Profiling drivers based on driver dependent vehicle driving features

Halim, Zahid; Kalsoom, Rizwana; Baig, Abdul Rauf

doi:10.1007/s10489-015-0722-6

Cited by 30 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It takes ranges of each parameter of all 3 types of players, ie, Expert, Medium, and Beginner player, and generates a random data of number of races required by the user (can be edited in the code). After getting required number of races, they are categorized in chunks of 5 races, and Steps 2 and 3 are computed on each chunk. Then, the result are saved in a matrix, and an NN LEARNER is trained() over the standard deviations of the player's performance as input, and the output is an entertainment value of per the performance ranging from 0 to 1. The target data is prepared by putting “1” against Expert, “0.5” against Intermediate, and “0” against Beginner player. Last, after the NN is trained with various number of iterations, real data of 5 different players with 5 races each is given to the NN (3 input neurons) and the relative amount of entertainment is achieved as the output of the NN trained.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…Then, the result are saved in a matrix, and an NN LEARNER is trained 26,27 over the standard deviations of the player's performance as input, and the output is an entertainment value of per the performance ranging from 0 to 1. Then, the result are saved in a matrix, and an NN LEARNER is trained 26,27 over the standard deviations of the player's performance as input, and the output is an entertainment value of per the performance ranging from 0 to 1.…”

Section: Algorithm For Measuring Entertainment Of Playermentioning

confidence: 99%

See 1 more Smart Citation

Player profiling and quality assessment of dynamic car racing tracks using entertainment quantifier technique

Javed¹,

Zafar²

2018

Computational Intelligence

View full text Add to dashboard Cite

Interactive games have been an interesting area of research and have many challenges. With the advancement in technology, games have been revolutionizing at each step per the emerging and variant interests of players. Recently, machine learning techniques are used for the generation of game content based on player's experience. The dynamic content generation in computer games based on player's experience and feedback is still a challenging task. This requires measurement of entertainment factor achieved by a player during a game. In order to measure entertainment factor, we need to incorporate human-computer interaction by evolution of game content with respect to player's response. Optimization techniques can be used for the measurement of entertainment factor and for the generation of dynamic game content. The use of computational intelligence techniques in game development can lead to a new domain called "computational intelligence in games." This research is focused on car racing game genre, and the paradigm selected for dynamicity is track generation of car racing game. It requires player profiling and classification of players. The optimization of track generation has been performed by using single and multiobjective genetic algorithm and particle swarm optimization. Initially, classification of player's rank based on data and theory-driven approaches has been performed. Moreover, 3 different techniques of defining ranges or boundaries of race parameters for player's rank classification are studied. The techniques are based on crisp values, neural 1046 network, and fuzzy inference process. Then, an entertainment quantifier technique is proposed for a player after playing a certain number of games based on dynamic content generation using multiobjective genetic algorithm using standard Pareto optimal front and an epsilon ( ) front. In conclusion, the method proposed for quantifying entertainment can be used to analyze and classify the trend in interests of a player according to which the game itself can dynamically generate. This will keep the interest of player intact and provides maximum entertainment experience per the interest of an individual. The proposed solution can easily be used in generation of any game content and can effectively be used in accurate measurement of entertaining factor of any game.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Section: Algorithm For Measuring Entertainment Of Playermentioning

confidence: 99%

Player profiling and quality assessment of dynamic car racing tracks using entertainment quantifier technique

Javed¹,

Zafar²

2018

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…The other groups found would require further investigation, as their criteria for classification of profiles and the attributes used for clustering are different. Other authors, such as Halim et al [9] have also identified those types of behaviour for smaller vehicles.…”

Section: B Comparison With the State-of-the-artmentioning

confidence: 97%

“…Halim et al [9] employed KM, fuzzy c-means and Model-Based Clustering (MBC) to determine four driving profiles from 50 drivers. Data was acquired with a hardware consisting of vehicle functionalities and a simulator software with a virtual driving environment.…”

Section: Related Workmentioning

confidence: 99%

Identifying Heavy Goods Vehicle Driving Styles in the United Kingdom

Figueredo

Agrawal

Mase

et al. 2019

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Although driving behaviour has been largely studied amongst private motor vehicles drivers, the literature addressing heavy goods vehicle (HGV) drivers is scarce. Identifying the existing groups of driving stereotypes and their proportions enables researchers, companies and policy makers to establish group-specific strategies to improve safety and economy. In addition, insights into driving styles can assist predicting drivers' reactions and therefore enable the modelling of interactions between vehicles and the possible obstacles encountered on a journey. Consequently, there are also contributions to the research and development of autonomous vehicles and smart roads. In this study our interest lies in investigating driving behaviour within the HGV community in the United Kingdom (UK). We conduct the analysis of a telematics dataset containing incident information on 21,193 HGV drivers across the UK. We are interested in answering two research questions: (i) What groups of behaviour are we able to uncover? (ii) How do these groups complement current findings in the literature? To answer these questions we apply a two-stage data analysis methodology involving consensus clustering and ensemble classification to the dataset. Through the analysis, eight patterns of behaviour are uncovered. It is also observed that although our findings have similarities to those from previous work on driving behaviour, further knowledge is obtained, such as extra patterns and driving traits arising from vehicle and road characteristics.

show abstract

“…Halim et al [17] also employs clustering algorithms i.e. K-Means, fuzzy c-means and Model-Based Clustering (MBC), to determine four driving profiles from 50 drivers, using 12 driving features in a controlled environment.…”

Section: Background a Related Workmentioning

confidence: 99%

Towards Real-Time Heavy Goods Vehicle Driving Behaviour Classification in the United Kingdom

Agrawal

Mase

Figueredo

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Determining the driving styles and the factors causing incidents in real time could assist stakeholders to promote actions and develop feedback systems to reduce risks, costs and to increase safety in roads. This paper presents a classification system for Heavy Goods Vehicles (HGVs) drivers, using a core set of driving pattern stereotypes which were uncovered from driving incidents across three years i.e. 2014, 2015 and 2016. To achieve that, the driving stereotypes are established by employing a 2-stage ensemble classification framework followed by a profile labelling algorithm to define the set of driving stereotypes. Very similar stereotypes are later merged to form the core driving stereotypes for UK HGV drivers. Upon establishing core driving stereotypes across these three years, a decision tree classifier learns the classification rules to identify the driving stereotypes for the HGV drivers in a new dataset. High accuracy is achieved, indicating that the core driving patterns uncovered in this work could potentially be employed to identify UK HGV driving patterns in real-time.

show abstract

Profiling drivers based on driver dependent vehicle driving features

Cited by 30 publications

References 38 publications

Player profiling and quality assessment of dynamic car racing tracks using entertainment quantifier technique

Player profiling and quality assessment of dynamic car racing tracks using entertainment quantifier technique

Identifying Heavy Goods Vehicle Driving Styles in the United Kingdom

Towards Real-Time Heavy Goods Vehicle Driving Behaviour Classification in the United Kingdom

Contact Info

Product

Resources

About