The availability of techniques for driver distraction detection has been difficult to put to use because of delays caused due to lag in inferencing the model. Distractions caused due to handheld devices have been major causes of traffic accidents as they affect the decision-making capabilities of the driver and gives them less time to react to difficult situations. Often drivers try to multitask which reduces their reaction time leading to accidents, which can easily be avoided if they had been attentive. As such, problems related to the driver’s negligence towards safety a possible solution is to monitor the driver and driving behavior and alerting them if they are distracted. In this paper, we propose a novel approach for detecting when a driver is distracted due to in hand electronic devices which is not only able to detect the distraction with high accuracy but also is energy and memory efficient. Our proposed compressed neural got an accuracy of 0.83 in comparison to 0.86 of heavyweight network.
MolchanovP., TyreeS., KarrasT., AilaT. and KautzJ., Pruning convolutional neural networks for resource efficient inference, arXiv preprint arXiv:1611.06440, (2016).
2.
AlzubiO.A., AlzubiJ.A., TedmoriS., RashaidehH. and AlmomaniO., Consensus-based combining method for classifier ensembles, Int Arab J Inf Technol15(1) (2018), 76–86.
3.
HanS., MaoH. and DallyW.J., Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding, arXiv preprint arXiv:1510.00149, (2015).
4.
AnwarS., HwangK. and SungW., Fixed point optimization of deep convolutional neural networks for object recognition, In Acoustics Speech and Signal Processing (ICASSP), 2015 IEEE International Conference (2015), 1131–1135.
5.
DenilM., ShakibiB. and DinhL., Nando de Freitas, Predicting parameters in deep learning, In Advances in Neural Information Processing Systems (2013), 2148–2156.
6.
AlzubiO.A., AlzubiJ.A., AlweshahM., QiqiehI., Al-ShamiS. and RamachandranM., An optimal pruning algorithm of classifier ensembles: dynamic programming approach, Neural Computing and Applications32(5) (2020), 1–17. doi: 10.1007/s00521-020-04761-6
7.
DentonE.L., ZarembaW., BrunaJ., LeCunY. and FergusR., Exploiting linear structure within convolutional networks for efficient evaluation, In Advances in Neural Information Processing Systems (2014), 1269–1277.
8.
GongY., LiuL., YangM. and BourdevL., Compressing deep convolutional networks using vector quantization, arXiv preprint arXiv:1412.6115, (2014).
9.
HanS., PoolJ., TranJ. and DallyW.J., Learning both weights and connections for efficient neural networks, In Advances in Neural Information Processing Systems, (2015).
10.
HamdounH., NazirS., AlzubiJ.A., LaskotP. and AlzubiO.A., Performance benefits of network coding for HEVC video communications in satellite networks, Iranian Journal of Electrical and Electronic Engineering (2020), https://doi.org/10.22068/IJEEE.17.3.1956.
11.
IandolaF.N., HanS., MoskewiczM.W., AshrafK., DallyW.J. and KeutzerK., SqueezeNet: AlexNet-level accuracy with 50×fewer parameters and <0.5 MB model size, arXiv preprint arXiv:1602.07360, (2016).
12.
AshrafK., IandolaB.W.F.N., MoskewiczM.W. and KeutzerK., Shallow networks for high-accuracy road object-detection, arXiv:1606.01561, (2016).
13.
SzegedyC., VanhouckeV., IoffeS., ShlensJ. and WojnaZ., Rethinking the inception architecture for computer vision, arXiv:1512.00567, (2015).
14.
SzegedyC., IoffeS. and VanhouckeV., Inception-v4, inception-resnet and the impact of residual connections on learning, arXiv:1602.07261, (2016).
15.
BergstraJ. and BengioY., An optimizationmethodology for neural network weights and architectures, JMLR (2012).
16.
LuoJ.H., WuJ. and LinW., Thinet: A filter level pruning method for deep neural network compression, In Proceedings of the IEEE international conference on computer vision (2017), 5058–5066.
17.
BengioY., CourvilleA. and VincentP., Representation learning: A review and new perspectives, TPAMI (2013), 1798–1828.
18.
GirshickR., Fast R-CNN. In ICCV (2015), 1440–1448.
19.
HuH., PengR., TaiY.W. and TangC.K., Network trimming: A data-driven neuron pruning approach towards efficient deep architectures, arXiv preprint arXiv:1607.03250 (2016), 1–9.
20.
LiH., KadavA., DurdanovicI., SametH. and GrafH.P., Pruning filters for efficient ConvNets, In ICLR(2017), 1–13.
21.
HeY., LinJ., LiuZ., WangH., LiL.J. and HanS., Amc: Automl for model compression and acceleration on mobile devices, In Proceedings of the European Conference on Computer Vision (2018), 784–800.
22.
AnwarS. and SungW., Compact deep convolutional neural networks with coarse pruning, arXiv (2016) arXiv: 1610.09639.
BakerB., GuptaO., NaikN. and RaskarR., Designing neural network architectures using reinforcement learning, arXiv (2016) preprint arXiv:1611.02167.
25.
DongX., HuangJ., YangY. and YanS., More is less: A more complicated network with less inference complexity, arXiv(2017) preprint arXiv:1703.08651.
26.
HanS., LiuX., MaoH., PuJ., PedramA., HorowitzM.A. and DallyW.J., Eie: efficient inference engine on compressed deep neural network. In Proceedings of the 43rd International Symposium on Computer Architecture (2016), 243–254.
27.
HanS., PoolJ., TranJ. and DallyW., Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems (2015), 1135–1143.
28.
HeY., ZhangX. and SunJ., Channel pruning for accelerating very deep neural networks, In Proceedings of the IEEE International Conference on Computer Vision (2017), 1389–1397.
29.
YangT.J., ChenY.H. and SzeV., Designing energy-efficient convolutional neural networks using energy-aware pruning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), 5687–5695.
30.
AlrabeaA., AlzubiO.A. and AlzubiJ.A., A task-based model for minimizing energy consumption in WSNs, Energy Systems13(2) (2019), 1–18. doi: 10.1007/s12667-019-00372-w
LiL., ZhongB.Jr., HutmacherC., LiangY., HorreyW.J. and XuX., Detection of driver manual distraction via image-based hand and ear recognition, Accident Analysis & Prevention137 (2020), 105432.
33.
DhakateK.R. and DashR., Distracted Driver Detection using Stacking Ensemble. In 2020 IEEE International Students’ Conference on Electrical Electronics and Computer Science (2020), 1–5.
34.
AlzubiO., Deep Learning-based Intrusion Detection Model for IndustrialWireless Sensor Networks, Journal of Intelligent & Fuzzy Systems (2021), In press.
35.
MaseJ.M., ChapmanP., FigueredoG.P. and TorresM.T., A Hybrid Deep Learning Approach for Driver Distraction Detection (2020).
36.
ShahverdyM., FathyM., BerangiR. and SabokrouM., Driver behavior detection and classification using deep convolutional neural networks, Expert Systems with Applications149 (2020), 113240.
37.
ArefinM.R., MakhmudkhujaevF., ChaeO. and KimJ., Aggregating CNN and HOG features for real-time distracted driver detection. In IEEE International Conference on Consumer Electronics (2019), 1–3.
38.
HuangC., WangX., CaoJ., WangS. and ZhangY., HCF: A Hybrid CNN Framework for Behavior Detection of Distracted Drivers, IEEE Access8 (2020), 109335–109349.
39.
MofidN., BayrootiJ. and RaviS., Keep Your AI-es on the Road: Tackling Distracted Driver Detection with Convolutional Neural Networks and Targetted Data Augmentation (2020), arXiv preprint arXiv:2006.10955.
40.
NazirS., AlzubiO.A., KaleemM. and HamdounH., Image Subset Communication for Resource-constrained Applications in Wireless, Turkish Journal of Electrical Engineering & Computer Sciences28(5) (2020), 2686–2701. doi: 10.3906/elk-2002-169
41.
KhanR. and DebnathR., Human Distraction Detection from Video Stream Using Artificial Emotional Intelligence, International Journal of Image, Graphics and Signal Processing12(2) (2020), 19.
42.
XieY., ChenK. and MurpheyY.L., Real-time and Robust Driver Yawning Detection with Deep Neural Networks, In IEEE Symposium Series on Computational Intelligence (2018), 532–538.
43.
MajdiM.S., RamS., GillJ.T. and RodriguezJ.J., Drive-net: Convolutional network for driver distraction detection, In IEEE Southwest Symposium on Image Analysis and Interpretation (2018), 1–4.
44.
KoesdwiadyA., BedawiS.M., OuC. and KarrayF., End-to-end deep learning for driver distraction recognition, In International Conference Image Analysis and Recognition (2017), 11–18.
45.
AlweshahO.A., AlzubiJ.A. and AlzubiS.A.M., Solving Attribute Reduction Problem using Wrapper Genetic Programming, International Journal of Computer Science and Network Security16(5) (2016), 78–84.
46.
Al-NajdawiN., TedmoriS., AlzubiO.A., DorghamO. and AlzubiJ.A., A Frequency Based Hierarchical Fast Search Block Matching Algorithm for Fast Video Communication, International Journal of Advanced Computer Science and Applications7(4) (2016), 447–455. doi: 10.14569/IJACSA.2016.070459
