A real-time driver identification system based on artificial neural networks and cepstral analysis

Campo, I. del; Finker, Raul; Martínez, María Victoria Luna; Echanobe, Javier; Doctor, Faiyaz

doi:10.1109/ijcnn.2014.6889772

Cited by 34 publications

(23 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…which might learn [5][6][7][8], predict [9,10] and/or actuate [9,11] based on their purpose functionality.…”

Section: Adas Functions Utilize Advanced Algorithmsmentioning

confidence: 99%

“…• Noise reduction by subtracting noise o Active Noise Cancellation [12][13][14][15] • Zero/minimum phase delay filtering o Adaptive and Predictive filters [16,17] o Forward-backward filters [18,19] • Noise characterization o Noise Adaptive Models [13,20] It is also in the scope of this research to use novel or uncommon analysis techniques such as presence of chaos determination [21][22][23] or Cepstral analysis [6]. The creation of supporting software tools is also considered.…”

Section: Adas Functions Utilize Advanced Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Advanced digital signal processing methods for effective noise cancellation of vehicle related signals. State of the Art

Rabadán

2018

DOCTUMH

View full text Add to dashboard Cite

Métodos avanzados de procesado digital de la señal para la cancelación eficiente del ruido en las señales características de un vehículo. Estado de la cuestión ISSN: 2530-7320 Vol. 3(1), 2017. Artículo p4 Daniel Carriazo Rabadán ABSTRACTThe current trend of vehicle technology's evolution points towards a further automation of the automobile. The information that such a vehicle processes and handles becomes therefore more important from the performance but also from the safety point of view. The main target of this research is to improve the reliability, accuracy and timing of the information measured by mass produced sensors, whether the sensors are set up in single or array configuration. The scope of the considered sensors covers those related to the automotive sector, both current and potential ones. It is planned to achieve the main target by 1) actively reducing the noise to increase the SNR of the sensor measurements and/or by 2) using advanced processing methods that remove/minimize the delay they introduce in the processing system.Key words: automotive, vehicle, digital signal processing, Active Noise Cancelling, Kalman filter, noise, chaos, filer, zero phase. RESUMENLa actual evolución de la tecnología automovilística apunta hacia una mayor automatización del automóvil. La información que este tipo de vehículo es capaz de manejar y procesar se convierte por tanto en clave, no sólo desde el rendimiento sino también desde el punto de vista de la seguridad. El principal objetivo de esta investigación es mejorar la fiabilidad, la precisión y el retraso de la información medida por sensores producidos de forma masiva, ya estén configurados aislada o matricialmente. El alcance de los sensores considerados abarca desde los actualmente usados en el sector automovilístico hasta los que potencialmente serán usados en dicho sector. Se planea conseguir el objetivo principal mediante 1) la reducción activa del ruido para aumentar la SNR de las medidas de los sensores y/o mediante 2) el uso de métodos avanzados de procesamiento que eliminan/minimizan el retraso introducido en el sistema de procesado.Palabras clave: automoción, vehículo, procesado digital de la señal, Cancelación Activa de Ruido, Kalman, ruido, caos, filtro, fase cero.

show abstract

“…which might learn [5][6][7][8], predict [9,10] and/or actuate [9,11] based on their purpose functionality.…”

Section: Adas Functions Utilize Advanced Algorithmsmentioning

confidence: 99%

Section: Adas Functions Utilize Advanced Algorithmsmentioning

confidence: 99%

Advanced digital signal processing methods for effective noise cancellation of vehicle related signals. State of the Art

Rabadán

2018

DOCTUMH

View full text Add to dashboard Cite

show abstract

“…Previous studies have been conducted on using direct human behavior signals, which are the record of activities performed by the drivers, including acceleration and brake pedal operations and steering angle of the steering wheel. The work in [11] proposed a method to identify drivers based on Artificial Neural Network and Cepstral Analysis using two driving signals collected from a specialized sensor-equipped vehicle which are gas pedal pressure and brake pedal pressure. They found that the identification rates decrease as the number of drivers to be identified increases.…”

Section: Modeling Of Driving Behaviorsmentioning

confidence: 99%

“…(1) Using unsupervised anomaly detection to minimize the necessity of assessing every input signal: driver identification usually involves recognition of numerous different patterns and previously proposed algorithms often find it necessary to recognize and assess every instant of input signals [7,[11][12][13]. However, for realtime applications, recognizing patterns by assessing every instant of input signal may not be practical as it can incur delays and also consume computational resources.…”

Section: Introductionmentioning

confidence: 99%

“…(2) Identifying drivers based on low-level signals using neural network with feature extraction and model construction: the proposed algorithms focus on using low-level signals from inertial sensors found in offthe-shelf devices (e.g., smartphones) unlike previous algorithms which require specialized sensors and/or driving simulators [7,8,[11][12][13][14]. The challenge is that, before being effectively deployed in real-world scenarios, driver identification algorithms will have to learn many distinct behaviors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining Unsupervised Anomaly Detection and Neural Networks for Driver Identification

Tanprasert

Saiprasert

Thajchayapong

2017

Journal of Advanced Transportation

View full text Add to dashboard Cite

This paper proposes an algorithm for real-time driver identification using the combination of unsupervised anomaly detection and neural networks. The proposed algorithm uses nonphysiological signals as input, namely, driving behavior signals from inertial sensors (e.g., accelerometers) and geolocation signals from GPS sensors. First anomaly detection is performed to assess if the current driver is whom he/she claims to be. If an anomaly is detected, the algorithm proceeds to find relevant features in the input signals and use neural networks to identify drivers. To assess the proposed algorithm, real-world data are collected from ten drivers who drive different vehicles on several routes in real-world traffic conditions. Driver identification is performed on each of the sevensecond-long driving behavior signals and geolocation signals in a streaming manner. It is shown that the proposed algorithm can achieve relatively high accuracy and identify drivers within 13 seconds. The proposed algorithm also outperforms the previously proposed driver identification algorithms. Furthermore, to demonstrate how the proposed algorithm can be deployed in real-world applications, results from real-world data associated with each operation of the proposed algorithm are shown step-by-step.

show abstract

Deep Neural Networks for Driver Identification Using Accelerometer Signals from Smartphones

Sánchez

Pozo

Gómez

2019

Business Information Systems

View full text Add to dashboard Cite

A real-time driver identification system based on artificial neural networks and cepstral analysis

Cited by 34 publications

References 15 publications

Advanced digital signal processing methods for effective noise cancellation of vehicle related signals. State of the Art

Advanced digital signal processing methods for effective noise cancellation of vehicle related signals. State of the Art

Combining Unsupervised Anomaly Detection and Neural Networks for Driver Identification

Deep Neural Networks for Driver Identification Using Accelerometer Signals from Smartphones

Contact Info

Product

Resources

About