An improved pulse coupled neural networks model for semantic IoT

Abstract

In recent years, the Internet of Things (IoT) has gradually developed applications such as collecting sensory data and building intelligent services, which has led to an explosion in mobile data traffic. Meanwhile, with the rapid development of artificial intelligence, semantic communication has attracted great attention as a new communication paradigm. However, for IoT devices, however, processing image information efficiently in real time is an essential task for the rapid transmission of semantic information. With the increase of model parameters in deep learning methods, the model inference time in sensor devices continues to increase. In contrast, the Pulse Coupled Neural Network (PCNN) has fewer parameters, making it more suitable for processing real-time scene tasks such as image segmentation, which lays the foundation for real-time, effective, and accurate image transmission. However, the parameters of PCNN are determined by trial and error, which limits its application. To overcome this limitation, an Improved Pulse Coupled Neural Networks (IPCNN) model is proposed in this work. The IPCNN constructs the connection between the static properties of the input image and the dynamic properties of the neurons, and all its parameters are set adaptively, which avoids the inconvenience of manual setting in traditional methods and improves the adaptability of parameters to different types of images. Experimental segmentation results demonstrate the validity and efficiency of the proposed self-adaptive parameter setting method of IPCNN on the gray images and natural images from the Matlab and Berkeley Segmentation Datasets. The IPCNN method achieves a better segmentation result without training, providing a new solution for the real-time transmission of image semantic information.

Keywords

Internet of things (IoT) / Semantic information / Real-time application / Improved pulse coupled neural network / Image segmentation

References

[1] W. Yang, H. Du, Z.Q. Liew, W.Y.B. Lim, Z. Xiong, D. Niyato, X. Chi, X.S. Shen, C. Miao, Semantic communications for future Internet: fundamentals, applications, and challenges, IEEE Commun. Surv. Tutor. 25 (1) (2023) 213-250.

[2] X. Luo, H.-H. Chen, Q. Guo, Semantic communications: overview, open issues, and future research directions, IEEE Wirel. Commun. 29 (1) (2022) 210-219.

[3] J. Kang, H. Du, Z. Li, Z. Xiong, S. Ma, D. Niyato, Y. Li, Personalized saliency in task-oriented semantic communications: image transmission and performance analysis, IEEE J. Sel. Areas Commun. (2022) 1.

[4] D. Wheeler, B. Natarajan, Engineering semantic communication: a survey, IEEE Ac-cess 11 (2023) 13965-13995.

[5] S. Cheng, Z. Cai, J. Li, H. Gao, Extracting kernel dataset from big sensory data in wireless sensor networks, IEEE Trans. Knowl. Data Eng. 29 (4) (2017) 813-827.

[6] J. Wu, C. Wu, Y. Lin, T. Yoshinaga, L. Zhong, X. Chen, Y. Ji, Semantic segmentation-based semantic communication system for image transmission, Digit. Commun. Netw. https://doi.org/10.1016/j.dcan.2023.02.006.

[7] H. Xie, Z. Qin, G.Y. Li, B.-H. Juang, Deep learning enabled semantic communication systems, IEEE Trans. Signal Process. 69 (2021) 2663-2675.

[8] E. Bourtsoulatze, D.B. Kurka, D. Gündüz, Deep joint source-channel coding for wire-less image transmission, IEEE Trans. Cogn. Commun. Netw. 5(3) (2019) 567-579.

[9] P. Zhang, W. Xu, H. Gao, K. Niu, X. Xu, X. Qin, C. Yuan, Z. Qin, H. Zhao, J. Wei, F. Zhang,Toward Wisdom-evolutionary and primitive-concise 6G: a new paradigm of semantic communication networks, Engineering 8 (2022) 60-73.

[10] J. Li, Automatic semantic analysis framework of dickinson’s portfolio based on character recognition and artificial intelligence, in: 2020 4th International Con-ference on Electronics, Communication and Aerospace Technology (ICECA), 2020, pp. 1660-1664.

[11] O. Ronneberger, P. Fischer, T. Brox, U-net: convolutional networks for biomed-ical image segmentation,in:Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18 th International Conference, Munich, Germany, Oc-tober 5-9, 2015, Proceedings, Part III 18, Springer, 2015, pp. 234-241.

[12] A. Abdulrahman, S. Varol,A review of image segmentation using MATLAB envi-ronment, in:2020 8th International Symposium on Digital Forensics and Security (ISDFS), 2020, pp. 1-5.

[13] P. Agrawal, S.K. Shriwastava, S.S. Limaye, MATLAB implementation of image seg-mentation algorithms, in: 2010 3rd International Conference on Computer Science and Information Technology 3 (2010) 427-431.

[14] O. Ronneberger, P. Fischer, T. Brox, U-net: convolutional networks for biomedical image segmentation,in: N. Navab, J. Hornegger, W.M. Wells, A.F. Frangi (Medical Image Computing and Computer-Assisted Intervention-MICCAI Eds.), 2015, Springer International Publishing, Cham, 2015, pp. 234-241.

[15] S. Cheng, Z. Cai, J. Li, Curve query processing in wireless sensor networks, IEEE Trans. Veh. Technol. 64 (11) (2015) 5198-5209.

[16] K. Jiao, P. Xu, S. Zhao, A novel automatic parameter setting method of PCNN for im-age segmentation, in: 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP), 2018, pp. 265-270.

[17] M.T. Hagan, H.B. Demuth, M. Beale, Neural Network Design, PWS Publishing Co., USA, 1997.

[18] Z. Hong-juan, Z. Zong-nian, L. Dong-mei, M. Yi-de,A novel image de-noising al-gorithm combined PCNN with morphology, in:2007 International Symposium on Intelligent Signal Processing and Communication Systems, 2007, pp. 208-211.

[19] K. Zhan, J. Shi, H. Wang, Y. Xie, Q. Li, Computational mechanisms of pulse-coupled neural networks: a comprehensive review, Arch. Comput. Methods Eng. 24 (2017) 573-588.

[20] J.L. Johnson, D. Ritter, Observation of periodic waves in a pulse-coupled neural network, Opt. Lett. 18 (15) (1993) 1253-1255.

[21] H. Ranganath, G. Kuntimad, J. Johnson, Pulse coupled neural networks for im-age processing, in: Proceedings IEEE Southeastcon ’95. Visualize the Future, 1995, pp. 37-43.

[22] J.M. Kinser, Simplified pulse-coupled neural network, in: Defense + Commercial Sensing, 1996.

[23] S. Basar, M. Ali, G. Ochoa-Ruiz, A. Waheed, G. Rodriguez-Hernandez, M. Zareei, A novel defocused image segmentation method based on pcnn and lbp, IEEE Access 9 (2021) 87219-87240.

[24] N.S. Mishra, S. Dhabal,On combination of fuzzy memberships for medical image fusion using NSST based fuzzy-PCNN, in:2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT), 2018, pp. 1-4.

[25] S.S. Adagale, S.S. Pawar, Image segmentation using PCNN and template matching for blood cell counting, in: 2013 IEEE International Conference on Computational Intelligence and Computing Research, 2013, pp. 1-5.

[26] H. Xie, Z. Qin, G.Y. Li, B.-H. Juang,Deep learning based semantic communications: an initial investigation, in: GLOBECOM 2020-2020 IEEE Global Communications Conference, IEEE, 2020, pp. 1-6.

[27] Z. Weng, Z. Qin, G.Y. Li, Semantic communications for speech signals, in: ICC 2021-IEEE International Conference on Communications, IEEE, 2021, pp. 1-6.

[28] Z. Zhang, Q. Yang, S. He, M. Sun, J. Chen, Wireless transmission of images with the assistance of multi-level semantic information, in: 2022 International Symposium on Wireless Communication Systems (ISWCS), IEEE, 2022, pp. 1-6.

[29] X. Kang, B. Song, J. Guo, Z. Qin, F.R. Yu, Task-oriented image transmission for scene classification in unmanned aerial systems, IEEE Trans. Commun. 70 (8) (2022) 5181-5192.

[30] X. Deng, C. Yan, Y. Ma, PCNN mechanism and its parameter settings, IEEE Trans. Neural Netw. Learn. Syst. 31 (2) (2020) 488-501.

[31] X. Gu, Feature extraction using unit-linking pulse coupled neural network and its applications, Neural Process. Lett. 27 (2007) 25-41.

[32] P. Duan, X. Kang, S. Li, P. Ghamisi, Multichannel pulse-coupled neural network-based hyperspectral image visualization, IEEE Trans. Geosci. Remote Sens. 58 (4)(2020) 2444-2456.

[33] Y. Chen, Y. Ma, D.H. Kim, S.-K. Park, Region-based object recognition by color segmentation using a simplified PCNN, IEEE Trans. Neural Netw. Learn. Syst. 26 (8)(2015) 1682-1697.

[34] S. Zhu, L. Wang, S. Duan, Memristive pulse coupled neural network with applica-tions in medical image processing, Neurocomputing 227 (2017) 149-157.

[35] Y. Guo, M. Dong, Z. Yang, X. Gao, K. Wang, C. Luo, Y. Ma, J. Zhang, A new method of detecting micro-calcification clusters in mammograms using contourlet transform and non-linking simplified PCNN, Comput. Methods Programs Biomed. 130 (2016) 31-45.

[36] P. Bai, K. Yang, X. Min, Z. Guo, C. Li, Y. Fu, C. Han, X. Lu, Q. Liu, A novel framework for improving pulse-coupled neural networks with fuzzy connectedness for medical image segmentation, IEEE Access 8 (2020) 138129-138140.

[37] H. Li, D. Xu, R. Zong,Face recognition based on unit-linking pcnn time signature, in:2009 International Conference on Advanced Computer Control, 2009, pp. 360-364.

[38] Y. Wu, B. Xu, X.-Y. Bian, An improved PCNN model and a new removing algorithm of salt and pepper noise, in: 2010 Second International Conference on Computa-tional Intelligence and Natural Computing 2 (2010) 178-182.

[39] N. Wang, Y. Ma, W. Wang,Research on spatial frequency motivated gray level image fusion based on improved PCNN, in:2013 International Conference on Information Science and Cloud Computing Companion, 2013, pp. 734-739.

[40] Y. Jia, C. Rong, Y. Zhu, Y. Yang, Y. Wang, A novel image fusion algorithm us-ing PCNN, in: NSCT Domain,in:2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), 2016, pp. 751-755.

[41] X. Jia,A novel segmentation method using improved PCNN for fabric defect image, in:2010 2nd International Conference on Signal Processing Systems, Vol. 1, 2010, pp. V1-388-V1-392.

[42] X. Xu, G. Wang, S. Ding, Y. Cheng, X. Wang, Pulse-coupled neural networks and parameter optimization methods, Neural Comput. Appl. 28 (1) (2017) 671-681.

[43] J. Lian, B. Shi, M. Li, Z. Nan, Y. Ma,An automatic segmentation method of a parameter-adaptive PCNN for medical images, Int. J. Comput. Assisted Radiol. Surg. 12 (9) (2017) 1511-1519.

[44] M. Monica Subashini, S.K. Sahoo, Pulse coupled neural networks and its applica-tions, Expert Syst. Appl. 41 (8) (2014) 3965-3974.

[45] C. Shen, D. Wang, S. Tang, H. Cao, J. Liu, Hybrid image noise reduction algorithm based on genetic ant colony and pcnn, Vis. Comput. 33 (2016) 1373-1384.

[46] C. Panigrahy, A. Seal, N.K. Mahato, MRI and SPECT image fusion using a weighted parameter adaptive dual channel PCNN, IEEE Signal Process. Lett. 27 (2020) 690-694.

[47] C. Huang, G. Tian, Y. Lan, Y. Peng, E.Y.K. Ng, Y. Hao, Y. Cheng, W. Che, A new pulse coupled neural network (PCNN) for brain medical image fusion empowered by shuffled frog leaping algorithm, Front. Neurosci. 13 (2019), https://doi.org/10.3389/fnins.2019.00210.

[48] X. Wang, Z. Li, H. Kang, Y. Huang, D. Gai, Medical image segmentation using pcnn based on multi-feature grey wolf optimizer bionic algorithm, J. Bionics Eng. 18 (2021) 711-720.

[49] C. Panigrahy, A. Seal, N.K. Mahato, Fractal dimension based parameter adaptive dual channel PCNN for multi-focus image fusion, Opt. Lasers Eng. 133 (2020) 106141.

[50] C. Panigrahy, A. Seal, N.K. Mahato, Parameter adaptive unit-linking dual-channel PCNN based infrared and visible image fusion, Neurocomputing 514 (2022) 21-38.

[51] M. Yin, X. Liu, Y. Liu, X. Chen, Medical image fusion with parameter-adaptive pulse coupled neural network in nonsubsampled shearlet transform domain, IEEE Trans. Instrum. Meas. 68 (1) (2019) 49-64.

[52] T.J. Jebaseeli, C.A.D. Durai, J.D. Peter, Retinal blood vessel segmentation from di-abetic retinopathy images using tandem pcnn model and deep learning based svm, Optik 199 (2019) 163328.

[53] R. Eckhorn, H.J. Reitboeck, M. Arndt, P. Dicke, Feature linking via synchronization among distributed assemblies: simulations of results from cat visual cortex, Neural Comput. 2(3) (1990) 293-307.

[54] G. Kuntimad, H. Ranganath, Perfect image segmentation using pulse coupled neural networks, IEEE Trans. Neural Netw. 10 (3) (1999) 591-598.

[55] N. Otsu, A threshold selection method from gray-level histograms, IEEE Trans. Syst. Man Cybern. 9(1) (1979) 62-66.

[56] D. Martin, C. Fowlkes, D. Tal, J. Malik,A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics, in:Proceedings Eighth IEEE International Conference on Com-puter Vision, ICCV 2001, Vol. 2, 2001, pp. 416-423.

[57] Y. Chen, S.-K. Park, Y. Ma, R. Ala, A new automatic parameter setting method of a simplified PCNN for image segmentation, IEEE Trans. Neural Netw. 22 (6) (2011) 880-892.

[58] M. Yi-de, L. Qing, Q. Zhi-bai, Automated image segmentation using improved PCNN model based on cross-entropy, in: Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004, pp. 743-746.