توضیحات
ABSTRACT
This article presents a data mining methodology for driving-condition monitoring via CAN-bus data that is based on the general data mining process. The approach is applicable to many driving condition problems, and the example of road type classification without the use of location information is investigated. Location information from Global Positioning Satellites and related map data are often not available for business reasons, or cannot represent the full dynamics of road conditions. In this work, Controller Area Network CAN-bus signals are used instead as inputs to models produced by machine learning algorithms. Road type classification is formulated as two related labeling problems: Road Type A, B, C, and Motorway and Carriageway Type Single or Dual. An investigation is presented into preprocessing steps required prior to applying machine learning algorithms, that is, signal selection, feature extraction, and feature selection. The selection methods used include principal components analysis PCA and mutual information MI, which are used to determine the relevance and redundancy of extracted features and are performed in various combinations. Finally, because there is an inherent bias toward certain road and carriageway labelings, the issue of class imbalance in classification is explained and investigated. A system is produced, which is demonstrated to successfully ascertain road type from CAN-bus data, and it is shown that the classification correlates well with input signals such as vehicle speed, steering wheel angle, and suspension height
INTRODUCTION
Driving conditions monitoring aims to detect parameters about the road and a vehicle’s surroundings (Huang et al., 2011), such as the road surface, level of congestion, or weather. Knowledge of the current driving conditions can have several benefits: user interface adaptation, engine power management, and driver monitoring (Huang et al 2011 Langari and Won, 2005; Murphey et al., 2008; Park et al., 2008); all of which strive to improve driver safety and vehicle efficiency. In this paper we present a data mining methodology, based on the general data mining process, for driving condition monitoring via Controller Area Network (CAN)-bus data. Two related classification problems are considered, Road Type labelling (into types A, B, C and Motorway) and Carriageway Type labelling (into types Single or Dual). Road Type labelling aims to detect the state or governmental designation of roads from vehicle telemetry data. Using the same inputs, Carriageway Type labelling aims to detect whether the vehicle is being driven on a single or dual (or multi) track road.,
Year : 2016
Publisher : Taylor & Francis
By : Phillip Taylor, Nathan Griffths, Abhir Bhalerao, Sarabjot Anand ,Thomas Popham, Zhou Xu , and Adam Gelencser
File Information : English Language / 31 Page / Size : 1.2 MB
Download : click
سال : 2016
ناشر : Taylor & Francis
کاری از : Phillip Taylor, Nathan Griffths, Abhir Bhalerao, Sarabjot Anand ,Thomas Popham, Zhou Xu , and Adam Gelencser
اطلاعات فایل : زبان انگلیسی / 31 صفحه / حجم : 1.2 MB
لینک دانلود : روی همین لینک کلیک کنید
نقد و بررسیها
هیچ دیدگاهی برای این محصول نوشته نشده است.