Artificial intelligence techniques for driving safety and vehicle crash prediction

Machine Learning Techniques for Arousal Classification from Electrodermal Activity: A Systematic Review

This article introduces a systematic review on arousal classification based on electrodermal activity (EDA) and machine learning (ML). From a first set of 284 articles searched for in six scientific databases, fifty-nine were finally selected according to various criteria established. The systematic review has made it possible to analyse all the steps to which the EDA signals are subjected: acquisition, pre-processing, processing and feature extraction. Finally, all ML techniques applied to the features of these signals for arousal classification have been studied. It has been found that support vector machines and artificial neural networks stand out within the supervised learning methods given their high-performance values. In contrast, it has been shown that unsupervised learning is not present in the detection of arousal through EDA. This systematic review concludes that the use of EDA for the detection of arousal is widely spread, with particularly good results in classification with the ML methods found.

Evaluation of Contributing Factors Affecting Number of Vehicles Involved in Crashes Using Machine Learning Techniques in Rural Roads of Cosenza, Italy

The evaluation of road safety is a critical issue having to be conducted for successful safety management in road transport systems, whereas safety management is considered in road transportation systems as a challenging task according to the dynamic of this issue and the presence of a large number of effective parameters on road safety. Therefore, the evaluation and analysis of important contributing factors affecting the number of vehicles involved in crashes play a key role in increasing the efficiency of road safety. For this purpose, in this research work, two machine learning algorithms, including the group method of data handling (GMDH)-type neural network and a combination of support vector machine (SVM) and the grasshopper optimization algorithm (GOA), are employed. Hence, the number of vehicles involved in an accident is considered to be the output, and the seven factors affecting transport safety, including Daylight (DL), Weekday (W), Type of accident (TA), Location (L), Speed limit (SL), Average speed (AS), and Annual average daily traffic (AADT) of rural roads in Cosenza, southern Italy, are selected as the inputs. In this study, 564 data sets from rural areas were investigated, and the relevant, effective parameters were measured. In the next stage, several models were developed to investigate the parameters affecting the safety management of road transportation in rural areas. The results obtained demonstrated that the “Type of accident” has the highest level and “Location” has the lowest importance in the investigated rural area. Finally, although the results of both algorithms were the same, the GOA-SVM model showed a better degree of accuracy and robustness than the GMDH model.

Solutions to the routing problem: towards trustworthy autonomous vehicles

The general expectation is that the traffic in the cities will be almost optimal when the collective behaviour of autonomous vehicles will determine the traffic. Each member of the collective of autonomous vehicles tries to adapt to the changing environment, therefore together they execute decentralised autonomous adaptation by exploiting real-time information about their environment. The routing of these vehicles needs proper computer science models to be able to develop the best information technology for their control. We review different traffic flow models in computer science, and we evaluate their usefulness and applicability to autonomous vehicles. The classical game theory model implies flow level decision making in route selection. Non-cooperative autonomous vehicles may produce unwanted traffic patterns. Improved decentralised autonomous adaptation techniques try to establish some kind of coordination among autonomous vehicles, mainly through intention awareness. The aggregation of the intentions of autonomous vehicles may help to predict future traffic situations. The novel intention-aware online routing game model points out that intention-awareness helps to avoid that the traffic generated by autonomous vehicles be worse than the traffic indicated by classical traffic flow models. The review helps to make the first steps towards research on global level control of autonomous vehicles by highlighting the strengths and weaknesses of the different formal models. The review also highlights the importance of research on intention-awareness and intention-aware traffic flow prediction methods.

Harnessing artificial intelligence for the next generation of 3D printed medicines

Artificial intelligence (AI) is redefining how we exist in the world. In almost every sector of society, AI is performing tasks with super-human speed and intellect; from the prediction of stock market trends to driverless vehicles, diagnosis of disease, and robotic surgery. Despite this growing success, the pharmaceutical field is yet to truly harness AI. Development and manufacture of medicines remains largely in a 'one size fits all' paradigm, in which mass-produced, identical formulations are expected to meet individual patient needs. Recently, 3D printing (3DP) has illuminated a path for on-demand production of fully customisable medicines. Due to its flexibility, pharmaceutical 3DP presents innumerable options during formulation development that generally require expert navigation. Leveraging AI within pharmaceutical 3DP removes the need for human expertise, as optimal process parameters can be accurately predicted by machine learning. AI can also be incorporated into a pharmaceutical 3DP 'Internet of Things', moving the personalised production of medicines into an intelligent, streamlined, and autonomous pipeline. Supportive infrastructure, such as The Cloud and blockchain, will also play a vital role. Crucially, these technologies will expedite the use of pharmaceutical 3DP in clinical settings and drive the global movement towards personalised medicine and Industry 4.0.

A dynamic center and multi threshold point based stable feature extraction network for driver fatigue detection utilizing EEG signals

Driver fatigue is the one of the main reasons of the traffic accidents. The human brain is a complex structure, whose function can be evaluated with electroencephalogram (EEG). Automated driver fatigue detection utilizing EEG decreases the incidence probability of related traffic accidents. Therefore, devising an appropriate feature extraction technique and selecting a competent classification method can be considered as the crucial part of the effective driver fatigue detection. Therefore, in this study, an EEG-based intelligent system was devised for driver fatigue detection. The proposed framework includes a new feature generation network, which is implemented by using texture descriptors, for fatigue detection. The proposed scheme contains pre-processing, feature generation, informative features selection and classification with shallow classifiers phases. In the pre-processing, discrete cosine transform and fast Fourier transform are used together. Moreover, dynamic center based binary pattern and multi threshold ternary pattern are utilized together to create a new feature generation network. To improve the detection performance, we utilized discrete wavelet transform as a pooling method, in which the functional brain network-based feature describing the relationship between fatigue and brain network organization. In the feature selection phase, a hybrid three layered feature selection method is presented, and benchmark classifiers are used in the classification phase to demonstrate the strength of the proposed method. In the experiments, the proposed framework achieved 97.29% classification accuracy for fatigue detection using EEG signals. This result reveals that the proposed framework can be utilized effectively for driver fatigue detection.

Prediction of gas velocity in two-phase flow using developed fuzzy logic system with differential evolution algorithm

In this investigation, differential evolution (DE) algorithm with the fuzzy inference system (FIS) are combined and the DE algorithm is employed in FIS training process. Considered data in this study were extracted from simulation of a 2D two-phase reactor in which gas was sparged from bottom of reactor, and the injected gas velocities were between 0.05 to 0.11 m/s. After doing a couple of training by making some changes in DE parameters and FIS parameters, the greatest percentage of FIS capacity was achieved. By applying the optimized model, the gas phase velocity in x direction inside the reactor was predicted when the injected gas velocity was 0.08 m/s.

Thermal prediction of turbulent forced convection of nanofluid using computational fluid dynamics coupled genetic algorithm with fuzzy interface system

Computational fluid dynamics (CFD) simulating is a useful methodology for reduction of experiments and their associated costs. Although the CFD could predict all hydro-thermal parameters of fluid flows, the connections between such parameters with each other are impossible using this approach. Machine learning by the artificial intelligence (AI) algorithm has already shown the ability to intelligently record engineering data. However, there are no studies available to deeply investigate the implicit connections between the variables resulted from the CFD. The present investigation tries to conduct cooperation between the mechanistic CFD and the artificial algorithm. The genetic algorithm is combined with the fuzzy interface system (GAFIS). Turbulent forced convection of Al₂O₃/water nanofluid in a heated tube is simulated for inlet temperatures (i.e., 305, 310, 315, and 320 K). GAFIS learns nodes coordinates of the fluid, the inlet temperatures, and turbulent kinetic energy (TKE) as inputs. The fluid temperature is learned as output. The number of inputs, population size, and the component are checked for the best intelligence. Finally, at the best intelligence, a formula is developed to make a relationship between the output (i.e. nanofluid temperatures) and inputs (the coordinates of the nodes of the nanofluid, inlet temperature, and TKE). The results revealed that the GAFIS intelligence reaches the highest level when the input number, the population size, and the exponent are 5, 30, and 3, respectively. Adding the turbulent kinetic energy as the fifth input, the regression value increases from 0.95 to 0.98. This means that by considering the turbulent kinetic energy the GAFIS reaches a higher level of intelligence by distinguishing the more difference between the learned data. The CFD and GAFIS predicted the same values of the nanofluid temperature.

Driver Fatigue Detection Systems Using Multi-Sensors, Smartphone, and Cloud-Based Computing Platforms: A Comparative Analysis

Internet of things (IoT) cloud-based applications deliver advanced solutions for smart cities to decrease traffic accidents caused by driver fatigue while driving on the road. Environmental conditions or driver behavior can ultimately lead to serious roadside accidents. In recent years, the authors have developed many low-cost, computerized, driver fatigue detection systems (DFDs) to help drivers, by using multi-sensors, and mobile and cloud-based computing architecture. To promote safe driving, these are the most current emerging platforms that were introduced in the past. In this paper, we reviewed state-of-the-art approaches for predicting unsafe driving styles using three common IoT-based architectures. The novelty of this article is to show major differences among multi-sensors, smartphone-based, and cloud-based architectures in multimodal feature processing. We discussed all of the problems that machine learning techniques faced in recent years, particularly the deep learning (DL) model, to predict driver hypovigilance, especially in terms of these three IoT-based architectures. Moreover, we performed state-of-the-art comparisons by using driving simulators to incorporate multimodal features of the driver. We also mention online data sources in this article to test and train network architecture in the field of DFDs on public available multimodal datasets. These comparisons assist other authors to continue future research in this domain. To evaluate the performance, we mention the major problems in these three architectures to help researchers use the best IoT-based architecture for detecting DFDs in a real-time environment. Moreover, the important factors of Multi-Access Edge Computing (MEC) and 5th generation (5G) networks are analyzed in the context of deep learning architecture to improve the response time of DFD systems. Lastly, it is concluded that there is a research gap when it comes to implementing the DFD systems on MEC and 5G technologies by using multimodal features and DL architecture.

A Novel Cross-Layer V2V Architecture for Direction-Aware Cooperative Collision Avoidance

The death toll due to highway crashes is increasing at an alarming rate across the globe. Vehicular Ad Hoc Networks (VANETs) have emerged as a promising solution to prevent crashes by enabling collision avoidance applications. However, a robust and stable collision avoidance application is a cross-layer problem that must address a number of key challenges across all layers of a VANET communication architecture. This paper presents and evaluates a novel VANET protocol suite, named Direction-Aware Vehicular Collision Avoidance (DVCA), which covers application, security services, network, and link layers. DVCA is a vehicle-to-vehicle communication architecture that provides enhanced collision probability computation and adaptive preventive measures for cooperative collision avoidance on bi-directional highways. Moreover, DVCA enables secure, in-time, and reliable dissemination of warning messages, which provides adequate time for vehicles to prevent collisions. Simulation and analytical results demonstrate reasonable reduction in collisions by DVCA, as compared with eminent VANET communication architectures.

Cyclist Injury Severity in Spain: A Bayesian Analysis of Police Road Injury Data Focusing on Involved Vehicles and Route Environment

This study analyses factors associated with cyclist injury severity, focusing on vehicle type, route environment, and interactions between them. Data analysed was collected by Spanish police during 2016 and includes records relating to 12,318 drivers and cyclist involving in collisions with at least one injured cyclist, of whom 7230 were injured cyclists. Bayesian methods were used to model relationships between cyclist injury severity and circumstances related to the crash, with the outcome variable being whether a cyclist was killed or seriously injured (KSI) rather than slightly injured. Factors in the model included those relating to the injured cyclist, the route environment, and involved motorists. Injury severity among cyclists was likely to be higher where an Heavy Goods Vehicle (HGV) was involved, and certain route conditions (bicycle infrastructure, 30 kph zones, and urban zones) were associated with lower injury severity. Interactions exist between the two: collisions involving large vehicles in lower-risk environments are less likely to lead to KSIs than collisions involving large vehicles in higher-risk environments. Finally, motorists involved in a collision were more likely than the injured cyclists to have committed an error or infraction. The study supports the creation of infrastructure that separates cyclists from motor traffic. Also, action needs to be taken to address motorist behaviour, given the imbalance between responsibility and risk.

PDMAC: A Priority-Based Enhanced TDMA Protocol for Warning Message Dissemination in VANETs

Vehicular ad hoc networks (VANETs) are the key enabling technology for intelligent transportation systems. Carrier-sense multiple access with collision avoidance (CSMA/CA) is the de facto media access standard for inter-vehicular communications, but its performance degrades in high-density networks. Time-division multiple access (TDMA)-based protocols fill this gap to a certain extent, but encounter inefficient clock synchronization and lack of prioritized message delivery. Therefore, we propose a priority-based direction-aware media access control (PDMAC) as a novel protocol for intra-cluster and inter-cluster clock synchronization. Furthermore, PDMAC pioneers a three-tier priority assignment technique to enhance warning messages delivery by taking into account the direction component, message type, and severity level on each tier. Analytical and simulation results validate the improved performance of PDMAC in terms of clock synchronization, channel utilization, message loss rate, end-to-end delays, and network throughput, as compared with eminent VANET MAC protocols.

A forward collision avoidance algorithm based on driver braking behavior

Measuring risk is critical for collision avoidance. The paper aims to develop an online risk level classification algorithm for forward collision avoidance systems. Assuming risk levels are reflected by braking profiles, deceleration curves from critical evasive braking events from the Virginia "100-car" database were first extracted. The curves are then clustered into different risk levels based on spectrum clustering, using curve distance and curve changing rate as dissimilarity metrics among deceleration curves. Fuzzy logic rules of safety indicators at critical braking onset for risk classification were then extracted according to the clustered risk levels. The safety indicators include time to collision, time headway, and final relative distance under emergency braking, which characterizes three kinds of uncertain critical conditions respectively. Finally, the obtained fuzzy risk level classification algorithm was tested and compared with other Automatic Emergency Braking (AEB) algorithms under Euro-NCAP testing scenarios in simulation. Results show the proposed algorithm is promising in balancing the objectives of avoiding collision and reducing interference with driver's normal driving compared with other algorithms.

Freeway crash risks evaluation by variable speed limit strategy using real-world traffic flow data

The primary objective of this study is to evaluate the real-time crash risk of freeways by using real-world traffic flow data. The crash risk expressed as the potential crash likelihood is assessed under variable speed limit (VSL) and without VSL, in which both spatial correlation between different sites and temporal similarity are contained. Traffic flow data of Whitemud Drive network (WMD) in Canada is used to perform the relevant analysis, including VSL implementation analysis, traffic flow similarity analysis, crash risk and congestion analysis. Analytical results demonstrate that the average traffic flow under VSL schemes 1, 2, 3 and 4 are highly correlated from spatial-temporal perspective. The crash likelihoods and congestions under these VSL schemes are greatly improved. The best VSL control scheme, the most dangerous area and time, together with the most congested station of WMD are eventually determined. Subsequently, a t-test is employed to examine the significance of these results. t-Test results suggest that the improvement degree between crash risk and congestion under the best VSL control scheme show a difference, i.e., the best VSL control scheme can reduce the crash risk of moderate risk area more than high risk area, while it may have a larger melioration on the most congested area than the relatively uncongested area. Finally, these results are considered to have the potential reference in the mitigation of WMD traffic issues.

3D Reconstruction for Road Scene with Obstacle Detection Feedback

This paper presented 3D reconstruction method for road scene with the help of obstacle detection. 3D reconstruction for road scene can be used in autonomous driving, driver assistance system, car navigation systems. However, some errors often rose when 3D reconstructing due to the shade from the moving object in the road scene. The presented 3D reconstruction method with obstacle detection feedback can avoid this problem. Firstly, this paper offers a framework for the 3D reconstruction of road scene by laser scanning and vision. A calibration method based on the location of horizon is proposed, and a method of attitude angle measuring based on vanishing point is proposed to revise the 3D reconstruction result. Secondly, the reconstruction framework is extended by integrating with an object recognition that can automatically detect and discriminate obstacles in the input video streams by a RANSAC approach and threshold filter, and localizes them in the 3D model. 3D reconstruction and obstacle detection are tightly integrated and benefit from each other. The experiment result verified the feasibility and practicability of the proposed method.

Methodological evolution and frontiers of identifying, modeling and preventing secondary crashes on highways

Secondary crashes (SCs) or crashes that occur within the boundaries of the impact area of prior, primary crashes are one of the incident types that frequently affect highway traffic operations and safety. Existing studies have made great efforts to explore the underlying mechanisms of SCs and relevant methodologies have been evolving over the last two decades concerning the identification, modeling, and prevention of these crashes. So far there is a lack of a detailed examination on the progress, lessons, and potential opportunities regarding existing achievements in SC-related studies. This paper provides a comprehensive investigation of the state-of-the-art approaches; examines their strengths and weaknesses; and provides guidance in exploiting new directions in SC-related research. It aims to support researchers and practitioners in understanding well-established approaches so as to further explore the frontiers. Published studies focused on SCs since 1997 have been identified, reviewed, and summarized. Key issues concentrated on the following aspects are discussed: (i) static/dynamic approaches to identify SCs; (ii) parametric/non-parametric models to analyze SC risk, and (iii) deployable countermeasures to prevent SCs. Based on the examined issues, needs, and challenges, this paper further provides insights into potential opportunities such as: (a) fusing data from multiple sources for SC identification, (b) using advanced learning algorithms for real-time SC analysis, and (c) deploying connected vehicles for SC prevention in future research. This paper contributes to the research community by providing a one-stop reference for research on secondary crashes.