Published October 20, 2024 | Version v1
Thesis Open

AN IMPROVED MODEL FOR RF SIGNAL ANALYSIS WITH NEURAL NETWORKS USING HYPERPARAMETER TUNING

Authors/Creators

  • 1. ROR icon Shri Venkateshwara University

Contributors

Supervisor:

  • 1. ROR icon Shri Venkateshwara University
  • 2. ROR icon J.C. Bose University of Science & Technology, YMCA

Description

This dissertation discusses models for signal analysis using neural networks. At this time
neural networks have shown significant results in various fields including bio-medical
ECGs, automation driving and large language models. It also has potential for
implementation in signal analysis in the RF range. Radio frequency is the most widely
used electromagnetic wave spectrum for communication, for that it has motivated us to
pursue this research.

By going through various review articles and scholarly papers, this dissertation highlights
the various models of neural networks and the methods implemented in signal analysis.
Many of the neural networks modals have been written over the years, each network
having some advantages over the other. This study provides a brief description neural
network modals and provides a comparative analysis. Based on this analysis, this study
puts forward hybrid convolutional neural network- long short term memory network also
know as CNN-LSTM neural network, that aids in proper signal analysis.
The neural network can be implemented in a number of programming languages, keeping
the model’s algorithm indistinguishable. While conducting this research, python language
was adopted and tensor-flow library by Google was used.

Files

organized.pdf

Files (24.3 MB)

Name Size Download all
md5:be4684e0ed0b71ae789ba5d38891b4c3
24.3 MB Preview Download

Additional details

Dates

Accepted
2024-08-03

Software

Repository URL
https://www.kaggle.com/code/shivantasahoo/cnn-lstm
Programming language
Python
Development Status
Active

References

  • [1] Radford, A., Liu, C., Kim, B. "Speech recognition using deep neural networks." IEEE Transactions on Signal Processing, vol. 71, pp. 345-360, 2023. [2] Cai, Z., Li, Y., Zhang, T., "EEG analysis with deep learning: a review." Journal of Neural Engineering, vol. 16, no. 6, 2019. [3] Zhang, Q., Wang, H., Xu, Y., "Designing mechanisms for active/passive RF and microwave components/circuits using neural networks." IEEE Transactions on Microwave Theory and Techniques, vol. 67, no. 5, 2023. [4] Kabir, H., Chen, M., Zhao, L., "Dynamic modeling of microwave circuits using deep and recurrent neural networks." IEEE Microwave Magazine, vol. 24, no. 2, 2023. [5] Fortino, G. F., Lombardo, S., Perillo, F., "Digital signal analysis for active target time projection chambers using convolutional neural networks." Journal of Instrumentation, vol. 15, no. 1, 2020. [6] Liu, C., Yang, H., Wang, X., "Graph neural networks for the analysis of brain connectomes." Neurocomputing, vol. 414, pp. 294-307, 2020. [7] Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi, Ayad Al-Dujaili, Ye Duan, Omran Al-Shamma, J. Santamaría, Mohammed A. Fadhel, Muthana Al-Amidie & Laith
  • Farhan. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8, 53 (2021). https://doi.org/10.1186/s40537-021-00444-8 [8] Shang, Z., Zhao, Z. & Yan, R. Denoising Fault-Aware Wavelet Network: A Signal Processing Informed Neural Network for Fault Diagnosis. Chin. J. Mech. Eng. 36, 9 (2023). https://doi.org/10.1186/s10033-023-00838-0 [9] Jens Oppliger, M. Michael Denner, Julia Küspert, Ruggero Frison, Qisi Wang, Alexander Morawietz, Oleh Ivashko, Ann-Christin Dippel, Martin von Zimmermann, Izabela Biało, Leonardo Martinelli, Benoît Fauqué, Jaewon Choi, Mirian Garcia- Fernandez, Ke-Jin Zhou, Niels Bech Christensen, Tohru Kurosawa, Naoki Momono, Migaku Oda, Fabian D. Natterer, Mark H. Fischer, Titus Neupert & Johan Chang. Weak signal extraction enabled by deep neural network denoising of diffraction data. Nat Mach Intell 6, 180–186 (2024). https://doi.org/10.1038/s42256-024-00790-1 [10] Abul Kalam Azad, Liang Wang, Nan Guo, Hwa-Yaw Tam, and Chao Lu, "Signal processing using artificial neural network for BOTDA sensor system," Opt. Express 24, 6769-6782 (2016) [11] Lin W-J, Lo S-H, Young H-T, Hung C-L. Evaluation of Deep Learning Neural Networks for Surface Roughness Prediction Using Vibration Signal Analysis. Applied Sciences. 2019; 9(7):1462. https://doi.org/10.3390/app9071462 [12] Zhang G, Nie X, Liu B, Yuan H, Li J, Sun W, Huang S. A multimodal fusion method for Alzheimer's disease based on DCT convolutional sparse representation. Front
  • [19] Panda, Balaram. (2019). Hyperparameter Tuning. 10.13140/RG.2.2.11820.21128. [20] Guillemard, Mijail & Iske, Armin & Krause-Solberg, Sara. (2011). Dimensionality Reduction Methods in Independent Subspace Analysis for Signal Detection [21] Tomer, Manjeet & Vashisht, Priyanka. (2020). Machine Learning Techniques in RFID Datasets. International Journal of Recent Technology and Engineering (IJRTE). 8. 4345-4353. 10.35940/ijrte.F9052.038620. [22] D. Roy, T. Mukherjee, M. Chatterjee, E. Blasch and E. Pasiliao, "RFAL: Adversarial Learning for RF Transmitter Identification and Classification," in IEEE Transactions on Cognitive Communications and Networking, vol. 6, no. 2, pp. 783-801, June 2020, doi: 10.1109/TCCN.2019.2948919. [23] Meneghetti, L., Demo, N. & Rozza, G. A dimensionality reduction approach for convolutional neural networks. Appl Intell 53, 22818–22833 (2023). https://doi.org/10.1007/s10489-023-04730-1 [24] Vincent, A.M., Jidesh, P. An improved hyperparameter optimization framework for AutoML systems using evolutionary algorithms. Sci Rep 13, 4737 (2023). https://doi.org/10.1038/s41598-023-32027-3
  • [25] Sarker IH. Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Comput Sci. 2021;2(3):160. doi: 10.1007/s42979-021-00592-x. Epub 2021 Mar 22. PMID: 33778771; PMCID: PMC7983091.
  • [26] Liu, Y., Chenl, Z., Wang, Z., Zhao, W., He, W., Zhu, J., Wang, O., Zhang, N., Jia, T., Ma, Y. et al. (2023c).Aa 22nm 0.43 pj/sop sparsity-aware in-memory neuromorphic computing system with hybrid spiking and artificial neural network and configurable topology.In 2023 IEEE Custom Integrated Circuits Conference (CICC) (pp. 1–2).IEEE. [27] Kim, K., Wu, F., Peng, Y., Pan, J., Sridhar, P., Han, K. J., & Watanabe, S. (2023).Ebranchformer: Branchformer with enhanced merging for speech recognition.In 2022 IEEE Spoken Language Technology Workshop (SLT) (pp. 84–91).IEEE. [28] Shevitski, Brian R., Watkins, Yijing Z., Man, Nicole, & Girard, Michael K. Digital Signal Processing Using Deep Neural Networks. United States. https://doi.org/10.2172/1984848 [29] Daniel Morton, Virgil Barnard, "Signal analyzing network tool using deep learning," Proc. SPIE 12547, Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII, 125470T (14 June 2023); https://doi.org/10.1117/12.2664141
  • [30] Setzler, Matthew & Coda, Elizabeth & Rounds, Jeremiah & Vann, Michael & Girard, Michael. (2022). Deep Learning for Spectral Filling in Radio Frequency Applications. [31] Theis, F. J., Hartl, D., Krauss-Etschmann, S., & Lang, E. W. (2003). Neural network signal analysis in immunology. In Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003 (pp. 235-238). Article 1224857 (Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003; Vol. 2). IEEE Computer Society. https://doi.org/10.1109/ISSPA.2003.1224857 [32] Choi, Sang Ho. (2024). Spiking neural networks for biomedical signal analysis. Biomedical Engineering Letters. 10.1007/s13534-024-00405-z. [33] Huttunen, Heikki & Shokrollahi, Fatemeh & Chen, Ke. (2016). Car type recognition with Deep Neural Networks. 1115-1120. 10.1109/IVS.2016.7535529. [34] Slavutskiy, Alexandr & Leonid, Slavutskii & Slavutskaya, Elena. (2021). Neural Network for Real-Time Signal Processing: the Nonlinear Distortions Filtering. 84-88. 10.1109/UralCon52005.2021.9559619. [35] Fortino, G.F. & Zamora, J. & Tamayose, L.E. & Hirata, Nina & Guimarães, Valdir. (2022). Digital signal analysis based on convolutional neural networks for active target time projection chambers. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment. 1031. 166497. 10.1016/j.nima.2022.166497.
  • [36] Gemelli, A., Vivoli, E., & Marinai, S. (2022). Graph Neural Networks and Representation Embedding for Table Extraction in PDF Documents. 2022 26th International Conference on Pattern Recognition (ICPR), 1719-1726. [37] Crowther, P.S., Cox, R.J. (2005). A Method for Optimal Division of Data Sets for Use in Neural Networks. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3684. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11554028_1 [38] Feng, S., Hua, X., Wang, J., & Zhu, X. (2020). A signal detection method based on matrix information geometric dimensionality reduction. Journal of Physics: Conference Series, 1544. [39] Padillo, Francisco & Luna, José María & Cano, Alberto & Ventura, Sebastian. (2016). A Data Structure to Speed-Up Machine Learning Algorithms on Massive Datasets. 365-376. 10.1007/978-3-319-32034-2_31. [40] Muraina, Ismail. (2022). Ideal Dataset Splitting Ratios in Machine Learning Algorithms: General Concerns for Data Scientists and Data Analysts. 7th International Mardin Artuklu Scientific Researches Feb (2022). [41] Günter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter. 2017. Self-normalizing neural networks. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 972–981.
  • [42] Z. Wang, M. Agung, R. Egawa, R. Suda and H. Takizawa, "Automatic Hyperparameter Tuning of Machine Learning Models under Time Constraints," 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, 2018, pp. 4967-4973, doi: 10.1109/BigData.2018.8622384. [43] Harris, T.J. & Yuan, Hui. (2010). Filtering and frequency interpretations of Singular Spectrum Analysis. Physica D-nonlinear Phenomena - PHYSICA D. 239. 1958-1967. 10.1016/j.physd.2010.07.005.
  • [44] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. [45] Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. [46] O'Shea, T., & Hoydis, J. (2017). An Introduction to Machine Learning Communications Systems. ArXiv:1702.00832. [47] Frédéric Cohen Tenoudji, Analog and Digital Signal Analysis: From Basics to Applications. [48] Mourad Fakhfakh, Esteban Tlelo-Cuautle, Patrick Siarry,Computational Intelligence in Analog and Mixed-Signal (AMS) and Radio-Frequency (RF) Circuit Design.
  • [49] Nirode Mohanty'l ,SIGNAL PROCESSING Signals, Filtering, and Detection, THE AEROSPACE CORPORATION, Los Angeles, California [50] Ljubiˇsa Stankovi´c, Miloˇs Dakovi´c, Thayananthan Thayaparan, Time- Frequency Signal Analysis [51] Boashash, Boualem. (2003). Time-Frequency Signal Analysis and Processing: A Comprehensive Reference.