Driver Behaviour Profiling Using Dynamic Bayesian Network

Obuhuma, James I.; Okoyo, Henry O.; McOyowo, Sylvester O.

doi:10.5815/ijmecs.2018.07.05

Cited by 12 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study extends the 2TBN model described in [2] by adding one extra variable i.e. obstacle to speed, altitude, direction and GPS signal strength variables.…”

Section: Driver Assistance and Profilingmentioning

confidence: 97%

“…There can be as many time-slices as the number of times the change in time is recorded. Driver behaviour profiles could thus be computed as described in [2] with a consideration of the additional obstacle variable.…”

Section: Driver Assistance and Profilingmentioning

confidence: 99%

“…A lot of research is being done towards assisting drivers in various ways to help improve on road safety. Two such recent studies were conducted by Obuhuma, Okoyo and McOyowo [1,2], in a move to explore mechanisms for driver assistance and driver profiling.…”

Section: Introductionmentioning

confidence: 99%

“…The second study [2] demonstrated the application of Dynamic Bayesian Networks (DBN) in the determination of driving styles with respect to acceleration, cornering and braking patterns. Test results showed that the 2-Time-slice Bayesian Network (2TBN) model is suitable for generation of driver profiles using only four GPS data parameters, namely, speed, altitude, direction and GPS signal strength against time [2]. The model classifies driver profiles into two sets of observations: driver behaviour and nature of operational environment.…”

Section: Introductionmentioning

confidence: 99%

“…The two studies [1,2] were limited to the use of only GPS data as a way to offer cost effective, easy to implement and use solutions that could find many applications in vehicle driver recruiting firms, vehicle insurance companies and transport and road safety authorities among other sectors.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Shortcomings of Ultrasonic Obstacle Detection for Vehicle Driver Assistance and Profiling

Obuhuma¹,

Okoyo²,

McOyowo³

2019

IJITCS

View full text Add to dashboard Cite

Obstacle detection is a challenging problem that has attracted much attention recently, especially in the context of research in self-driving car technologies. A number of obstacle detection technologies exist.Ultrasound is among the commonly used technologies due to its low cost compared to other technologies. This paper presents some findings on the research that has been carried out by the authors with regard to vehicle driver assistance and profiling. It discusses an experiment for detection of obstacles in a vehicle driver's operational environment using ultrasound technology. Experiment results clearly depict the capabilities and limitations of ultrasound technology in detection of obstacles under motion and obstacles with varied surfaces. Ultrasound's wavelength, beam width, directionality among others are put into consideration. Pros and cons of other technologies that could replace ultrasound, for instance RADAR and LIDAR technologies are also discussed. The study recommends sensor fusion where several types of sensor technologies are combined to complement one another. The study was a technical test of configurable technology that could guide future studies on obstacle detection intending to use infrared, sound, radio or laser technologies particularly when both the sensor and obstacle are in motion and when obstacles have differing unpredictable surface properties.

show abstract

“…This study extends the 2TBN model described in [2] by adding one extra variable i.e. obstacle to speed, altitude, direction and GPS signal strength variables.…”

Section: Driver Assistance and Profilingmentioning

confidence: 97%

Section: Driver Assistance and Profilingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Shortcomings of Ultrasonic Obstacle Detection for Vehicle Driver Assistance and Profiling

Obuhuma¹,

Okoyo²,

McOyowo³

2019

IJITCS

View full text Add to dashboard Cite

show abstract

Determination of Race Using the FFRACE Software Package

Zvyagin

Фомина

Galitskaya

et al. 2022

Advances in Artificial Systems for Medicine and Education V

View full text Add to dashboard Cite

Information technologies are used in all spheres of public life. They are also effectively introduced into the work of forensic experts and criminologists. The use of specialized software can significantly increase the efficiency of solving practical problems and the scientific validity of the conclusions obtained as a result of an expertise. This article describes the algorithm and software package "FFRACE", designed to determine the race of an individual (Caucasoid or Mongoloid) by eighteen external identification features of the head. The proposed algorithm is based on the step-by-step Bayes procedure modified by A.A. Genkin. The software complex, developed on the basis of the constructed algorithm, includes a module for inputting initial information, a module for fixing external identification features of the head, and a module for racial diagnostics. The result of the race determination in the software package is an expert opinion containing a conclusion about the race of the individual. The software package is intended for use both in laboratory research and at a scene of an accident.

show abstract