Signal Collection Research Articles

1D-CNNs model for classification of sputum deposition degree in mechanical ventilated patients based on airflow signals

Sputum deposition has always been a significant problem in patients with mechanical ventilation. If not handled in time, it can induce bacterial infection and even endanger the life safety of patients. Currently, the evaluation of sputum deposition heavily depends on the medical staff's clinical experience. This paper designs a sputum deposition monitoring system that realizes remote airway pressure and flow signals collection and management for mechanically ventilated patients. Forty-six patients in the intensive care unit were involved in this study. Meanwhile, a one-dimensional convolution neural networks model was proposed to classify four sputum deposition categories (no, slight, moderate, and severe). The experimental results showed that the overall classification accuracy could reach more than 78%. Moreover, the model has been optimized for practical application by setting thresholds for the output of the softmax layer. Finally, the classification accuracy of no sputum, slight, moderate, and severe deposition reaches 85.84%, 84.29%, 93.19%, and 93.38%, respectively. This study's proposed system and method could significantly increase the automation and intelligence of medical care.

Development of a two-beveled-fiber polarized fiber-optic Raman probe coupled with a ball lens for in vivo superficial epithelial Raman measurements in endoscopy.

We report on the development of a two-beveled-fiber polarized (TBFP) fiber-optic Raman probe coupled with a ball lens for in vivo superficial epithelial Raman measurements in endoscopy. The two-beveled fibers positioned symmetrically along a ball lens, in synergy with paired parallel-polarized polarizers integrated between the fibers and the ball lens, maximize the Raman signal excitation and collection from the superficial epithelium where gastrointestinal (GI) precancer arises. Monte Carlo (MC) simulations and two-layer tissue phantom experiments show that the probe developed detects ∼90% of the Raman signal from the superficial epithelium. The suitability of the probe developed for rapid (<3 s) superficial epithelial Raman measurements is demonstrated on fresh swine esophagus, stomach, and colon tissues, followed by their differentiation with high accuracies (92.1% for esophagus [sensitivity: 89.3%, specificity: 93.2%], 94.1% for stomach [sensitivity: 86.2%, specificity: 97.2%], and 94.1% for colon [sensitivity: 93.2%, specificity: 94.7%]). The presented results suggest the great potential of the developed probe for enhancing in vivo superficial epithelial Raman measurements in endoscopy.

A waterproof, environment‐friendly, multifunctional, and stretchable thermoelectric fabric for continuous self‐powered personal health signal collection at high humidity

AbstractThermoelectric sensors have attracted increasing attention in smart wearables due to the recognition of multiple signals in self‐powered mode. However, present thermoelectric devices show disadvantages of low durability, weak wearability, and complex preparation processes and are susceptible to moisture in the microenvironment of the human body, which hinders their further application in wearable electronics. Herein, we prepared a new thermoelectric fabric with thermoplastic polyurethane/carbon nanotubes (TPU/CNTs) by combining vacuum filtration and electrospraying techniques. Electrospraying TPU microsphere coating with good biocompatibility and environmental friendliness made the fabric worn directly and exhibits preferred water resistance, mechanical durability, and stability even after being bent 4000 times, stretched 1000 times, and washed 1000 times. Moreover, this fabric showed a Seebeck coefficient of 49 μV K−1 and strain range of 250% and could collect signals well and avoided interference from moisture. Based on the biocompatibility and safety of the fabric, it can be fabricated into devices and mounted on the human face and elbow for long‐term and continuous collection of data on the body's motion and breathing simultaneously to provide collaborative support information. This thermoelectric fabric‐based sensor will show great potential in advanced smart wearables for health monitoring, motion detection, and human–computer interaction.

Target aided self-assembly of DNA hyperbranched nanostructures for bacterial 16 S ribosomal DNA gene SERS detection

Quantity analysis of bacterial 16 S rDNA gene is still a challenge. Here we successfully achieved bacterial 16 S rDNA gene SERS analysis with target aided self-assembly of DNA hyperbranched nanostructures. Catalytic hairpin assembly (CHA) was first introduced for self-assembly of branched nanostructures, including target bacterial DNA served as trigger probe and three hairpin probes for further target activated cross opening. Rolling cycle amplification (RCA) was then introduced by using a circular DNA as template and single stranded branches of the formed branched nanostructures as primer, forming a concatemer containing multiple copies of tandem repeating segments with same sequences complementary to the circular templates. After that, thousands of Raman-Au nanoprobe would hybridize this long single stranded DNAs for DNA-AuNPs nanoaggretates assembly. By using SERS signal collection, target bacterial DNAs would be successfully analyzed with ultra-sensitivity as low as 15.0 fM. Furthermore, selectivity test for targets with mismatched DNA sequences and other bacterial 16 S rDNA genes show good results. This sensing method was extended to quantify target genes in human plasma samples, showing its excellent applicability in complex samples.

Integrated Flexible Microscale Mechanical Sensors Based on Cascaded Free Spectral Range-Free Cavities.

Photonic mechanical sensors offer several advantages over their electronic counterparts, including immunity to electromagnetic interference, increased sensitivity, and measurement accuracy. Exploring flexible mechanical sensors on deformable substrates provides new opportunities for strain-optical coupling operations. Nevertheless, existing flexible photonics strategies often require cumbersome signal collection and analysis with bulky setups, limiting their portability and affordability. To address these challenges, we propose a waveguide-integrated flexible mechanical sensor based on cascaded photonic crystal microcavities with inherent deformation and biaxial tensile state analysis. Leveraging the advanced multiplexing capability of the sensor, for the first time, we successfully demonstrate 2D shape reconstruction and quasi-distributed strain sensing with 110 μm spatial resolution. Our microscale mechanical sensor also exhibits exceptional sensitivity with a detected force level as low as 13.6 μN in real-time measurements. This sensing platform has potential applications in various fields, including biomedical sensing, surgical catheters, aircraft and spacecraft engineering, and robotic photonic skin development.

ELM-based stroke classification using wavelet and empirical mode decomposition techniques

ABSTRACT Biomedical signal processing is crucial in many sectors that save lives. Artificial intelligence improvement in signal collection and conditioning boosted this application’s adaptability to varied bodily circumstances. In this study, a novel method is put forth for predicting the type of stroke in the human brain based on the observation of the Electroencephalography (EEG) signal. The signal is the first condition for removing undesirable frequencies by passing through a lowpass filter. To accurately extract the signal features, the signal is first transformed into a 1-second frame format and then normalised. Certain statistical and frequency domain aspects are highlighted to increase taxonomic accuracy. Under the wavelet packet transform, the empirical mode decomposition approach is utilised to recover the most information feasible from the signal. After training on extracted characteristics, the extreme learning machine is regarded to conduct classification. These work achieves 94.95 of Sensitivity, 84.95 of Specificity, 93.74 of Precision, 96.96 of Accuracy, 96.12 of F1 Score. Compared to the standard procedures, the proposed techniques have a greater accuracy rate of about 98%.

Research on Mental Workload of Deep-Sea Oceanauts Driving Operation Tasks from EEG Data.

A person's present mental state is closely associated with the frequency and temporal domain features of spontaneous electroencephalogram (EEG) impulses, which directly reflect neurophysiological signals of brain activity. EEG signals are employed in this study to measure the mental workload of drivers while they are operating a vehicle. A technique based on the quantum genetic algorithm (QGA) is suggested for improving the kernel function parameters of the multi-class support vector machine (MSVM). The performance of the algorithm based on the quantum genetic algorithm is found to be superior to that of other ways when other methods and the quantum genetic algorithm are evaluated for the parameter optimization of kernel function via simulation. A multi-classification support vector machine based on the quantum genetic algorithm (QGA-MSVM) is applied to identify the mental workload of oceanauts through the collection and feature extraction of EEG signals during driving simulation operation experiments in a sea basin area, a seamount area, and a hydrothermal area. Even with a limited data set, QGA-MSVM is able to accurately identify the cognitive burden experienced by ocean sailors, with an overall accuracy of 91.8%.

An Innovative Electromechanical Joint Approach for Contact Pair Fault Diagnosis of Oil-Immersed On-Load Tap Changer

This paper presents a novel fault diagnosis method for oil-immersed on-load tap changers (OLTC) to address the issue of limited diagnostic accuracy. The proposed method combines the analysis of mechanical vibration signals and high-frequency current signals from the contact pair, aiming to improve the precision of fault diagnosis. To begin with, an experimental platform was used to simulate the OLTC contact, enabling the collection of mechanical vibration signals and high-frequency current signals under different operational states. These signals underwent wavelet packet transform for denoising, followed by correlation analysis to investigate their interrelationships across various states. Features were then extracted and analyzed using ensemble empirical mode decomposition and the Hilbert–Huang transform. Subsequently, a support vector machine (SVM) was employed to analyze both the mechanical vibration signal and high-frequency current signal, facilitating the classification of the OLTC contact state. The results demonstrated that the joint analysis of electrical and mechanical signals provided a comprehensive representation of the actual contact state under different conditions. The SVM classification achieved an error below 10% in predicting the values of the two signal types, validating the efficiency and feasibility of the proposed fault diagnosis method for OLTC contacts. The findings presented in this paper offer valuable insights for on-site fault diagnosis of practical OLTCs.

Compressed Sensing Techniques Applied to Medical Images Obtained with Magnetic Resonance

The fast and reliable processing of medical images is of paramount importance to adequately generate data to feed machine learning algorithms that can prevent and diagnose health issues. Here, different compressed sensing techniques applied to magnetic resonance imaging are benchmarked as a means to reduce the acquisition time spent in the collection of data and signals that form the image. It is shown that by using these techniques, it is possible to reduce the number of signals needed and, therefore, substantially decrease the time to acquire the measurements. To this end, different algorithms are considered and compared: the iterative re-weighted least squares, the iterative soft thresholding algorithm, the iterative hard thresholding algorithm, the primal dual algorithm and the log barrier algorithm. Such algorithms have been implemented in different analysis programs that have been used to perform the reconstruction of the images, and it was found that the iterative soft thresholding algorithm gives the optimal results. It is found that the images obtained with this algorithm have lower quality than the original ones, but in any case, the quality should be good enough to distinguish each body structure and detect any health problems under an expert evaluation and/or statistical analysis.

Variable density points pressure sensor with wide sensing range and spatial pressure mapping

Wearable flexible pressure sensors are a novel class of human activity detection device. However, the preparation of pressure sensors with high sensitivity and wide sensing range still faces great challenges. This study reveals an flexible heat-resistant variable density point pressure sensing array (PSA) with ultra-wide sensing range based on Ti3C2Tx-MXene. MXene containing polar oxygen-containing functional groups coated polyester fiber fabricated the pressure sensing layer while a stainless steel wire core is used as a flexible electrode for signal collection. The signal processing device rapidly converts the mechanical signal into electrical signal output to increase the transmission speed and range. Experimental results show that the PSA can effectively sense dynamic and static pressures with high sensitivity (0.14–0.87 kPa−1 over a pressure range of 7.2 Pa–2000 kPa), a wide sensing range (0–15000 kPa), fast response time (80 ms), 10,000 cycles (2000 kPa) stability and maintains a 81.25% current response. The noval fully woven structural flexible PSA exhibited larger area, of which the weave density is varied to control resolution and the pressure mapping is referenced to each pixel point to qualitatively and quantitatively analyze shape and pressure distribution. Variable density points pressure sensor with wide sensing range and spatial pressure mappinghas promising applications in healthcare.

Fault Analysis of Worm Gear Box Using Symlets Wavelet

This research highlights the vibration analysis on worm gears at various conditions of oil using the experimental set up. An experimental rig was developed to facilitate the collection of the vibration signals which consisted of a worm gear box coupled to an AC motor. The four faults were induced in the gear box and the vibration data were collected under full, half and quarter oil conditions. An accelerometer was used to collect the signals and for further analysis of the vibration signals, MATLAB software was used to process the data. Symlet wavelet transform was applied to the raw FFT to compare the features of the data. ANN was implemented to classify various faults and the accuracy is 93.3%.

Falling weight deflectometer dispersion curve method for pavement modulus calculation.

The falling weight deflectometer (FWD) test is a common non-destructive testing method for evaluating the structural capacity of pavements. At present, data processing of the FWD test mainly focuses on the deflection data, while paying less attention to the deflection-time history. Because a FWD is equipped with impulse loads and geophones, which allow for the generation and capture of surface wave signal propagation, it is hypothesized that Rayleigh wave dispersion theory can be applied to calculate the modulus profile along the pavement depth by analysing the dispersive properties of the deflection signal measured during FWD tests. To test this hypothesis, we develop a new methodology for the FWD test and data analysis, referred to as the FWD dispersion curve method. We first introduce the concept of the new method, followed by an illustration of the procedure and the experimental set-up. Case studies on three concrete pavement segments are then presented to evaluate the effectiveness of the FWD dispersion curve method. Modifications to the existing FWD device are further recommended for the impact loading sources and signal collection process so that the modulus of a much shallower layer, such as the concrete slab and upper asphalt layers, can be obtained. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

Construction of Magnetic Core-Large Mesoporous Satellite Immunosensor for Long-Lasting Chemiluminescence and Highly Sensitive Tumor Marker Determination.

Chemiluminescence immunoassay exhibits high sensitivity and signal-to-noise ratio, thus attracting great attention in the early diagnosis and dynamic monitoring of diseases. However, the collection of conventional flash-type chemiluminescence signal (<5s) relies heavily on automatic sampling and reading instrument. Herein, a novel core-satellite multifunctional chemiluminescence immunosensor is designed for the efficient enrichment and highly sensitive determination of cancer biomarker carcinoembryonic antigen (CEA) with enhanced and long-lasting output signal that can be conveniently recorded by a simple microplate plate reading instrument. Anti-CEA monoclonal antibody 2 (Ab2) modified Fe3 O4 @SiO2 microspheres (Fe3 O4 @SiO2 -Ab2, 370nm in diameter) are synthesized as the core for selectively capturing and enriching target CEA in solution, and anti-human CEA monoclonal antibody 1 (Ab1) and horseradish peroxidase (HRP) co-immobilized dendritic large-mesoporous silica nanospheres (MSNs-HRP/Ab1, 80nm in diameter, pore size: 17nm) are synthesized as the satellite for efficient immunological recognition and signal amplification. The as-designed core-satellite magnetic chemiluminescence immunosensors exhibit a broad linear range of 0.01-20ngmL-1 and a low detection limit of 3.0pgmL-1 for the convenient, highly specific, and sensitive determination of CEA in human serum. Such core-satellite chemiluminescence immunosensors are expected to act as a powerful tool for in vitro detection of various biomarkers, overcome the defect of conventional chemiluminescence relying heavily on expensive and bulky automatic instruments and popularize chemiluminescence analysis to primary medical institutions and remote areas.

Efficient Graph-based Signal Motif Discovery with Performance Bounds

In this paper, we investigate the problem of signal motif discovery. In the formulation considered, the goal is to find an unknown pattern (or motif) repeated across multiple data sets. This problem formulation can be applied to various domains, such as DNA sequence alignment and matching, motif discovery in time-series, and object detection and localization in images. We take the approach of minimizing an objective that is the sum over a measure of the difference between a candidate instance in each signal collection (or set) and the unknown pattern. Additionally, a non-negative instance dependent penalty is introduced. The proposed general objective can be used to capture well-known problems (e.g., blind joint time-delay estimation). Due to the non-convex nature of the problem and often the integer programming flavor of the approach, brute-force solution is non-polynomial and computationally prohibitive for large scale problems. We propose an efficient polynomial time (quadratic in the number of instances) bipartite graph based approximation to solve the problem. We provide a theoretical analysis for the proposed solution including bounds on the gap from the optimal solution and conditions for optimality. In particular, we show that the objective value for the proposed solution is no more than twice the objective value of the optimal solution. To illustrate the merit of the proposed approach, we present qualitative and quantitative empirical analysis of the proposed approach on several applications and compare our method to appropriate alternatives.

Emotion Recognition for Everyday Life Using Physiological Signals From Wearables: A Systematic Literature Review

Smart wearables, equipped with sensors monitoring physiological parameters, are becoming an integral part of our life. In this work, we investigate the possibility of utilizing such wearables to recognize emotions in the wild. In most reviewed papers, the authors apply a similar procedure consisting of participant recruitment, stimuli preparation and annotation, signal collection and processing, self-assessment, and machine learning model learning and validation. Besides, we identified seven emotion recognition scenarios and analyzed the transition from psychological models to machine learning tasks.

Design and implementation of high sampling rate and multichannel wireless recorder for EEG monitoring and SSVEP response detection.

The collection and process of human brain activity signals play an essential role in developing brain-computer interface (BCI) systems. A portable electroencephalogram (EEG) device has become an important tool for monitoring brain activity and diagnosing mental diseases. However, the miniaturization, portability, and scalability of EEG recorder are the current bottleneck in the research and application of BCI. For scalp EEG and other applications, the current study designs a 32-channel EEG recorder with a sampling rate up to 30 kHz and 16-bit accuracy, which can meet both the demands of scalp and intracranial EEG signal recording. A fully integrated electrophysiology microchip RHS2116 controlled by FPGA is employed to build the EEG recorder, and the design meets the requirements of high sampling rate, high transmission rate and channel extensive. The experimental results show that the developed EEG recorder provides a maximum 30 kHz sampling rate and 58 Mbps wireless transmission rate. The electrophysiological experiments were performed on scalp and intracranial EEG collection. An inflatable helmet with adjustable contact impedance was designed, and the pressurization can improve the SNR by approximately 4 times, the average accuracy of steady-state visual evoked potential (SSVEP) was 93.12%. Animal experiments were also performed on rats, and spike activity was captured successfully. The designed multichannel wireless EEG collection system is simple and comfort, the helmet-EEG recorder can capture the bioelectric signals without noticeable interference, and it has high measurement performance and great potential for practical application in BCI systems.

Rapid cardiac ischemia detection with an epicardial graphene probe.

In this study, a new probe was designed to enable electrocardiography of a rotated heart during cardiac surgery when skin electrodes became non-functional. This probe adhered non-invasively to the epicardium and collected the ECG signal independently from the position of the heart. The study compared the accuracy of cardiac ischemia detection between classic skin and epicardial electrodes in an animal model. Using six pigs, an open chest model was devised with cardiac ischemia induction by coronary artery ligation in two non-physiologic heart positions. Both the accuracy and the time of detection of electrocardiographic symptoms of acute cardiac ischemia were compared between skin and epicardial methods of signal collection. Heart rotation to expose either the anterior or the posterior wall resulted in a distortion or loss of the ECG signal collected by skin electrodes after coronary artery ligation, standard skin ECG monitoring did not reveal any ischemia symptoms. Attachment of an epicardial probe on the anterior and posterior walls helped in the recovery of the normal ECG wave. After ligation of the coronary artery, the epicardial probes recorded cardiac ischemia within 40 s. This study highlighted the effectiveness of ECG monitoring with epicardial probes in a rotated heart. It can be concluded that epicardial probes can detect the presence of acute ischemia of a rotated heart when skin ECG monitoring becomes ineffective.

Localization and imaging of internal hidden defects in concrete slabs based on deep learning of vibration signals

Internal hidden defects such as delamination and voids are common distress of concrete slabs and the localization of these defects is important for structural safety. This paper develops a damage inspection method that is feasible for locating and imaging internal defects of concrete slabs based on deep learning of impact-caused vibration signals. To alleviate the problem of low efficiency of manual signal collection, a prototype of mobile detection system is developed for the automatic generation and acquisition of vibration signals. Two optimized deep learning models in the framework convolutional neural network (CNN) are proposed for 1D time series signal and 2D time-frequency spectrogram to address the problems of low recognition accuracy and long training time of the traditional network, where the principal component analysis (PCA) and squeeze and excitation (SE) modules are incorporated respectively for a better feature learning and extraction of vibration signals of internal defects. The softmax layer is added in the networks to calculate the state probability value for the completion of damage contour maps. The network proposed in this paper is used to systematically compare the training and recognition effects of the data collected by contact senor (accelerometer) and air coupled sensor (microphone). The experiments show that the detection accuracy of the one-dimensional (1D) and two-dimensional (2D) network based on the accelerometer-acquired data reaches 90.4% and 93.4%, respectively. The generalizability of trained models is also validated based on the independent dataset from other research and actual concrete floor of a multistorey building. In the future, the prototype of the hardware system can be further improved by embedding GPS information to realize the real-time automatic localization of hidden defects of engineering structures.

Don't just tell me, show me: Impacting perceptions of organizational attraction and fit using activating LGBT diversity signals

AbstractTo appeal to traditionally hard‐to‐reach populations such as the LGBT community, many organizations have made diversity and inclusion a focal point of their recruitment messaging. However, extant research provides little evidence of the effectiveness of this messaging for its intended and non‐intended targets. Building upon a proposed signaling theory typology, we suggest that activating signals—signals that show how diversity and inclusion are actively embodied or “activated” through organizational practices—are more effective than pointing signals—signals that merely tell an individual that diversity and inclusion is valued. After validating a collection of individual diversity signals using this typology, we test our theory across multiple studies. In Study 1, we focus specifically on LGBT job seekers and conduct an experiment to examine the degree to which various LGBT diversity signals on a fictional company website influence initial assessments of organizational attraction and person‐organization fit. In Study 2, we replicate and extend Study 1 by demonstrating how the positive effects of LGBT diversity signals are similar in a sample of non‐LGBT job seekers. Finally, in Study 3, we extend the generalizability of our theorizing using a sample of recent job seekers and real organizational websites.

Rapid-Scan Resonant Two-Dimensional Impulsive Stimulated Raman Spectroscopy of Excited States.

Photochemical reactions occur in the electronically excited state, which is effectively represented by a multidimensional potential energy surface (PES) with a vast degree of freedom of nuclear coordinates. The elucidation of the intricate shape of the PES constitutes an important topic in the field of photochemistry and has long been studied both experimentally and theoretically. Recently, fully time-domain resonant two-dimensional Raman spectroscopy has emerged as a potentially powerful tool to provide unique information about the coupling between vibrational manifolds in the excited state. However, the wide application of this technique has been significantly hampered by the technical difficulties associated with experimental implementation and remains challenging. Herein, we demonstrate time-domain resonant two-dimensional impulsive stimulated Raman spectroscopy (2D-ISRS) of excited states using sub-10 fs pulses based on the rapid scan of the time delay, which facilitates the efficient collection of time-domain vibrational signals with high sensitivity. As a proof-of-principle experiment, we performed 2D-ISRS of 6,13-bis(triisopropylsilylethynyl)pentacene (TIPS-pentacene) in solution. Through 2D Fourier transformation of the high-quality time-time oscillatory signal, we obtained a 2D frequency-frequency correlation map of excited-state TIPS-pentacene in the broad frequency window of 0-2000 cm-1. The data clearly resolve a number of cross peaks that signify the correlations among excited-state vibrational manifolds. The high capability of the rapid-scan-based 2D-ISRS spectrometer presented in this study enables the systematic investigation of various photochemical reaction systems, thereby further promoting the understanding and applications of this new multidimensional spectroscopy.