Driving behavior classification based on sensor data fusion using LSTM recurrent neural networks

Saleh, Khaled J.; Hossny, Mohammed; Nahavandi, Saeid

doi:10.1109/itsc.2017.8317835

Cited by 108 publications

(87 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note that Saleh et al [9] used an 50% overlap with great success, which seems to validate the use of rolling windows. However, the authors used a supervised approach and Keogh and Lin [18] only argues against using rolling windows in unsupervised methods.…”

Section: Driving Behaviour In Telematic Datamentioning

confidence: 83%

Finding manoeuvre motifs in vehicle telematics

Silva¹,

Henriques²

2020

Accident Analysis & Prevention

View full text Add to dashboard Cite

Driving behaviour has a great impact on road safety. A popular way of analysing driving behaviour is to move the focus to the manoeuvres as they give useful information about the driver who is performing them. In this paper, we investigate a new way of identifying manoeuvres from vehicle telematics data, through motif detection in time-series. We implement a modified version of the Extended Motif Discovery (EMD) algorithm, a classical variable-length motif detection algorithm for time-series and we applied it to the UAH-DriveSet, a publicly available naturalistic driving dataset. After a systematic exploration of the extracted motifs, we were able to conclude that the EMD algorithm was not only capable of extracting simple manoeuvres such as accelerations, brakes and curves, but also more complex manoeuvres, such as lane changes and overtaking manoeuvres, which validates motif discovery as a worthwhile line for future research.

show abstract

Section: Driving Behaviour In Telematic Datamentioning

confidence: 83%

Finding manoeuvre motifs in vehicle telematics

Silva¹,

Henriques²

2020

Accident Analysis & Prevention

View full text Add to dashboard Cite

show abstract

“…Therefore, anyone who develops a network model based on Deep Learning does not need to have indepth knowledge in the application domain. In the analyzed studies, this approach was found in only one research [57], which is limited to a specific type of perception. Therefore, it is an approach that should be further explored in this research area.…”

Section: Discussionmentioning

confidence: 99%

“…Mahboob et al [42] used a SVM to identify left turn, right turn, u-turn, abrupt brake and smooth brake. Finally, Saleh et al [57] applied an LSTM convolutional recurrent neural network to classify driving behavior in normal driving, aggressive driving and drowsiness driving.…”

Section: Other Approachesmentioning

confidence: 99%

“…Transformation matrix N/A [42] N/A N/A N/A [51] Simple moving average Standard deviation N/A N/A [56] N/A N/A N/A [57] N/A N/A N/A [61] Root mean square (RMS) Virtual reorientation N/A [68] N/A Euler angles N/A [71] Low-pass second-order Butterworth N/A N/A [72] Infinite impulse response Mapping the orientation N/A Table 13 Processing for proprioception…”

Section: Appendix 1: Summary Datamentioning

confidence: 99%

See 1 more Smart Citation

Vehicular Perception Based on Inertial Sensing: A Structured Mapping of Approaches and Methods

Menegazzo

Wangenheim

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

In this paper, we present a structured literature mapping of the state-of-the-art of vehicular perception methods and approaches using inertial sensors. An in-depth investigation and classification were performed employing the results of a systematic literature review. The analysis focused on identifying methods that capture signals provided by inertial sensors such as accelerometers and gyroscopes to recognize transient or persistent events associated with the vehicle's movement. We classified these events into vehicular exteroception, associated with potholes, cracks, speed bumps, pavement type, conservation state; and vehicular proprioception, associated with lane change, braking, skidding, aquaplaning, turning right or left. Through the comprehensive study of publications in a 7-year time window, in addition to the methods, we have also identified their dependency factors, hardware platforms and applications.

show abstract

“…Some researches have explored the use of LSTM on non-medical EEG-based applications. Most of the EEG-based LSTM applications were used in brain-computer interface (BCI), such as motor imagery classification [ 40 , 41 , 42 , 43 , 44 , 45 , 46 ], emotion classification [ 47 , 48 , 49 , 50 , 51 , 52 ], depression detection [ 53 , 54 , 55 ], biometrics [ 56 , 57 ], sleep stage classification [ 58 , 59 , 60 , 61 , 62 , 63 ], driving behavioral classification [ 64 , 65 ], directional signal classification [ 66 ], machine health monitoring [ 67 ] and EEG signal classification [ 68 ]. There are some research works on LSTM for medical applications reported in the literature [ 69 , 70 , 71 , 72 , 73 , 74 , 75 ], but as far as our concern, there is still no approach being proposed to identify TBI using LSTM networks.…”

Section: Introductionmentioning

confidence: 99%

Classification of Non-Severe Traumatic Brain Injury from Resting-State EEG Signal Using LSTM Network with ECOC-SVM

Lai

Ibrahim

Hamid

et al. 2020

Sensors

View full text Add to dashboard Cite

Traumatic brain injury (TBI) is one of the common injuries when the human head receives an impact due to an accident or fall and is one of the most frequently submitted insurance claims. However, it is often always misused when individuals attempt an insurance fraud claim by providing false medical conditions. Therefore, there is a need for an instant brain condition classification system. This study presents a novel classification architecture that can classify non-severe TBI patients and healthy subjects employing resting-state electroencephalogram (EEG) as the input, solving the immobility issue of the computed tomography (CT) scan and magnetic resonance imaging (MRI). The proposed architecture makes use of long short term memory (LSTM) and error-correcting output coding support vector machine (ECOC-SVM) to perform multiclass classification. The pre-processed EEG time series are supplied to the network by each time step, where important information from the previous time step will be remembered by the LSTM cell. Activations from the LSTM cell is used to train an ECOC-SVM. The temporal advantages of the EEG were amplified and able to achieve a classification accuracy of 100%. The proposed method was compared to existing works in the literature, and it is shown that the proposed method is superior in terms of classification accuracy, sensitivity, specificity, and precision.

show abstract

Driving behavior classification based on sensor data fusion using LSTM recurrent neural networks

Cited by 108 publications

References 8 publications

Finding manoeuvre motifs in vehicle telematics

Finding manoeuvre motifs in vehicle telematics

Vehicular Perception Based on Inertial Sensing: A Structured Mapping of Approaches and Methods

Classification of Non-Severe Traumatic Brain Injury from Resting-State EEG Signal Using LSTM Network with ECOC-SVM

Contact Info

Product

Resources

About