Feature Selection for Abnormal Driving Behavior Recognition Based on Variance Distribution of Power Spectral Density
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The detection and recognition of abnormal driving becomes crucial for achieving safety in Intelligent Transportation Systems (ITS). This paper presents a feature extraction method based on spectral data to train a neural network model for driving behavior recognition. The proposed method uses a two stage signal processing approach to derive time-saving and efficient feature vectors. For the first stage, the feature vector set is obtained by calculating variances from each frequency bin containing the power spectrum data. The feature set is further reduced in the second stage where an intersection method is used to select more significant features that are finally applied for training a neural network model. A stream of live signals are fed to the trained model which recognizes the abnormal driving behaviors. The driving behaviors considered in this study are weaving, sudden braking and normal driving. The effectiveness of the proposed method is demonstrated by comparing with existing methods, which are Particle Swarm Optimization (PSO) and Convolution Neural Network (CNN). The experiments show that the proposed approach achieves satisfactory results with less computational complexity.
Abstract
The detection and recognition of abnormal driving becomes crucial for achieving safety in Intelligent Transportation Systems (ITS). This paper presents a feature extraction method based on spectral data to train a neural network model for driving behavior recognition. The proposed method uses a two stage signal processing approach to derive time-saving and efficient feature vectors. For the first stage, the feature vector set is obtained by calculating variances from each frequency bin containing the power spectrum data. The feature set is further reduced in the second stage where an intersection method is used to select more significant features that are finally applied for training a neural network model. A stream of live signals are fed to the trained model which recognizes the abnormal driving behaviors. The driving behaviors considered in this study are weaving, sudden braking and normal driving. The effectiveness of the proposed method is demonstrated by comparing with existing methods, which are Particle Swarm Optimization (PSO) and Convolution Neural Network (CNN). The experiments show that the proposed approach achieves satisfactory results with less computational complexity.
참고문헌 (22)
- "Road Traffic Injuries" (2018)[URL]
- Z. Li, "Online Detection of Driver Fatigue Using Steering Wheel Angles for Real Driving Conditions", Sensors, 17(3), pp.495~ (2017)
- C. Ma, "DrivingSense: Dangerous Driving Behavior Identification Based on Smartphone Autocalibration", Mobile Information Systems, 2017 (2017)
- P. M. Lyons-Wall, "Abnormal Behavior Detection Using a Multi-modal Stochastic Learning Approach", International Conference on Intelligent Sensors, Sensor Networks and Information Processing (2008)
- G. Singh, "A Smartphone Based Technique to Monitor Driving Behavior Using DTW and Crowdsensing", Pervasive and Mobile Computing, 40, pp.56~70 (2017)
- M. Victoria, "Driving Behavior Signals and Machine Learning : A Personalized Driver Assistance System", 2015 IEEE 18th International Conference on Intelligent Transportation Systems, pp.2933~2940 (2015)
- C. Deng, "Driving Style Recognition Method Using Braking Characteristics Based on Hidden Markov Model", PloS one, 12(8), pp.e0182419~ (2017)
- X. Zhang, "SIFT-based Local Spectrogram Image Descriptor : a Novel Feature for Robust Music Identification", EURASIP Journal on Audio, Speech, and Music Processing, 2015(1), pp.6~ (2015)
- O. Steven Eyobu, "Feature Representation and Data Augmentation for Human Activity Classification Based on Wearable IMU Sensor Data Using a Deep LSTM Neural Network", Sensors, 18(9), pp.2892~ (2018)
- J. Wang, "Resting State EEG Abnormalities in Autism Spectrum Disorders", Journal of Neurodevelopmental Disorders, 5(1), pp.24~ (2013)
- R. Sun, "An Integrated Solution for Lane Level Irregular Driving Detection on Highways", Transportation Research Part C : Emerging Technologies, 56, pp.61~79 (2015)
- I. Vasconcelos, "Smartphone-based Outlier Detection : a Complex Event Processing Approach for Driving Behavior Detection", Journal of Internet Services and Applications, 8(1), pp.13~ (2017)
- J. Stipancic, "Vehicle Manoeuvers as Surrogate Safety Measures : Extracting Data From the GPS-Enabled Smartphones of Regular Drivers", Accident Analysis & Prevention, 115, pp.160~169 (2018)
- N. Kalra, "Analyzing Driver Behavior Using Smartphone Sensors : a Survey", Int. J. Electron. Electr. Eng, 7(7), pp.697~702 (2014)
- X. Su, "Activity Recognition with Smartphone Sensors", Tsinghua Science and Technology, 19(3), pp.235~249 (2014)
- M. M. Bejani, "A Context Aware System for Driving Style Evaluation by an Ensemble Learning on Smartphone Sensors Data", Transportation Research Part C : Emerging Technologies, 89, pp.303~320 (2018)
- P. Dhar, "Unsafe Driving Detection System Using Smartphone as Sensor Platform", International Journal of Enhanced Research in Management & Computer Applications, 3(3), pp.65~70 (2014)
- H. Nassuna, "Feature Selection Based on Variance Distribution of Power Spectral Density for Driving Behavior Recognition", 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp.335~338 (2019)
- M. Zhang, "SafeDrive : Online Driving Anomaly Detection From Large-scale Vehicle Data", IEEE Transactions on Industrial Informatics, 13(4), pp.2087~2096 (2017)
- F. Li, "Dangerous Driving Behavior Detection Using Smartphone Sensors", 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), pp.1902~1907 (2016)
- M. Hall, "The WEKA Data Mining Software : an Update", ACM SIGKDD explorations newsletter, 11(1), pp.10~18 (2009)
- "Patternnet"[URL]