Neural Networks Based Modeling with Adaptive Selection of Hidden Layer's Node for Path Loss Model
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The auto-encoder network which is a good candidate to handle the modeling of the signal strength attenuation is designed for denoising and compensating the distortion of the received data. It provides a non-linear mapping function by iteratively learning the encoder and the decoder. The encoder is the non-linear mapping function, and the decoder demands accurate data reconstruction from the representation generated by the encoder. In addition, the adaptive network width which supports the automatic generation of new hidden nodes and pruning of inconsequential nodes is also implemented in the proposed algorithm for increasing the efficiency of the algorithm. Simulation results show that the proposed method can improve the neural network training surface to achieve the highest possible accuracy of the signal modeling compared with the conventional modeling method.
Abstract
The auto-encoder network which is a good candidate to handle the modeling of the signal strength attenuation is designed for denoising and compensating the distortion of the received data. It provides a non-linear mapping function by iteratively learning the encoder and the decoder. The encoder is the non-linear mapping function, and the decoder demands accurate data reconstruction from the representation generated by the encoder. In addition, the adaptive network width which supports the automatic generation of new hidden nodes and pruning of inconsequential nodes is also implemented in the proposed algorithm for increasing the efficiency of the algorithm. Simulation results show that the proposed method can improve the neural network training surface to achieve the highest possible accuracy of the signal modeling compared with the conventional modeling method.
참고문헌 (26)
- Ashfahani, A., "Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments", Proceedings of the 2019 SIAM International Conference on Data Mining, Society for Industrial and Applied Mathematics, pp.666~674 (2019)
- Y. Bengio, "Representation Learning: A Review and New Perspectives", IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), pp.1798~1828 (2013), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Sreevardhan Cheerla, "Neural network-based path loss model for cellular mobile networks at 800 and 1800 MHz bands", AEU - International Journal of Electronics and Communications, 94, pp.179~186 (2018), Elsevier BV[DOI]
- Deng, L., "Binary coding of speech spectrograms using a deep auto-encoder", Proc. Interspeech, pp.1692~1695 (2010)
- Anupriya Gogna, "Semi-supervised Stacked Label Consistent Autoencoder for Reconstruction and Analysis of Biomedical Signals", IEEE Transactions on Biomedical Engineering, 64(9), pp.2196~2205 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Gondara, L., "Medical image denoising using convolutional denoising autoencoders", Proc. IEEE 16th Int. Conf. Data Mining Workshops, pp.241~246 (2016)
- Hamid, M., "Path loss models for LTE and LTE-A relay stations", Universal journal of communications and network, 1, pp.119~126 (2013)[DOI]
- Salaheddin Hosseinzadeh, "A Neural Network Propagation Model for LoRaWAN and Critical Analysis with Real-World Measurements", Big Data and Cognitive Computing, 1(1), pp.7~ (2017), MDPI AG[DOI]
- Ying-Hui Lai, "A Deep Denoising Autoencoder Approach to Improving the Intelligibility of Vocoded Speech in Cochlear Implant Simulation", IEEE Transactions on Biomedical Engineering, 64(7), pp.1568~1578 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Guan-Yi Liu, "Path Loss Measurements of Indoor LTE System for the Internet of Things", Applied Sciences, 7(6), pp.537~ (2017), MDPI AG[DOI]
- Peng Liu, "Deep Learning with Stacked Denoising Auto-Encoder for Short-Term Electric Load Forecasting", Energies, 12(12), pp.2445~ (2019), MDPI AG[DOI]
- Lu, X., "Speech enhancement based on deep denoising autoencoder", Proc. Interspeech, pp.436~440 (2013)
- Mom, J. M., "Application of artificial neural network for path loss prediction in urban macrocellular environment", American Journal of Engineering Research, 3, pp.270~275 (2014)
- E Ostlin, "Macrocell Path-Loss Prediction Using Artificial Neural Networks", IEEE Transactions on Vehicular Technology, 59(6), pp.2735~2747 (2010), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- "Artificial Neural Network Modeling for Path Loss Prediction in Urban Environments" (2019)[URL]
- Popescu, I., "ANN Prediction Models for Outdoor Environment", 2006 IEEE 17th International Symposium on Personal, Indoor and Mobile Radio Communications, pp.1~5 (2006)
- "Autonomous Deep Learning: Incremental Learning of Denoising Autoencoder for Evolving Data Streams" (2018)[URL]
- Mahardhika Pratama, "Online Tool Condition Monitoring Based on Parsimonious Ensemble+", IEEE Transactions on Cybernetics, 50(2), pp.664~677 (2020), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Mahardhika Pratama, "Evolving Ensemble Fuzzy Classifier", IEEE Transactions on Fuzzy Systems, 26(5), pp.2552~2567 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- "An incremental construction of deep neuro fuzzy system for continual learning of non-stationary data streams" (2018)[URL]
- "Progressive neural networks" (2016)[URL]
- Song, C., "Autoencoder based data clustering, Iberoamerican Congress on Pattern Recognition", pp.117~124 (2013), Springer
- Vincent, P., "Extracting and composing robust features with denoising autoencoders", Proc. 25th Int. Conf. Mach. Learn., pp.1096~1103 (2008)
- "Lifelong learning with dynamically expandable networks" (2017)[URL]
- Zhou, G., "Online incremental feature learning with denoising autoencoders", Artificial intelligence and statistics, pp.1453~1461 (2012)
- Alhareth Zyoud, "Parameterized indoor propagation model for mobile communication links", Microwave and Optical Technology Letters, 58(4), pp.823~826 (2016), Wiley[DOI]