Signal Compression Research Articles

Efficient Data Compression of Acoustic Signals in Rail Using Sparse Decomposition and Kurtosis-Guided Resampling

Efficient Data Compression of Acoustic Signals in Rail Using Sparse Decomposition and Kurtosis-Guided Resampling

Television and the Origins of Visual Pattern Recognition AI in Japan: a ‘Quest for a Seeing Machine’

Abstract This article traces the genealogy of contemporary data-driven computer vision to developments at the Japan Broadcasting Corporation (NHK) in the 1960s. Specifically, it examines NHK’s Visual and Auditory Information Science Unit and its role in the invention of the world’s first deep convolutional neural network. The use of television to collect viewer behaviour data enabled modelling of eye-brain information processing, in particular mechanisms of feature extraction. This, in turn, linked Fukushima Kunihiko’s formative work on signal compression to the development of a pattern recognition machine, resulting in the creation of the world’s first convolutional neural network. Recovering this history is important for two reasons. First, it helps counter a trend of ‘digital universalism’ that covertly homogenizes local differences into a single culture of artificial intelligence in the Cold-War-era US. Second, it reveals the largely ignored role of television in the genesis of digital image technologies and AI more broadly.

FlexPoints: Efficient electrocardiogram signal compression for machine learning

The electrocardiogram (ECG) stands out as one of the most frequently used medical tests, playing a crucial role in the accurate diagnosis and treatment of patients. While ECG devices generate a huge amount of data, only a fraction of it holds valuable medical information. To deal with this problem, many compression algorithms and filters have been developed over the years. However, the rapid development of new machine-learning techniques introduces new challenges. To address this class of problems, we have introduced a FlexPoints algorithm. This innovative algorithm searches for characteristic points on the ECG signal and ignores all other points that lack pertinent medical information. The conducted experiments have demonstrated that our proposed algorithm can significantly reduce the number of data points representing ECG signals without losing valuable medical insights. These sparse but essential characteristic points, referred to as flex points, serve as well-fitted input for modern machine learning models. Such models exhibit enhanced performance when using flex points as input, as opposed to raw data or data compressed by other popular algorithms.

A Deep-learning-based Auto Encoder-Decoder Model for Denoising Electrocardiogram Signals

Learning-based denoising techniques have become superior to the traditional assumption-based denoising methods in this modern era. Also, with the advancement of wearable technologies and remote electrocardiogram (ECG) monitoring systems, the requirement for optimal storage has increased due to the limited availability of hardware resources. Therefore, denoising and compression both are essential at the preprocessing stage of the ECG signal. Deep learning-based denoising auto encoder-decoder (DAED) models guarantee cutting-edge performance for these tasks. This article presents a lightweight, adaptive, hybrid Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) based DAED model that achieves a signal compression ratio of 64 with high signal-to-noise ratio improvement for the elimination of ECG noises. The novelty of this work lies in the customization of the CNN layers and utilization of the advantages of the GRU layer in a proper channel for compression and denoising ECG signals. The comparative study with other complex deep learning-based DAED arrangements and state-of-the-art denoising techniques shows the proposed model has simplicity in construction and an improved signal-to-noise ratio with minimum mean square error.

Design of Intelligent Control Under Machine Learning Supervision and Signal Compression Mechanism Design for NCSs Under DoS Attacks

Design of Intelligent Control Under Machine Learning Supervision and Signal Compression Mechanism Design for NCSs Under DoS Attacks

Morse theoretic signal compression and reconstruction on chain complexes

At the intersection of Topological Data Analysis (TDA) and machine learning, the field of cellular signal processing has advanced rapidly in recent years. In this context, each signal on the cells of a complex is processed using the combinatorial Laplacian, and the resultant Hodge decomposition. Meanwhile, discrete Morse theory has been widely used to speed up computations by reducing the size of complexes while preserving their global topological properties. In this paper, we provide an approach to signal compression and reconstruction on chain complexes that leverages the tools of algebraic discrete Morse theory. The main goal is to reduce and reconstruct a based chain complex together with a set of signals on its cells via deformation retracts, preserving as much as possible the global topological structure of both the complex and the signals. We first prove that any deformation retract of real degree-wise finite-dimensional based chain complexes is equivalent to a Morse matching. We will then study how the signal changes under particular types of Morse matchings, showing its reconstruction error is trivial on specific components of the Hodge decomposition. Furthermore, we provide an algorithm to compute Morse matchings with minimal reconstruction error.

Automatic Classification of Anomalous ECG Heartbeats from Samples Acquired by Compressed Sensing.

In this paper, a method for the classification of anomalous heartbeats from compressed ECG signals is proposed. The method operating on signals acquired by compressed sensing is based on a feature extraction stage consisting of the evaluation of the Discrete Cosine Transform (DCT) coefficients of the compressed signal and a classification stage performed by means of a set of k-nearest neighbor ensemble classifiers. The method was preliminarily tested on five classes of anomalous heartbeats, and it achieved a classification accuracy of 99.40%.

Biomedical ECG Signal Compression by Combining Wavelet Transform and Unsupervised Autoencoder Techniques

Abstract: Storing biomedical signal data is a significant concern in the field of biomedical signal processing because it requires a substantial amount of storage space. These biomedical signals often contain hours of information, necessitating extensive storage capacity. Researchers employ Electrocardiogram (ECG) signal compression techniques to address this issue. However, compressing the ECG signal could potentially lead to the loss of important features or data. This loss may adversely impact the accurate analysis of heart patient conditions. This paper introduces a novel approach for compressing ECG signals by the combined power of Wavelet Transform (WT) and unsupervised Autoencoder (AE) techniques. ECG signal compression plays a crucial role in reducing data storage and transmission requirements without compromising diagnostic accuracy. The proposed methodology, termed WT-AutoEncoder, integrates Wavelet Transform for signal decomposition and feature extraction, followed by an Autoencoder for efficient encoding and reconstruction of the original signal. Unlike conventional methods, this approach utilizes the strengths of both WT and AE to achieve high compression ratios while preserving signal accuracy. The study conducts comprehensive experiments and evaluations using benchmark MIT-BIH datasets to assess the performance of the WT-AutoEncoder on specific records (101-109) in terms of compression ratio of 32.31, PRDN of 33.26, PRD of 3.06, and QS of 13.49. The final results demonstrate the effectiveness of the proposed model compared with existing methods in compressing ECG signals while maintaining high accuracy, suggesting its potential for secure transmission and storage in various healthcare applications.

Multilinear compressive learning and reconstruction of hyperspectral data with U-Net architecture for enhanced spectral imaging

Hyperspectral (HSI) data provide vast amounts of data which contain rich spatial and spectral information about each pixel of an image, such information is useful in detecting objects and identifying materials. However, the information provided by the HSI image is challenging to process. Hence, the compression of HSI makes it easier to utilize the data without the need for any heavy computation. Traditional compressive sensing techniques are adequate for lower dimensional signals, but they fail to preserve the essential spectral information provided by HSIs while performing compression. The proposed method aims to implement a Multilinear Compressive Learning (MCL) model for ideal compression of HSIs and a CNN based U-NET architecture is used for effective reconstruction of the compressed signal. The core of the algorithm involves two key blocks: (a) A multidimensional compressive sensing block for performing compression along every dimension, preserving spectral and spatial correlations. The employed sensing matrix is learned with respect to the given data for effective compression, (b) Reconstruction of the signal using a CNN based U-NET algorithm, which consists of encoders and decoders for effective reconstruction of the signal. Band selection is also performed in this technique to optimally select the most informative bands. The proposed model was implemented on the Indian Pines, Pavia University, and Salinas scenes datasets. The compression and reconstruction results were evaluated using performance metrics.

Experimental qualification and modelling of the non-linear response of the DEPFET active pixel sensor for the DSSC camera

A modified Depleted P-Channel Field Effect Transistor (DEPFET) is the key feature of the DEPFET Sensor with Signal Compression (DSSC), a 1 Mpixel X-ray camera aiming at ultra-fast imaging of soft X-rays at the European XFEL. Operation of large-area devices with a large number of DSSC-type DEPFET pixels requires the accurate knowledge of the sensitivity of the response to the relevant DEPFET parameters. The paper presents the experimental qualification of the response of DSSC-type DEPFET pixels in the space of 4 relevant parameters: drain current, source voltage, drain voltage and back side voltage. The obtained results allow estimation of the impact of the inevitable parameter fluctuations in large monolithic sensors and of the actual trimming range of the shape of signal compression in view of the pixelwise calibration of the 1 Mpixel DSSC camera.

Detection of human movement by combining supervised machine learning and an embroidered textile capacitance sensor

This study contributes to respiratory pattern detection by introducing a fabric sensor utilizing capacitance measurement and a semi-supervised machine learning algorithm known as an AI-based autoencoder. The sensor, consisting of two embroidered electrodes composed of silver-coated conductive nylon filaments, leverages the body as a dielectric material. In the research, a garment-type respiratory sensor was employed to continuously monitor respiratory data during both static (standing) and dynamic (walking, brisk walking, running) actions. The sparse autoencoder algorithm was particularly employed for individual static and dynamic actions, effectively distinguishing respiratory patterns corresponding to various movements. In addition, the sparse autoencoder helps prevent overfitting, fundamentally minimizing errors between the compression and reconstruction of signals. The maximum number of epochs was set to 2000, and the target error was set at 0.005. All data were compared against the static walking as the training baseline. Ultimately, the root mean squared error (RMSE) between static postures averaged 0.1, while the RMSEs between dynamic actions of walking, brisk walking, and running were 0.61, 0.91, and 2.78, respectively. These results suggest that movement detection through error detection is practically feasible and possesses discernible capabilities.

Retraction Note: Huffman quantization approach for optimized EEG signal compression with transformation technique

Retraction Note: Huffman quantization approach for optimized EEG signal compression with transformation technique

Analog Front-End for the Readout of LGAD-Based Particle Detectors

This paper presents an analog front-end channel for the readout of Low Gain Avalanche Diodes (LGADs) based particle detectors for the next generation of space-borne experiments. The circuit has been designed in a 65 nm CMOS technology. The charge generated by the detector is integrated by a Charge Sensitive Amplifier (CSA) with dynamic signal compression feature to achieve improved noise performance, along with enhanced time resolution capabilities over the wide range of input charge to be detected (from 45fC to 16pC). An RC-CR shaper with selectable shaping time, a fast discriminator and a Time-to-Amplitude Converter (TAC) complete the readout circuit. An SNR around 300, together with a time resolution of slightly below 60ps, is achieved in post-layout simulations.

Surface Susceptibility Synthesis of Spatially Dispersive Metasurfaces for Space Compression and Spatial Signal Processing

Surface Susceptibility Synthesis of Spatially Dispersive Metasurfaces for Space Compression and Spatial Signal Processing

Mechanical vibration signal compression based on speech codecs for intelligent manufacturing

ABSTRACT How to effectively compress mechanical signals so that they can support remote and real-time health monitoring is a hot issue in the context of intelligent manufacturing. Due to the characteristics of small repeatability, high noise, and high numerical accuracy of vibration signal, traditional compression algorithms cannot well balance the compression ratio, reconstruction quality, compression time indicators. Therefore, this paper presents a novel mechanical vibration signal compression scheme based on speech codecs, which can realize signal compression in many scenarios such as tool wear detection and bearing fault diagnosis. In this work, mechanical vibration signal compression is first transformed into a multi-objective optimization problem, and the feasibility of solving this problem from the perspective of speech coding is deeply analyzed. Further, this paper presents five possible compression methods with different compression ratios. The presented methods are evaluated with real-time data for tool wear detection in stone processing and public datasets for bearing fault diagnosis. The experimental results show that the proposed methods achieve high compression ratios (4.0 ~ 24.6) while ensuring low time overhead (the average time for compressing a sample point is not more than 0.0194 ms) and high reconstruction quality (the MSE index all less than 0.008), outperforming other state-of-the-art methods.

A novel ECG compression algorithm using Pulse-Width Modulation integrated quantization for low-power real-time monitoring

Cardiac monitoring systems in Internet of Things (IoT) healthcare, reliant on limited battery and computational capacity, need efficient local processing and wireless transmission for comprehensive analysis. Due to the power-intensive wireless transmission in IoT devices, ECG signal compression is essential to minimize data transfer. This paper presents a real-time, low-complexity algorithm for compressing electrocardiogram (ECG) signals. The algorithm uses just nine arithmetic operations per ECG sample point, generating a hybrid Pulse Width Modulation (PWM) signal storable in a compact 4-bit resolution format. Despite its simplicity, it performs comparably to existing methods in terms of Percentage Root-Mean-Square Difference (PRD) and space-saving while significantly reducing complexity and maintaining robustness against signal noise. It achieves an average Bit Compression Ratio (BCR) of 4 and space savings of 90.4% for ECG signals in the MIT-BIH database, with a PRD of 0.33% and a Quality Score (QS) of 12. The reconstructed signal shows no adverse effects on QRS complex detection and heart rate variability, preserving both the signal amplitude and periodicity. This efficient method for transferring ECG data from wearable devices enables real-time cardiac activity monitoring with reduced data storage requirements. Its versatility suggests potential broader applications, extending to compression of various signal types beyond ECG.

Debiasing Welch’s method for spectral density estimation

Abstract Welch’s method provides an estimator of the power spectral density that is statistically consistent. This is achieved by averaging over periodograms calculated from overlapping segments of a time series. For a finite-length time series, while the variance of the estimator decreases as the number of segments increases, the magnitude of the estimator’s bias increases: a bias-variance trade-off ensues when setting the segment number. We address this issue by providing a novel method for debiasing Welch’s method that maintains the computational complexity and asymptotic consistency, and leads to improved finite-sample performance. Theoretical results are given for fourth-order stationary processes with finite fourth-order moments and an absolutely convergent fourth-order cumulant function. The significant bias reduction is demonstrated with numerical simulation and an application to real-world data. Our estimator also permits irregular spacing over frequency and we demonstrate how this may be employed for signal compression and further variance reduction. The code accompanying this work is available in R and python.

Superimposed Semantic Communication for IoT-Based Real-Time ECG Monitoring.

Real-time electrocardiogram (ECG) monitoring and diagnosis through Internet of Things (IoT) are crucial for addressing the severity and timely treatment of cardiovascular diseases, enabling timely intervention and preventing life-threatening complications. However, current ECG monitoring research predominantly focuses on individual aspects such as signal compression, diagnostic analysis, or secure transmission, lacking joint optimization of various modules in IoT scenarios. To address this gap, this work proposes a novel framework based on superimposed semantic communication for real-time ECG monitoring in IoT. The framework comprises three hierarchical levels: the edge level for data collection and processing, the relay level for signal compression and coding, and the cloud level for data analysis and reconstruction. The proposed framework offers several unique advantages. By employing semantic encoding guided by ECG classification tasks, it selectively extracts crucial features within and between signals, improving compression ratio and adaptability to channel noise. The superimposed semantic encoding achieves content encryption without requiring any additional operations. Moreover, the framework utilizes lightweight anomaly detection neural networks, reducing edge device power consumption and conserving communication resources. Simulation and real experimental results demonstrate that the proposed method achieves real-time encoding and transmission of ECG signals with a compression ratio of 0.019 on the MIT-BIH dataset. Furthermore, it attains a heartbeat classification accuracy of 0.988 and a reconstruction error of 0.061.

Diagnosing Incipient Faults for a Faster Adoption of Sustainable Aerospace Technologies

Next-generation aircraft require the development and integration of a deal of innovative green technologies to meet the ambitious sustainability goals set for aviation. Those transformational efforts are associated with a tremendous increase in the complexity of the onboard systems and their multiphysics-coupled behaviors and dynamics. A critical aspect relates to the identification of the coupled faults resulting from the integration of those green technologies, which introduce damage identifiability issues and demand new approaches for the efficient and accurate identification of non-nominal fault conditions. Model-based fault detection and identification (FDI) methodologies have been proven essential to identify onboard the damages affecting the systems from physical signal acquisitions, but existing methods are typically computationally expensive and fail to capture incipient coupled faults, which prevents their adoption and scaling with the increasing complexity of novel multiphysics systems. This work introduces a multifidelity framework to accelerate the identification of fault modes affecting complex systems. An original two-stage compression computes an optimally informative and highly reduced representation of the monitoring signals for the minimum demand of onboard resources. A multifidelity scheme for Bayesian inversion is developed to infer multidomain fault parameters from the compressed signals: variable cost and fidelity models are optimally queried for a major reduction of the overall computational expense. The framework is demonstrated and validated for aerospace electromechanical actuators affected by incipient multimodal faults. Remarkable accelerations of the FDI procedure are observed, and the exact identification of the incipient fault condition was achieved one order of magnitude faster than with standard algorithms.

Non-intrusive method for audio quality assessment of lossy-compressed music recordings using convolutional neural networks

Most of the existing algorithms for the objective audio quality assessment are intrusive, as they require access both to an unimpaired reference recording and an evaluated signal. This feature excludes them from many practical applications. In this paper, we introduce a non-intrusive audio quality assessment method. The proposed method is intended to account for audio artefacts arising from the lossy compression of music signals. During its development, 250 high-quality uncompressed music recordings were collated. They were subsequently processed using the selection of five popular audio codecs, resulting in the repository of 13,000 audio excerpts representing various levels of audio quality. The proposed non-intrusive method was trained with the data obtained employing a well-established intrusive model (ViSQOL v3). Next, the performance of the trained model was evaluated utilizing the quality scores obtained in the subjective listening tests undertaken remotely over the Internet. The listening tests were carried out in compliance with the MUSHRA recommendation (ITU-R BS.1534-3). In this study, the following three convolutional neural networks were compared: (1) a model employing 1D convolutional filters, (2) an Inception-based model, and (3) a VGG-based model. The last-mentioned model outperformed the model employing 1D convolutional filters in terms of predicting the scores from the listening tests, reaching a correlation value of 0.893. The performance of the Inceptionbased model was similar to that of the VGG-based model. Moreover, the VGG-based model outperformed the method employing a stacked gated-recurrent-unit-based deep learning framework, recently introduced by Mumtaz et al. (2022).