin, Fellow, IEEE7.Improved Vehicle Steering PatternRecognition by Using Selected Sensor Data.
Zhenchao Ouyang, Jianwei Niu,Member, IEEE, Mohsen Guizani, Fellow, IEEE.8. Full auto-calibrationof a smartphone on board a vehicle using IMU and GPS embedded sensors.
Javier Almaz´an, Luis M. Bergasa, J. JavierYebes, Rafael Barea and Roberto Arroyo.9. DriveSafe: an App forAlerting Inattentive Drivers and Scoring Driving Behaviors. Luis M. Bergasa,Daniel Almería, Javier Almazán, J.
Javier Yebes, Roberto Arroyo.10.TrackingVehicular Speed Variations bDriving Style Recognition Using a Smartphone as aSensor Platform11. Driving Style Recognition Using a Smartphoneas a Sensor Platform. Derick A. Johnson and Mohan M. ignal Strengths.
12.Are You aSafe Driver. Lonnie Langle, Ram Dantu13.Smartphone-BasedSensor Fusion for Improved Vehicular Navigation. Oliver Walter, JoergSchmalenstroeer, Andreas Engler, Reinhold Haeb-Umbach14.
BodySensor Networks for Driver Distraction Identification. Amardeep Sathyanarayana,Sandhya Nageswaren, Hassan Ghasemzadeh, Member, IEEE, Roozbeh Jafari, Member,IEEE, John H.L. Hansen, Fellow, IEEE.15.DetectingDriver Phone Calls in a Moving Vehicle Based on Voice Features.
Tianyi Song1,Xiuzhen Cheng1, Hongjuan Li1, Jiguo Yu2, Shengling Wang3, Rongfang Bie3