Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/11
Browse
2 results
Search Results
Article Citation - WoS: 9Citation - Scopus: 12Intensity and Phase Stacked Analysis of a 40-Otdr System Using Deep Transfer Learning and Recurrent Neural Networks(Optica Publishing Group, 2023) Kayan, Ceyhun Efe; Yüksel Aldoğan, Kıvılcım; Gümüş, AbdurrahmanDistributed acoustic sensors (DAS) are effective apparatuses that are widely used in many application areas for recording signals of various events with very high spatial resolution along optical fibers. To properly detect and recognize the recorded events, advanced signal processing algorithms with high computational demands are crucial. Convolutional neural networks (CNNs) are highly capable tools to extract spatial information and are suitable for event recognition applications in DAS. Long short-term memory (LSTM) is an effective instrument to process sequential data. In this study, a two-stage feature extraction methodology that combines the capabilities of these neural network architectures with transfer learning is proposed to classify vibrations applied to an optical fiber by a piezoelectric transducer. First, the differential amplitude and phase information is extracted from the phasesensitive optical time domain reflectometer (40-OTDR) recordings and stored in a spatiotemporal data matrix. Then, a state-of-the-art pre-trained CNN without dense layers is used as a feature extractor in the first stage. In the second stage, LSTMs are used to further analyze the features extracted by the CNN. Finally, a dense layer is used to classify the extracted features. To observe the effect of different CNN architectures, the proposed model is tested with five state-of-the-art pre-trained models (VGG-16, ResNet-50, DenseNet-121, MobileNet, and Inception-v3). The results show that using the VGG-16 architecture in the proposed framework manages to obtain a 100% classification accuracy in 50 trainings and got the best results on the 40-OTDR dataset. The results of this study indicate that pre-trained CNNs combined with LSTM are very suitable to analyze differential amplitude and phase information represented in a spatiotemporal data matrix, which is promising for event recognition operations in DAS applications. (c) 2023 Optica Publishing GroupArticle Citation - WoS: 6Citation - Scopus: 6Structure and Performance Evaluation of Fractional Lower-Order Covariance Method in Alpha-Stable Noise Environments(Bentham Science Publishers B.V., 2019) Ahmed, Areeb; Savacı, Ferit AcarBackground: All existing time delay estimation methods, i.e. correlation and covariance, depend on second or higher-order statistics which are inapplicable for the correlation of alpha-stable noise signals. Therefore, fractional lower order covariance is the most appropriate method to measure the similarity between the alpha-stable noise signals. Methods: In this paper, the effects of skewness and impulsiveness parameters of alpha-stable distributed noise on fractional lower order covariance method have been analyzed. Results: It has been found that auto-correlation, i.e. auto fractional lower order covariance, \ of non delayed alpha-stable noise signals follows a specific trend for specific ranges of impulsiveness and skewness parameters of alpha-stable distributed noise. The results also depict that, by maintaining the skewness and impulsiveness parameters of alpha-stable noise signals in a certain suggested range, better auto-correlation can be obtained between the transmitted and the received alpha-stable noise signals in the absence and presence of additive white Gaussian noise. Conclusion: The obtained results would improve signal processing in alpha-stable noise environment which is used extensively to model impulsive noise in many noise-based systems. Mainly, it would optimize the performance of random noise-based covert communication, i.e. random communication.