“…They reveal similar data reduction ratios, implying that drivers exhibit homogeneous behavior from the viewpoint of data reduction. However, in terms of other viewpoints, such as the number of sudden brakes or abrupt steering-changes, drivers exhibit different patterns, which was also observed in [35]. We also find that the distinguishable patterns between two states (relatively constant in a drowsy state vs. continuously fluctuating in a non-drowsy state) observed in Figure 7 are stable over time, meaning that they can be used as pertinent indicators for exploring driver drowsiness.…”
Section: Correlation Analysis Resultssupporting
confidence: 57%
“…This paper demonstrates one specific objective; the interface is linked with a function that determines whether a driver has his/her eyes open or closed based on EAR for drowsiness detection. Our scheme can also be used for other objectives, such as over-speed recognition, aggressive turn detection and good driver selection, wherein the generic interface is linked with a function of speed estimation [29], steering wheel angle calculation [32] and driving score assessment [35], respectively.…”
Section: Discussionmentioning
confidence: 99%
“…However, our analysis reveals the correlations between OBD data and driver behavior video. Another area is making use of multiple correlated driving events to enhance analysis accuracy [32,35]. Besides, our approach can be used for data clustering on existing driving datasets, such as KITTI [8] and BDDV [24].…”
A variety of deep learning techniques are actively employed for advanced driver assistance systems, which in turn require gathering lots of heterogeneous driving data, such as traffic conditions, driver behavior, vehicle status and location information. However, these different types of driving data easily become more than tens of GB per day, forming a significant hurdle due to the storage and network cost. To address this problem, this paper proposes a novel scheme, called CoDR, which can reduce data volume by considering the correlations among heterogeneous driving data. Among heterogeneous datasets, CoDR first chooses one set as a pivot data. Then, according to the objective of data collection, it identifies data ranges relevant to the objective from the pivot dataset. Finally, it investigates correlations among sets, and reduces data volume by eliminating irrelevant data from not only the pivot set but also other remaining datasets. CoDR gathers four heterogeneous driving datasets: two videos for front view and driver behavior, OBD-II and GPS data. We show that CoDR decreases data volume by up to 91%. We also present diverse analytical results that reveal the correlations among the four datasets, which can be exploited usefully for edge computing to reduce data volume on the spot.
“…They reveal similar data reduction ratios, implying that drivers exhibit homogeneous behavior from the viewpoint of data reduction. However, in terms of other viewpoints, such as the number of sudden brakes or abrupt steering-changes, drivers exhibit different patterns, which was also observed in [35]. We also find that the distinguishable patterns between two states (relatively constant in a drowsy state vs. continuously fluctuating in a non-drowsy state) observed in Figure 7 are stable over time, meaning that they can be used as pertinent indicators for exploring driver drowsiness.…”
Section: Correlation Analysis Resultssupporting
confidence: 57%
“…This paper demonstrates one specific objective; the interface is linked with a function that determines whether a driver has his/her eyes open or closed based on EAR for drowsiness detection. Our scheme can also be used for other objectives, such as over-speed recognition, aggressive turn detection and good driver selection, wherein the generic interface is linked with a function of speed estimation [29], steering wheel angle calculation [32] and driving score assessment [35], respectively.…”
Section: Discussionmentioning
confidence: 99%
“…However, our analysis reveals the correlations between OBD data and driver behavior video. Another area is making use of multiple correlated driving events to enhance analysis accuracy [32,35]. Besides, our approach can be used for data clustering on existing driving datasets, such as KITTI [8] and BDDV [24].…”
A variety of deep learning techniques are actively employed for advanced driver assistance systems, which in turn require gathering lots of heterogeneous driving data, such as traffic conditions, driver behavior, vehicle status and location information. However, these different types of driving data easily become more than tens of GB per day, forming a significant hurdle due to the storage and network cost. To address this problem, this paper proposes a novel scheme, called CoDR, which can reduce data volume by considering the correlations among heterogeneous driving data. Among heterogeneous datasets, CoDR first chooses one set as a pivot data. Then, according to the objective of data collection, it identifies data ranges relevant to the objective from the pivot dataset. Finally, it investigates correlations among sets, and reduces data volume by eliminating irrelevant data from not only the pivot set but also other remaining datasets. CoDR gathers four heterogeneous driving datasets: two videos for front view and driver behavior, OBD-II and GPS data. We show that CoDR decreases data volume by up to 91%. We also present diverse analytical results that reveal the correlations among the four datasets, which can be exploited usefully for edge computing to reduce data volume on the spot.
“…For instance, in the work of [5] the authors attempt to score driving trips using a Bayesian classifier to differentiate between risky and safe maneuvers. In [7], the authors compared a Fuzzy Inference System [1], a Safety Index [13], a Bayesian regressor [5], a Multi-layer perceptron, a Random Forrest, a Support Vector regressor and a GP approach to learn how individuals score 200 virtual road trips, where each trip was represented by a feature vector containing the frequency of risky maneuvers. Results showed that the GP strategy was superior than competitors, even in some cases with statistical significance.…”
Section: Related Workmentioning
confidence: 99%
“…The problem of calculating a driving score based on the performance of the driver could be seen as a computational learning task, where given a feature vector that contains the frequency of risky maneuvers the goal is to assign a score to represent the driver's performance in a risk-safety scale (this problem could also be seen as a machine learning problem for human-rating). Recently, in [7] the authors presented the evaluation of seven different Machine Learning (ML) approaches to learn how individuals assigned a driving score. From this comparison a clear winner emerged, this being the Genetic Programming (GP) approach.…”
Road traffic injuries are a serious concern in emerging economies. Their death toll and economic impact are shocking, with 9 out of 10 deaths occurring in low or middle-income countries; and road traffic crashes representing 3% of their gross domestic product. One way to mitigate these issues is to develop technology to effectively assist the driver, perhaps making him more aware about how her (his) decisions influence safety. Following this idea, in this paper we evaluate computational models that can score the behavior of a driver based on a risky-safety scale. Potential applications of these models include car rental agencies, insurance companies or transportation service providers. In a previous work, we showed that Genetic Programming (GP) was a successful methodology to evolve mathematical functions with the ability to learn how people subjectively score a road trip. The input to this model was a vector of frequencies of risky maneuvers, which were supposed to be detected in a sensor layer. Moreover, GP was shown, even with statistical significance, to be better than six other Machine Learning strategies, including Neural Networks, Support Vector Regression and a Fuzzy Inference system, among others. A pending task, since then, was to evaluate if a more detailed comparison of different strategies based on GP could improve upon the best GP model. In this work, we evaluate, side by side, scoring functions evolved by three different variants of GP. In the end, the results suggest that two of these strategies are very competitive in terms of accuracy and simplicity, both generating models that could be implemented in current technology that seeks to assist the driver in real-world scenarios.
In this study, the relationship between space mean speed (
SMS
), flow rate and density of pedestrians was investigated in different pedestrian facilities, including 1 walkway, 2 sidewalks, 2 signalized crosswalks and 2 mid-block crosswalks. First, statistical analysis was performed to investigate the normality of data and correlation of variables. Regression analysis was then applied to determine the relationship between
SMS
, flow rate, and density of pedestrians. Finally, two prediction models of density were obtained using genetic programming (GP) and group method of data handling (GMDH) models, and k-fold and holdout cross-validation methods were used to evaluate the models. By the use of regression analysis, the mathematical relationships between variables in all facilities were calculated and plotted, and the best relationships were observed in flow rate-density diagrams. Results also indicated that GP had a higher
R
2
than GMDH in the prediction of pedestrian density in terms of flow rate and
SMS
, suggesting that GP was better able to model
SMS
and pedestrian density. Moreover, the application of k-fold cross-validation method in the models led to better performances compared to the holdout cross-validation method, which shows that the prediction models using k-fold were more reliable. Finally, density relationships in all facilities were obtained in terms of
SMS
and flow rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.