ANFIS Analysis of Wireless Sensor Data with FPGA

Applications related with WSNs may include thousands of separate sensor nodes, production and control data for different industrial sectors. It is important to manage these applications, monitor the network and reprogram the nodes to avoid operational problems. In this study, we propose a smart wireless sensor network using a reconfigurable embedded system of Field-Programmable Gate Arrays (FPGAs) with a soft-core processor. This processor can be programmed dynamically and synthesized to implement the preprocessing of sensed data by ensemble Hybrid Neuro-Fuzzy algorithms such as Adaptive Neuro-Fuzzy Inference System (ANFIS). The first part of the proposed work is based on Matlab software to develop and train the ANFIS algorithm. Two different types of data sets (temperature and humidity) downloaded from Internet have been used in order to make a comparison between the Matlab Toolbox and modified ANFIS algorithm with momentum factor. The results obtained in this study have shown that the modified ANFIS algorithm is the convenient choice in terms of speed, accuracy.

Anahtar Kelimeler:

ANFIS, Neuro-Fuzzy System, FPGA, Sensor Nodes, Smart Node

Ideal Steganography Scenario: Calculation of Capacities of Carrier Images, OPA Method in Frequency-Based Steganography

In this study, digital image steganography, a branch of steganography, and DCT (Discrete Cosine Transform) and DWT (Discrete Wavelet Transform, frequency-based steganography methods that are a sub-branch of it, are mentioned. Methods such as MSE (Mean Squared Error), PSNR (Peak Signal Noise Ratio) which are performance calculation parameters of steganographic methods are explained and the methods of calculating image capacity like KL-Divergence, JS-Divergence and QTS (Quard Tree Segmentation) for increasing the values of these parameters are mentioned. This study explains the OPAP (Optimum Pixel Adjustment Process) method, which allows the existing capacity in the pictures to be further increased, in detail and provides an ideal steganography scenario. Here, we made use of the ability of the DWT to extract low frequency and bands suitable for data hiding and the use of the LSB method by obtaining the feature coefficients of DCT in these bands.. In addition, this scenario has been tried and consequently reached the result that the images with higher data concealment capacity than QTS have higher PSNR values.

Keywords:

DCT, DWT, KL-Divergence Jensen-Shannon Divergence, Information Technology Security, Data Security, Data Hiding, Frequency Based Steganography,

PDF

___

[1] Ahmed, E.,Mohamed, S., Khaled, M., Ahmed, A., (2016), A hybrid neuro-fuzzy power prediction system for wind energy generation, International Journal of Electrical Power & Energy Systems,74, 384-395.
[2] Akyıldız, L., Sankarasubramaniam, Y., Su, W., Cayırcı, E. ,(2002), “Wireless sensor networks: A survey”, Journal of Computer Networks, 38, 393-422.
[3] Andrzej, P., Meng, J. ,(2016), “The method of hardware implementation of fuzzy systems on FPGA”, International Conference on Artificial Intelligence and Soft Computing, ICAISC 2016, 284-298.
[4] Brassai, S., Hajdu, S., Tamas, T., 4(2015), “Hardware implementation of a neuro-fuzzy controller using high level synthesis tool”, Conference on Recent Achievements in Mechatronics, Automation, Computer Science and Robotics, 10.1515/macro-2015-0018.
[5] Brassai, S., Hajdu, Sz., Tamas, T., Bakó, L., (2015), “Hardware implemented adaptive neuro-Fuzzy system”, Carpathian Control Conference, 10.1109/Carpathian CC.2015.7145046.
[6] Campo, I., Basterretxea, K., Echanobe, J., (2012), “A System-on-chip development of a neuro–fuzzy embedded agent for ambient-intelligence environments”, IEEE Transactions on Systems, 10.1109/TSMCB.2011.2168516.
[7] Cheng-Jian, L., Chun-Cheng, P., (2014), “Classification using an efficient neuro-fuzzy classifier based on adaptive fuzzy reasoning method”, Conference on Computer, Consumer and Control, 10.1109/IS3C.2014.34.
[8] Cihan, K.arakuzua, F., Mehmet, A. ,(2016), “FPGA implementation of neuro-fuzzy system with improved PSO learning”, Journal of the International Neural Network Society,79- 2016, 128-140).
[9] Doaa, M., Hanaa, T., (2017), “Analysis and design of greenhouse temperature control using adaptive neuro-fuzzy inference system”, Journal of Electrical Systems and Information Technology, 4(1), 34-48.
[10] François, Ph., (2014), “Runtime hardware reconfiguration in wireless sensor networks for condition monitoring”, Universitäts - und Landesbibliothek, Darmstadt.
[11] Janusz, K., (2000), “Introduction to neuro-fuzzy systems”, Advances in Soft Computing. Springer-Verlag, ISBN 978-3-7903-1852-9. Berlin/Heildelberg.
[12] Janusz, K. (2002), “Neuro-fuzzy architectures and hybrid learning”, Springer-Verlag,ISBN 978-3-7903-1802-4, Berlin/Heildelberg
[13] Maicon, M.,Luci, P., Silvana, R., Flavia, C., Claudio, M., Paulo F., Albert, Y., (2017), “Damage prediction for wind turbines using wireless sensor and actuator networks”, Journal of Network and Computer Applications. 80,123-140.
[14] Meena, S. & Krishna, N., (2014), “Simulation of dynamically reconfigurable wireless sensor node”, International Conference on Electronics and Communication System, Coimbatore, 10.1109/ECS.2014.6892795. India.
[15] Melin, P., Soto, J., Castillo, O., Soria, J., (2013), “Time series prediction using ensembles of ANFIS models with genetic optimization of interval type-2 and type-1 fuzzy integrators”, Journal of Hybrid Intelligent Systems, 10.3233/HIS-140196.
[16] Potdar, V., Sharif, A., Chang, E., (2009), “Wireless sensor networks: a Survey”, International Conference on Advanced Information Networking and Applications Workshops, 10.1109/WAINA.2009.192. UK, Bradford.
[17] Rajasekaran, C., Jeyabharath, R. and Veena, P., (2014), “Hardware-software reconfigurable techniques for wireless sensor network”, Journal of Applied Sciences, Engineering and Technology 8(17): 1855-1862.
[18] Rasika, A. and Pathan, M., (2015), “Design and implementation of ANFIS algorithm using VHDL for vehicular system”, Journal on Recent and Innovation Trends in Computing and Communication 3, 2: 820-824.
[19] Sándor, T., Szabolcs, H., Tibor, T., (2015), “Embedded adaptive neuro-fuzzy inference system with hardware implemented real time parameter update”, International Conference on Recent Achievements in Mechatronics, Automation, Computer Science and Robotics, 10.1515/macro-2015-0021
[20] Taylor, J., Buizza, R., (2002), “Neural network load forecasting with weather ensemble predictions”, IEEE Transactions on Power Systems, 10.1109/TPWRS.2002.800906.

Yayın Aralığı: Yılda 2 Sayı
Başlangıç: 2017
Yayıncı: İstanbul Üniversitesi

Arşiv

Sayıdaki Diğer Makaleler

ANFIS Analysis of Wireless Sensor Data with FPGA

Khazal AHMED, Tuncay Ercan

Validity Issues in Linked Data Driven IS Research

Ziya Nazim Perdahci, Mehmet Nafiz Aydin, Kenan Kafkas

İdeal Steganografi Senaryosu: Taşıyıcı Resimlerin Kapasitelerinin Hesaplanması, Frekans Tabanlı Steganografide OPA Yöntemi

Ferdi Sönmez, Faruk Takaoğlu, Oğuz Kaynar

Bir Güvenlik Trendi: Bal Küpü

Süleyman Muhammed ARIKAN, Recep BENZER

A REAL LIFE WEB BASED MARKETING OPTIMIZATION FRAMEWORK with EXTERNAL DATA

Şadi Evren ŞEKER