Signal-based Approach Research Articles

Digital Futures: A Signal-Based Approach to Inclusive Digital Youth Work for Socially Vulnerable Youth

This article examines inclusivity in digital youth work initiatives which use and discuss media and technology. The research focusses on initiatives aimed at socially vulnerable youth. Socially vulnerable and digitally excluded youth face educational inequalities due to limited resources, such as inadequate hardware or lack of academic support at home (Correa et al., 2020; Faure et al., 2022; Garmendia & Karrera, 2019). Youth work as non-formal learning plays a crucial role here, possessing certain advantages that formal education does not have—for instance, the freedom to set needs-specific learning goals that are more responsive to societal signals. Through a two-fold comparative case study analysis, we delve deeper into the successful approaches to organising digitally inclusive digital youth work. The case studies (<em>N</em> = 14), located in Flanders, Belgium, were conducted through an in-depth analysis consisting of a QuickScan of practices and in-depth interviews with practice representatives. Our findings identify four success factors for the setup of digitally inclusive practices: (a) providing young people with the means to actively participate during the activity, (b) informing youth workers about digital inclusion factors, (c) providing youth workers with the means to seek help from other actors working on digital inclusion, and (c) including the target group in the creation process of the activity. Based on these four success factors, this study emphasises the importance of a signal-based approach that starts from the needs and talents of youth.

An algorithm for localization of fatigue crack in spinning rotor based on proof by negation

This paper presents an innovative signal-based approach for detection and localization of a fatigue crack induced in spinning rotors. For development of the algorithm and demonstration of the its capabilities, a conventional rotor supported by rigid end bearings has been considered. In this demonstration, a cracked rotor is simulated using finite elements with four degrees of freedom per node. The model accounts for the gyroscopic effects caused by the offset disc and the breathing of the fatigue crack. The gyroscopic effects are accounted for by the introduction of the gyroscopic matrix in the finite element formulation, and the crack breathing effect is considered by introduction of the crack excitation function in the equations of motion The developed algorithm can also be used to simultaneously determine the magnitude and direction of the disc unbalance relative to the crack front. Also, the algorithm is used to validate the crack location hypothesis at a single node by introducing a variable crack location flag vector. The crack location flag vector with the highest crack stiffness value accurately represents the true crack location.

A phase-time-path-difference approach for online wave direction and wave number estimation from measured ship motions in zero and forward speed using a single inertial measurement unit

This study investigates the potential capability of a relatively new and unexplored signal-based approach for shipboard wave estimation. The approach uses the phase-time-path-differences (PTPDs) from an array of shipboard sensors to uniquely resolve the wave propagation direction and wave number. We derive a kinematic PTPD model accounting for forward vessel speed and assess its theoretical foundation to model the sensor delays on a rigid body. The forward-speed PTPD model is structurally equivalent to the zero-speed model considered in previous works, thus retaining the same observability results provided by a noncollinear array of a minimum of three sensors. Moreover, based on the outlined theory and PTPD model, we propose a methodology to estimate the main wave propagation direction and wave number online by employing a fast Fourier transform (FFT), an unscented Kalman filter (UKF), and a rigid-body measurement transformation based on a single inertial measurement unit (IMU). Provided that the vessel in question can be considered a rigid body, a single IMU is sufficient to obtain the desired wave quantities instead of three IMUs, as initially proposed in our previous work. Additionally, our methodology incorporates a novel frequency threshold to avoid distorted wave components caused by the effect of vessel filtering. The performance of our PTPD method is evaluated on data collected from a wave tank and full-scale experiments involving a vessel with zero and non-zero forward speed. The results show very good agreement with the reference wave values reported from a commercial wave radar and wave buoys operating in proximity to the vessel, indicating that our proposed method is competitive with existing wave measurement technology in terms of accuracy and online performance while being cheap, easy to install, flexible, and robust against environmental influences.

A Brain-Myoelectric Signal-Based Approach to Hand Rehabilitation in Stroke

The existing hand function rehabilitation training model for stroke patients has problems such as single mode, low patient participation, poor rehabilitation effect and long rehabilitation period. In this paper, we propose an active stroke hand rehabilitation training method based on brain EMG signals, including the use of EEG signals to help stroke patients achieve brain neural remodelling and EMG signals to achieve real-time hand function rehabilitation training to assist patients to complete hand rehabilitation. Firstly, a multimodal guided motor imagery experimental paradigm with a mixture of pictures and Chinese characters was designed to improve the stability of the spontaneous motor imagery EEG signals. Then, a gesture acquisition paradigm based on surface EMG signals was designed to exercise the flexibility of stroke patients' arm muscles and fingers. The experimental results showed that the stroke hand rehabilitation training method based on brain-myoelectric signals could achieve better rehabilitation results.

Automatic segmentation and fibre orientation estimation from low resolution X-ray computed tomography images of 3D woven composites

In this work, we compare different methods for the automatic segmentation of microtomographic images at the mesoscopic scale of 3D woven carbon fibre composite materials. We use a dense neural network approach fed with features based on the monogenic signal and features learned by a convolutional neural network. To determine local fibre orientations in the composite, we also propose to use the monogenic signal with a structure tensor approach. The performance of the segmentation methods is compared on a first sample for which a reference solution is given. To demonstrate the global capability of the method, the neural networks are then used to segment a second similar sample, for which there is no reference solution. A transfer learning strategy is proposed to take advantage of the knowledge learned on the first sample and to limit the interaction with the user. This simply consists of re-learning only the decision layers, thus limiting the number of examples required. Finally, the best result is obtained with a combination of the signal-based approach and the learning-based approach by merging the monogenic and convolutional neural network features.

Optimal Channels and Features Selection Based ADHD Detection From EEG Signal Using Statistical and Machine Learning Techniques

Attention deficit hyperactivity disorder (ADHD) is one of the major psychiatric and neurodevelopment disorders worldwide. Electroencephalography (EEG) signal-based approach is very important for the early detection and classification of children with ADHD. However, diagnosing children with ADHD using full EEG channels with all features may lead to computational complexity and overfitting problems. To solve these problems, machine learning (ML)-based ADHD detection was designed by identifying optimal channels and its significant features. In this work, support vector machine and t-test based, two separate approaches were devised to select optimal channels individually and then proposed a hybrid channel selection approach by combining these two channel selection methods in order to select the optimal channels. After that, LASSO logistic regression-based model was used to select the important features from the selected channels. Finally, six ML-based classifiers, like Gaussian process classification (GPC), random forest, k-nearest neighbors, multilayer perceptron, decision tree, and logistic regression were applied for the detection of children with ADHD and evaluated their performances using accuracy and area under the curve (AUC). This study utilized a total of one hundred twenty-one children, with sixty-one children with ADHD, aged 7-12 years, and had nineteen channels. Ten different channels were selected by SVM based and an independent t-test-based approach separately and six overlapping channels were identified from both channel selection methods. Then, we selected twenty-eight features from selected six channels using LASSO. Using only six channels and twenty-eight features, GP-based classifier achieved an accuracy rate of 97.53% and AUC of 0.999. This is an improvement of 3% over previously published values in the literature. This study illustrated that LASSO with GP-based system performed outstanding performance in distinguishing children with ADHD from healthy children. This proposed system will be helpful to doctors and physicians in order to detect children with ADHD at an early stage and take the necessary steps for the patients to access appropriate healthcare services, receive effective treatment, and be more conscious of maintaining their lives.

Speech and multilingual natural language framework for speaker change detection and diarization

Speaker Change Detection (SCD) is the problem of splitting an audio-recording by its speaker-turns. Many real-world problems, such as the Speaker Diarization (SD) or automatic speech transcription, are influenced by the quality of the speaker-turns estimation. Previous works have already shown that auxiliary textual information (for mono-lingual systems) can be of great use for detection of speaker-turns and the diarization systems’ performance. In this paper, we suggest a framework for speaker-turn estimation, as well as the determination of clustered speaker identities to the SD system, and examine our approach over a multi-lingual dataset that consists of three mono-lingual datasets—in English, French, and Hebrew. As such, we propose a generic and language-independent framework for the SCD problem that is learned through textual information using state-of-the-art transformer-based techniques and speech-embedding modules. Comprehensive experimental evaluation shows that (i) our multi-lingual SCD framework is competitive enough when compared to a framework over mono-lingual datasets, and that (ii) textual information improves the solution’s quality compared to the speech signal-based approach. In addition, we show that our multi-lingual SCD approach does not harm the performance of SD systems.

Handling Turn Transitions in Australian Tactile Signed Conversations

ABSTRACT This article explores how deafblind Australian Sign Language (Auslan) users, who communicate through an alternative range of modalities including tactile (hands) and kinetic (body movement) inputs, manage turn transitions. Studies of deafblind communication have typically employed a signal-based approach. In contrast, this article applies broader Conversational Analysis (CA) frameworks, which have been developed based on interlocutors who primarily rely on auditory-vocal and visual resources but have been productively applied to a range of languages, participants, and settings. Through fine-grained analyses of a single case study, this article examines how tactile Auslan signers orient to the relevance of turn transitions at possible completion points. The research illuminates the mechanics of how tactile Auslan signers negotiate turns and advances our understanding of both the analytical potentials of CA and the ways particular deafblind Auslan signers coordinate sequences, actions, and multimodalities in their interactional choreography. Data are in tactile Auslan.

Diesel engine diagnosis based on entropy of vibration signals and machine learning techniques

Compression-ignition (CI) engines, aka diesel engines, are responsible for an essential percentage of the world-polluting emissions. Moreover, bearings installed in industrial machinery constitute the most common failure affecting global energy consumption. Since industries’ energy demand has a growing tendency, efficient maintenance is a must. Maintenance requires a fast and accurate diagnosis, commonly based on an intrusive or expensive sensor to capture monitoring signals, i.e. pressure, emissions, temperature, fuel consumption and rotational speed. Here, a vibration signal-based approach is introduced to combustion engines and bearings diagnosis. Namely, a multi-scale permutation entropy (MPE)-based feature extraction is conducted within a variability-based relevance analysis (VRA) stage to feed a straightforward classifier, the K-nearest neighbours (KNN). Accuracy was validated using a signals’ database from a single-cylinder engine under multiple work conditions. Also, the methodology is compared through classification accuracy of a widely known bearing vibration signal database obtaining an outstanding performance.

Diagnosis of Valve Internal Leakage for Ship Piping System using Acoustic Emission Signal-based Machine Learning Approach

Diagnosis of Valve Internal Leakage for Ship Piping System using Acoustic Emission Signal-based Machine Learning Approach

GNSS-IR Inshore Tide Measurement Based on Low-cost Chipset

Multipath signals that impact positioning accuracy are progressively being utilized to recover land and ocean geophysical information with the introduction of Global Navigation Satellite Systems (GNSS). An interference signal-based approach is GNSS-interferometry reflectometry (GNSS-IR). In this work, interference signals are gathered for sea surface altimetry using a low-cost GNSS signal receiver outfitted with a right-handed circularly polarized antenna, which can reduce cost of tide measurement. This study decompose the raw signal-to-noise ratio and extracts several frequency components using an empirical mode decomposition technique. The vertical distance between the antenna phase center and the sea surface is then calculated using Lomb-Scargle periodogram after the spectra of various frequency components has been analyzed. The final inversion tide is then obtained by removing the wild spots using the sinusoidal fitting approach. According to the results, there is a 0.89 correlation between the measured and recovered tides, and the RMSE is 0.23 m.

Signal-based optical map alignment.

In genomics, optical mapping technology provides long-range contiguity information to improve genome sequence assemblies and detect structural variation. Originally a laborious manual process, Bionano Genomics platforms now offer high-throughput, automated optical mapping based on chips packed with nanochannels through which unwound DNA is guided and the fluorescent DNA backbone and specific restriction sites are recorded. Although the raw image data obtained is of high quality, the processing and assembly software accompanying the platforms is closed source and does not seem to make full use of data, labeling approximately half of the measured signals as unusable. Here we introduce two new software tools, independent of Bionano Genomics software, to extract and process molecules from raw images (OptiScan) and to perform molecule-to-molecule and molecule-to-reference alignments using a novel signal-based approach (OptiMap). We demonstrate that the molecules detected by OptiScan can yield better assemblies, and that the approach taken by OptiMap results in higher use of molecules from the raw data. These tools lay the foundation for a suite of open-source methods to process and analyze high-throughput optical mapping data. The Python implementations of the OptiTools are publicly available through http://www.bif.wur.nl/.

An encoder signal-based approach for low-speed planetary gearbox fault diagnosis

Low-speed rotating machines are extensively used in heavy industry. Among those, the planetary gearbox is a pivotal component with a high power–weight ratio and large loadbearing capacity, which inevitably fail due to the tough working conditions. The fault signature in such conditions is rather weak due to the complex planetary structure and the low rotating speed. Hence, the diagnosis of planetary gearbox problems in low-speed working conditions is considered as a bottleneck issue. In view of this, a rotary encoder signal, instead of conventional vibration, is initially applied to capture the fault-related information from the low-speed planetary gearbox. Then, a periodic group sparse-robust principal component analysis (PGS-RPCA) model with adaptive parameter programming, called adaptive PGS-RPCA (APGS-RPCA) is presented to extract the weak fault transient immersed in harmonic interferences and heavy noise. Finally, the effectiveness of the presented APGS-RPCA approach is verified via an experimental encoder signal at a very low input frequency. The diagnostic results show that the presented approach is superior to the conventional approach, and it may provide a promising solution for health monitoring of low-speed rotating machinery.

Fault diagnosis of the 10MW Floating Offshore Wind Turbine Benchmark: A mixed model and signal-based approach

Floating Offshore Wind Turbines (FOWTs) operate in the harsh marine environment with limited accessibility and maintainability. Not only failures are more likely to occur than in land-based turbines, but also corrective maintenance is more expensive. In the present study, a mixed model and signal-based Fault Diagnosis (FD) architecture is developed to detect and isolate critical faults in FOWTs. More specifically, a model-based scheme is developed to detect and isolate the faults associated with the turbine system. It is based on a fault detection and approximation estimator and fault isolation estimators, with time-varying adaptive thresholds to guarantee against false-alarms. In addition, a signal-based scheme is established, within the proposed architecture, for detecting and isolating two representative mooring lines faults. For the purpose of verification, a 10 MW FOWT benchmark is developed and its operating conditions, which contains predefined faults, are simulated by extending the high-fidelity simulator. Based on it, the effectiveness of the proposed architecture is illustrated. In addition, the advantages and limitations are discussed by comparing its fault detection to the results delivered by other approaches. Results show that the proposed architecture has the best performance in detecting and isolating the critical faults in FOWTs under diverse operating conditions.

Open circuit fault detection and FTC for sensorless PMS motor control based on the back-EMF SMO

ABSTRACT The detection of the electrical fault in speed controller under a Motor Control Unit System (MCUS) has been amply viewed in the research paper. Nevertheless, the research work in this domain have been constantly followed on sensor-based vector control of synchronous motor. This paper combines the Power Inverter Voltage (PIV) faults detection (signal-based approach) with sliding mode technique (model-based) to provide Fault Tolerant Control (FTC) for sensorless speed Permanent Magnet Synchronous (PMS) motor drive. Back-EMF sliding mode observer (Back-EMF-SMO) is used for rotor position and stator currents estimation and simultaneously MCUS fault diagnosis. The fault diagnosis for MCUS faults of PMS motor drives using a Hilbert Transform. The motor phase currents signals shapes for various modes of MCUS faults are examined. A PIV Faults Detection and Isolation (FDI) algorithm is used to allow the switchover to a redundant leg. The obtained findings exhibit the effectiveness of the suggested FDI process particularly to detect and to isolate a PIV faults for sensorless PMS motor drives.

Interfacing With Alpha Motor Neurons in Spinal Cord Injury Patients Receiving Trans-spinal Electrical Stimulation.

Trans-spinal direct current stimulation (tsDCS) provides a non-invasive, clinically viable approach to potentially restore physiological neuromuscular function after neurological impairment, e.g., spinal cord injury (SCI). Use of tsDCS has been hampered by the inability of delivering stimulation patterns based on the activity of neural targets responsible to motor function, i.e., α-motor neurons (α-MNs). State of the art modeling and experimental techniques do not provide information about how individual α-MNs respond to electrical fields. This is a major element hindering the development of neuro-modulative technologies highly tailored to an individual patient. For the first time, we propose the use of a signal-based approach to infer tsDCS effects on large α-MNs pools in four incomplete SCI individuals. We employ leg muscles spatial sampling and deconvolution of high-density fiber electrical activity to decode accurate α-MNs discharges across multiple lumbosacral segments during isometric plantar flexion sub-maximal contractions. This is done before, immediately after and 30 min after sub-threshold cathodal stimulation. We deliver sham tsDCS as a control measure. First, we propose a new algorithm for removing compromised information from decomposed α-MNs spike trains, thereby enabling robust decomposition and frequency-domain analysis. Second, we propose the analysis of α-MNs spike trains coherence (i.e., frequency-domain) as an indicator of spinal response to tsDCS. Results showed that α-MNs spike trains coherence analysis sensibly varied across stimulation phases. Coherence analyses results suggested that the common synaptic input to α-MNs pools decreased immediately after cathodal tsDCS with a persistent effect after 30 min. Our proposed non-invasive decoding of individual α-MNs behavior may open up new avenues for the design of real-time closed-loop control applications including both transcutaneous and epidural spinal electrical stimulation where stimulation parameters are adjusted on-the-fly.

A Review on Time Series Motif Discovery Techniques an Application to ECG Signal Classification

Cardiovascular disease diagnosis from an ECG signal plays an important and significant role in the health care system. Recently, numerous researchers have developed an automatic time series-based multi-step diagnosis system for the fast and accurate diagnosis of ECG abnormalities. The multi-step procedure involves ECG signal acquisition, signal pre-processing, feature extraction, and classification. Among which, the feature extraction plays a vital role in the field of accurate diagnosis. The features may be different types such as statistical, morphological, wavelet or any other signal-based approach. This article discusses various time series motif-based feature extraction techniques with respect to a different dimension of ECG signal.

Mixed model‐based and signal‐based approach for open‐switches fault diagnostic in sensorless speed vector controlled induction motor drive using sliding mode observer

This study deals with a mixed model-based and signal-based approach for sensorless speed-controlled induction motor drive (IM) and insulated-gate bipolar transistors open-switch fault diagnosis. In comparison to the classical sensored drive systems, this structure presents particular characteristics in post-fault operation mode which can be taken into account for fault detection and identification process designing. Firstly, the fault effects analysis is achieved in the abc frame of the IM. Based on such analysis, a diagnostic algorithm, using the measured and estimated currents, is used to define the fault indices, which allow the detection of single open-switch, multiple open-switch and open-phase faults. The sensorless control algorithm used for rotor speed estimation, as well as the fault diagnostic algorithm, are all based on a first-order sliding mode observer. In addition to the simplicity and the fast fault detection, there are no-additional sensors or extra-hardware used by the proposed method. Experimental results, based on a dSPACE DS1104 controller board and a 3-kW induction machine, are shown to validate the proposed strategy.

Fault Diagnosis and Fault Tolerant Control of a Three-Phase VSI Supplying Sensorless Speed Controlled Induction Motor Drive

Fault diagnosis in variable speed drives under inverter faults has been widely addressed in the literature. However, research activities in this field have been always focused only on sensored motor drives. This paper deals with a mixed model-based and signal-based approach for both insulated-gate bipolar transistor (IGBT) open-circuit fault diagnosis and fault tolerant control in sensorless speed-controlled induction motor (IM) drive. Sliding mode observer (SMO) is used for speed and stator currents estimation and simultaneously open-switch fault diagnosis. Unlike the classical sensored drive systems, this structure presents particular dynamics under faulty operation-mode which can be taken into account for fault detection and identification (FDI) process designing. The proposed diagnostic algorithm is based on similarity test between measured and estimated currents to define the FDI index in the inverter. The proposed method allows detection and localization of single and multiple IGBT open-switch faults. To improve the reliability of the motor drive, the ability of the SMO to reconstitute the motor state estimation after the disturbance stage of the FTC application is verified. The proposed FDI and FTC schemes are implemented on a dSPACE DS1104 controller board for a 3-kW IM drive system. Several experiments are displayed to show the effectiveness and feasibility of the proposed method.

THE DICHOTOMY BETWEEN SIGNAL AND CONTENT AS BASIS OF BROADCAST COPYRIGHT: A KENYAN AND SOUTH AFRICAN PERSPECTIVE

The concept of broadcast copyright is one of the most controversial and non-felicitous subjects, both at national and transnational levels. Most municipal copyright laws and relevant international instruments merely provide that broadcasting organizations shall enjoy protection over their broadcasts and programme-carrying signals. Some of those international instruments include The Rome Convention for the Protection of Performers, Producers of Phonograms and Broadcasting Organizations of 1961 (hereinafter “the Rome Convention”). Article 13 thereof grants specific exclusive rights against certain activities in relation to the broadcasts of broadcasting organizations. Additionally, Article 1 of the Rome Convention guarantees that its exercise and implementation shall leave intact and in no way affect the protection of copyright in literary and artistic works. The Agreement on Trade-Related Aspects of Intellectual Property Rights (hereinafter “the TRIPs Agreement”) of 1994 follows the model of the Rome Convention, and under Article 14 (3) grants broadcasting organizations the same neighbouring rights as the latter does. In both instruments, the object of protection in a broadcast or broadcasts was never defined. The Convention Relating to the Distribution of Programme-Carrying Signals Transmitted by Satellite (hereinafter “the Satellite Convention”) of 1974 does not grant broadcasting organizations any specific right but obliges Contracting Parties to prevent unauthorized distribution on or from their territories of any programme-carrying signal by any distributor for whom the signal emitted to or passing through the satellite is not intended. The protection conferred upon the broadcasting organizations under the above international instruments are replicated in the copyright laws of Kenya and South Africa without clarifying upon the property and the scope of protection of a broadcast. The failure to specifically define the subject matter of protection in broadcast copyright as well as its outer boundaries forms the genesis of the current controversy. Amid this controversy, this article examines two emerging global approaches around which broadcast copyright revolves, namely the content or rights-based approach, and the signal-based approach. Drawing from the two approaches, the article examines the extent to which they apply to Kenya and South Africa.