ABSTRACT
Small-sized, highly sensitive dynamic pressure sensors are crucial in the field of turbomachinery application. In this paper, a fiber-tip structure dynamic pressure sensor utilizing a small piece of glass tube as the air cavity and PDMS material as the diaphragm was fabricated. It has the advantage of being small in size with the diameter of 125 µm while having high sensitivity of 26.26 pm/kPa. The fabrication process was described in detail, which is simple and cost-effective. The sensor characteristics were studied theoretically and experimentally. Quasi-square pressure signal of different frequencies generated by the siren disk were measured by the sensor and compared with that obtained from the commercial piezoresistive pressure sensor to verify the accuracy of the proposed sensor. The R2 of the four pairs of pressure waveforms were 0.94, 0.81, 0.93, and 0.96, respectively. Stability testing of the sensor was also performed, showing that the sensor can work reliably under dynamic pressure environment.
ABSTRACT
FBG array sensors have been widely used in the multi-point monitoring of large structures due to their excellent optical multiplexing capability. This paper proposes a cost-effective demodulation system for FBG array sensors based on a Neural Network (NN). The stress variations applied to the FBG array sensor are encoded by the array waveguide grating (AWG) as transmitted intensities under different channels and fed to an end-to-end NN model, which receives them and simultaneously establishes a complex nonlinear relationship between the transmitted intensity and the actual wavelength to achieve absolute interrogation of the peak wavelength. In addition, a low-cost data augmentation strategy is introduced to break the data size bottleneck common in data-driven methods so that the NN can still achieve superior performance with small-scale data. In summary, the demodulation system provides an efficient and reliable solution for multi-point monitoring of large structures based on FBG array sensors.
ABSTRACT
Fiber Bragg grating (FBG) sensors have been widely applied in various applications, especially for structural health monitoring. Low cost, wide range, and low error are necessary for an excellent performance FBG sensor signal demodulation system. Yet the improvement of performance is commonly accompanied by costly and complex systems. A high-performance, low-cost wavelength interrogation method for FBG sensors was introduced in this paper. The information from the FBG sensor signal was extracted by the array waveguide grating (AWG) and fed into the proposed cascaded neural network. The proposed network was constructed by cascading a convolutional neural network and a residual backpropagation neural network. We demonstrate that our network yields a vastly significant performance improvement in AWG-based wavelength interrogation over that given by other machine learning models and validate it in experiments. The proposed network cost-effectively widens the wavelength interrogation range of the demodulation system and optimizes the wavelength interrogation error substantially, also making the system scalable.
ABSTRACT
For FPI sensor demodulation systems to be used in actual engineering measurement, they must have high performance, low cost, stability, and scalability. Excellent performance, however, necessitates expensive equipment and advanced algorithms. This research provides a new absolute demodulation system for FPI sensors that is high-performance and cost-effective. The reflected light from the sensor was demultiplexed into distinct channels using an array waveguide grating (AWG), with the interference spectrum features change translated as the variation of the transmitted intensity in each AWG channel. This data was fed into an end-to-end neural network model, which was utilized to interrogate multiple interference peaks' absolute peak wavelengths simultaneously. This architecturally simple network model can achieve remarkable generalization capabilities without training large-scale datasets using an appropriate data augmentation strategy. Experiments show that in simultaneous multi-wavelength and cavity length interrogations, the proposed system has the precision of up to ± 14 pm and ± 0.07 µm, respectively. The interrogation resolution can theoretically reach the pm level benefit from the neural network method. Furthermore, the system's outstanding demodulation repeatability and suitability were demonstrated. The system is expected to provide a high-performance and cost-effective, reliable solution for practical engineering applications.
ABSTRACT
Growing nonlinearity demands in mid-infrared applications place more outstanding requirements on fiber structure design. Chalcogenide suspended-core fibers (SCFs) are considered excellent candidates for mid-infrared applications due to their significant advantages in nonlinearity and dispersion management. However, traditional numerical methods for accurate modeling and optimization of SCFs often rely on the performance of computing devices and have many limitations when dealing with complex models. A machine learning algorithm is applied to calculate the optical properties of chalcogenide SCFs, including effective mode area, nonlinear coefficient, and dispersion. The established artificial neural network (ANN) model enables accurate prediction of the above optical properties of As2S3 SCF, for which in the wavelength range of 1.0 to 4.0 µm, the radius of the fiber core is 0.4 to 0.6 µm, and width of the cantilever is 0.06 to 0.09 µm. We demonstrate that this simple ANN model has considerable advantages over the traditional numerical calculation model in computational speed and resource utilization. In summary, the proposed model can quickly provide more accurate optical property predictions, providing a cost-effective solution for precise modeling and optimization of chalcogenide SCFs.
ABSTRACT
Suspended-core fibers (SCFs) are considered the best candidates for enhancing fiber nonlinearity in mid-infrared applications. Accurate modeling and optimization of its structure is a key part of the SCF structure design process. Due to the drawbacks of traditional numerical simulation methods, such as low speed and large errors, the deep learning-based inverse design of SCFs has become mainstream. However, the advantage of deep learning models over traditional optimization methods relies heavily on large-scale a priori datasets to train the models, a common bottleneck of data-driven methods. This paper presents a comprehensive deep learning model for the efficient inverse design of SCFs. A semi-supervised learning strategy is introduced to alleviate the burden of data acquisition. Taking SCF's three key optical properties (effective mode area, nonlinear coefficient, and dispersion) as examples, we demonstrate that satisfactory computational results can be obtained based on small-scale training data. The proposed scheme can provide a new and effective platform for data-limited physical computing tasks.
ABSTRACT
Functional and nutritional compounds are increased during foxtail millet germination while bad smell is produced due to the fatty acid oxidation. To eliminate the unpleasant aroma, the origins of the volatiles must be known. A comprehensive two-dimensional gas chromatography-time-of-flight mass spectrometry showed forty-nine volatiles containing 8 ketones, 10 aldehydes, 20 alkanes, 4 alcohols, 5 alkenes, and 2 furans were tentatively identified, and they increased during the germination of the foxtail millet. To identify the origin of some volatiles, model experiments by adding 6 fatty acids to the crude enzymes of the foxtail millet was designed, and 17 volatiles could be detected. The saturated fatty acids (palmitic acid and stearic acid) had no contributions to the formation of the volatiles, whereas the unsaturated fatty acid played important roles in the formation of volatiles. Among the unsaturated fatty acids, palmitoleic acid and linoleic acid produced most aldehydes, alcohols, and ketones, while linolenic acid produced the most alkanes and alkenes. This study will be helpful for controlling the smell of germinated seeds from the raw material selection.
Subject(s)
Fatty Acids, Volatile/isolation & purification , Fatty Acids/chemistry , Germination , Setaria Plant/chemistry , Fatty Acids/isolation & purification , Fatty Acids, Volatile/chemistry , Gas Chromatography-Mass Spectrometry , Odorants/analysis , Setaria Plant/growth & development , SmellABSTRACT
BACKGROUND: A great number of studies reported that 12/15-lipoxygenase (12/15-LO) played an important role in atherosclerosis. And its arachidonic acid(AA) metabolite, 15(S)-hydroperoxy-5,8,11,13-(Z,Z,Z,E)-eicosatetraenoic acid (15(S)-HETE), is demonstrated to mediate endothelial dysfunction. 15-oxo-5,8,11,13-(Z,Z,Z,E)-eicosatetraenoic acid (15-oxo-ETE) was formed from 15-hydroxyprostaglandin dehydrogenase (PGDH)-mediated oxidation of 15(S)-HETE. However, relatively little is known about the biological effects of 15-oxo-ETE in cardiovascular disease. Here, we explore the likely role of 15-lipoxygenase (LO)-1-mediated AA metabolism,15-oxo-ETE, in the early pathogenesis of atherosclerosis. METHODS: The 15-oxo-ETE level in serum was detected by means of liquid chromatography and online tandem mass spectrometry (LC-MS/MS). And the underlying mechanisms were illuminated by molecular techniques, including immunoblotting, MTT assay, immunocytochemistry and Immunohistochemistry. RESULTS: Increased 15-oxo-ETE level is found in in patients with acute myocardial infarction (AMI). After 15-oxo-ETE treatment, Human umbilical vein endothelial cells (HUVECs) showed more attractive to monocytes, whereas monocyte adhesion is suppressed when treated with PKC inhibitor. In ex vivo study, exposure of arteries from C57 mice and ApoE-/-mice to 15-oxo-ETE led to significantly increased E-selectin expression and monocyte adhesion. CONCLUSIONS: This is the first report that 15-oxo-ETE promotes early pathological process of atherosclerosis by accelerating E-selectin expression and monocyte adhesion. 15-oxo-ETE -induced monocyte adhesion is partly attributable to activation of PKC.
Subject(s)
Arachidonic Acids/blood , Endothelial Cells/cytology , Endothelial Cells/metabolism , Monocytes/cytology , Monocytes/metabolism , Aged , Cell Adhesion/physiology , Cell Line , Chromatography, Liquid , Female , Human Umbilical Vein Endothelial Cells , Humans , Immunoblotting , Immunohistochemistry , Male , Middle Aged , Tandem Mass SpectrometryABSTRACT
Retinal optical coherence tomography (OCT) images provide crucial insights into the health of the posterior ocular segment. Therefore, the advancement of automated image analysis methods is imperative to equip clinicians and researchers with quantitative data, thereby facilitating informed decision-making. The application of deep learning (DL)-based approaches has gained extensive traction for executing these analysis tasks, demonstrating remarkable performance compared to labor-intensive manual analyses. However, the acquisition of retinal OCT images often presents challenges stemming from privacy concerns and the resource-intensive labeling procedures, which contradicts the prevailing notion that DL models necessitate substantial data volumes for achieving superior performance. Moreover, limitations in available computational resources constrain the progress of high-performance medical artificial intelligence, particularly in less developed regions and countries. This paper introduces a novel ensemble learning mechanism designed for recognizing retinal diseases under limited resources (e.g., data, computation). The mechanism leverages insights from multiple pre-trained models, facilitating the transfer and adaptation of their knowledge to retinal OCT images. This approach establishes a robust model even when confronted with limited labeled data, eliminating the need for an extensive array of parameters, as required in learning from scratch. Comprehensive experimentation on real-world datasets demonstrates that the ensemble models constructed by the proposed ensemble method show superior performance over the baseline models under sparse labeled data, especially the triple ensemble model, which achieves the accuracy of 92.06%, which is 8.27%, 7.99%, and 11.14% better than the three baseline models, respectively. In addition, compared with the three baseline models learned from scratch, the triple ensemble model has fewer trainable parameters, only 3.677M, which is lower than the three baseline models of 8.013M, 4.302M, and 20.158M, respectively.
ABSTRACT
Chest imaging plays an essential role in diagnosing and predicting patients with COVID-19 with evidence of worsening respiratory status. Many deep learning-based approaches for pneumonia recognition have been developed to enable computer-aided diagnosis. However, the long training and inference time makes them inflexible, and the lack of interpretability reduces their credibility in clinical medical practice. This paper aims to develop a pneumonia recognition framework with interpretability, which can understand the complex relationship between lung features and related diseases in chest X-ray (CXR) images to provide high-speed analytics support for medical practice. To reduce the computational complexity to accelerate the recognition process, a novel multi-level self-attention mechanism within Transformer has been proposed to accelerate convergence and emphasize the task-related feature regions. Moreover, a practical CXR image data augmentation has been adopted to address the scarcity of medical image data problems to boost the model's performance. The effectiveness of the proposed method has been demonstrated on the classic COVID-19 recognition task using the widespread pneumonia CXR image dataset. In addition, abundant ablation experiments validate the effectiveness and necessity of all of the components of the proposed method.
Subject(s)
COVID-19 , Pneumonia , Humans , X-Rays , Pneumonia/diagnostic imaging , COVID-19/diagnostic imaging , Thorax/diagnostic imaging , Diagnosis, Computer-AssistedABSTRACT
Stroke is a major disease that seriously endangers the lives and health of middle-aged and elderly people in our country, but its implementation of secondary prevention needs to be improved urgently. The application of IoT technology in home health monitoring and telemedicine, as well as the popularization of cloud computing, contributes to the early identification of ischemic stroke and provides intelligent, humanized, and preventive medical and health services for patients at high risk of stroke. This article clarifies the networking structure and networking objects of the rehabilitation system Internet of Things, clarifies the functions of each part, and establishes an overall system architecture based on smart medical care; the design and optimization of the mechanical part of the stroke rehabilitation robot are carried out, as well as kinematics and dynamic analysis. According to the functions of different types of stroke rehabilitation robots, strategies are given for the use of lower limb rehabilitation robots; standardized codes are used to identify system objects, and RFID technology is used to automatically identify users and devices. Combined with the use of the Internet and GSM mobile communication network, construct a network database of system networking objects and, on this basis, establish information management software based on a smart medical rehabilitation system that takes care of both doctors and patients to realize the system's Internet of Things architecture. In addition, this article also gives the recovery strategy generation in the system with the design method of resource scheduling method and the theoretical algorithm of rehabilitation strategy generation is given and verified. This research summarizes the application background, advantages, and past practice of the Internet of Things in stroke medical care, develops and applies a medical collaborative cloud computing system for systematic intervention of stroke, and realizes the module functions such as information sharing, regional monitoring, and collaborative consultation within the base.