Acquisition Device Research Articles

Portable Structure Surface Crack Detection System Based on Android Platform

Cracks, potholes, and other defects often occur on infrastructure such as bridges, among which cracks are one of the most frequent defects. They have diverse shapes and are difficult to detect. Traditional manual inspection methods are inefficient and have low accuracy, while automated inspection machines are bulky and inconvenient to carry and use. Based on the shortcomings of existing detection technologies, this paper proposes a portable structural surface crack detection system based on the Android platform using a portable handheld image acquisition device. The system captures cracks on the structure's surface and obtains high-definition crack images. Then, these images are transmitted to portable smartphone terminals through Wi-Fi. Next, the image is pre-processed using weighted averaging, grayscale linear transformation, and adaptive median filtering. Then, the improved Canny edge detection algorithm is applied to identify crack information, and the edge segmentation algorithm is used to determine the crack width. Finally, based on camera calibration, the pixels are converted into the length data required for actual measurement. The results show that the system is easy to operate, and it not only has crack storage and tracking functions, but also can effectively measure the crack width on the surface of components. The measurement accuracy of this system reaches the sub-pixel level, and in actual testing, compared with the crack width gauge, the maximum relative error does not exceed 6.25%.

MSLTE: multiple self-supervised learning tasks for enhancing EEG emotion recognition

Objective. The instability of the EEG acquisition devices may lead to information loss in the channels or frequency bands of the collected EEG. This phenomenon may be ignored in available models, which leads to the overfitting and low generalization of the model. Approach. Multiple self-supervised learning tasks are introduced in the proposed model to enhance the generalization of EEG emotion recognition and reduce the overfitting problem to some extent. Firstly, channel masking and frequency masking are introduced to simulate the information loss in certain channels and frequency bands resulting from the instability of EEG, and two self-supervised learning-based feature reconstruction tasks combining masked graph autoencoders (GAE) are constructed to enhance the generalization of the shared encoder. Secondly, to take full advantage of the complementary information contained in these two self-supervised learning tasks to ensure the reliability of feature reconstruction, a weight sharing (WS) mechanism is introduced between the two graph decoders. Thirdly, an adaptive weight multi-task loss (AWML) strategy based on homoscedastic uncertainty is adopted to combine the supervised learning loss and the two self-supervised learning losses to enhance the performance further. Main results. Experimental results on SEED, SEED-V, and DEAP datasets demonstrate that: (i) Generally, the proposed model achieves higher averaged emotion classification accuracy than various baselines included in both subject-dependent and subject-independent scenarios. (ii) Each key module contributes to the performance enhancement of the proposed model. (iii) It achieves higher training efficiency, and significantly lower model size and computational complexity than the state-of-the-art (SOTA) multi-task-based model. (iv) The performances of the proposed model are less influenced by the key parameters. Significance. The introduction of the self-supervised learning task helps to enhance the generalization of the EEG emotion recognition model and eliminate overfitting to some extent, which can be modified to be applied in other EEG-based classification tasks.

Study of the in situ test setup and analysis methods for self-healing properties of metallized film capacitors.

Metallized film capacitors (MFCs) are widely used in the power electronics industry due to their unique self-healing (SH) capability. SH performance is an essential assessment for MFC reliability verification in industrial production. The SH phenomenon of metallized films usually occurs rapidly in a very short period, and its real-time evolution details are often difficult to capture and analyze. In this paper, a test system for the SH performance of metallized films for capacitors was constructed. The system consists of three components: a voltage-current characteristic testing and current pulse capture device, a microscopic image real-time acquisition device, and an integrated analysis processing device. Through the voltage-current characteristic testing and current pulse capture device, the electrical parameters of the SH point, such as SH times, breakdown field strength, SH current, and SH energy, are obtained; through a microscopic image real-time acquisition device, the real-time spatial positioning of the SH point was obtained, and the interconnection between the morphology of the SH point and the electrical properties was established. The relationship between the SH point and the temperature distribution was further established using thermal imaging technology, which lays the foundation for a thorough and timely assessment and analysis of the failure mechanism and the real-time evolution of the metallized film SH process. This significantly improves the effectiveness of SH property research.

Comprehensive beam delivery latency evaluation for gated proton therapy system using customized multi-channel signal acquisition platform.

Beam delivery latency in respiratory-gated particle therapy systems is a crucial issue to dose delivery accuracy. The aim of this study is to develop a multi-channel signal acquisition platform for investigating gating latencies occurring within RPM respiratory gating system (Varian, USA) and ProBeam proton treatment system (Varian, USA) individually. The multi-channel signal acquisition platform consisted of several electronic components, including a string position sensor for target motion detection, a photodiode for proton beam sensing, an interfacing board for accessing the trigger signal between the respiratory gating system and the proton treatment system, a signal acquisition device for sampling and synchronizing signals from the aforementioned components, and a laptop for controlling the signal acquisition device and data storage. RPM system latencies were determined by comparing the expected gating phases extracted from the motion signal with the trigger signal's state turning points. ProBeam system latencies were assessed by comparing the state turning points of the trigger signal with the beam signal. The total beam delivery latencies were calculated as the sum of delays in the respiratory gating system and the cyclotron proton treatment system. During latency measurements, simulated sinusoidal motion were applied at different amplitudes and periods for complete beam delivery latency evaluation under different breathing patterns. Each breathing pattern was repeated 30 times for statistical analysis. The measured gating ON/OFF latencies in the RPM system were found to be 104.20±13.64ms and 113.60±14.98ms, respectively. The measured gating ON/OFF delays in the ProBeam system were 108.29±0.85ms and 1.20±0.04ms, respectively. The total beam ON/OFF latencies were determined to be 212.50±13.64ms and 114.80±14.98ms. With the developed multi-channel signal acquisition platform, it was able to investigate the gating lags happened in both the respiratory gating system and the proton treatment system. The resolution of the platform is enough to distinguish the delays at the millisecond time level. Both the respiratory gating system and the proton treatment system made contributions to gating latency. Both systems contributed nearly equally to the total beam ON latency, with approximately 100ms. In contrast, the respiratory gating system was the dominant contributor to the total beam OFF latency.

Face anti-spoofing with cross-stage relation enhancement and spoof material perception

Face Anti-Spoofing (FAS) seeks to protect face recognition systems from spoofing attacks, which is applied extensively in scenarios such as access control, electronic payment, and security surveillance systems. Face anti-spoofing requires the integration of local details and global semantic information. Existing CNN-based methods rely on small stride or image patch-based feature extraction structures, which struggle to capture spatial and cross-layer feature correlations effectively. Meanwhile, Transformer-based methods have limitations in extracting discriminative detailed features. To address the aforementioned issues, we introduce a multi-stage CNN-Transformer-based framework, which extracts local features through the convolutional layer and long-distance feature relationships via self-attention. Based on this, we proposed a cross-attention multi-stage feature fusion, employing semantically high-stage features to query task-relevant features in low-stage features for further cross-stage feature fusion. To enhance the discrimination of local features for subtle differences, we design pixel-wise material classification supervision and add a auxiliary branch in the intermediate layers of the model. Moreover, to address the limitations of a single acquisition environment and scarcity of acquisition devices in the existing Near-Infrared dataset, we create a large-scale Near-Infrared Face Anti-Spoofing dataset with 380k pictures of 1040 identities. The proposed method could achieve the state-of-the-art in OULU-NPU and our proposed Near-Infrared dataset at just 1.3GFlops and 3.2M parameter numbers, which demonstrate the effective of the proposed method.

Real-time straw moisture content detection system for mobile straw granulator

In order to improve the molding rate of biomass particles extruded by ring mold of the mobile straw granulator, a real-time straw moisture content detection system based on frequency was designed in this paper. The detection system comprised the frequency based acquisition devices and the supporting circuits, and support vector regression (SVR) based calculation method. The acquisition device contained a soil separation cylinder and a signal detection chamfer. The soil separation cylinder was used to remove the soil from the straw. The moisture of the straw was transformed into the relatively stable frequency for detection, but the temperature can affect the Brownian movement of free water. Hence, the designed signal detection chamfer mainly contained a frequency sensor and a temperature sensor. The proposed calculation method blended the frequency and temperature to acquire the accurate moisture of the straw. A water replenishment module was also designed to verify the effectiveness of the detection system, and it was used to supply water to the straw when it becomes too dry. The system was verified in the experimental plots and field. The actual moisture content was obtained by 105℃ drying method. The results obtained in the experiment plots showed that the detectable moisture content range was between 9.09% to 46.68%, the maximum detection error was less than 0.44%, and the average absolute error was less than 0.33%, and the molding rate could reach approximately 94%. The results obtained in the fieldd showed that the average molding rate achieved was 93.57% and 89.76% for straws with moisture content of about 20% and 15%, respectively. The detection system comprehensively takes into account the influence of temperature and soil on moisture content and can effectively improve the working efficiency of the mobile straw granulator.

Study on visual localization and evaluation of automatic freshwater fish cutting system based on deep learning framework

ABSTRACT Pre-treatment processing technology plays a crucial role in the overall freshwater fish processing procedure, and automatic head and tail cutting stands out as a significant pre-treatment technique within the industry. The system for removing the head and tail of freshwater fish comprised a Cartesian coordinate manipulator, a fish transfer device, a control system, and an image acquisition device. In the vision system, five image segmentation methods were utilized for fish head and tail image segmentation comparison tests. These methods include U-Net (U-shaped Deep Neural Network), DeeplabV3, PSPNet (Pyramid Scene Parsing Network), FastSCNN (Fast Semantic Segmentation Network), and ICNet (Image Cascade Network), all of which were employed to evaluate their performance. Among the tested segmentation methods, the ICNet demonstrated the most excellent segmentation capability. The experimental results indicated a segmentation accuracy of 99.01%, a mean intersection over union (MIoU) of 82.50%, and an image processing time of 15.25 ms. The results showed that the fish head and tail were successfully cut off using this model for recognition with a circular knife. Consequently, the segmentation model employed in the machine vision system within this study has demonstrated successful applicability in automatically cutting the heads and tails of freshwater fish of various sizes.

Design and Development of an Android-based Remote Cardiac Monitoring Device for Continuous Real-time ECG Signal Acquisition, Transmission, and Analysis

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, necessitating innovative solutions for early detection and continuous monitoring. This research aims to develop an Android-based remote cardiac monitoring device for real-time electrocardiogram (ECG) signal acquisition, transmission, and analysis. The system comprises hardware for acquiring ECG signals, algorithms for processing and machine learning models for anomaly classification. The hardware unit captures ECG data using electrodes and sensors. The signals are filtered, processed, and transmitted to the cloud infrastructure enabling real-time monitoring and analysis. Machine learning models including support vector machines, ensemble methods and Artificial neural networks are trained on ECG datasets to classify signals and detect cardiac abnormalities. Comprehensive testing validates the system's capabilities in real-time signal acquisition, processing, anomaly detection and data transmission. The integration of hardware, algorithms and machine learning enables round-the-clock monitoring of cardiac activity, facilitating prompt interventions and improved patient outcomes. This affordable and user-friendly system demonstrates potential for enhanced accessibility and effectiveness of preventive cardiac care.

A coloured Petri nets-based system for validation of biomedical signal acquisition devices

A coloured Petri nets-based system for validation of biomedical signal acquisition devices

Multi-scale characterization of fatigue crack tip deformation and propagation in QP steel

A novel measurement method for multi-scale characterization of fatigue crack tip deformation and propagation behaviors in high strength and plasticity, multi-phase, fine-grain Quenching and Partitioning (QP) steel was proposed. The fatigue crack propagation (FCP) test system with the macro/micro images acquisition devices was built to measure the FCP rate and crack tip deformation simultaneously. First, at the mesoscale, the evolution characteristics of the crack tip deformation fields, plasticity induced crack closure (PICC) behaviors and plastic zone during the FCP process were analyzed using the sub-image stitching and matching digital image correlation (DIC) method. Then, the FCP models were established with special emphasis on the model considering the PICC effect based on the obtained crack opening load at the mesoscale. Moreover, the corresponding microscale surface crack and fracture morphologies, microstructure phase transformation and deformations were observed and analyzed by electron backscatter diffraction (EBSD) and scanning electron microscope (SEM) techniques.

Six methods to determine expiratory time constants in mechanically ventilated patients: a prospective observational physiology study

BackgroundExpiratory time constant (τ) objectively assesses the speed of exhalation and can guide adjustments of the respiratory rate and the I:E ratio with the goal of achieving complete exhalation. Multiple methods of obtaining τ are available, but they have not been compared. The purpose of this study was to compare six different methods to obtain τ and to test if the exponentially decaying flow corresponds to the measured time constants.MethodsIn this prospective study, pressure, flow, and volume waveforms of 30 postoperative patients undergoing volume (VCV) and pressure-controlled ventilation (PCV) were obtained using a data acquisition device and analyzed. τ was measured as the first 63% of the exhaled tidal volume (VT) and compared to the calculated τ as the product of expiratory resistance (RE) and respiratory system compliance (CRS), or τ derived from passive flow/volume waveforms using previously published equations as proposed by Aerts, Brunner, Guttmann, and Lourens. We tested if the duration of exponentially decaying flow during exhalation corresponded to the duration of the predicted second and third τ, based on multiples of the first measured τ.ResultsMean (95% CI) measured τ was 0.59 (0.57–0.62) s and 0.60 (0.58–0.63) s for PCV and VCV (p = 0.45), respectively. Aerts method showed the shortest values of all methods for both modes: 0.57 (0.54–0.59) s for PCV and 0.58 (0.55–0.61) s for VCV. Calculated (CRS * RE) and Brunner’s τ were identical with mean τ of 0.64 (0.61–0.67) s for PCV and 0.66 (0.63–069) s for VCV. Mean Guttmann’s τ was 0.64 (0.61–0.68) in PCV and 0.65 (0.62–0.69) in VCV. Comparison of each τ method between PCV and VCV was not significant. Predicted time to exhale 95% of the VT (i.e., 3*τ) was 1.77 (1.70–1.84) s for PCV and 1.80 (1.73–1.88) s for VCV, which was significantly longer than measured values: 1.27 (1.22–1.32) for PCV and 1.30 (1.25–1.35) s for VCV (p < 0.0001). The first, the second and the third measured τ were progressively shorter: 0.6, 0.4 and 0.3 s, in both ventilation modes (p < 0.0001).ConclusionAll six methods to determine τ show similar values and are feasible in postoperative mechanically ventilated patients in both PCV and VCV modes.

Contactless Blood Oxygen Saturation Estimation from Facial Videos Using Deep Learning.

Blood oxygen saturation (SpO2) is an essential physiological parameter for evaluating a person's health. While conventional SpO2 measurement devices like pulse oximeters require skin contact, advanced computer vision technology can enable remote SpO2 monitoring through a regular camera without skin contact. In this paper, we propose novel deep learning models to measure SpO2 remotely from facial videos and evaluate them using a public benchmark database, VIPL-HR. We utilize a spatial-temporal representation to encode SpO2 information recorded by conventional RGB cameras and directly pass it into selected convolutional neural networks to predict SpO2. The best deep learning model achieves 1.274% in mean absolute error and 1.71% in root mean squared error, which exceed the international standard of 4% for an approved pulse oximeter. Our results significantly outperform the conventional analytical Ratio of Ratios model for contactless SpO2 measurement. Results of sensitivity analyses of the influence of spatial-temporal representation color spaces, subject scenarios, acquisition devices, and SpO2 ranges on the model performance are reported with explainability analyses to provide more insights for this emerging research field.

Flood Forecasting Method and Application Based on Informer Model

Flood Forecasting Method and Application Based on Informer Model

An Intelligent Health Surveillance System: Predictive Modeling of Cardiovascular Parameters through Machine Learning Algorithms Using LoRa Communication and Internet of Medical Things (IoMT)

In several nations, the majority of heart attacks lead to fatality prior to patients receiving any kind of medical intervention. The traditional healthcare system is mostly passive, requiring patients to initiate contact with healthcare services independently. People often do not request the treatment if they are unconscious during a heart disease episode. The use of Internet of Medical Things (IoMT) methods offers significant advantages in addressing the issue of caring for patients with cardiac problems. These techniques may transform service delivery into ubiquitous and activate healthcare services. Low-cost remote monitoring systems are essential to implementing a widespread healthcare service. In this article, we proposed a cost-effective Personal Health Care Device(PHCD) based on the Internet of Things (IoT). The PHCD transmits user somatic signals to data acquisition devices using a LoRa (Long-range and low-power) wireless communication network. The received data is uploaded to the cloud using IoT platforms like Adafruit IO. Further, various Machine learning (ML) algorithms, Naïve Bayes, ANN, CNN, and LSTM, were applied to collected data to predict heart rate and SpO2 behavior. The performance results of different forecast models were compared to identify precise modeling and reliable forecasts to prevent emergency cardiovascular conditions.

Monitoring of cooling tower water pumps using Arduino data acquisition device

Investing equipment to monitor the condition of assets through vibration can be expensive. Recent development of alternative microcontrollers has enabled researchers to study its potential to replace expensive equipment for monitoring purposes. This study aimed to investigate the potential of alternative microcontrollers to be used as devices to monitor the condition of water pumps. An internet of things (IoT) device was developed that can measure vibration and be applied to monitor water pumps. The vibration data was obtained when the pumps were operated and sent to the condition-based monitoring system (CBMS) database via Wi-Fi network. The vibration data was observed, and current and future condition was identified through vibration analysis.

Spherical image acquisition and defect detection of nuclear fuel based on the line scan

Graphite balls are used as matrix materials of nuclear fuel. To ensure the safe use of nuclear energy, it is necessary to detect the surface defects of graphite balls to screen out the balls that do not meet safety requirements. However, due to the small surface defects and complex background of graphite balls, the detection accuracy based on traditional detection methods is difficult to meet engineering requirements. To solve the above problems, this paper designs an image acquisition device for graphite balls based on line scanning to collect spherical images and designs an improved algorithm based on the U2-Netp network to solve the problem of low accuracy of defect detection. Firstly, the algorithm replaces the up-sampling in the RSU module with cubic linear interpolation to enhance the smoothness of the image. Secondly, spatial channel attention and multi-feature fusion modules are built between the encoder and the decoder to improve the accuracy of the model to obtain interesting information. Finally, the prediction output of Sigmoid and Threshold fusion is designed to solve the problems caused by the gradient disappearance and the uneven polarity of positive and negative samples. Tested on the actual collected data set, the improved U2-Netp algorithm improved the average accuracy of detecting surface defects on graphite balls by 8.1% compared to the original U2-Netp algorithm, reaching 85.3%.

A reliable evaluation approach for multichannel signal denoising algorithms based on a novel arterial pulse acquisition system

BackgroundTactile sensors are utilized to measure multichannel pulse signals in pulse wave analysis (PWA). Owing to noise interferences, researchers have applied various denoising algorithms on multichannel pulse signals. To comprehensively assess these algorithms, numerous evaluation metrics have been proposed. However, these studies did not investigate the noise mechanisms in depth and lacked reference pulse signals, thus making the evaluations insufficiently objective. Materials and methodsAn applicable denoising evaluation approach for multichannel pulse signal algorithms based on an arterial pulse acquisition system is established by superimposing real-world multichannel noise to the reference signals. The system, comprising a SphygmoCor and a uniaxial noise acquisition device, allows us to acquire single-reference pulse signals as well as real-world multichannel noise. ResultsWe assess eight popular denoising algorithms with three evaluation metrics, including amplitude relative error (ARE), mean square error (MSE) and increased percentage signal-noise ratio (SNR%). Our proposed approach provides accurate and objective evaluations of multichannel pulse signal denoising. Notably, classic algorithms for single-channel denoising are not recommended for multichannel denoising. Comparatively, RPCA-based algorithms can denoise pulse signals independently for each channel. ConclusionThis study sets the stage for the establishment of accurate and objective pulse signal denoising evaluations and provides insights for data-driven clinical diagnoses in cardiovascular medicine.

Agent-Guided Non-Local Network for Underwater Image Enhancement and Super-Resolution Using Multi-Color Space

The absorption and scattering of light in water usually result in the degradation of underwater image quality, such as color distortion and low contrast. Additionally, the performance of acquisition devices may limit the spatial resolution of underwater images, resulting in the loss of image details. Efficient modeling of long-range dependency is essential for understanding the global structure and local context of underwater images to enhance and restore details, which is a challenging task. In this paper, we propose an agent-guided non-local attention network using a multi-color space for underwater image enhancement and super-resolution. Specifically, local features with different receptive fields are first extracted simultaneously in the RGB, Lab, and HSI color spaces of underwater images. Then, the designed agent-guided non-local attention module with high expressiveness and lower computational complexity is utilized to model long-range dependency. Subsequently, the results from the multi-color space are adaptively fused with learned weights, and finally, the reconstruction block composed of deconvolution and the designed non-local attention module is used to output enhanced and super-resolution images. Experiments on multiple datasets demonstrated that our method significantly improves the visual perception of degraded underwater images and efficiently reconstructs missing details, and objective evaluations confirmed the superiority of our method over other state-of-the-art methods.

An MRI Compatible Data Acquisition Device for Rat Brain Recording Inside 16.4T Magnet.

Concurrent recording of neural activities and functional magnetic resonance imaging (fMRI) data is useful for studying the neurovascular coupling relationship. This article presents a low-noise, frequency-shaping based neural recorder chip that is insensitive to radio frequency (RF) pulses and gradient echo artifacts under strong magnetic environment. To support simultaneous recording of local field potentials (LFPs), extracellular spikes, and fMRI data, a magnetic resonance imaging (MRI) compatible data acquisition (DAQ) device based on the designed recorder chip is developed with multiple circuit optimization techniques. Bench-top measurement shows that the designed DAQ device has 4.5 μV input-referred noise integrated from 300 Hz to 3000 Hz, which is not greatly affected by electromagnetic interference (EMI) at ultrahigh magnetic field (UMF, 16.4 T). In animal experiments, the designed DAQ device has been demonstrated to be capable of acquiring both the LFPs and extracellular spikes from a rat's brain before, during, and after MRI scanning. Besides, no obvious artifacts are seen from the designed DAQ device at multiple typical MRI scanning modes, and the system recovery time after gradient artifacts is reduced from more than 25 ms to less than 5 ms. The proposed DAQ device architecture based on the frequency-shaping neural recorder chip is MRI compatible and can provide highly competitive performance for concurrent recording of neural activities and fMRI data.

A real-time automatic rail extraction algorithm for low-density mobile laser scanning data

Automatic detection of railroad infrastructure using Mobile Laser Scanning systems is a key technology for both advanced rail driver assistance and intelligent track maintenance. The recent research into railway facility extraction or condition monitoring usually relies on high-density point cloud dataset with known sensor parameters but ignores the processing performance in actual deployment and has high requirements for the acquisition device. To address these limitations, a novel rail extraction algorithm is proposed for processing Mobile Laser Scanning data in real time during acquisition, which could extract rail features by a hierarchical coarse-to-fine method with basic structural parameters. Using the geometric and global statistical characteristics of rail in raw data, a new rail descriptor is defined based on the quantitative statistics of points satisfying height difference in generalized local neighborhood. The approach is evaluated experimentally by a simulated real-time acquisition data and compared with a reference method. The experimental results show that the proposed algorithm has a finer extraction effect and good real-time performance.