El Gharbi, MariamFernandez-Garcia, RaulGil, Ignacio
9页
查看更多>>摘要：In this paper we present the design and the validation of a novel fully embroidered meander dipole antenna based sensor integrated into a commercially available T-shirt for real-time breathing monitoring using the technique based on chest well movement analysis. The embroidered antenna-based sensor is made of a silver coated nylon thread. The proposed antenna-sensor is integrated into a cotton T-shirt and placed on the middle of the human chest. The breathing antenna-based sensor was designed to operate at 2.4 GHz. The sensing mechanism of the system is based on the resonant frequency shift of the meander dipole antenna-sensor induced by the chest expansion and the displacement of the air volume in the lungs during breathing. The resonant frequency shift was continuously measured using a Vector Network Analyzer (VNA) to a remote PC via LAN interface in real-time. A program was developed via Matlab to collect respiration data information using a PC host via LAN interface to be able to transfer data with instrumentation over TCP/IP. The measurements were carried out to monitor the breathing of a female volunteer for various positions (standing and sitting) with different breathing patterns: eupnea (normal respiration), apnea (absence of breathing), hypopnea (shallow breathing) and hyperpnea (deep breathing). The measured resonance frequency shift to 2.98 GHz, 3.2 GHz and 2 GHz for standing position and 2.84 GHz, 2.95 GHz and 2.15 GHz for sitting position, for eupnea, hyperpnea and hypopnea, respectively. The area of the textile sensor is 45 x 4.87 mm2, reducing the surface consumption significatively with regard to other reported breath wearable sensors for health monitoring.
查看更多>>摘要：In this work, we have proposed the first WiFi-based attention model for intrinsic human activity information measuring. First, both convolutional layers and time-recurrent layers are integrated in a one-off manner for joint feature learning. Based on this, a temporal attention module is introduced to capture activity moments and reduce lengthy data collections. In addition, a channel-spatial attention module is further designed to retrieve the activity feature of interest, without requiring any additional supervision. Extensive experiments were conducted for performance comparison under diverse environmental settings. The results showed that our model can achieve the best overall accuracy of 94.62%, 94.36% and 91.04% in three datasets with minimal manual efforts involved, and consistently outperforms other baselines under diverse parameter settings.
Kamruzzaman, M. M.Alanazi, SaadAlruwaili, MadallahAlrashdi, Ibrahim...
13页
查看更多>>摘要：Health care monitoring systems have mainly depended on the internet of things (IoT) devices to collect, manage and analyze data from patients. Patients' health can be constantly monitored and controlled with the remote health monitoring systems. From these points, a Fuzzy-assisted machine learning framework (F-AMLF) with fog computing increases the effectiveness of the health care monitoring system. This paper presents an F-AMLF to recognize how device resource cost reduction is achieved while maintaining efficiency limitations. Patients can submit their demands for health care by a fuzzy assisted fog computing system. These systems use fuzzy logic to calculate how much computing capacity is needed to maintain fog and cloud projections. The F-AMLF shows the highest accuracy ratio of 93.6%, monitoring ratio of 92.5%, prediction ratio of 95.3%, data management ratio of 91.4%, and the lowest latency ratio of 19.7%, energy consumption ratio of 20.1%, and the cost-effective ratio of 21.5% compared to the existing methods.
查看更多>>摘要：Surface defects in the bolts can affect the assembly speed of the assembly line, which in turn affects the work of the entire assembly line. At the same time, defects in bolts may also affect the quality of the product. At present, it is difficult for bolt surface defect detection to meet the requirements of fast detection, high recognition rate, and online detection at the same time. This paper studies a defect detection algorithm designed based on an improved template matching algorithm. It solves the problem of difficult template matching for bolted images during online inspection, and has a significant speedup compared to the original template matching algorithm. The final experimental results show that the method can meet the requirements of online, high speed and high accuracy to some extent.
查看更多>>摘要：In emergent nanotechnology areas like Micro Electro-Mechanical Systems (MEMS) the components capacity to dissipate strain energy is a key factor to evaluate their potential lifespan. In this context, we present the direct derivation of an analytical expression to estimate the elastic-plastic solids energy dissipation capacity from Depth Sensing Indentation (DSI) data. An expression to the fast calculation of the elastic (U-e)-to-total (U-t) strain energy ratios (U-e/U-t) from loading and unloading curves was particularly proposed. Assuming reasonable power law behaviors for these curves this expression allows calculating the strain energy ratios only considering the maximum displacement (h(m)) and plastic hysteresis (h(p)), which are experimentally easy to estimate. The simplifications and assumptions taken in this work ensure, in the worst of the cases, U-e/U(t )ratios with uncertainties about 8 %. Despite this, the results could represent an interesting improvement in the time spending-to-accuracy relation for estimating these ratios.
查看更多>>摘要：Under complicated fatigue loading conditions, cracks initiate and grow in the arbitrary direction from corrosion pits in the aerospace equipment. The monitoring of crack propagation angle is very important for the safety assessment of the aerospace equipment, which is still a challenge by the conventional structural health monitoring (SHM) method. In this paper, a novel crack angle quantitative monitoring method is presented based on the rotating alternating current field measurement (RACFM). A theoretical model of the crack angle measuring method is established to analyze the perturbation principle of the induced electromagnetic field. The relationships between the angle, length and depth of the crack and the Bz signal are analyzed. The probe and testing system are established, and experiments are carried out. The results show that the phase of the Bz signal has a linear relationship with the crack angle for the same crack, and the amplitude of the Bz signal can correct the crack angle for the different cracks. The angle of fatigue cracks can be quantitatively measured by the Bz phase difference method based on the RACFM.
查看更多>>摘要：Online automatic monitoring of abnormal vibrations, such as vortex-induced vibration (VIV) and high amplitude vibration (HAV), of stay-cables is important for bridge maintenance. However, the existing methods either require manual intervention or yield unreasonable identification results and are not suitable for online automatic monitoring. This study proposes a fully automatic method to identify the abnormal vibrations of stay-cables based on acceleration data. Two quantified feature indices are extracted from frequency domain and complex domain to characterize the VIV. A feature vector is established to distinguish the VIV from ambient vibration, and Minimum Euclidean Distance Classifier is utilized to automate the online identification process. The HAV is automatically identified based on root mean square of acceleration. The proposed method avoids any manual intervention and can yield correct and convincible identification results. Case study of a cable-stayed bridge finally validates the feasibility and novelty of the proposed method.
查看更多>>摘要：In the design of underground spaces, the value of the effective stress (chi) parameter is important while dealing with unsaturated soils. The estimating procedure might be complex due to the non-linearity of the connection between chi parameter and dependant parameters. As a result, two novel hybrid optimization models are proposed in this paper: relevance vector regression (RVR) optimized using artificial bee colony (ABC) and harmony search (HS) algorithms (RVR-ABC and RVR-HS models). The RVR-HS and RVR-ABC models' prediction abilities were demonstrated using 120 datasets from open-source literatures. In this dataset, characteristics of unsaturated soils such as bubbling pressure, soil-water characteristic curve fitting parameter, saturated volumetric water content, net conning pressure, residual water content, and suction were used as the inputs, while chi parameter was used as the output. The proposed models performances were assessed by comparing them regarding some statistical metrics, e.g., correlation coefficient (R-2). For the RVR-ABC and RVR-HS models, the R2 of 0.86 and 0.89 were attained, respectively. The findings showed that the RVR-ABC and RVR-HS models were effective in predicting the chi parameter. However, the RVR-HS model, outperformed the RVR-ABC model as this issue shows, the HS algorithm contributed significantly to the optimization of the suggested model.
查看更多>>摘要：Three-dimensional quantitative phase imaging (3D QPI) delivers volumetric information about the refractive index distribution within microobjects. Such imaging and measurement capabilities are of great interest for technical and biomedical applications, yet there are no standardized methods for testing and reporting metrological performance. Proper metrology is crucial for further developments in QPI and for cross-referencing a range of physical properties with other laboratories and techniques. In this paper we present methodology for metrological evaluation of the 3D QPI instruments for single-cell and subcellular structures. The methodology entails suitable phantom, its digital twin, quality assessment metric and easily reproducible protocol that is attainable for both numerical and experimental analysis. We demonstrate its applicability by comparing simulated reconstructions with measurement results from 3 optical diffraction tomography systems. The results will serve as a reference point for past and future research, encourage to benchmark the new systems in a similar manner and further the efforts towards the standardization in 3D QPI metrology.
NSTL
Elsevier