Deep Learning-based Signal Research Articles

Advancements in Bearing Defect Diagnosis: Deep Learning-based Signal Processing and Real-time Fault Detection

Advancements in Bearing Defect Diagnosis: Deep Learning-based Signal Processing and Real-time Fault Detection

Deep Learning Enhanced Label-Free Action Potential Detection Using Plasmonic-Based Electrochemical Impedance Microscopy.

Measuring neuronal electrical activity, such as action potential propagation in cells, requires the sensitive detection of the weak electrical signal with high spatial and temporal resolution. None of the existing tools can fulfill this need. Recently, plasmonic-based electrochemical impedance microscopy (P-EIM) was demonstrated for the label-free mapping of the ignition and propagation of action potentials in neuron cells with subcellular resolution. However, limited by the signal-to-noise ratio in the high-speed P-EIM video, action potential mapping was achieved by averaging 90 cycles of signals. Such extensive averaging is not desired and may not always be feasible due to factors such as neuronal desensitization. In this study, we utilized advanced signal processing techniques to detect action potentials in P-EIM extracted signals with fewer averaged cycles. Matched filtering successfully detected action potential signals with as few as averaging five cycles of signals. Long short-term memory (LSTM) recurrent neural network achieved the best performance and was able to detect single-cycle stimulated action potential successfully [satisfactory area under the receiver operating characteristic curve (AUC) equal to 0.855]. Therefore, we show that deep learning-based signal processing can dramatically improve the usability of P-EIM mapping of neuronal electrical signals.

Diagnosis of EV Gearbox Bearing Fault Using Deep Learning-Based Signal Processing

Diagnosis of EV Gearbox Bearing Fault Using Deep Learning-Based Signal Processing

Joint Parallel Tabu Search Algorithm-Based Look-Up Table Design and Deep Learning-Based Signal Detection for OFDM-AIM

Joint Parallel Tabu Search Algorithm-Based Look-Up Table Design and Deep Learning-Based Signal Detection for OFDM-AIM

Direct Positron Emission Imaging Using Ultrafast Timing Performance Detectors

This is an explanatory paper on Sun Il Kwon et al., Nat. Photon. 15: 914-918, 2021 and some parts of this manuscript are translated from the paper. Medical imaging modalities such as X-ray computed tomography, Magnetic resonance imaging, positron emission tomography (PET), and single photon emission computed tomography, require image reconstruction processes, consequently constraining them to form cylindrical shapes. However, among them, only PET can use additional information, so called time of flight, on an event-by-event basis. If coincidence time resolution (CTR) of PET detectors improved to 30 ps, which corresponds to spatial resolution of 4.5 mm, directly localizing electron-positron annihilation point is possible, allowing us to circumvent image reconstruction processes and free us from the geometric constraint. We call this concept direct positron emission imaging (dPEI). We have developed ultrafast radiation detectors by focusing on Cherenkov photon detection. Furthermore, the CTR of 32 ps being equivalent to 4.8 mm spatial resolution is achieved by combining deep learning-based signal processing with the detectors. In this article, we explain how we developed the detectors and demonstrated the first dPEI using different types of phantoms, how we will tackle limitations to be addressed to make the dPEI more practical, and how dPEI will emerge as an imaging modality in nuclear medicine.

Deep learning-based denoising of acoustic images generated with point contact method

Abstract The versatile nature of ultrasound imaging finds applications in various fields. A point contact excitation and detection method is generally used for visualizing the acoustic waves in Lead Zirconate Titanate (PZT) ceramics. Such an excitation method with a delta pulse generates a broadband frequency spectrum and wide directional wave vector. The presence of noise in the ultrasonic signals severely degrades the resolution and image quality. Deep learning-based signal and image denoising has been demonstrated recently. This paper bench-marked and compared several state-of-the-art deep learning image denoising methods with the classical denoising methods. The best-performing deep learning models are observed to be performing at par or, in some cases, even better than the classical methods on ultrasonic images. We further demonstrate the effectiveness and versatility of the deep learning-based denoising model for the unexplored domain of ultrasound/ultrasonic data. We conclude with a discussion on selecting the best method for denoising ultrasonic images. The impact of this work may help ultrasound-based defects identification equipment manufacturers to adopt a deep learning-based denoising model for more wider and versatile use.

Simulation of memristive crossbar arrays for seizure detection and prediction using parallel Convolutional Neural Networks

<h2>Abstract</h2> For epileptic seizure detection and prediction, to address the computational bottleneck of the von Neumann architecture, we develop an in-memory memristive crossbar-based accelerator simulator. The simulator software is composed of a Python-based neural network training component and a MATLAB-based memristive crossbar array component. The software provides a baseline network for developing deep learning-based signal processing tasks, as well as a platform to investigate the impact of weight mapping schemes and device and peripheral circuitry non-idealities.

A generic AI pipeline for identifying known species and discovering new species

To counterattack the current biodiversity crisis, we need innovative tools and technologies that can greatly improve species identification and discovery at scale. Here, we describe a data analysis pipeline to automatically identify biological sound categories in soundscape data and accelerate the discovery of new species. The pipeline consists of two components: (1) Unsupervised audio event detection and clustering that enables automatic detection and categorization of biological sounds in large audio datasets and (2) supervised deep learning-based signal detection that enables automated cluster labeling and detection of known sound categories in new audio. We evaluated the results of our unsupervised analysis tools applied to a labeled dataset of ∼18 h of recordings from Panama. Experts assigned a label to each sound event with a max frequency of 6 kHz. Our results show that clusters generally had high homogeneity and completeness and indicate that our cluster analysis tool can successfully detect and group like-sounds together, improving data processing and species identification. In addition, we were able to implement these analytical tools in a user-friendly data analysis platform that will provide scientists, wildlife managers, conservationists, and public and private environmental organizations with the information they need to make informed conservation and management decisions.

Distributed deep learning-based signal classification for time–frequency synchronization in wireless networks

In this paper, we propose a novel distributed deep learning (DL) network for signal classification to achieve accurate time–frequency synchronization in wireless communication networks. Restricted by the non-random signal generated by the transmitter, the existing time–frequency synchronization algorithms cannot obtain reliable synchronization results. With the development of DL, feature-based signal classification has become an effective way to improve the precision of time–frequency synchronization. Considering the multipath effect in the practical propagation environments, a distributed DL network for wireless communication is proposed, where the received signal is classified by the distributed DL network. Specifically, preprocessed images are obtained by applying the discrete Fourier transform (DFT) and short-time Fourier transform (STFT) to facilitate the signal feature extraction. Convolutional neural network (CNN) architecture is designed for feature extraction on the preprocessed images. Meanwhile, a feature fusion module based on attention mechanisms is proposed to fuse data adaptively and obtain the final signal classification results. Simulation results show that the proposed distributed DL network can achieve higher classification accuracy than traditional DL networks under multiple modulation schemes. More importantly, reliable signal classification can effectively improve the performance of time–frequency synchronization in wireless communication networks.

Deep Learning-Based Signal Detection for Rate-Splitting Multiple Access Under Generalized Gaussian Noise

In this paper, we propose a long short-term memory-based deep learning (DL) architecture for signal detection in uplink and downlink rate-splitting multiple access systems with multi-carrier modulation, over Nakagami-m fading and generalized Gaussian noise (GGN). The proposed DL detector completely eliminates the need for the use of successive interference cancellation (SIC), which suffers from disadvantages such as error propagation. In an orthogonal frequency division multiplexing setting, we show that the proposed DL detector outperforms the standard SIC receivers such as the least squares detector and the minimum mean-squared error receiver, and attains the performance of the optimal maximum likelihood detector, in terms of the symbol error rate (SER). Furthermore, we study the effects of the shaping parameter of GGN, hyperparameters of the DL network such as batch size and learning rate on the SER performance.

Reconfigurable Intelligent Surface-Aided Orthogonal Time Frequency Space and Its Deep Learning-Based Signal Detection

Orthogonal time frequency space (OTFS) has emerged as a promising modulation for next-generation wireless systems. This two-dimensional (2D) modulation has the inherent capability of providing uninterrupted connectivity and improved performance in a high-mobility doubly-selective channel by mapping the information symbols to the delay-Doppler (DD) domain. In order to improve the directivity of OTFS signals, this paper considers a reconfigurable intelligent surface (RIS)-aided OTFS transmission for a high-speed environment. While OTFS mitigates the dispersion due to the highly mobile wireless channels by mapping the transmit symbols to the DD domain, RIS improves the directivity by appropriately shifting the phase of the signal in non-line-of-sight (NLOS) communication channels. We provide a concrete matrix-based mathematical model of the RIS-aided OTFS communication system. Capitalizing on the simple matrix multiplication-based model, a number of detectors can be used. These include the usual zero-forcing (ZF) and the minimum mean-squared error (MMSE) linear detectors, and a low-complexity message passing algorithm (MPA)-assisted detector. We evaluate the performance of these detectors for RIS-based OTFS systems. A deep learning (DL)-based signal detector is also proposed for the RIS-aided OTFS system. A significant improvement in bit-error-rate (BER) performance is achieved using the system considered, while the RIS-induced computational burden is not high. Furthermore, in NLOS communication, our system can ensure seamless connectivity with a reduced number of base stations (BS).

Deep Learning-Based Signal Detection for Underwater Acoustic OTFS Communication

Orthogonal time frequency space (OTFS) is a novel two-dimensional (2D) modulation technique that provides reliable communications over time- and frequency-selective channels. In underwater acoustic (UWA) channel, the multi-path delay and Doppler shift are several magnitudes larger than wireless radio communication, which will cause severe time- and frequency-selective fading. The receiver has to recover the distorted OTFS signal with inter-symbol interference (ISI) and inter-carrier interference (ICI). The conventional UWA OTFS receivers perform channel estimation explicitly and equalization to detect transmitted symbols, which requires prior knowledge of the system. This paper proposes a deep learning-based signal detection method for UWA OTFS communication, in which the deep neural network can recover the received symbols after sufficient training. In particular, it cascades a convolutional neural network (CNN) with skip connections (SC) and a bidirectional long short-term memory (BiLSTM) network to perform signal recovery. The proposed method extracts feature information from received OTFS signal sequences and trains the neural network for signal detection. The numerical results demonstrate that the SC-CNN-BiLSTM-based OTFS detection method performs with a lower bit error rate (BER) than the 2D-CNN, FC-DNN, and conventional signal detection methods.

Deep Learning-Based Signal Quality Assessment for Wearable ECGs

Nowadays, use of the dynamic electrocardiogram (ECG) has developed rapidly because of the wide application of wearable devices [1]–[3]. Most ECG-based diagnostic algorithms require that the ECG signal have a clear waveform and accurate feature points. However, the collected wearable ECG signal usually contains a certain amount of noise and causes many false alarms in the ECG analysis system [4], [5]. Thus, signal quality assessment (SQA) plays a prominent role in ruling out the ECG segments with poor signal quality [6]. Compared with traditional static ECG signals, dynamic wearable ECGs contain more noise, which brings greater challenges to disease detection algorithms [7]–[9]. These artifacts and noises in dynamic ECG signals can seriously affect the R-peaks detection, ECG beat extraction, ECG morphological feature extraction and the detection of noise peaks, resulting in frequent false alarms [10]. In 2008, Li et al. [11] proposed the bSQI signal quality indexes: comparison of two beat detectors on a single ECG lead. Liu et al. [12] generalized the two QRS wave complex (QRS) detectors-based bSQI to multiple QRS detectors-based bSQI (GbSQI) to improve the SQA performance. Liu et al. [8] proposed an efficient real-time SQA method for healthy subjects.

A versatile deep-neural-network-based music preprocessing and remixing scheme for cochlear implant listeners

While cochlear implants (CIs) have proven to restore speech perception to a remarkable extent, access to music remains difficult for most CI users. In this work, a methodology for the design of deep learning-based signal preprocessing strategies that simplify music signals and emphasize rhythmic information is proposed. It combines harmonic/percussive source separation and deep neural network (DNN) based source separation in a versatile source mixture model. Two different neural network architectures were assessed with regard to their applicability for this task. The method was evaluated with instrumental measures and in two listening experiments for both network architectures and six mixing presets. Normal-hearing subjects rated the signal quality of the processed signals compared to the original both with and without a vocoder which provides an approximation of the auditory perception in CI listeners. Four combinations of remix models and DNNs have been selected for an evaluation with vocoded signals and were all rated significantly better in comparison to the unprocessed signal. In particular, the two best-performing remix networks are promising candidates for further evaluation in CI listeners.

Distributed Deep Learning-Based Signal Classification for Time-Frequency Synchronization in Wireless Networks

Distributed Deep Learning-Based Signal Classification for Time-Frequency Synchronization in Wireless Networks

Two-Dimensional Convolutional Neural Network-Based Signal Detection for OTFS Systems

Orthogonal time frequency space (OTFS) modulation is a newly proposed modulation technique for providing a solution to high mobility doubly dispersive channel problems. In several recent research works, it is shown that OTFS has better performance over the existing conventional multicarrier modulations. OTFS modulate information symbols in a two-dimensional (2D) delay-Doppler domain rather than in time frequency domain, which can exploit the full channel diversity over time and frequency. This unique ability of OTFS can provide to design an advanced signal detection method. In this letter, we present a deep learning-based signal detection for OTFS systems. Since the input-output relation of OTFS is in 2D delay-Doppler domain, we propose a two-dimensional convolutional neural network (2D-CNN) based detector. We also employ data augmentation technique based on the widely used message-passing (MP) algorithm to improve learning ability of the proposed method. Simulation results show that the proposed method has an improved performance over the MP detector and achieves nearly the same performance as an optimal maximum <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a posteriori</i> (MAP) detector with a very low time complexity.

Deep learning-augmented radioluminescence imaging for radiotherapy dose verification.

We developed a novel dose verification method using a camera-based radioluminescence imaging system (CRIS) combined with a deep learning-based signal processing technique. The CRIS consists of a cylindrical chamber coated with scintillator material on the inner surface of the cylinder, coupled with a hemispherical mirror and a digital camera at the two ends. After training, the deep learning model is used for image-to-dose conversion to provide absolute dose prediction at multiple depths of a specific water phantom from a single CRIS image under the assumption of a good consistency between the TPS setting and actual beam energy. The model was trained using a set of captured radioluminescence images and the corresponding dose maps from the clinical treatment planning system (TPS) for the sake of acceptable data collection. To overcome the latent error and inconsistency that exists between the TPS calculation and the corresponding measurement, the model was trained in an unsupervised manner. Validation experiments were performed on five square fields (ranging from 2 × 2 to 10 × 10cm2 ) and three clinical intensity-modulated radiation therapy (IMRT) cases. The results were compared to the TPS calculations in terms of gamma index at 1.5, 5, and 10cm depths. The mean 2%/2mm gamma pass rates were 100% for square fields and 97.2% (range from 95.5% to 99.5%) for the IMRT fields. Further validations were performed by comparing the CRIS results with measurements on various regular fields. The results show a mean gamma pass rate of 91% (1%/1mm) for cross-profiles and a mean percentage deviation of 1.15% for percentage depth doses (PDDs). The system is capable of converting the irradiated radioluminescence image to corresponding water-based dose maps at multiple depths with a spatial resolution comparable to the TPS calculations.

Deep learning-enabled EPID-based 3D dosimetry for dose verification of step-and-shoot radiotherapy.

The study aims at a novel dosimetry methodology to reconstruct a 3D dose distribution as imparted to a virtual cylindrical phantom using an electronic portal imaging device (EPID). A deep learning-based signal processing strategy, referred to as 3DosiNet, is utilized to learn a mapping from an EPID image to planar dose distributions at given depths. The network was trained with the volumetric dose exported from the clinical treatment planning system (TPS). Given the latent inconsistency between measurements and corresponding TPS calculations, unsupervised learning is formulated in 3DosiNet to capture abstractive image features that are less sensitive to the potential variations. Validation experiments were performed using five regular fields and three clinical intensity-modulated radiation therapy (IMRT) cases. The measured dose profiles and percentage depth dose (PDD) curves were compared with those measured using standard tools in terms of the 1D gamma index. The mean gamma pass rates (2%/2mm) over the regular fields are 100% and 97.3% for the dose profile and PDD measurements, respectively. The measured volumetric dose was compared to the corresponding TPS calculation in terms of the 3D gamma index. The mean 2%/2mm gamma pass rates are 97.9% for square fields and 94.9% for the IMRT fields. The system promises to be a practical 3D dosimetric tool for pre-treatment patient-specific quality assurance and further developed for in-treatment patient dose monitoring.

Deep learning-based signal processing for evaluating energy dispersal in bridge structures

Deep learning-based signal processing for evaluating energy dispersal in bridge structures

A Supplementary Explanation for Experimental Environment of “Implementation Methodologies of Deep Learning-Based Signal Detection for Conventional MIMO Transmitters”

To solve practical challenges for implementing deep learning-based algorithm in MIMO signal detector such as handling complex number or designing proper neural network for a specific communication system, (Baek et al., 2019) has proposed candidate implementation methodologies with simple verification experiments. According to (Baek et al., 2019), it was shown that the proposed algorithms can achieve the optimal ML performance. However, due to the lack of explanation on the experimental environment, it is difficult for readers to reproduce the presented experiments and obtain the same results. This document precisely explains on the experimental environments of (Baek et al., 2019) including the exact channel profiles.