Detection of Driver Cognitive Distraction Using Machine Learning Methods

Misra, Apurva

doi:10.1109/access.2023.3245122

Cited by 19 publications

(2 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a plethora of studies that utilize several traditional machine-learning techniques to classify driver behavior [25], [26]. In a recent study, Misra et al [27] analyzed the data extracted from bio-signals and vehicular sensors to classify drivers. The study applied multiple machine learning algorithms to investigate the driving behavior of 40 drivers in different scenarios.…”

Section: A Traditional Machine Learning Based Techniquesmentioning

confidence: 99%

A Deep Learning-Based IDS for Automotive Theft Detection for In-Vehicle CAN Bus

Khan,

Lim,

Kim

2023

IEEE Access

View full text Add to dashboard Cite

Driver behavior features extracted from the controller area network (CAN) have potential applications in improving vehicle safety. However, the development of a classifier-based IDS for in-vehicle networks remains an open research problem. To address this challenge, we incorporate novel n-fold crossvalidation windowing techniques on two publicly available driving behavior datasets. A driver classificationbased IDS is proposed using the LSTM-FCN model that utilizes the strengths of both fully convolutional network (FCN) and long short-term memory (LSTM) networks. These modules allow the model to learn spatial and temporal features and utilize contextual information. In addition, we combine three squeeze and excite (SnE) layers following FCN layers to incorporate adjacent spatial locations and augment a scaled dot product attention mechanism into the LSTM to improve its feature selection and extraction capabilities. Our proposed IDS uses hacking and countermeasure research lab (HCRL) and test datasets, which achieve an improvement in accuracy of 4.18% and 13.99% respectively, from the baseline LSTM-FCN model. The experimental results of our method exhibited an overall accuracy of 99.36% and 96.36% for both datasets and outperformed various state-of-the-art methods.

show abstract

Section: A Traditional Machine Learning Based Techniquesmentioning

confidence: 99%

A Deep Learning-Based IDS for Automotive Theft Detection for In-Vehicle CAN Bus

Khan,

Lim,

Kim

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Machine learning algorithms are increasingly used to detect driver behavior patterns by analyzing data collected through smartphone motion sensors [6], [7]. Machine learning models can identify safe or risky driving behavior patterns by monitoring speed, acceleration, and braking.…”

Section: Introductionmentioning

confidence: 99%

Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach

Raza,

Akhtar,

Abualigah

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Driver behavior refers to the actions and attitudes of individuals behind the wheel of a vehicle. Poor driving behavior can have serious consequences, including accidents, injuries, and fatalities. One of the main disadvantages of poor driving behavior is the increased risk of road accidents, higher insurance premiums, fines, and even criminal charges. The primary aim of our study is to detect driver behavior early with high-performance scores. The publicly available smartphone motion sensor data is utilized to conduct our study experiments. A novel LR-RFC (Logistic Regression Random Forest Classifier) method is proposed for feature engineering. The proposed LR-RFC method combines the logistic regression and random forest classifier for feature engineering from the motion sensor data. The original smartphone motion sensor data is input into the LR-RFC method, generating new probabilistic features. The newly extracted probabilistic features are then input to the applied machine learning methods for predicting driver behavior. The study results show that the proposed LR-RFC approach achieves the highest performance score. Extensive study experiments demonstrate that the random forest achieved the highest performance score of 99% using the proposed LR-RFC method. The performance is validated using k-fold cross-validation and hyperparameter optimization. Our novel proposed study has the potential to revolutionize the early detection of driver behavior to avoid road accidents.INDEX TERMS Machine learning, driver behavior, sensor data, feature engineering, ensemble learning.

show abstract

Smart Driving Hardware Augmentation by Flexible Piezoresistive Sensor Matrices with Grafted‐on Anticreep Composites

Chen,

Yang,

Wang

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Signal drift and hysteresis of flexible piezoresistive sensors pose significant challenges against the widespread applications in emerging fields such as electronic skin, wearable equipment for metaverse and human‐AI (artificial intelligence) interfaces. To address the creep and relaxation issues associated with pressure‐sensitive materials, a highly stable piezoresistive composite is proposed, using polyamide‐imide (PAI) fibers as the matrix and in situ grafted‐polymerized polyaniline (PANI) as the semi‐conducting layer. The PAI with large rigid fluorenylidene groups exhibits a high glass transition temperature of 372 °C (PAI 5‐5), which results in an extremely long relaxation time at room temperature and consequently offers outstanding anti‐creep/relaxation performances. The enhancement of PAI‐PANI interfacial bonding through in situ grafting improves the sensor reliably. The sensor presents high linear sensitivity of 35.3 kPa−1 over a pressure range of 0.2–20 kPa, outstanding repeatability, and excellent dynamic stability with only a 3.8% signal deviation through ≈10 000 cycles. Real‐time visualization of pressure distribution is realized by sensor matrices, which demonstrate the capability of tactile gesture recognition on both flat and curved surfaces. The recognition of sitting postures is achieved by two 12 × 12 matrices facilitated by machine learning, which prompts the potential for the augmentation of smart driving.

show abstract

Detection of Driver Cognitive Distraction Using Machine Learning Methods

Cited by 19 publications

References 69 publications

A Deep Learning-Based IDS for Automotive Theft Detection for In-Vehicle CAN Bus

A Deep Learning-Based IDS for Automotive Theft Detection for In-Vehicle CAN Bus

Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach

Smart Driving Hardware Augmentation by Flexible Piezoresistive Sensor Matrices with Grafted‐on Anticreep Composites

Contact Info

Product

Resources

About