When the drivers approaching signalized intersections(onset of yellow signal),the drivers would enter into a zone,where they will be in uncertain mode assessing their capabilities to stop or cross the intersection.The...When the drivers approaching signalized intersections(onset of yellow signal),the drivers would enter into a zone,where they will be in uncertain mode assessing their capabilities to stop or cross the intersection.Therefore,any improper decision might lead to a right-angle or back-end crash.To avoid a right-angle collision,drivers apply the harsh brakes to stop just before the signalized intersection.But this may lead to a back-end crash when the following driver encounters the former's sudden stopping decision.This situation gets multifaceted when the traffic is heterogeneous,containing various types of vehicles.In order to reduce this issue,this study's primary objective is to identify the driving behaviour at signalized intersections based on the driving features(parameters).The secondary objective is to classify the outcome of driving behaviour(safe stopping and unsafe stopping)at the signalized intersection using a support vector machine(SVM)technique.Turning moments are used to identify the zones and label them accordingly for further classification.The classification of 50 instances is identified for training and testing using a 70%-30% rule resulted in an accuracy of 85% and 86%,respectively.Classification performance is further verified by random sampling using five cross-validation and 30 iterations,which gave an accuracy of 97% and 100% for training and testing.These results demonstrate that the proposed approach can help develop a pre-warning system to alert the drivers approaching signalized intersections,thus reducing back-end crash and accidents.展开更多
Traditional wireless sensor networks(WSNs)are not suitable for rough terrains that are difficult or impossible to access by humans.Smart dust is a technology that works with the combination of many tiny sensors which ...Traditional wireless sensor networks(WSNs)are not suitable for rough terrains that are difficult or impossible to access by humans.Smart dust is a technology that works with the combination of many tiny sensors which is highly useful for obtaining remote sensing information from rough terrains.The tiny sensors are sprinkled in large numbers on rough terrains using airborne distribution through drones or aircraftwithout manually setting their locations.Although it is clear that a number of remote sensing applications can benefit from this technology,but the small size of smart dust fundamentally restricts the integration of advanced hardware on tiny sensors.This raises many challenges including how to estimate the location of events sensed by the smart dusts.Existing solutions on estimating the location of events sensed by the smart dusts are not suitable for monitoring rough terrains as these solutions depend on relay sensors and laser patterns which have their own limitations in terms of power constraint and uneven surfaces.The study proposes a novel machine learning based localization algorithm for estimating the location of events.The approach utilizes timestamps(time of arrival)of sensed events received at base stations by assembling them into a multidimensional vector and input to a machine learning classifier for estimating the location.Due to the unavailability of real smart dusts,we built a simulator for analysing the accuracy of the proposed approach formonitoring forest fire.The experiments on the simulator show reasonable accuracy of the approach.展开更多
基金supported by Universiti Brunei Darussalam under the University Bursary ScholarshipUniversiti Brunei Darussalam's Research Grants(Nos,UBD/PNC2/2/RG/1(311)and UBD/RSCH/1.11/FICBF/2018/002)。
文摘When the drivers approaching signalized intersections(onset of yellow signal),the drivers would enter into a zone,where they will be in uncertain mode assessing their capabilities to stop or cross the intersection.Therefore,any improper decision might lead to a right-angle or back-end crash.To avoid a right-angle collision,drivers apply the harsh brakes to stop just before the signalized intersection.But this may lead to a back-end crash when the following driver encounters the former's sudden stopping decision.This situation gets multifaceted when the traffic is heterogeneous,containing various types of vehicles.In order to reduce this issue,this study's primary objective is to identify the driving behaviour at signalized intersections based on the driving features(parameters).The secondary objective is to classify the outcome of driving behaviour(safe stopping and unsafe stopping)at the signalized intersection using a support vector machine(SVM)technique.Turning moments are used to identify the zones and label them accordingly for further classification.The classification of 50 instances is identified for training and testing using a 70%-30% rule resulted in an accuracy of 85% and 86%,respectively.Classification performance is further verified by random sampling using five cross-validation and 30 iterations,which gave an accuracy of 97% and 100% for training and testing.These results demonstrate that the proposed approach can help develop a pre-warning system to alert the drivers approaching signalized intersections,thus reducing back-end crash and accidents.
基金This research is supported by Universiti Brunei Darussalam(UBD)under FIC allied research grant program.
文摘Traditional wireless sensor networks(WSNs)are not suitable for rough terrains that are difficult or impossible to access by humans.Smart dust is a technology that works with the combination of many tiny sensors which is highly useful for obtaining remote sensing information from rough terrains.The tiny sensors are sprinkled in large numbers on rough terrains using airborne distribution through drones or aircraftwithout manually setting their locations.Although it is clear that a number of remote sensing applications can benefit from this technology,but the small size of smart dust fundamentally restricts the integration of advanced hardware on tiny sensors.This raises many challenges including how to estimate the location of events sensed by the smart dusts.Existing solutions on estimating the location of events sensed by the smart dusts are not suitable for monitoring rough terrains as these solutions depend on relay sensors and laser patterns which have their own limitations in terms of power constraint and uneven surfaces.The study proposes a novel machine learning based localization algorithm for estimating the location of events.The approach utilizes timestamps(time of arrival)of sensed events received at base stations by assembling them into a multidimensional vector and input to a machine learning classifier for estimating the location.Due to the unavailability of real smart dusts,we built a simulator for analysing the accuracy of the proposed approach formonitoring forest fire.The experiments on the simulator show reasonable accuracy of the approach.
