Deep learning techniques of losses in data transmitted in wireless sensor network

Wireless sensor network (WSN) systems are frequently used today as a result of rapid technological develop- ments. Wireless sensor networks, which form the basis of the Internet of Things (IoT), have a wide range of use in the world from education to health, and from military applications to home applications. It enables the data obtained from the sensors to be transferred between nodes with the help of end-to-end wireless protocols. In parallel with the increasing number of nodes in WSN, data traﬀic density also increases. Due to the limitations of the WSN network, lost packet rates also increase with increasing data traﬀic. In this study, a data set was created by examining the data transfers of different amounts of WSN nodes placed in different places. The effects of the number of sensors and the distance between them were evaluated from the data set. In this study, a data set was created by collecting the data from the sensor nodes placed at 1500m x 1500m intervals in the ns-3 discrete event emulator program. Today, with the rapid development of technology, deep learning methods which are one of the artificial intelligence methods, are also used in WSN. In this study, the loss rate in the transferred data packets was tried to be estimated with the highest accuracy by using deep belief network (DBN), recurrent neural network (RNN), and deep neural network (DNN) over the obtained dataset. Of these three deep learning methods, DNN deep learning method was found to accurately estimate the loss rate in the transferred data packets with an accuracy rate of 88.50%.

PDF

___

[1] Vikram N, Harish KS, Nihaal MS, Umesh R, Shetty A et al. A low cost home automation system using wi-fi based wireless sensor network incorporating internet of things (IoT), In: 7th IEEE International Advanced Computing Conference; Hyderabad, Telangana, India; 2017. pp. 174-178.
[2] Kocakulak M, Butun I. An overview of wireless sensor networks towards internet of things, In: 2017 IEEE 7th Annual Computing and Communication Workshop and Conference; Las Vegas, NV, USA; 2017. pp. 1-6.
[3] Bera S, Misra S, Roy SK, Obaidat MS. Soft-WSN: Software-defined WSN management system for IoT applications. IEEE Systems Journal 2016; 12 (3): 2074-2081. doi: 10.1109/JSYST.2016.2615761.
[4] Wu F, Xu L, Kumari S, Li X, Shen J et al. An eﬀicient authentication and key agreement scheme for multi-gateway wireless sensor networks in IoT deployment. Journal of Network and Computer Applications 2017; 89: 72-85. doi: 10.1016/j.jnca.2016.12.008.
[5] Li X, Niu J, Kumari S, Wu F, Sangaiah AK et al. A three-factor anonymous authentication scheme for wireless sensor networks in internet of things environments. Journal of Network and Computer Applications 2018; 103; 194-204. doi: 10.1016/j.jnca.2017.07.001.
[6] Ndiaye M, Hancke GP, Abu-Mahfouz AM. Software defined networking for improved wireless sensor network management: A survey. Sensors 2017; 17 (5): 1-32. doi: 10.3390/s17051031
[7] Sohrabi K, Gao J, Ailawadhi V, Pottie GJ. Protocols for self-organization of a wireless sensor network. IEEE Personal Communications 2000; 7 (5): 16-27. doi: 10.1017/CBO9781107415324.004.
[8] Yick J, Mukherjee B, Ghosal D. Wireless sensor network survey. Computer Networks 2008; 52 (12): 2292-2330. doi: 10.1016/j.comnet.2008.04.002.
[9] Qian, J, Tiwari P, Gochhayat SP, Pandey HM. A noble double dictionary based ECG compression technique for IoTH. IEEE Internet of Things Journal 2020; 4662 (c): 1–1. doi: 10.1109/jiot.2020.2974678
[10] Muñoz R, Vilalta R, Yoshikane, N, Casellas R, Martínez R et al. IoT-aware multi-layer transport SDN and cloud architecture for traﬀic congestion avoidance through dynamic distribution of IoT analytics. In: 2017 European Conference on Optical Communication (ECOC); Gothenburg, Sweden; 2017. pp. 1-3.
[11] Ancillotti E, Bruno R. BDP-CoAP: Leveraging bandwidth-delay product for congestion control in CoAP. In: 2019 IEEE 5th World Forum on Internet of Things (WF-IoT); Limerick, Ireland; 2019.pp. 656-661.
[12] Toprasert T, Lilakiataskun W. TCP congestion control with MDP algorithm for IoT over heterogeneous network. In: 2017 17th International Symposium on Communications and Information Technologies (ISCIT); Cairns, Queensland, Australia; 2017; pp. 1-5.
[13] Amanullah MA, Habeeb RAA, Nasaruddin FH, Gani A, Ahmed E et al. Deep learning and big data technologies for IoT security. Computer Communications 2020; 151: 495-517. doi: 10.1016/j.comcom.2020.01.016
[14] Seyitoğlu Z. Changing of consumer experience in digital public relations in Turkey: Chatbot applications. MSc, İstanbul Kültür University, Bakırköy, Istanbul, Turkey, 2019 (in Turkish).
[15] Koç E, Çalışkan S, Yazıcıoğlu SA, Demirci U, Kuş Z. Artificial neural networks, word vectors and deep learning applications. MSc, Fatih Sultan Mehmet Vakıf University, Fatih, İstanbul, Turkey, 2018 (in Turkish).
[16] Özkan İ, Ülker E. Deep learning and deep learning models used in image analysis. Gaziosmanpaşa Bilimsel Araştırma Dergisi 2017; 6 (3): 85-104 (in Turkish).
[17] Mallick PK, Ryu SH, Satapathy SK, Mishra, S, Nguyen GN et al. Brain MRI image classification for cancer detection using deep wavelet autoencoder-based deep neural network. IEEE Access 2019; 7: 46278-46287.
[18] Tiwari P, Melucci M. Towards a quantum-inspired binary classifier. IEEE Access 2109; 7: 42354-42372.
[19] Tiwari P, Melucci M. Towards a quantum-inspired framework for binary classification. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management; Torino, Italy; 2018. pp. 1815-1818.
[20] Tiwari P, Melucci M. Binary classifier inspired by quantum theory. In: Proceedings of the AAAI Conference on Artificial Intelligence; Honolulu, Hawaii, USA; 2019. pp. 10051-10052.
[21] Tiwari P, Melucci M. Multi-class classification model inspired by quantum detection theory. ArXiv preprint arXiv 2018; 1810.04491.
[22] Uyulan Ç, Ergüzel TT, Tarhan N. The use of deep learning algorithms on EEG based signal analysis. The Journal Of Neurobehavioral Sciences 2019; 6 (2): 108-124. doi: 10.5455/JNBS.1553607558
[23] Çelenli Hİ. Application of paragraph vectors to news and tweet data. In: 26th Signal Processing and Communications Applications Conference (SIU); Izmir, Turkey; 2018. pp. 1-4.
[24] Işık G, Artuner H. Recognition of radio signals with deep learning neural networks. In: 24th Signal Processing and Communication Application Conference (SIU); Zonguldak, Turkey; 2016. pp. 837-840.
[25] Daş R, Polat B, Tuna G. Recognition and tracking of objects in pictures and videos using deep learning. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 2019; 31 (2): 571-581 (in Turkish). doi: 10.35234/fumbd.608778
[26] Işık G. (2019). Identification of Turkish dialects using deep learning techniques.PhD, Hacettepe University, Sıhhiye, Ankara, Turkey, 2019 (in Turkish).
[27] Nergiz G, Safali Y, Avaroğlu E, Erdoğan S. Classification of Turkish news content by deep learning based LSTM using Fasttext model. In: International Artificial Intelligence and Data Processing Symposium (IDAP); Malatya, Turkey; 2019. pp. 1-6 (in Turkish).
[28] Mendoza JM, Tan V, Fuentes V, Perez G, Tiglao NM. Audio event detection using wireless sensor networks based on deep learning. In: International Wireless Internet Conference; Taipei, Taiwan; 2018. pp. 105-115. doi: 10.1007/978- 3-030-06158-6-11
[29] Liao RF, Wen H, Wu J, Pan F, Xu A et al. Deep-learning-based physical layer authentication for industrial wireless sensor networks. Sensors 2019; 19 (11): 1-17. doi: 10.3390/s19112440
[30] Lee KS, Lee SR, Kim Y, Lee CG. Deep learning–based real-time query processing for wireless sensor network. International Journal of Distributed Sensor Networks 2017; 13 (5): 1- 10. doi: 10.1177/1550147717707896
[31] Wang L, Xia K. Data fusion algorithms for wireless sensor networks based on deep learning model. In: 3rd International Conference on High Performance Compilation, Computing and Communications Conference; Xi’an, China; 2019. pp. 155-158. doi: 10.1145/3318265.3318297
[32] Velásquez D, Sánchez A, Sarmiento S, Toro M, Maiza M et al. A method for detecting coffee leaf rust through wireless sensor networks, remote sensing, and deep learning: Case study of the Caturra Variety in Colombia. Applied Sciences 2020; 10 (2): 697. doi: 10.3390/app10020697
[33] Turabieh H, Sheta A. Cascaded layered recurrent neural network for indoor localization in wireless sensor networks. In: IEEE 2019 2nd International Conference on new Trends in Computing Sciences; Amman, Jordan; 2019. pp. 1-6
[34] Khalid W, Sattar A, Qureshi MA, Amin A, Malik MA et al. A smart wireless sensor network node for fire detection. Turkish Journal of Electrical Engineering & Computer Sciences 2019; 27(4): 2541-2556. doi:10.3906/elk-1812-81
[35] Panda M, Gouda BS, Panigrahi T. Fault Diagnosis in Wireless Sensor Networks Using a Neural Network Constructed by Deep Learning Technique. In: De D, Mukherjee A, Kumar Das S, Dey N (editors). Nature Inspired Computing for Wireless Sensor Networks. Singapore: Springer Nature Singapore Pte Ltd, 2020, pp. 77-101.
[36] Sergiou C, Vassiliou V, Paphitis A. Congestion control in Wireless Sensor Networks through dynamic alternative path selection. Computer Networks 2014; 75: 226–238. doi: 10.1016/j.comnet.2014.10.007
[37] Akyildiz IF, Su W, Sankarasubramaniam Y, Cayirci E. Wireless sensor networks: A survey. Computer Networks 2002; 38 (4): 393–422. doi: 10.1016/S1389-1286(01)00302-4
[38] Solaiman BF, Sheta A. Energy optimization in wireless sensor networks using a hybrid K-means PSO cluster- ing algorithm. Turkish Journal of Electrical Engineering and Computer Sciences 2016; 24 (4): 2679–2695. doi: 10.3906/elk-1403-293
[39] Abbasi M, Rafiee M, Khosravi MR. Investigating the eﬀiciency of multi-threading application programming in- terfaces for parallel packet classification in wireless sensor networks. Turkish Journal of Electrical Engineering & Computer Sciences 2020; 28 (3): 1699-1715 doi: 10.3906/elk-1910-168
[40] Gochhayat SP, Kaliyar P, Conti M, Tiwari P, Prasath VBS et al. LISA: Lightweight context-aware IoT service architecture. Journal of Cleaner Production 2019; 212: 1345–1356. doi: 10.1016/j.jclepro.2018.12.096
[41] Görkemli B, Al-Dulaimi Z. On the performance of quick artificial bee colony algorithm for dynamic deployment of wireless sensor networks. Turkish Journal of Electrical Engineering and Computer Sciences 2019; 27 (6): 4038–4054. doi: 10.3906/ELK-1902-189
[42] Diao W, Sun X, Zheng X, Dou F, Wang H, et al. Eﬀicient saliency-based object detection in remote sensing images using deep belief networks. IEEE Geoscience and Remote Sensing Letters 2016; 13 (2): 137-141. doi: 10.1109/LGRS.2015.2498644
[43] Şeker A, Diri B, Balık HH. A review about deep learning methods and applications. Gazi Mühendislik Bilimleri Dergisi (GMBD) 2017; 3 (3): 47-64.
[44] Gündüz G, Cedimoğlu İH. Gender estimation with image by using deep learning algorithms. Sakarya University Journal of Computer and Information Sciences 2009; 2 (1): 9-17. doi: 10.35377/saucis.02.01.517930
[45] Küçük D, Arıcı N. A literature study on deep learning applications in natural language processing. Uluslararası Yönetim Bilişim Sistemleri ve Bilgisayar Bilimleri Dergisi 2018; 2 (2): 76-86.
[46] Kaya U, Yılmaz A, Dikmen Y. Deep learning methods used in the field of health. Avrupa Bilim ve Teknoloji Dergisi 2019; 16: 792-808. doi: 10.31590/ejosat.573248
47] Kutlu Y, Altan G, İşçimen B, Doğdu SA, Turan C. Recognition of species of triglidae family using deep learning. Journal of the Black Sea/Mediterranean Environment 2017; 23 (1): 56-65.
[48] Ma M, Sun C, Chen X. Discriminative deep belief networks with ant colony optimization for health status as- sessment of machine. IEEE Transactions on Instrumentation and Measurement 2017; 66 (12): 3115-3125. doi: 10.1109/TIM.2017.2735661
[49] Karhunen J, Raiko T, Cho K. Unsupervised deep learning: A short review. In: Advances in Independent Component Analysis and Learning Machines. 1st ed. Finland: Academic Press, 2015, pp. 125-142. doi: 10.1016/B978-0-12- 802806-3.00007-5
[50] Doğan F, Türkoğlu İ. Deep learning and application areas. DÜMF Mühendislik Dergisi 2019; 10 (2): 409-445. doi:10.24012/dumf.411130
[51] Ezel E. Image-based Turkish sign language recognition using deep learning method. PhD, Selçuk University, Konya, Turkey, 2018.
[52] Feng W, Guan N, Li Y, Zhang X, Luo Z. Audio visual speech recognition with multimodal recurrent neural networks. In: IEEE 2017 International Joint Conference on Neural Networks (IJCNN); Anchorage, Alaska, USA; 2017. pp. 681-688.
[53] Uysal F, Hardalaç F, Koç M. A Review about segmentation of magnetic resonance prostate images with deep learning. In: TIPTEKNO 2018 Bildirileri; Gazi Magosa, Turkish Republic of Northern Cyprus (TRNC); 2018. pp. 143-146.
[54] Raghavan VV, Gudivada VN, Govindaraju V, Rao CR. Cognitive computing: Theory and applications. North Holland: Elsevier, 2016.
[55] Zocca V, Spacagna G, Slater D, Roelants P. Python Deep Learning. Birmingham: Packt Publishing, 2017.
[56] Ser G, Bati CT. Determining the best model with deep neural networks:Keras application on mushroom data. Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi 2019; 29 (3): 406-417. doi: 10.29133/yyutbd.505086
[57] Rodríguez Sánchez A, Salmerón Gómez R, García C. The coeﬀicient of determination in the ridge regression. Communications in Statistics-Simulation and Computation 2019; 26 (9): 1-19. doi: 10.1080/03610918.2019.1649421
[58] Clark TE, Ravazzolo F. Macroeconomic forecasting performance under alternative specifications of time‐varying volatility. Journal of Applied Econometrics 2015; 30 (4): 551-575. doi: 10.1002/jae.2379
[59] Kaur T, Kumar S, Segal R. Application of artificial neural network for short term wind speed forecasting. In: IEEE 2016 Biennial international conference on power and energy systems: towards sustainable energy (PESTSE); Bangalore, Karnataka, India; 2016. pp. 1-5
[60] Ramos P, Santos N, Rebelo R. Performance of state space and ARIMA models for consumer retail sales forecasting. Robotics and Computer-Integrated Manufacturing 2015; 34: 151-163. doi: 10.1016/j.rcim.2014.12.015
[61] Kim S, Kim H. A new metric of absolute percentage error for intermittent demand forecasts. International Journal of Forecasting 2016; 32 (3): 669-679. doi: 10.1016/j.ijforecast.2015.12.003
[62] Fumo N, Biswas MR. Regression analysis for prediction of residential energy consumption. Renewable and Sustain- able Energy Reviews 2015; 45: 332-343. doi: 10.1016/j.rser.2015.03.035