scholarly journals Spectral-Based SPD Matrix Representation for Signal Detection Using a Deep Neutral Network

Entropy ◽  
2020 ◽  
Vol 22 (5) ◽  
pp. 585 ◽  
Author(s):  
Jiangyi Wang ◽  
Xiaoqiang Hua ◽  
Xinwu Zeng
Keyword(s):  
Deep Learning ◽  
Signal Detection ◽  
Detection Method ◽  
Binary Classification ◽  
Underlying Structure ◽  
Classification Problems ◽  
Frequency Spectra ◽  
Time Frequency ◽  
Target Signal ◽  
Simulated Signal

The symmetric positive definite (SPD) matrix has attracted much attention in classification problems because of its remarkable performance, which is due to the underlying structure of the Riemannian manifold with non-negative curvature as well as the use of non-linear geometric metrics, which have a stronger ability to distinguish SPD matrices and reduce information loss compared to the Euclidean metric. In this paper, we propose a spectral-based SPD matrix signal detection method with deep learning that uses time-frequency spectra to construct SPD matrices and then exploits a deep SPD matrix learning network to detect the target signal. Using this approach, the signal detection problem is transformed into a binary classification problem on a manifold to judge whether the input sample has target signal or not. Two matrix models are applied, namely, an SPD matrix based on spectral covariance and an SPD matrix based on spectral transformation. A simulated-signal dataset and a semi-physical simulated-signal dataset are used to demonstrate that the spectral-based SPD matrix signal detection method with deep learning has a gain of 1.7–3.3 dB under appropriate conditions. The results show that our proposed method achieves better detection performances than its state-of-the-art spectral counterparts that use convolutional neural networks.

LFM Signal Detection Method Based on Fractional Fourier Transform

2014 ◽  
Vol 989-994 ◽  
pp. 4001-4004 ◽  
Author(s):  
Yan Jun Wu ◽  
Gang Fu ◽  
Yu Ming Zhu
Keyword(s):  
Fourier Transform ◽  
Signal Detection ◽  
Frequency Analysis ◽  
Experimental Analysis ◽  
Fractional Fourier Transform ◽  
Detection Method ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Frequency Information ◽  
Strong Impulse

As a generalization of Fourier transform, the fractional Fourier Transform (FRFT) contains simultaneity the time-frequency information of the signal, and it is considered a new tool for time-frequency analysis. This paper discusses some steps of FRFT in signal detection based on the decomposition of FRFT. With the help of the property that a LFM signal can produce a strong impulse in the FRFT domain, the signal can be detected conveniently. Experimental analysis shows that the proposed method is effective in detecting LFM signals.

scholarly journals Comparison of Attention-based Deep LearningModels for EEG Classification

2021 ◽  
Author(s):  
Giulia Cisotto ◽  
Alessio Zanga ◽  
Joanna Chlebus ◽  
Italo Zoppis ◽  
Sara Manzoni ◽  
...  
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Classification Performance ◽  
Classification Problems ◽  
Large Variability ◽  
Eeg Classification ◽  
Time Frequency ◽  
Promising Strategy ◽  
Complex Reasoning

Abstract Deep Learning (DL) has recently shown promising classification performance in Electroencephalography (EEG) in many different scenarios. However, the complex reasoning of such models often prevent the user to explain their classification abilities. Attention, one of the most recent and influential ideas in DL, allows the models to learn which portions of the data are relevant to the final classification output. In this work, we compared three attention-enhanced DL models, the brand-new InstaGATs , an LSTM with attention and a CNN with attention. We used these models to classify normal and abnormal, including artifactual and pathological, EEG patterns in three different datasets. We achieved the state of the art in all classification problems, regardless the large variability of the datasets and the simple architecture of the attention-enhanced models. Additionally, we proved that, depending on how the attention mechanism is applied and where the attention layer is located in the model, we can alternatively leverage the information contained in the time, frequency or space domain of the EEG dataset. Therefore, attention represents a promising strategy to evaluate the quality of the EEG information, and its relevance for classification, in different real-world scenarios.

Sub-Optimum Detector Based on Reverbertion-Whiten in FrFT Field

2014 ◽  
Vol 577 ◽  
pp. 810-815
Author(s):  
Zhen Gang Li
Keyword(s):  
Signal Detection ◽  
Target Detection ◽  
Colored Noise ◽  
Detection Method ◽  
Unknown Parameters ◽  
Coherent Signal ◽  
Time Frequency ◽  
Linear Transform ◽  
Focusing Property ◽  
Sine Signal

Target detection in the presence of strong seabed reverberation is a hot research topic nowadays. This kind of target detection method is similar to signal detection with known shape and unknown parameters under non-WGN or coherent signal detection in reverberation. When a LFM signal is choose as transmitted signal, target echo has excellent time-frequency focusing property on a certain rotating angle and reverberation could lose its original linear modulation property. LFM signal can be transformed to a sine signal with some rank FrFT. Since FrFT is a linear transform, interference including reverberation and noise will keep former statistic characteristics. So LFM signal detection is thus equivalent to detection of sine signals in absence of colored noise. The reverberation will be easily erased and target echo will be preserved. Based on the analysis above all, a sub-optimum detector based on reverberation-whiten in FrFT field is advanced. The validity of these conclusions is validated by computer simulations. A satisfying result is achieved.

scholarly journals Deep Ordinal Regression Based on Data Relationship for Small Datasets

2017 ◽  
Author(s):  
Yanzhu Liu ◽  
Adams Wai Kin Kong ◽  
Chi Keong Goh
Keyword(s):  
Deep Learning ◽  
Deep Neural Networks ◽  
Color Image ◽  
Binary Classification ◽  
Ordinal Regression ◽  
Learning Problems ◽  
Classification Problems ◽  
Regression Problem ◽  
New Approach ◽  
High Level

Ordinal regression aims to classify instances into ordinal categories. As with other supervised learning problems, learning an effective deep ordinal model from a small dataset is challenging. This paper proposes a new approach which transforms the ordinal regression problem to binary classification problems and uses triplets with instances from different categories to train deep neural networks such that high-level features describing their ordinal relationship can be extracted automatically. In the testing phase, triplets are formed by a testing instance and other instances with known ranks. A decoder is designed to estimate the rank of the testing instance based on the outputs of the network. Because of the data argumentation by permutation, deep learning can work for ordinal regression even on small datasets. Experimental results on the historical color image benchmark and MSRA image search datasets demonstrate that the proposed algorithm outperforms the traditional deep learning approach and is comparable with other state-of-the-art methods, which are highly based on prior knowledge to design effective features.

scholarly journals Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks

Sensors ◽  
2019 ◽  
Vol 19 (14) ◽  
pp. 3079 ◽  
Author(s):  
Attila Reiss ◽  
Ina Indlekofer ◽  
Philip Schmidt ◽  
Kristof Van Laerhoven
Keyword(s):  
Heart Rate ◽  
Deep Learning ◽  
Large Scale ◽  
Learning Approach ◽  
Frequency Spectra ◽  
Time Frequency ◽  
Rate Estimation ◽  
Wide Range ◽  
Public Datasets ◽  
Heart Rate Estimation

Photoplethysmography (PPG)-based continuous heart rate monitoring is essential in a number of domains, e.g., for healthcare or fitness applications. Recently, methods based on time-frequency spectra emerged to address the challenges of motion artefact compensation. However, existing approaches are highly parametrised and optimised for specific scenarios of small, public datasets. We address this fragmentation by contributing research into the robustness and generalisation capabilities of PPG-based heart rate estimation approaches. First, we introduce a novel large-scale dataset (called PPG-DaLiA), including a wide range of activities performed under close to real-life conditions. Second, we extend a state-of-the-art algorithm, significantly improving its performance on several datasets. Third, we introduce deep learning to this domain, and investigate various convolutional neural network architectures. Our end-to-end learning approach takes the time-frequency spectra of synchronised PPG- and accelerometer-signals as input, and provides the estimated heart rate as output. Finally, we compare the novel deep learning approach to classical methods, performing evaluation on four public datasets. We show that on large datasets the deep learning model significantly outperforms other methods: The mean absolute error could be reduced by 31 % on the new dataset PPG-DaLiA, and by 21 % on the dataset WESAD.

A Fault Detection Approach Based on Sound Signal Analysis for Equipment Monitoring

2020 ◽  
pp. 129-139
Author(s):  
Weihai Sun ◽  
Lemei Han
Keyword(s):  
Fault Detection ◽  
Signal Analysis ◽  
Energy Analysis ◽  
Detection Method ◽  
Sound Signal ◽  
Practical Significance ◽  
Time Frequency ◽  
Detection Approach ◽  
Machine Fault ◽  
Learning Data

Machine fault detection has great practical significance. Compared with the detection method that requires external sensors, the detection of machine fault by sound signal does not need to destroy its structure. The current popular audio-based fault detection often needs a lot of learning data and complex learning process, and needs the support of known fault database. The fault detection method based on audio proposed in this paper only needs to ensure that the machine works normally in the first second. Through the correlation coefficient calculation, energy analysis, EMD and other methods to carry out time-frequency analysis of the subsequent collected sound signals, we can detect whether the machine has fault.

Sign in / Sign up

Export Citation Format

Share Document