Smartphone-based outlier detection: a complex event processing approach for driving behavior detection

Abstract

The majority of fatal car crashes are caused by reckless driving. With the sophistication of vehicle instrumentation, reckless maneuvers, such as abrupt turns, acceleration, and deceleration, can now be accurately detected by analyzing data related to the driver-vehicle interactions. Such analysis usually requires very specific in-vehicle hardware and infrastructure sensors (e.g. loop detectors and radars), which can be costly. Hence, in this paper, we investigated if off-the-shelf smartphones can be used to online detect and classify the driver's behavior in near real-time. To do so, we first modeled and performed an intrinsic evaluation to assess the performance of three outlier detection algorithms formulated as a data stream processing network which receives as input and processes data streams of smartphone and vehicle sensors. Next, we implemented a novel scoring mechanism based on online outlier detection to quantitatively evaluate drivers' maneuvers as either cautious or reckless. Thus, we adapted a data mining mechanism which takes into account a sensor's data rates and power to determine driver behavior in the scoring process. Finally, as the intrinsic evaluation does not necessarily reveal how well an algorithm will perform in a real-world scenario, we evaluated the algorithm that achieved the best result in a real-world case study to assess drivers' driving behavior. Our results indicate that the algorithm performs quickly and accurately; the algorithm classifies driver behavior with 95.45% accuracy. Moreover, such results are obtained within 100 milliseconds of processing time on average.

Analysis of Pedestrian Lane Change Behavior Spectrum Based on Video Data at Ticket Gate Facilities in Subway Stations

“…e interquartile method was common in outlier detection, which could be used to calculate the threshold of various distributed data [30]. In this research, the quartile method was used as a method to determine the threshold value of indicators of lane change behavior to obtain the upper and lower threshold range, which could be further used as a basis for distinguishing abnormal lane change behavior.…”

Risky Driver Recognition with Class Imbalance Data and Automated Machine Learning Framework

“…We determine the threshold using the Interquartile Range (IQR) method, which was proposed by Laurikkala et al [ 32 ]. It is a common method in outlier detection and can be used to calculate the threshold of abnormal data under various distribution [ 33 ]. The threshold can be calculated as follows.…”

Intelligent Intrusion Detection System Using Log Cluster Knowledge Inference Bayes in Complex Event Processing

“…This leaded to numerous variations in the substructure that answered curious and inspiring research questions. The resultant dynamic CEP infrastructure made not only the present requests more in uential and calmer to retain but also enabled original presentation domains [19]. Vasconcelos et al (2017) adapted and compared three classical o ine outlier discovery procedures to achieve online data stream treating with a CEP model.…”