# A Precise Drunk Driving Detection Using Weighted Kernel Based on Electrocardiogram

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Design of ECG-Based DDD (ECG-DDD)

#### 2.1. ECG Datasets and Samples

#### 2.2. Preprocessing of ECG Signal

- Bandpass filter: During ECG signal segregation, the high energy components are utilized to distinguish two successive ECG samples because they are more likely to be identified. The energy of QRS components are relatively high and their energy spectra are concentrated within 5 Hz to 15 Hz [17]. The role of the bandpass filter is to filter out other unnecessary frequencies outside the range of QRS components.
- Differentiation: The turning points of Q, R, and S waves can be estimated by the changes of their slopes. The peak positions and values of Q, R, and S can consequently be obtained from the estimated turning points. Hence, the slopes of Q, R, and S waves are determined at this stage. The peak-to-peak values of QRS can be computed by the five-point derivative filter.
- Squaring and moving window integration: Signal squaring is a process that turns all data points positive and amplifies them for further processing. Practically, QRS cannot be determined by utilizing the slope of R alone because this slope can be different in many abnormal cases. Hence, moving window integration will be implemented to sort out more parameters such as QS interval. Extracted parameters will be used to determine QRS together with the slope of R.

#### 2.3. Feature Extraction for SVM

#### 2.4. Kernel for SVM

_{i}, x

_{j}) represents the kernel function for mapping the data to a feature space having higher dimension. There are four typical kernel functions [11,12]:

_{c}(x

_{i}, x

_{j}) will be formulated as:

_{p}is the weighting of the corresponding feature p.

_{p}of kernel K

_{c}is customized and the optimization function is formulated as:

## 3. Testing Results and Discussion

## 4. Conclusions

## Acknowledgments

## Author Contributions

## Conflicts of Interest

## References

- World Report on Road Traffic Injury Prevention; World Health Organization: Geneva, Switzerland, 2004.
- Dalal, K.; Lin, Z.; Gifford, M.; Svanström, L. Economics of global burden of road traffic injuries and their relationship with health system variables. Int. J. Prev. Med.
**2013**, 4, 1442–1450. [Google Scholar] [PubMed] - Drinking and Driving: A Road Safety Manual for Decision-Makers and Practitioners; Global Road Safety Partnership: Geneva, Switzerland, 2007.
- Global Status Report on Road Safety 2013: Supporting A Decade of Action, World Health Organization; World Health Organization: Geneva, Switzerland, 2013.
- Sakairi, M. Water-Cluster-Detecting Breath Sensor and Applications in Cars for Detecting Drunk or Drowsy Driving. IEEE Sens. J.
**2012**, 12, 1078–1083. [Google Scholar] [CrossRef] - Li, Z.; Jin, X.; Zhao, X. Drunk driving detection based on classification of multivariate time series. J. Saf. Res.
**2015**, 54, 61–67. [Google Scholar] [CrossRef] [PubMed] - Dai, J.; Teng, J.; Bai, X.; Shen, Z.; Xuan, D. Mobile phone based drunk driving detection. In Proceedings of the 2010 IEEE 4th International Conference on-NO PERMISSIONS in Pervasive Computing Technologies for Healthcare (PervasiveHealth), Munich, Germany, 22–25 March 2010; pp. 1–8.
- Murata, K.; Fujita, E.; Kojima, S.; Maeda, S.; Ogura, Y.; Kamei, T.; Tsuji, T.; Kaneko, S.; Yoshizumi, M.; Suzuki, N. Noninvasive Biological Sensor System for Detection of Drunk Driving. IEEE Trans. Inf. Technol. Biomed.
**2011**, 15, 19–25. [Google Scholar] [CrossRef] [PubMed] - Sun, Y.; Yu, X.B. An Innovative Nonintrusive Driver Assistance System for Vital Signal Monitoring. IEEE J. Biomed. Health Inf.
**2014**, 18, 1932–1939. [Google Scholar] [CrossRef] [PubMed] - Zhao, Z.; Yang, L.; Chen, D.; Luo, Y. A Human ECG Identification System Based on Ensemble Empirical Mode Decomposition. Sensors
**2013**, 13, 6832–6864. [Google Scholar] [CrossRef] [PubMed] - Santos, P.; Villa, L.F.; Reñones, A.; Bustillo, A.; Maudes, J. An SVM-Based Solution for Fault Detection in Wind Turbines. Sensors
**2015**, 15, 5627–5648. [Google Scholar] [CrossRef] [PubMed] - Li, X.; Chen, X.; Yan, Y.; Wei, W.; Wang, Z.J. Classification of EEG Signals Using a Multiple Kernel Learning Support Vector Machine. Sensors
**2014**, 14, 12784–12802. [Google Scholar] [CrossRef] [PubMed] - Memedi, M.; Khan, T.; Grenholm, P.; Nyholm, D.; Westin, J. Automatic and Objective Assessment of Alternating Tapping Performance in Parkinson’s Disease. Sensors
**2013**, 13, 16965–16984. [Google Scholar] [CrossRef] [PubMed] - Kypri, K.; Langley, J.; Stephenson, S. Episode-centred analysis of drinking to intoxication in university students. Alcohol Alcohol.
**2005**, 40, 447–452. [Google Scholar] [CrossRef] [PubMed] - Uyarel, H.; Ozdöl, C.; Karabulut, A.; Okmen, E.; Cam, N. Acute alcohol intake and P-wave dispersion in healthy men. Anatol. J. Cardiol.
**2005**, 5, 289–293. [Google Scholar] - Vapnik, V.N. Nature of Statistical Learning; Springer: Berlin, Germany, 1995. [Google Scholar]
- Tompkins, W.J. Biomedical Digital Signal Processing C-Language Examples and Laboratory Experiments for the IBM®PC; Prentice Hall: Upper Saddle River, NJ, USA, 2000; pp. 245–264. [Google Scholar]
- Kyoso, M.; Uchiyama, A. Development of an ECG identification system. In Proceedings of the IEEE 23rd Annual International Conference on Engineering in Medicine and Biology Society, Istanbul, Turkey, 25–28 October 2001; Volume 4, pp. 3721–3723.
- Sun, Q.; Feng, H.; Yan, X.; Zeng, Z. Recognition of a Phase-Sensitivity OTDR Sensing System Based on Morphologic Feature Extraction. Sensors
**2015**, 15, 15179–15197. [Google Scholar] [CrossRef] [PubMed] - Reeves, D.M.; Jacyna, G.M. Support vector machine regularization. Wiley Interdiscip. Rev. Comput. Stat.
**2011**, 3, 204–215. [Google Scholar] [CrossRef] - Hou, H.; Gao, Y.; Liu, D. A support vector machine with maximal information coefficient weighted kernel functions for regression. In Proceedings of the IEEE 2nd International Conference on Systems and Informatics (ICSAI), Shanghai, China, 15–17 November 2014; pp. 938–942.
- Zhu, W.; Zeng, N.; Wang, N. Sensitivity, specificity, accuracy, associated confidence interval and ROC analysis with practical SAS
^{®}implementations. In Proceedings of the NESUG proceedings: Health Care and Life Sciences, Baltimore, MA, USA, 14–17 November 2010; pp. 1–9. - Li, G.; Chung, W.-Y. Detection of Driver Drowsiness Using Wavelet Analysis of Heart Rate Variability and a Support Vector Machine Classifier. Sensors
**2013**, 13, 16494–16511. [Google Scholar] [CrossRef] [PubMed] - MedGadget. Toyota to Integrate ECG Sensors into Steering Wheels. Available online: http://www.medgadget.com/2011/07/toyota-to-integrate-ecg-sensors-into-steering-wheels.html (accessed on 19 January 2016).
- MedGadget. Ford Unveils Contactless ECG Sensing Driver Seat. Available online: http://www.medgadget.com/2011/05/ford-unveils-contactless-ecg-sensing-driver-seat.html (accessed on 19 January 2016).

Characteristics | Variations (Averaged) |
---|---|

P wave peak value | −11.21% |

R wave peak value | +19.54% |

S wave peak value | +8.14% |

R-R interval | −8.43% |

P-wave maximum duration (Pmax) | +9.07% |

P-wave dispersion (Pd) | +23.77% |

Kernel Types | Acc | Se | Sp | |
---|---|---|---|---|

K1a | Linear | 62.83% | 60.34% | 65.32% |

K1b | Weighted Linear | 69.04% | 67.86% | 70.22% |

K2a | Quadratic | 66.17% | 67.07% | 65.26% |

K2b | Weighted Quadratic | 75.61% | 73.27% | 77.95% |

K3a | Third order polynomial | 76.39% | 77.17% | 75.60% |

K3b | Weighted Third order polynomial | 87.52% | 88.32% | 86.71% |

K4a | Radial basis | 69.43% | 68.75% | 70.12% |

K4b | Weighted Radial basis | 81.76% | 81.01% | 82.49% |

© 2016 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Wu, C.K.; Tsang, K.F.; Chi, H.R.; Hung, F.H.
A Precise Drunk Driving Detection Using Weighted Kernel Based on Electrocardiogram. *Sensors* **2016**, *16*, 659.
https://doi.org/10.3390/s16050659

**AMA Style**

Wu CK, Tsang KF, Chi HR, Hung FH.
A Precise Drunk Driving Detection Using Weighted Kernel Based on Electrocardiogram. *Sensors*. 2016; 16(5):659.
https://doi.org/10.3390/s16050659

**Chicago/Turabian Style**

Wu, Chung Kit, Kim Fung Tsang, Hao Ran Chi, and Faan Hei Hung.
2016. "A Precise Drunk Driving Detection Using Weighted Kernel Based on Electrocardiogram" *Sensors* 16, no. 5: 659.
https://doi.org/10.3390/s16050659