nach oben

Arabian Journal for Science and Engineering

Erschienen in:

06.10.2021 | Research Article-Computer Engineering and Computer Science

Comparative Analysis of AlexNet, ResNet18 and SqueezeNet with Diverse Modification and Arduous Implementation

verfasst von: Asad Ullah, Hassan Elahi, Zhaoyun Sun, Amna Khatoon, Ishfaq Ahmad

Erschienen in: Arabian Journal for Science and Engineering | Ausgabe 2/2022

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Road cracks are caused due to the abundant usage of the roads, heavy traffic, and increased prerequisite of transportation. So road maintenance is an important aspect of such a huge number of vehicles on the roads to have safety measures and continuity. Besides the traffic, bad weather is also contributing its part in creating road cracks. In the proposed research automatic road cracks have been detected, it looks simple apparently but the intensity, and complexity of the background make it a challenging task. In this challenging task, the contrast of the processed image, complexity of different kinds of crack recognition, assembly of proper database images, elapsed time, and approximate classification, etc., are processed to get the optimum results. Deep learning has multiple neural networks among them few networks are used like AlexNet, ResNet18, and SqueezeNet for the data recognition mainly for the huge database having the optimum results in minimum throughput. In the accomplished research 4333 images with eight diverse road cracks classes are used. The classified images are processed by utilizing three different networks through a supervised dataset. Dataset is built by mixing the university resources-collected images and some online datasets. The best expected result is gained after proper training and tested along with classification. In this experiment, the training and testing images were kept the same in epoch and iteration. But the ResNet18 was superlative with an accuracy of 85.20%.

Vorheriger Artikel COLCONF: Collaborative ConvNet Features-based Robust Visual Place Recognition for Varying Environments

Nächster Artikel To Secure the Communication in Powerful Internet of Things Using Innovative Post-Quantum Cryptographic Method

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Sun Z.; Wang C.; Sha A.: Study of image-based pavement cracking measurement techniques,’ ICEMI 2009 - Proc. 9th Int. Conf. Electron. Meas. Instruments, pp. 2140–2143, 2009.,” [Online]. Available: Z. Sun, C. Wang, and A. Sha, “Study of image-based pavement cracking measurement techniques,” ICEMI 2009 - Proc. 9th Int. Conf. Electron. Meas. Instruments, pp. 2140–2143, (2009)

Mubaraki, M.: Study the Relationship between Pavement Surface Distress and Roughness Data,’ vol. 2012, pp. 4–8, 2016.,” [Online]. Available: M. Mubaraki, “Study the Relationship between Pavement Surface Distress and Roughness Data. 2012 4–8 (2016)

Ragnoli, A.; De Blasiis, M.R.; Di Benedetto, A.: Pavement distress detection methods : a review,’ n (2018)

Surampudi, R.; Koppula, B.; Rao, S.; Prasad, M.V.N.K.: First international conference on artificial intelligence and cognitive computing, 815: (2019)

Mubaraki, M.: ScienceDirect Highway subsurface assessment using pavement surface distress and roughness data. Int. J. Pavement Res. Technol. 9(5), 393–402 (2016)CrossRef

Edition, F.: ‘PAVEMENT SURFACE CONDITION RATING,’ (2016)

Farashah, M.K.: Development practices for municipal pavement management systems application. (2012)

Verrelst, J.; Rivera Caicedo, J.; Vicent, J.; Morcillo Pallarés, P.; Moreno, J.: Approximating empirical surface reflectance data through emulation: opportunities for synthetic scene generation. Remote Sens. (2019). https://doi.org/10.3390/rs11020157CrossRef

Puan, O.C.; Mustaffar, M.; Ling, T.-C.: AUTOMATED PAVEMENT IMAGING PROGRAM (APIP) FOR PAVEMENT CRACKS CLASSIFICATION AND QUANTIFICATION,’ (2007)

10.

Su, Y., et al.: Pavement crack detection using sketch token. Remote Sens. 3(2), 809–814 (2018). https://doi.org/10.1016/j.procs.2018.10.231CrossRef

11.

Zhang, L.; Yang, F.; Zhang, Y.D.; Zhu, Y.J.: Road crack detection using deep convolutional neural network. 2017, (2016) doi: https://doi.org/10.1109/ICIP.2016.7533052.

12.

Elhenawy, M.; Ashqar, H.I.; Masoud, M.; Almannaa, M.H.; Rakotonirainy, A.; Rakha, H.A.: Deep transfer learning for vulnerable road users detection using smartphone sensors data. Remote Sens. 12(21), 1–12 (2020). https://doi.org/10.3390/rs12213508CrossRef

13.

Holm, A., et al.: Pavement distress detection with picucha methodology for area-scan cameras and dark images. IEEE Trans. Image Process. 7(4), 2–5 (2018). https://doi.org/10.1016/j.isprsjprs.2017.05.005CrossRef

14.

Riid, A., et al.: Pavement cracking detection based on three-dimensional data using improved active contour model. J. Transp. Eng. Part B Pavements 2019(2), 100006 (2019). https://doi.org/10.1061/JPEODX.0000006CrossRef

15.

Moore, G.K., et al.: A Min-max medial axis transformation. IEEE Trans. Pattern Anal. Mach. Intell. 10(4), 463–471 (2018). https://doi.org/10.1109/24.756091CrossRef

16.

Zhang, Z.; Liu, Q.; Wang, Y.: Road extraction by deep residual U-Net. IEEE Geosci. Remote Sens. Lett. 15(5), 749–753 (2018). https://doi.org/10.1109/LGRS.2018.2802944CrossRef

17.

Zhu, J.; Song, J.: An intelligent classification model for surface defects on cement concrete bridges. Appl. Sci. 10(3), 972 (2020). https://doi.org/10.3390/app10030972CrossRef

18.

Oszust, M.: No-reference image quality assessment with local gradient orientations. Symmetry (Basel) (2019). https://doi.org/10.3390/sym11010095CrossRef

19.

Ashwin, T.V., et al.: C ontrast. Int. J. Mod. Educ. Comput. Sci. 7109(5), 118–123 (2010). https://doi.org/10.5815/ijmecs.2018.05.06CrossRef

20.

Berkeley, U.C.; Davis, U.C.: 100-epoch ImageNet Training with AlexNet in 24 Minutes. (2017)

21.

Yang, L.: Sun, X.; Li, Z.: An efficient framework for remote sensing parallel processing: integrating the artificial bee colony algorithm and multiagent technology,’ Remote Sens. (2019)

22.

Kim, B.: Automated vision-based detection of cracks on concrete surfaces using a deep learning technique,” no. 2013. (2018) doi: https://doi.org/10.3390/s18103452.

23.

Vaswani, A., et al.: Attention is all you need,” Adv. Neural Inf. Process. Syst., vol. 2017-December, no. Nips, pp. 5999–6009. (2017)

24.

Devlin, J.; Chang, M.W.; Lee, K.; Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL HLT 2019 - 2019 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. - Proc. Conf., 1, pp. 4171–4186, (2019)

25.

Bowen, L.H.; Françon, M.: On Abbreviations. Mod. Lang. J. (1934). https://doi.org/10.1111/j.1540-4781.1934.tb05817.xCrossRef

26.

Chen et al. pdf.” pp. 1–9

27.

Alexy, E.M.; Burgess, A.W.; Baker, T.; Smoyak, S.A.: Perceptions of cyberstalking among college students. Br. Treat. Cris. Interv. 5(3), 279–289 (2005). https://doi.org/10.1093/brief-treatment/mhi020CrossRef

28.

Liu, C.; Ying, J.; Yang, H.; Hu, X.; Liu, J.: Improved human action recognition approach based on two-stream convolutional neural network model. Vis. Comput. 37(6), 1327–1341 (2021). https://doi.org/10.1007/s00371-020-01868-8CrossRef

29.

Locatello, F., et al.(2019) Challenging common assumptions in the unsupervised learning of disentangled representations. 36th Int. Conf. Mach. Learn. ICML 2019: 2019: 7247–7283 (2019)

30.

Touvron, H.; Cord, M.; Douze, M.; Massa, F.; Sablayrolles, A.; Jégou, H.: Training data-efficient image transformers & distillation through attention. (2020), [Online]. Available: http://arxiv.org/abs/2012.12877.

31.

Mahajan, A., et al.: Fine-mapping type 2 diabetes loci to single-variant resolution using high-density imputation and islet-specific epigenome maps. Nat. Genet. 50(11), 1505–1513 (2018). https://doi.org/10.1038/s41588-018-0241-6CrossRef

32.

Fan, R.; Bocus, M.J.; Zhu, d Y.: Road crack detection using deep convolutional neural network and adaptive road crack detection using deep convolutional neural network and adaptive thresholding. IEEE Intell. Veh. Symp. pp. 474–479 (2019)

33.

Fan, Z.; Member, S.; Wu, Y.; Lu, J.; Li, W.: Based on structured prediction with the convolutional neural network. pp. 1–9

34.

Li, W.; Huyan, J.; Tighe, S.L.; Ren, Q.Q.; Sun, Z.Y.: Three-dimensional pavement crack detection algorithm based on two-dimensional empirical mode decomposition”. J. Transp. Eng. Part B Pavements 143, 2 (2017). https://doi.org/10.1061/JPEODX.0000006CrossRef

35.

Shijie, J.; Ping, W.: Research on data augmentation for image classification based on convolution neural networks. no. 201602118

36.

Sensing, R., Scene, I.: Pre-trained alexnet architecture with pyramid pooling and supervision for high spatial resolution remote sensing image scene classification. (2017) doi: https://doi.org/10.3390/rs9080848.

37.

Kazemi, Y.: A deep learning pipeline for classifying different stages of alzheimer ’ s disease from fMRI data. (2017)

38.

Fan, R., et al.: Three-dimensional pavement crack detection algorithm based on two-dimensional empirical mode decomposition. J. Transp. Eng. Part B Pavements 2019(2), 474–479 (2019). https://doi.org/10.1061/JPEODX.0000006CrossRef

39.

Li, W.; Huyan, J.; Tighe, S.L.; Ren, Q.; Sun, Z.: Three-dimensional pavement crack detection algorithm based on Two- Three-dimensional pavement crack detection algorithm based on Two-dimensional empirical mode decomposition. (2017) https://doi.org/10.1061/JPEODX.0000006.

40.

Peleg, S.; Rosenfeld, A.: A Min-max medial axis transformation. IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-3, no. 2, pp. 208–210, 1981, doi: https://doi.org/10.1109/TPAMI.1981.4767082.

41.

Jean, G.; Banon, F.: Mathematical morphology and its applications to signal and image processing. (2007)

42.

Beheshti, N., et al.: Fault diagnosis of high-speed train bogie by residual-squeeze net. IEEE Trans. Ind. Informatics 15(7), 3856–3863 (2019). https://doi.org/10.1109/CVPRW50498.2020.00190CrossRef

43.

Beheshti, N.; Johnsson, L.: Squeeze U-net: a memory and energy efficient image segmentation network. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work. 2020 1495–1504 (2020) doi: https://doi.org/10.1109/CVPRW50498.2020.00190.

44.

Lee, H.J.; Ullah, I.; Wan, W.; Gao, Y.; Fang, Z.: Real-Time vehicle make and model recognition with the residual squeezenet architecture. Sensors (Switzerland) 19, 5 (2019). https://doi.org/10.3390/s19050982CrossRef

45.

Hassanpour, M., et al.: Document image classification using squeezenet convolutional neural network”, 5th Iran. Conf. Signal Process. Intell. Syst. ICSPIS 2019, 18–19 (2019). https://doi.org/10.1109/ICSPIS48872.2019.9066032CrossRef

46.

Tang, J. et al.: First International Conference on Artificial Intelligence and Cognitive Computing. Exp. Syst. Appl., 38, no. Eusipco, pp. 19–22, (2009), doi: https://doi.org/10.1145/2800835.2800981.

47.

https://data.mendeley.com/datasets/xnzhj3x8v4/2,” [Online]. Available: https://data.mendeley.com/datasets/xnzhj3x8v4/2.

48.

“https://github.com/datasets,” [Online]. Available: https://github.com/datasets.

49.

https://github.com/google-research-datasets/Objectron,” [Online]. Available: https://github.com/google-research-datasets/Objectron.

50.

https://data.mendeley.com/datasets/5y9wdsg2zt/2,” [Online]. Available: https://data.mendeley.com/datasets/5y9wdsg2zt/2.

51.

https://www.kaggle.com/sachinpatel21/pothole-image-dataset,” [Online]. Available: https://www.kaggle.com/sachinpatel21/pothole-image-dataset.

52.

https://digitalcommons.usu.edu/all_datasets/48/,” [Online]. Available: https://digitalcommons.usu.edu/all_datasets/48/.

53.

Alom Z.; Taha T.M.; Yakopcic, C.S.; Westberg; Sidike, P.; Nasrin, M.S.: The history began from AlexNet: a comprehensive survey on deep learning approaches. (2018).

54.

Krizhevsky, B.A.; Sutskever, I. Hinton G.E.: ImageNet classification with deep convolutional neural networks. (2012)

55.

Yang, L.; Sun, X.; Li, Z.: An efficient framework for remote sensing parallel processing: integrating the artificial bee colony algorithm and multiagent technology. Remote Sens. (2019). https://doi.org/10.3390/rs11020152CrossRef

56.

https://bulkresizephotos.com/en,” [Online]. Available: https://bulkresizephotos.com/en.

57.

Jin, P.; Adu-Gyamfi Professor, Y.; Buttlar Professor, W.G.; Barton Chair, G.: PID: A new benchmark dataset to classify and densify pavement distresses hamed majidifard, Corresponding Author,” no. October, (2018).

58.

Li, W.; Huyan, J.; Tighe, S.L.; Ren, Q.Q.; Sun, Z.Y.: Three-dimensional pavement crack detection algorithm based on two-dimensional empirical mode decomposition. J. Transp. Eng. Part B Pavements 143(2), 1–12 (2017). https://doi.org/10.1061/JPEODX.0000006CrossRef

59.

Sa, P.K., et al.: Image enhancement processing. Image Enhanc. by Adapt. Power-Law Transform. 3(1), 1–11 (2012). https://doi.org/10.1007/978-981-10-3376-6_62CrossRef

60.

Liu Y.; Huang C.: Scene classification via triplet networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., (2018), doi: https://doi.org/10.1109/JSTARS.2017.2761800.

Titel: Comparative Analysis of AlexNet, ResNet18 and SqueezeNet with Diverse Modification and Arduous Implementation
verfasst von: Asad Ullah
Hassan Elahi
Zhaoyun Sun
Amna Khatoon
Ishfaq Ahmad
Publikationsdatum: 06.10.2021
Verlag: Springer Berlin Heidelberg
Erschienen in: Arabian Journal for Science and Engineering / Ausgabe 2/2022
Print ISSN: 2193-567X
Elektronische ISSN: 2191-4281
DOI: https://doi.org/10.1007/s13369-021-06182-6

Premium Partner

Marktübersichten

Die im Laufe eines Jahres in der „adhäsion“ veröffentlichten Marktübersichten helfen Anwendern verschiedenster Branchen, sich einen gezielten Überblick über Lieferantenangebote zu verschaffen.

Zur Marktübersicht

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Weitere Artikel der Ausgabe 2/2022

Cuckoo Energy-Efficient Load-Balancing On-Demand Multipath Routing Protocol

Design of Backpropagated Intelligent Networks for Nonlinear Second-Order Lane–Emden Pantograph Delay Differential Systems

Entity-Context and Relation-Context Combined Knowledge Graph Embeddings

Augmenting Driver’s Situational Awareness using Smartphones in VANETs

Convalescing the Process of Ranking Metabolites for Diseases using Subcellular Localization

An Effective Hash-Based Assessment and Recovery Algorithm for Healthcare Systems

Premium Partner

Marktübersichten